{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DD05e4TSge4P",
        "outputId": "e367fe9f-08fa-4273-bab1-16c7dda2a688"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (2.0.2)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (3.10.0)\n",
            "Requirement already satisfied: seaborn in /usr/local/lib/python3.12/dist-packages (0.13.2)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (1.6.1)\n",
            "Requirement already satisfied: shap in /usr/local/lib/python3.12/dist-packages (0.50.0)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.3.3)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (4.61.0)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.4.9)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (25.0)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (11.3.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (3.2.5)\n",
            "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.15.3)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.5.2)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (3.6.0)\n",
            "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.12/dist-packages (from shap) (4.67.1)\n",
            "Requirement already satisfied: slicer==0.0.8 in /usr/local/lib/python3.12/dist-packages (from shap) (0.0.8)\n",
            "Requirement already satisfied: numba>=0.54 in /usr/local/lib/python3.12/dist-packages (from shap) (0.60.0)\n",
            "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.12/dist-packages (from shap) (3.1.2)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.12/dist-packages (from shap) (4.15.0)\n",
            "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.54->shap) (0.43.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
          ]
        }
      ],
      "source": [
        "pip install pandas numpy matplotlib seaborn scikit-learn shap"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install fairlearn\n"
      ],
      "metadata": {
        "id": "CjYZ8Udut_OX",
        "outputId": "6d97b886-01b8-45d8-edcc-8357dd676b92",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: fairlearn in /usr/local/lib/python3.12/dist-packages (0.13.0)\n",
            "Requirement already satisfied: narwhals>=1.14.0 in /usr/local/lib/python3.12/dist-packages (from fairlearn) (2.13.0)\n",
            "Requirement already satisfied: numpy>=1.24.4 in /usr/local/lib/python3.12/dist-packages (from fairlearn) (2.0.2)\n",
            "Requirement already satisfied: pandas>=2.0.3 in /usr/local/lib/python3.12/dist-packages (from fairlearn) (2.2.2)\n",
            "Requirement already satisfied: scikit-learn>=1.2.1 in /usr/local/lib/python3.12/dist-packages (from fairlearn) (1.6.1)\n",
            "Requirement already satisfied: scipy<1.16.0,>=1.9.3 in /usr/local/lib/python3.12/dist-packages (from fairlearn) (1.15.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas>=2.0.3->fairlearn) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas>=2.0.3->fairlearn) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas>=2.0.3->fairlearn) (2025.2)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.2.1->fairlearn) (1.5.2)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.2.1->fairlearn) (3.6.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas>=2.0.3->fairlearn) (1.17.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install streamlit\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZUN1G0nSueu3",
        "outputId": "7d563883-8952-4e56-f30c-e67a5cf1abee"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting streamlit\n",
            "  Downloading streamlit-1.52.1-py3-none-any.whl.metadata (9.8 kB)\n",
            "Requirement already satisfied: altair!=5.4.0,!=5.4.1,<7,>=4.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (5.5.0)\n",
            "Requirement already satisfied: blinker<2,>=1.5.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (1.9.0)\n",
            "Requirement already satisfied: cachetools<7,>=4.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (6.2.2)\n",
            "Requirement already satisfied: click<9,>=7.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (8.3.1)\n",
            "Requirement already satisfied: numpy<3,>=1.23 in /usr/local/lib/python3.12/dist-packages (from streamlit) (2.0.2)\n",
            "Requirement already satisfied: packaging>=20 in /usr/local/lib/python3.12/dist-packages (from streamlit) (25.0)\n",
            "Requirement already satisfied: pandas<3,>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (2.2.2)\n",
            "Requirement already satisfied: pillow<13,>=7.1.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (11.3.0)\n",
            "Requirement already satisfied: protobuf<7,>=3.20 in /usr/local/lib/python3.12/dist-packages (from streamlit) (5.29.5)\n",
            "Requirement already satisfied: pyarrow>=7.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (18.1.0)\n",
            "Requirement already satisfied: requests<3,>=2.27 in /usr/local/lib/python3.12/dist-packages (from streamlit) (2.32.4)\n",
            "Requirement already satisfied: tenacity<10,>=8.1.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (9.1.2)\n",
            "Requirement already satisfied: toml<2,>=0.10.1 in /usr/local/lib/python3.12/dist-packages (from streamlit) (0.10.2)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.4.0 in /usr/local/lib/python3.12/dist-packages (from streamlit) (4.15.0)\n",
            "Requirement already satisfied: watchdog<7,>=2.1.5 in /usr/local/lib/python3.12/dist-packages (from streamlit) (6.0.0)\n",
            "Requirement already satisfied: gitpython!=3.1.19,<4,>=3.0.7 in /usr/local/lib/python3.12/dist-packages (from streamlit) (3.1.45)\n",
            "Collecting pydeck<1,>=0.8.0b4 (from streamlit)\n",
            "  Downloading pydeck-0.9.1-py2.py3-none-any.whl.metadata (4.1 kB)\n",
            "Requirement already satisfied: tornado!=6.5.0,<7,>=6.0.3 in /usr/local/lib/python3.12/dist-packages (from streamlit) (6.5.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (3.1.6)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.12/dist-packages (from altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (4.25.1)\n",
            "Requirement already satisfied: narwhals>=1.14.2 in /usr/local/lib/python3.12/dist-packages (from altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (2.13.0)\n",
            "Requirement already satisfied: gitdb<5,>=4.0.1 in /usr/local/lib/python3.12/dist-packages (from gitpython!=3.1.19,<4,>=3.0.7->streamlit) (4.0.12)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas<3,>=1.4.0->streamlit) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas<3,>=1.4.0->streamlit) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas<3,>=1.4.0->streamlit) (2025.2)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.27->streamlit) (3.4.4)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.27->streamlit) (3.11)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.27->streamlit) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.27->streamlit) (2025.11.12)\n",
            "Requirement already satisfied: smmap<6,>=3.0.1 in /usr/local/lib/python3.12/dist-packages (from gitdb<5,>=4.0.1->gitpython!=3.1.19,<4,>=3.0.7->streamlit) (5.0.2)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (3.0.3)\n",
            "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.12/dist-packages (from jsonschema>=3.0->altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (25.4.0)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.12/dist-packages (from jsonschema>=3.0->altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (2025.9.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.12/dist-packages (from jsonschema>=3.0->altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (0.37.0)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.12/dist-packages (from jsonschema>=3.0->altair!=5.4.0,!=5.4.1,<7,>=4.0->streamlit) (0.30.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas<3,>=1.4.0->streamlit) (1.17.0)\n",
            "Downloading streamlit-1.52.1-py3-none-any.whl (9.0 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.0/9.0 MB\u001b[0m \u001b[31m26.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pydeck-0.9.1-py2.py3-none-any.whl (6.9 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m29.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: pydeck, streamlit\n",
            "Successfully installed pydeck-0.9.1 streamlit-1.52.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Importing Libraries**"
      ],
      "metadata": {
        "id": "EMtSJ23kmaiL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.metrics import (\n",
        "    accuracy_score, classification_report, confusion_matrix\n",
        ")\n",
        "\n",
        "from fairlearn.metrics import (\n",
        "    demographic_parity_difference,\n",
        "    equalized_odds_difference\n",
        ")\n",
        "\n",
        "import shap\n",
        "import streamlit as st\n"
      ],
      "metadata": {
        "id": "nJAVjyCCjE3k"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Loading and Viewing the Dataset**"
      ],
      "metadata": {
        "id": "GU4mMOi3mcba"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "city2_financial_data = pd.read_csv(\"city2_financial_data.csv\")\n",
        "city2_financial_data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 226
        },
        "id": "xFQ6ZolgjE62",
        "outputId": "1a9c7d8d-850d-4626-9d6a-32051a82e60a"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         Date City      Revenue     Expenses       Profit  Customers  \\\n",
              "0  01/01/2020   UK  54331.84411  24728.38845  14606.33550        395   \n",
              "1  02/01/2020   UK  54254.82683  20673.18542  24215.83602        406   \n",
              "2  03/01/2020   UK  38879.25182  33020.36529  14380.12070        131   \n",
              "3  04/01/2020   UK  38285.15911  41716.10057  17385.31555        147   \n",
              "4  05/01/2020   UK  61701.94743  28822.77867  24393.67087        426   \n",
              "\n",
              "   Transactions  Stock_Price  Market_Sentiment  Loan_Approval_Rate  \\\n",
              "0           118    82.460011          0.429902            0.741248   \n",
              "1           188    91.905840          0.282992            0.705286   \n",
              "2           148   118.247638          0.593407            0.833708   \n",
              "3           123    85.339835          0.535897            0.972350   \n",
              "4           152   112.866993          0.804489            0.791580   \n",
              "\n",
              "   Employee_Count  Marketing_Spend  \n",
              "0              45     12173.986810  \n",
              "1              24      3108.474133  \n",
              "2              62     13095.592560  \n",
              "3              71      9559.047874  \n",
              "4              57     16335.363610  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-730afbab-d1c0-4ae7-b5a2-23920ee1da94\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Date</th>\n",
              "      <th>City</th>\n",
              "      <th>Revenue</th>\n",
              "      <th>Expenses</th>\n",
              "      <th>Profit</th>\n",
              "      <th>Customers</th>\n",
              "      <th>Transactions</th>\n",
              "      <th>Stock_Price</th>\n",
              "      <th>Market_Sentiment</th>\n",
              "      <th>Loan_Approval_Rate</th>\n",
              "      <th>Employee_Count</th>\n",
              "      <th>Marketing_Spend</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>01/01/2020</td>\n",
              "      <td>UK</td>\n",
              "      <td>54331.84411</td>\n",
              "      <td>24728.38845</td>\n",
              "      <td>14606.33550</td>\n",
              "      <td>395</td>\n",
              "      <td>118</td>\n",
              "      <td>82.460011</td>\n",
              "      <td>0.429902</td>\n",
              "      <td>0.741248</td>\n",
              "      <td>45</td>\n",
              "      <td>12173.986810</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>02/01/2020</td>\n",
              "      <td>UK</td>\n",
              "      <td>54254.82683</td>\n",
              "      <td>20673.18542</td>\n",
              "      <td>24215.83602</td>\n",
              "      <td>406</td>\n",
              "      <td>188</td>\n",
              "      <td>91.905840</td>\n",
              "      <td>0.282992</td>\n",
              "      <td>0.705286</td>\n",
              "      <td>24</td>\n",
              "      <td>3108.474133</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>03/01/2020</td>\n",
              "      <td>UK</td>\n",
              "      <td>38879.25182</td>\n",
              "      <td>33020.36529</td>\n",
              "      <td>14380.12070</td>\n",
              "      <td>131</td>\n",
              "      <td>148</td>\n",
              "      <td>118.247638</td>\n",
              "      <td>0.593407</td>\n",
              "      <td>0.833708</td>\n",
              "      <td>62</td>\n",
              "      <td>13095.592560</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>04/01/2020</td>\n",
              "      <td>UK</td>\n",
              "      <td>38285.15911</td>\n",
              "      <td>41716.10057</td>\n",
              "      <td>17385.31555</td>\n",
              "      <td>147</td>\n",
              "      <td>123</td>\n",
              "      <td>85.339835</td>\n",
              "      <td>0.535897</td>\n",
              "      <td>0.972350</td>\n",
              "      <td>71</td>\n",
              "      <td>9559.047874</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>05/01/2020</td>\n",
              "      <td>UK</td>\n",
              "      <td>61701.94743</td>\n",
              "      <td>28822.77867</td>\n",
              "      <td>24393.67087</td>\n",
              "      <td>426</td>\n",
              "      <td>152</td>\n",
              "      <td>112.866993</td>\n",
              "      <td>0.804489</td>\n",
              "      <td>0.791580</td>\n",
              "      <td>57</td>\n",
              "      <td>16335.363610</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-730afbab-d1c0-4ae7-b5a2-23920ee1da94')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-730afbab-d1c0-4ae7-b5a2-23920ee1da94 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-730afbab-d1c0-4ae7-b5a2-23920ee1da94');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-8fcc1452-4aa4-4f2c-af6f-b5d2fd5d8bd5\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-8fcc1452-4aa4-4f2c-af6f-b5d2fd5d8bd5')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-8fcc1452-4aa4-4f2c-af6f-b5d2fd5d8bd5 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "city2_financial_data",
              "summary": "{\n  \"name\": \"city2_financial_data\",\n  \"rows\": 1000,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          \"05/06/2021\",\n          \"07/01/2022\",\n          \"10/01/2022\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"City\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"UK\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Revenue\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 10026.194414562044,\n        \"min\": 9459.499152,\n        \"max\": 80517.1132,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          48183.30439\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Expenses\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 7901.092134860611,\n        \"min\": 7606.465225,\n        \"max\": 52276.70559,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          39301.56135\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Profit\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5258.051496106228,\n        \"min\": 4126.255309,\n        \"max\": 35777.68939,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          23754.06872\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Customers\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 113,\n        \"min\": 100,\n        \"max\": 499,\n        \"num_unique_values\": 366,\n        \"samples\": [\n          251\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Transactions\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 43,\n        \"min\": 50,\n        \"max\": 199,\n        \"num_unique_values\": 150,\n        \"samples\": [\n          126\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Stock_Price\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 28.280892558885828,\n        \"min\": 50.01755159,\n        \"max\": 149.6814976,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          146.5551775\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Market_Sentiment\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.20100881705984422,\n        \"min\": -0.09855128,\n        \"max\": 1.163516598,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          0.517580002\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Loan_Approval_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.08759536162255396,\n        \"min\": 0.700002789,\n        \"max\": 0.999908449,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          0.958215912\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Employee_Count\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 25,\n        \"min\": 10,\n        \"max\": 99,\n        \"num_unique_values\": 90,\n        \"samples\": [\n          30\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Marketing_Spend\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4891.606622524889,\n        \"min\": -5432.997148,\n        \"max\": 23317.13689,\n        \"num_unique_values\": 1000,\n        \"samples\": [\n          19999.07034\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Data Inspection***"
      ],
      "metadata": {
        "id": "tHOAmpGCmn9X"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "print(city2_financial_data.info())\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1pnj4BIajFE8",
        "outputId": "3e796bd0-3220-4b74-ecaa-13cf52c92823"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1000 entries, 0 to 999\n",
            "Data columns (total 12 columns):\n",
            " #   Column              Non-Null Count  Dtype  \n",
            "---  ------              --------------  -----  \n",
            " 0   Date                1000 non-null   object \n",
            " 1   City                1000 non-null   object \n",
            " 2   Revenue             1000 non-null   float64\n",
            " 3   Expenses            1000 non-null   float64\n",
            " 4   Profit              1000 non-null   float64\n",
            " 5   Customers           1000 non-null   int64  \n",
            " 6   Transactions        1000 non-null   int64  \n",
            " 7   Stock_Price         1000 non-null   float64\n",
            " 8   Market_Sentiment    1000 non-null   float64\n",
            " 9   Loan_Approval_Rate  1000 non-null   float64\n",
            " 10  Employee_Count      1000 non-null   int64  \n",
            " 11  Marketing_Spend     1000 non-null   float64\n",
            "dtypes: float64(7), int64(3), object(2)\n",
            "memory usage: 93.9+ KB\n",
            "None\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Summary Statistics***"
      ],
      "metadata": {
        "id": "WU3polGDmp8q"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "city2_financial_data.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 320
        },
        "id": "oP5sA8Z2jFHL",
        "outputId": "b7910702-6390-4acd-f6d9-9e784b156e42"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            Revenue      Expenses        Profit    Customers  Transactions  \\\n",
              "count   1000.000000   1000.000000   1000.000000  1000.000000   1000.000000   \n",
              "mean   49587.224799  30026.725048  19975.418321   299.151000    124.447000   \n",
              "std    10026.194415   7901.092135   5258.051496   113.581905     43.827754   \n",
              "min     9459.499152   7606.465225   4126.255309   100.000000     50.000000   \n",
              "25%    42813.364635  24434.710492  16228.024268   201.000000     86.750000   \n",
              "50%    49669.335075  30301.631690  20126.802320   299.500000    124.000000   \n",
              "75%    56359.233228  35074.579503  23640.567198   396.000000    162.000000   \n",
              "max    80517.113200  52276.705590  35777.689390   499.000000    199.000000   \n",
              "\n",
              "       Stock_Price  Market_Sentiment  Loan_Approval_Rate  Employee_Count  \\\n",
              "count  1000.000000       1000.000000         1000.000000     1000.000000   \n",
              "mean     99.487907          0.502056            0.848123       52.748000   \n",
              "std      28.280893          0.201009            0.087595       25.810903   \n",
              "min      50.017552         -0.098551            0.700003       10.000000   \n",
              "25%      75.589833          0.366848            0.772894       31.000000   \n",
              "50%      98.911444          0.501434            0.847648       51.500000   \n",
              "75%     123.062436          0.636046            0.923874       75.000000   \n",
              "max     149.681498          1.163517            0.999908       99.000000   \n",
              "\n",
              "       Marketing_Spend  \n",
              "count      1000.000000  \n",
              "mean      10052.094807  \n",
              "std        4891.606623  \n",
              "min       -5432.997148  \n",
              "25%        6634.057125  \n",
              "50%       10135.327325  \n",
              "75%       13299.255310  \n",
              "max       23317.136890  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a58f4d71-0e50-4859-b4d6-e0411ba6b4a8\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Revenue</th>\n",
              "      <th>Expenses</th>\n",
              "      <th>Profit</th>\n",
              "      <th>Customers</th>\n",
              "      <th>Transactions</th>\n",
              "      <th>Stock_Price</th>\n",
              "      <th>Market_Sentiment</th>\n",
              "      <th>Loan_Approval_Rate</th>\n",
              "      <th>Employee_Count</th>\n",
              "      <th>Marketing_Spend</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "      <td>1000.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>49587.224799</td>\n",
              "      <td>30026.725048</td>\n",
              "      <td>19975.418321</td>\n",
              "      <td>299.151000</td>\n",
              "      <td>124.447000</td>\n",
              "      <td>99.487907</td>\n",
              "      <td>0.502056</td>\n",
              "      <td>0.848123</td>\n",
              "      <td>52.748000</td>\n",
              "      <td>10052.094807</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>10026.194415</td>\n",
              "      <td>7901.092135</td>\n",
              "      <td>5258.051496</td>\n",
              "      <td>113.581905</td>\n",
              "      <td>43.827754</td>\n",
              "      <td>28.280893</td>\n",
              "      <td>0.201009</td>\n",
              "      <td>0.087595</td>\n",
              "      <td>25.810903</td>\n",
              "      <td>4891.606623</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>9459.499152</td>\n",
              "      <td>7606.465225</td>\n",
              "      <td>4126.255309</td>\n",
              "      <td>100.000000</td>\n",
              "      <td>50.000000</td>\n",
              "      <td>50.017552</td>\n",
              "      <td>-0.098551</td>\n",
              "      <td>0.700003</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>-5432.997148</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>42813.364635</td>\n",
              "      <td>24434.710492</td>\n",
              "      <td>16228.024268</td>\n",
              "      <td>201.000000</td>\n",
              "      <td>86.750000</td>\n",
              "      <td>75.589833</td>\n",
              "      <td>0.366848</td>\n",
              "      <td>0.772894</td>\n",
              "      <td>31.000000</td>\n",
              "      <td>6634.057125</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>49669.335075</td>\n",
              "      <td>30301.631690</td>\n",
              "      <td>20126.802320</td>\n",
              "      <td>299.500000</td>\n",
              "      <td>124.000000</td>\n",
              "      <td>98.911444</td>\n",
              "      <td>0.501434</td>\n",
              "      <td>0.847648</td>\n",
              "      <td>51.500000</td>\n",
              "      <td>10135.327325</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>56359.233228</td>\n",
              "      <td>35074.579503</td>\n",
              "      <td>23640.567198</td>\n",
              "      <td>396.000000</td>\n",
              "      <td>162.000000</td>\n",
              "      <td>123.062436</td>\n",
              "      <td>0.636046</td>\n",
              "      <td>0.923874</td>\n",
              "      <td>75.000000</td>\n",
              "      <td>13299.255310</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>80517.113200</td>\n",
              "      <td>52276.705590</td>\n",
              "      <td>35777.689390</td>\n",
              "      <td>499.000000</td>\n",
              "      <td>199.000000</td>\n",
              "      <td>149.681498</td>\n",
              "      <td>1.163517</td>\n",
              "      <td>0.999908</td>\n",
              "      <td>99.000000</td>\n",
              "      <td>23317.136890</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a58f4d71-0e50-4859-b4d6-e0411ba6b4a8')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-a58f4d71-0e50-4859-b4d6-e0411ba6b4a8 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-a58f4d71-0e50-4859-b4d6-e0411ba6b4a8');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-ad6e5b67-2de7-42b2-9011-bc7c25d6708d\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ad6e5b67-2de7-42b2-9011-bc7c25d6708d')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-ad6e5b67-2de7-42b2-9011-bc7c25d6708d button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"city2_financial_data\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"Revenue\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 27779.379858723456,\n        \"min\": 1000.0,\n        \"max\": 80517.1132,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          49587.224798582,\n          49669.335074999995,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Expenses\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 17129.488860066347,\n        \"min\": 1000.0,\n        \"max\": 52276.70559,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          30026.725048062,\n          30301.631690000002,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Profit\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 11731.284048765005,\n        \"min\": 1000.0,\n        \"max\": 35777.68939,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          19975.418320840003,\n          20126.80232,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Customers\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 290.58637551355434,\n        \"min\": 100.0,\n        \"max\": 1000.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          299.151,\n          299.5,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Transactions\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 318.059049473547,\n        \"min\": 43.82775448346705,\n        \"max\": 1000.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          124.447,\n          124.0,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Stock_Price\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 324.2914631047407,\n        \"min\": 28.280892558885828,\n        \"max\": 1000.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          99.48790694286,\n          98.91144431000001,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Market_Sentiment\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 353.38829683728005,\n        \"min\": -0.09855128,\n        \"max\": 1000.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.50205591053,\n          0.5014341705,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Loan_Approval_Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 353.2918705488684,\n        \"min\": 0.08759536162255396,\n        \"max\": 1000.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.848123315227,\n          0.8476480264999999,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Employee_Count\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 337.3086489791152,\n        \"min\": 10.0,\n        \"max\": 1000.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          52.748,\n          51.5,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Marketing_Spend\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 8556.029514832715,\n        \"min\": -5432.997148,\n        \"max\": 23317.13689,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          10052.094806931802,\n          10135.327324999998,\n          1000.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **Data Cleaning & Preparation**"
      ],
      "metadata": {
        "id": "jsdRIiwumvY5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Converting Date\n",
        "city2_financial_data['Date'] = pd.to_datetime(city2_financial_data['Date'], dayfirst=True)\n",
        "\n",
        "# Droping City\n",
        "city2_financial_data.drop(columns=['City'], inplace=True)\n",
        "\n",
        "# Missing values checking\n",
        "print(\"Missing values:\\n\", city2_financial_data.isnull().sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hDt87lOtjXC8",
        "outputId": "e19b54e8-0685-47c1-9d3f-fda3612f53d2"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Missing values:\n",
            " Date                  0\n",
            "Revenue               0\n",
            "Expenses              0\n",
            "Profit                0\n",
            "Customers             0\n",
            "Transactions          0\n",
            "Stock_Price           0\n",
            "Market_Sentiment      0\n",
            "Loan_Approval_Rate    0\n",
            "Employee_Count        0\n",
            "Marketing_Spend       0\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Exploratory Data Analysis**"
      ],
      "metadata": {
        "id": "yHLGMORnmyeY"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Loan Approval Rate Over Time***"
      ],
      "metadata": {
        "id": "UzT2NIetmzL4"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(8,5))\n",
        "plt.plot(city2_financial_data['Date'], city2_financial_data['Loan_Approval_Rate'], marker='o')\n",
        "plt.title(\"Loan Approval Rate Over Time\")\n",
        "plt.xlabel(\"Date\")\n",
        "plt.ylabel(\"Loan Approval Rate\")\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "UtHxL8vEjXFt",
        "outputId": "1ec57d2d-7c30-4a1c-fbde-9828d976dc42"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x500 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Transactions vs Market Sentiment***"
      ],
      "metadata": {
        "id": "pG91uV4_m04R"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure()\n",
        "plt.scatter(city2_financial_data[\"Transactions\"], city2_financial_data[\"Market_Sentiment\"])\n",
        "plt.xlabel(\"Transactions\")\n",
        "plt.ylabel(\"Market Sentiment\")\n",
        "plt.title(\"Transactions vs Market Sentiment\")\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "xN1KQpJ5jXIm",
        "outputId": "9b93f670-8898-48de-c495-098396be5187"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Correlation Matrix***"
      ],
      "metadata": {
        "id": "o2JiXff8m23l"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(10,6))\n",
        "sns.heatmap(\n",
        "    city2_financial_data.corr(),\n",
        "    annot=True,\n",
        "    fmt=\".2f\",\n",
        "    cmap=\"coolwarm\",\n",
        "    linewidths=0.5,\n",
        "    annot_kws={\"size\": 9}\n",
        ")\n",
        "plt.title(\"Correlation Matrix of Financial Variables\")\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 672
        },
        "id": "7zh_cyECjXLF",
        "outputId": "1a435b70-0038-43de-e2b7-e50bffd7cbb1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Revenue, Expenses, and Profit Over Time***"
      ],
      "metadata": {
        "id": "k20Jz36U4lsx"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(12,6))\n",
        "plt.stackplot(\n",
        "    city2_financial_data[\"Date\"],\n",
        "    city2_financial_data[\"Revenue\"],\n",
        "    city2_financial_data[\"Expenses\"],\n",
        "    city2_financial_data[\"Profit\"],\n",
        "    labels=[\"Revenue\", \"Expenses\", \"Profit\"],\n",
        "    colors=[\"#1f77b4\", \"#ff7f0e\", \"#2ca02c\"],\n",
        "    alpha=0.6\n",
        ")\n",
        "plt.xlabel(\"Date\")\n",
        "plt.ylabel(\"Amount (£)\")\n",
        "plt.title(\"Revenue, Expenses, and Profit Over Time (Stacked Area)\")\n",
        "plt.legend(loc=\"upper left\")\n",
        "plt.grid(True, alpha=0.3)\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "id": "b2bluEQI3tuM",
        "outputId": "a60f95b5-322c-4ea6-b85a-0e7802e2bdfd"
      },
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Distribution of Loan Approval Rates***"
      ],
      "metadata": {
        "id": "LV0WkqB85E-S"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(8,5))\n",
        "sns.histplot(city2_financial_data[\"Loan_Approval_Rate\"], bins=10, kde=True, color='skyblue')\n",
        "plt.xlabel(\"Loan Approval Rate\")\n",
        "plt.title(\"Distribution of Loan Approval Rates\")\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "hE2lmLOs354m",
        "outputId": "353df8c7-5dc1-48a1-8c4c-6f4f58fc876a"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x500 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Data Preprocessing**"
      ],
      "metadata": {
        "id": "om6V2mPU5KF6"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Feature Selection (Regulatory Justification)***"
      ],
      "metadata": {
        "id": "OSbX6JaLzu5V"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "selected_features = [\n",
        "    'Transactions',\n",
        "    'Market_Sentiment',\n",
        "    'Stock_Price',\n",
        "    'Revenue',\n",
        "    'Loan_Approval_Rate',\n",
        "    'Expenses'\n",
        "]\n",
        "\n",
        "X = city2_financial_data[selected_features]\n"
      ],
      "metadata": {
        "id": "pCDg7KY6oBqr"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Risk / Fraud Proxy Target***"
      ],
      "metadata": {
        "id": "dAkczh_Izw-r"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "city2_financial_data['risk_flag'] = np.where(\n",
        "    (city2_financial_data['Transactions'] > city2_financial_data['Transactions'].quantile(0.75)) &\n",
        "    (city2_financial_data['Profit'] < city2_financial_data['Profit'].median()),\n",
        "    1, 0\n",
        ")\n",
        "\n",
        "y = city2_financial_data['risk_flag']\n"
      ],
      "metadata": {
        "id": "lhSG7Ko9oBvp"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Demographic Proxy"
      ],
      "metadata": {
        "id": "Priv1D13zzCs"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "city2_financial_data['approval_group'] = np.where(\n",
        "    city2_financial_data['Loan_Approval_Rate'] >= city2_financial_data['Loan_Approval_Rate'].median(),\n",
        "    'High Approval',\n",
        "    'Low Approval'\n",
        ")\n"
      ],
      "metadata": {
        "id": "1q6cuIGnoHTI"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Train–Test Splitting & Scaling***"
      ],
      "metadata": {
        "id": "-GPeXDVxz1nD"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "scaler = StandardScaler()\n",
        "X_scaled = scaler.fit_transform(X)\n",
        "\n",
        "X_train, X_test, y_train, y_test, g_train, g_test = train_test_split(\n",
        "    X_scaled,\n",
        "    y,\n",
        "    city2_financial_data['approval_group'],\n",
        "    test_size=0.3,\n",
        "    random_state=42\n",
        ")"
      ],
      "metadata": {
        "id": "1vuUjgihoHWJ"
      },
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **MODEL 1: LOGISTIC REGRESSION (PRIMARY REGULATORY MODEL)**"
      ],
      "metadata": {
        "id": "HaHedtXUz48L"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Train Logistic Regression***"
      ],
      "metadata": {
        "id": "XMbWtWtbz5db"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "\n",
        "log_model = LogisticRegression(max_iter=1000)\n",
        "log_model.fit(X_train, y_train)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "l8V_-I8-oXWC",
        "outputId": "83f5b5d5-3f08-4bd5-bd92-b267453e6fd7"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LogisticRegression(max_iter=1000)"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {\n",
              "  /* Definition of color scheme common for light and dark mode */\n",
              "  --sklearn-color-text: #000;\n",
              "  --sklearn-color-text-muted: #666;\n",
              "  --sklearn-color-line: gray;\n",
              "  /* Definition of color scheme for unfitted estimators */\n",
              "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
              "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
              "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
              "  --sklearn-color-unfitted-level-3: chocolate;\n",
              "  /* Definition of color scheme for fitted estimators */\n",
              "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
              "  --sklearn-color-fitted-level-1: #d4ebff;\n",
              "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
              "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
              "\n",
              "  /* Specific color for light theme */\n",
              "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
              "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
              "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
              "  --sklearn-color-icon: #696969;\n",
              "\n",
              "  @media (prefers-color-scheme: dark) {\n",
              "    /* Redefinition of color scheme for dark theme */\n",
              "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
              "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
              "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
              "    --sklearn-color-icon: #878787;\n",
              "  }\n",
              "}\n",
              "\n",
              "#sk-container-id-1 {\n",
              "  color: var(--sklearn-color-text);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 pre {\n",
              "  padding: 0;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 input.sk-hidden--visually {\n",
              "  border: 0;\n",
              "  clip: rect(1px 1px 1px 1px);\n",
              "  clip: rect(1px, 1px, 1px, 1px);\n",
              "  height: 1px;\n",
              "  margin: -1px;\n",
              "  overflow: hidden;\n",
              "  padding: 0;\n",
              "  position: absolute;\n",
              "  width: 1px;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-dashed-wrapped {\n",
              "  border: 1px dashed var(--sklearn-color-line);\n",
              "  margin: 0 0.4em 0.5em 0.4em;\n",
              "  box-sizing: border-box;\n",
              "  padding-bottom: 0.4em;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-container {\n",
              "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
              "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
              "     so we also need the `!important` here to be able to override the\n",
              "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
              "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
              "  display: inline-block !important;\n",
              "  position: relative;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-text-repr-fallback {\n",
              "  display: none;\n",
              "}\n",
              "\n",
              "div.sk-parallel-item,\n",
              "div.sk-serial,\n",
              "div.sk-item {\n",
              "  /* draw centered vertical line to link estimators */\n",
              "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
              "  background-size: 2px 100%;\n",
              "  background-repeat: no-repeat;\n",
              "  background-position: center center;\n",
              "}\n",
              "\n",
              "/* Parallel-specific style estimator block */\n",
              "\n",
              "#sk-container-id-1 div.sk-parallel-item::after {\n",
              "  content: \"\";\n",
              "  width: 100%;\n",
              "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
              "  flex-grow: 1;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-parallel {\n",
              "  display: flex;\n",
              "  align-items: stretch;\n",
              "  justify-content: center;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  position: relative;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-parallel-item {\n",
              "  display: flex;\n",
              "  flex-direction: column;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
              "  align-self: flex-end;\n",
              "  width: 50%;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
              "  align-self: flex-start;\n",
              "  width: 50%;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
              "  width: 0;\n",
              "}\n",
              "\n",
              "/* Serial-specific style estimator block */\n",
              "\n",
              "#sk-container-id-1 div.sk-serial {\n",
              "  display: flex;\n",
              "  flex-direction: column;\n",
              "  align-items: center;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  padding-right: 1em;\n",
              "  padding-left: 1em;\n",
              "}\n",
              "\n",
              "\n",
              "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
              "clickable and can be expanded/collapsed.\n",
              "- Pipeline and ColumnTransformer use this feature and define the default style\n",
              "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
              "*/\n",
              "\n",
              "/* Pipeline and ColumnTransformer style (default) */\n",
              "\n",
              "#sk-container-id-1 div.sk-toggleable {\n",
              "  /* Default theme specific background. It is overwritten whether we have a\n",
              "  specific estimator or a Pipeline/ColumnTransformer */\n",
              "  background-color: var(--sklearn-color-background);\n",
              "}\n",
              "\n",
              "/* Toggleable label */\n",
              "#sk-container-id-1 label.sk-toggleable__label {\n",
              "  cursor: pointer;\n",
              "  display: flex;\n",
              "  width: 100%;\n",
              "  margin-bottom: 0;\n",
              "  padding: 0.5em;\n",
              "  box-sizing: border-box;\n",
              "  text-align: center;\n",
              "  align-items: start;\n",
              "  justify-content: space-between;\n",
              "  gap: 0.5em;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
              "  font-size: 0.6rem;\n",
              "  font-weight: lighter;\n",
              "  color: var(--sklearn-color-text-muted);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
              "  /* Arrow on the left of the label */\n",
              "  content: \"▸\";\n",
              "  float: left;\n",
              "  margin-right: 0.25em;\n",
              "  color: var(--sklearn-color-icon);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
              "  color: var(--sklearn-color-text);\n",
              "}\n",
              "\n",
              "/* Toggleable content - dropdown */\n",
              "\n",
              "#sk-container-id-1 div.sk-toggleable__content {\n",
              "  max-height: 0;\n",
              "  max-width: 0;\n",
              "  overflow: hidden;\n",
              "  text-align: left;\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-toggleable__content pre {\n",
              "  margin: 0.2em;\n",
              "  border-radius: 0.25em;\n",
              "  color: var(--sklearn-color-text);\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
              "  /* Expand drop-down */\n",
              "  max-height: 200px;\n",
              "  max-width: 100%;\n",
              "  overflow: auto;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
              "  content: \"▾\";\n",
              "}\n",
              "\n",
              "/* Pipeline/ColumnTransformer-specific style */\n",
              "\n",
              "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  color: var(--sklearn-color-text);\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "/* Estimator-specific style */\n",
              "\n",
              "/* Colorize estimator box */\n",
              "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
              "#sk-container-id-1 div.sk-label label {\n",
              "  /* The background is the default theme color */\n",
              "  color: var(--sklearn-color-text-on-default-background);\n",
              "}\n",
              "\n",
              "/* On hover, darken the color of the background */\n",
              "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
              "  color: var(--sklearn-color-text);\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "/* Label box, darken color on hover, fitted */\n",
              "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
              "  color: var(--sklearn-color-text);\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "/* Estimator label */\n",
              "\n",
              "#sk-container-id-1 div.sk-label label {\n",
              "  font-family: monospace;\n",
              "  font-weight: bold;\n",
              "  display: inline-block;\n",
              "  line-height: 1.2em;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-label-container {\n",
              "  text-align: center;\n",
              "}\n",
              "\n",
              "/* Estimator-specific */\n",
              "#sk-container-id-1 div.sk-estimator {\n",
              "  font-family: monospace;\n",
              "  border: 1px dotted var(--sklearn-color-border-box);\n",
              "  border-radius: 0.25em;\n",
              "  box-sizing: border-box;\n",
              "  margin-bottom: 0.5em;\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-estimator.fitted {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-0);\n",
              "}\n",
              "\n",
              "/* on hover */\n",
              "#sk-container-id-1 div.sk-estimator:hover {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
              "\n",
              "/* Common style for \"i\" and \"?\" */\n",
              "\n",
              ".sk-estimator-doc-link,\n",
              "a:link.sk-estimator-doc-link,\n",
              "a:visited.sk-estimator-doc-link {\n",
              "  float: right;\n",
              "  font-size: smaller;\n",
              "  line-height: 1em;\n",
              "  font-family: monospace;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  border-radius: 1em;\n",
              "  height: 1em;\n",
              "  width: 1em;\n",
              "  text-decoration: none !important;\n",
              "  margin-left: 0.5em;\n",
              "  text-align: center;\n",
              "  /* unfitted */\n",
              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
              "  color: var(--sklearn-color-unfitted-level-1);\n",
              "}\n",
              "\n",
              ".sk-estimator-doc-link.fitted,\n",
              "a:link.sk-estimator-doc-link.fitted,\n",
              "a:visited.sk-estimator-doc-link.fitted {\n",
              "  /* fitted */\n",
              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
              "  color: var(--sklearn-color-fitted-level-1);\n",
              "}\n",
              "\n",
              "/* On hover */\n",
              "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
              ".sk-estimator-doc-link:hover,\n",
              "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
              ".sk-estimator-doc-link:hover {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
              "  color: var(--sklearn-color-background);\n",
              "  text-decoration: none;\n",
              "}\n",
              "\n",
              "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
              ".sk-estimator-doc-link.fitted:hover,\n",
              "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
              ".sk-estimator-doc-link.fitted:hover {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-3);\n",
              "  color: var(--sklearn-color-background);\n",
              "  text-decoration: none;\n",
              "}\n",
              "\n",
              "/* Span, style for the box shown on hovering the info icon */\n",
              ".sk-estimator-doc-link span {\n",
              "  display: none;\n",
              "  z-index: 9999;\n",
              "  position: relative;\n",
              "  font-weight: normal;\n",
              "  right: .2ex;\n",
              "  padding: .5ex;\n",
              "  margin: .5ex;\n",
              "  width: min-content;\n",
              "  min-width: 20ex;\n",
              "  max-width: 50ex;\n",
              "  color: var(--sklearn-color-text);\n",
              "  box-shadow: 2pt 2pt 4pt #999;\n",
              "  /* unfitted */\n",
              "  background: var(--sklearn-color-unfitted-level-0);\n",
              "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
              "}\n",
              "\n",
              ".sk-estimator-doc-link.fitted span {\n",
              "  /* fitted */\n",
              "  background: var(--sklearn-color-fitted-level-0);\n",
              "  border: var(--sklearn-color-fitted-level-3);\n",
              "}\n",
              "\n",
              ".sk-estimator-doc-link:hover span {\n",
              "  display: block;\n",
              "}\n",
              "\n",
              "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
              "\n",
              "#sk-container-id-1 a.estimator_doc_link {\n",
              "  float: right;\n",
              "  font-size: 1rem;\n",
              "  line-height: 1em;\n",
              "  font-family: monospace;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  border-radius: 1rem;\n",
              "  height: 1rem;\n",
              "  width: 1rem;\n",
              "  text-decoration: none;\n",
              "  /* unfitted */\n",
              "  color: var(--sklearn-color-unfitted-level-1);\n",
              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
              "  /* fitted */\n",
              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
              "  color: var(--sklearn-color-fitted-level-1);\n",
              "}\n",
              "\n",
              "/* On hover */\n",
              "#sk-container-id-1 a.estimator_doc_link:hover {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
              "  color: var(--sklearn-color-background);\n",
              "  text-decoration: none;\n",
              "}\n",
              "\n",
              "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-3);\n",
              "}\n",
              "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(max_iter=1000)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression(max_iter=1000)</pre></div> </div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Evaluation & Confidence Levels***"
      ],
      "metadata": {
        "id": "5nfHxqaQz7hU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "log_pred = log_model.predict(X_test)\n",
        "log_prob = log_model.predict_proba(X_test)[:, 1]\n",
        "\n",
        "print(\"Accuracy:\", accuracy_score(y_test, log_pred))\n",
        "print(classification_report(y_test, log_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QHM0jJ-GoXZa",
        "outputId": "80793c07-ea4c-4f59-dcb6-bbfe57ef06e2"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy: 0.8633333333333333\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.91      0.94      0.92       256\n",
            "           1       0.54      0.43      0.48        44\n",
            "\n",
            "    accuracy                           0.86       300\n",
            "   macro avg       0.72      0.68      0.70       300\n",
            "weighted avg       0.85      0.86      0.86       300\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Confusion Matrix***"
      ],
      "metadata": {
        "id": "cRDZ4PaT0FXM"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "cm = confusion_matrix(y_test, log_pred)\n",
        "sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Blues\")\n",
        "plt.title(\"Logistic Regression – Confusion Matrix\")\n",
        "plt.xlabel(\"Predicted\")\n",
        "plt.ylabel(\"Actual\")\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "hwkvUnu7oXe8",
        "outputId": "85afd29a-edf5-432c-92f8-b3bfd1de9d80"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Explainability – Model Coefficients***"
      ],
      "metadata": {
        "id": "RYvdWqD70LLL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "coef_df = pd.DataFrame({\n",
        "    'Feature': selected_features,\n",
        "    'Coefficient': log_model.coef_[0]\n",
        "}).sort_values(by='Coefficient', ascending=False)\n",
        "\n",
        "print(coef_df)\n",
        "\n",
        "sns.barplot(x='Coefficient', y='Feature', data=coef_df)\n",
        "plt.title(\"Logistic Regression – Feature Influence\")\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 594
        },
        "id": "RrCczYs2oXkR",
        "outputId": "e94403b9-e915-401f-f716-f1d0110a6cbe"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              Feature  Coefficient\n",
            "0        Transactions     3.386396\n",
            "4  Loan_Approval_Rate     0.128976\n",
            "1    Market_Sentiment     0.117218\n",
            "3             Revenue    -0.017368\n",
            "2         Stock_Price    -0.034154\n",
            "5            Expenses    -0.229175\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAArEAAAHHCAYAAACoSQBsAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAW39JREFUeJzt3Xt8z/X///H7e5udTw5jDrM55Hw+n+c8OdQk55op4oMipw+fcopSziqJ1IaIEElFqElSMXMeSUQZE9nMGLbX7w+/vb/etmmbMa+5XS+X9+Wy1+v1fL1ej+f79Z7dPd/P9+ttMQzDEAAAAGAidrldAAAAAJBVhFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAD73mzZurefPmOXa8gIAAhYaG5tjxIFksFk2cODG3y0Au2bhxo2rUqCFnZ2dZLBZdunRJoaGhCggIyO3SkIcRYgFkWnh4uCwWi3bv3p3bpfyrH3/8URMnTtSlS5fu63kCAgJksVisDzc3N9WrV09Lliy5r+fFvbnzut3+uHbt2n055xtvvKF169bdl2Pfq4CAAHXs2DFb+164cEHdunWTi4uL5s2bp6VLl8rNzS2HKwTScsjtAgDg33zzzTdZ3ufHH3/UpEmTFBoaKm9vb5ttR48elZ1dzv0fvkaNGhoxYoQkKSYmRosWLVKfPn2UlJSk/v3759h5HmZXr16Vg4O5/qTcft1u5+joeF/O98Ybb+jpp59WcHDwfTl+btm1a5cuX76syZMnq3Xr1rldDh4h5voXB8AjKadDhZOTU44er3jx4nrmmWesy6GhoSpdurRmz579wEPslStXcmUUzNnZ+YGf817ded3MKCUlRdevX8/V5z82NlaS0vxnEbjfmE4AIMdFRUXp8ccfl6enp9zd3dWqVSv99NNPadrt379fgYGBcnFxUYkSJTRlyhSFhYXJYrHo5MmT1nbpzYl95513VLlyZbm6uip//vyqU6eOli9fLkmaOHGiRo0aJUkqVaqU9W3i1GOmNyf20qVLevnllxUQECAnJyeVKFFCISEh+vvvv7Pcfx8fH1WoUEHHjx+3WZ+SkqI5c+aocuXKcnZ2VpEiRTRgwAD9888/adpNnDhRxYoVk6urq1q0aKHDhw+nqTt1ese2bds0aNAgFS5cWCVKlLBu//rrr9W0aVO5ubnJw8NDHTp00KFDh2zOdfbsWfXt21clSpSQk5OTihYtqieffNLm+d+9e7eCgoJUqFAhubi4qFSpUnruuedsjpPenNjMvA5S+7Bjxw4NHz5cPj4+cnNzU+fOnXX+/PnMPuX3xaVLlzRs2DD5+fnJyclJZcuW1VtvvaWUlBSbdjNmzFCjRo1UsGBBubi4qHbt2lq9erVNG4vFoitXrmjx4sXW12Pqtcxo7ujEiRNlsVjSHGfIkCFatmyZKleuLCcnJ23cuFGS9Ndff+m5555TkSJF5OTkpMqVK+ujjz7KVt9Pnjwpi8WiGTNmaOHChSpTpoycnJxUt25d7dq1y9quefPm6tOnjySpbt26Nv26U0REhCwWiyIiItI9V3h4uM36I0eO6Omnn1aBAgXk7OysOnXqaP369TZtsvr6+frrrxUYGCgPDw95enqqbt261n83Uv38889q166dvLy85OrqqsDAQO3YsSOTzxweJEZiAeSoQ4cOqWnTpvL09NTo0aOVL18+LViwQM2bN9e2bdtUv359Sbf+4LZo0UIWi0Vjx46Vm5ubFi1alKlR0g8++EAvvfSSnn76aQ0dOlTXrl3T/v379fPPP6tXr1566qmn9Ouvv+qTTz7R7NmzVahQIUm3wmV6EhIS1LRpU0VHR+u5555TrVq19Pfff2v9+vX6888/rftn1s2bN/Xnn38qf/78NusHDBig8PBw9e3bVy+99JJOnDihd999V1FRUdqxY4fy5csnSRo7dqymTZumTp06KSgoSPv27VNQUFCGczUHDRokHx8fjR8/XleuXJEkLV26VH369FFQUJDeeustJSYmav78+WrSpImioqKsoalLly46dOiQXnzxRQUEBCg2NlabN2/WqVOnrMtt27aVj4+PxowZI29vb508eVKfffbZXZ+DzL4OUr344ovKnz+/JkyYoJMnT2rOnDkaMmSIVq5cmaXnPitu3LiR5j8prq6ucnV1VWJiogIDA/XXX39pwIABKlmypH788UeNHTtWMTExmjNnjnWfuXPn6oknnlDv3r11/fp1rVixQl27dtWGDRvUoUMHSbeuR79+/VSvXj298MILkqQyZcpkq+5vv/1Wn376qYYMGaJChQopICBA586dU4MGDawh18fHR19//bWef/55xcfHa9iwYdk61/Lly3X58mUNGDBAFotF06ZN01NPPaXff/9d+fLl0yuvvKLy5ctr4cKFeu2111SqVKls9+t2hw4dUuPGjVW8eHGNGTNGbm5u+vTTTxUcHKw1a9aoc+fONu0z8/oJDw/Xc889p8qVK2vs2LHy9vZWVFSUNm7cqF69ekm69dw+/vjjql27tiZMmCA7OzuFhYWpZcuW2r59u+rVq3fPfUMOMgAgk8LCwgxJxq5duzJsExwcbDg6OhrHjx+3rjtz5ozh4eFhNGvWzLruxRdfNCwWixEVFWVdd+HCBaNAgQKGJOPEiRPW9YGBgUZgYKB1+cknnzQqV65811qnT5+e5jip/P39jT59+liXx48fb0gyPvvsszRtU1JS7noef39/o23btsb58+eN8+fPGwcOHDCeffZZQ5IxePBga7vt27cbkoxly5bZ7L9x40ab9WfPnjUcHByM4OBgm3YTJ040JNnUnXo9mjRpYty8edO6/vLly4a3t7fRv39/m2OcPXvW8PLysq7/559/DEnG9OnTM+zf2rVr//WaG4ZhSDImTJhgXc7s6yC1D61bt7Z5rl9++WXD3t7euHTp0l3Pm13+/v6GpDSP1D5MnjzZcHNzM3799Veb/caMGWPY29sbp06dsq5LTEy0aXP9+nWjSpUqRsuWLW3Wu7m52Vy/VH369DH8/f3TrJ8wYYJx559pSYadnZ1x6NAhm/XPP/+8UbRoUePvv/+2Wd+jRw/Dy8srTY138vf3Nzp06GBdPnHihCHJKFiwoHHx4kXr+s8//9yQZHzxxRfWdRn9u3Bnv7777jtDkvHdd9/ZtEs9V1hYmHVdq1atjKpVqxrXrl2zrktJSTEaNWpkPPbYY2nO/W+vn0uXLhkeHh5G/fr1jatXr9qcP3W/lJQU47HHHjOCgoJsjpWYmGiUKlXKaNOmTYbPH3IH0wkA5Jjk5GR98803Cg4OVunSpa3rixYtql69eumHH35QfHy8pFu35GnYsKFq1KhhbVegQAH17t37X8/j7e2tP//80+ZtzXuxZs0aVa9ePc3ojqQ0b+em55tvvpGPj498fHxUtWpVLV26VH379tX06dOtbVatWiUvLy+1adNGf//9t/VRu3Ztubu767vvvpMkbd26VTdv3tSgQYNszvHiiy9meP7+/fvL3t7eurx582ZdunRJPXv2tDmXvb296tevbz2Xi4uLHB0dFRERkWZKQ6rUeY4bNmzQjRs3/vW5kLL2Okj1wgsv2DzXTZs2VXJysv74449MnTM76tevr82bN9s8QkJCJN26Xk2bNlX+/PltnsPWrVsrOTlZ33//vfU4Li4u1p//+ecfxcXFqWnTptqzZ899qTswMFCVKlWyLhuGoTVr1qhTp04yDMOm3qCgIMXFxWW7lu7du9u8o9C0aVNJ0u+//35vnbiLixcv6ttvv1W3bt10+fJla18uXLigoKAgHTt2TH/99ZfNPv/2+tm8ebMuX76sMWPGpJk/nLrf3r17dezYMfXq1UsXLlywnvfKlStq1aqVvv/++zRTSZC7mE4AIMecP39eiYmJKl++fJptFStWVEpKik6fPq3KlSvrjz/+UMOGDdO0K1u27L+e57///a+2bNmievXqqWzZsmrbtq169eqlxo0bZ6vu48ePq0uXLtnaV7oVhqZMmaLk5GQdPHhQU6ZM0T///GPzgbRjx44pLi5OhQsXTvcYqR+OSf2je+fzUKBAgTTTE1KVKlXKZvnYsWOSpJYtW6bb3tPTU9KtD7i99dZbGjFihIoUKaIGDRqoY8eOCgkJka+vr6RbgalLly6aNGmSZs+erebNmys4OFi9evXKcOpHVl4HqUqWLGnTLrWvGYVr6dYdEeLi4tLd5uXlZRMu01OoUKEMP01/7Ngx7d+/P8MpKKnXS7oV8KdMmaK9e/cqKSnJuj4z/wHKjjuv9/nz53Xp0iUtXLhQCxcu/Nd6syI71+Ve/fbbbzIMQ+PGjdO4cePSbRMbG6vixYtnus7U+elVqlTJ8Lypvzepc3zTExcXl+HvIR48QiwA06lYsaKOHj2qDRs2aOPGjVqzZo3ee+89jR8/XpMmTXrg9dwehoKCglShQgV17NhRc+fO1fDhwyXd+rBW4cKFtWzZsnSPkVFYyow7w1rqaNHSpUutYfR2t98Ka9iwYerUqZPWrVunTZs2ady4cZo6daq+/fZb1axZUxaLRatXr9ZPP/2kL774Qps2bdJzzz2nmTNn6qeffpK7u3u2677d7SPJtzMMI8N9Vq5cqb59+6a7LSws7J6+0CIlJUVt2rTR6NGj091erlw5SdL27dv1xBNPqFmzZnrvvfdUtGhR5cuXT2FhYWk+MJSRjMJucnJyuuszut7PPPNMhgGsWrVqmarlTtm5LhnJbD9T+zNy5EgFBQWlu8+d/8nLiTpTzzt9+nSbd4hul1Ovd+QMQiyAHOPj4yNXV1cdPXo0zbYjR47Izs5Ofn5+kiR/f3/99ttvadqlty49bm5u6t69u7p3767r16/rqaee0uuvv66xY8davzUos8qUKaODBw9muv2/6dChgwIDA/XGG29owIABcnNzU5kyZbRlyxY1btz4riOE/v7+km49D7ePuF24cCHTo1+pH6wpXLhwpu7bWaZMGY0YMUIjRozQsWPHVKNGDc2cOVMff/yxtU2DBg3UoEEDvf7661q+fLl69+6tFStWqF+/fmmOl5XXwb0ICgrS5s2b0912+yhvdpQpU0YJCQn/+vytWbNGzs7O2rRpk83IdFhYWJq2Gb0m8+fPn+6XcmR2KoWPj488PDyUnJz8UN+nNXUE886+3tnP1Cko+fLly7H+pP5OHDx4MMN3e1LbeHp6PtTPI/4Pc2IB5Bh7e3u1bdtWn3/+uc0tms6dO6fly5erSZMm1reyg4KCtHPnTu3du9fa7uLFixmOVN7uwoULNsuOjo6qVKmSDMOwzttMvVdqZr6xq0uXLtq3b5/Wrl2bZlt2RpykW1MeLly4oA8++ECS1K1bNyUnJ2vy5Mlp2t68edNaZ6tWreTg4KD58+fbtHn33Xczfe6goCB5enrqjTfeSHcea+qthxITE9Pc8aBMmTLy8PCwvi3+zz//pHkOUkepbn/r/HZZeR3ci6JFi6p169bpPooWLXpPx+7WrZt27typTZs2pdl26dIl3bx5U9KtvlosFpvRxJMnT6b7zVxubm7pvh7LlCmjuLg47d+/37ouJiYm3ddjeuzt7dWlSxetWbMm3f+M5fatylL5+/vL3t7eZj6xJL333ns2y4ULF1bz5s21YMECxcTEpDlOdvrTtm1beXh4aOrUqWle86mv79q1a6tMmTKaMWOGEhIScuS8uL8YiQWQZR999JH13pS3Gzp0qKZMmaLNmzerSZMmGjRokBwcHLRgwQIlJSVp2rRp1rajR4/Wxx9/rDZt2ujFF1+03mKrZMmSunjx4l1HUtu2bStfX181btxYRYoUUXR0tN5991116NBBHh4ekm79QZKkV155RT169FC+fPnUqVOndL8IYNSoUVq9erW6du2q5557TrVr19bFixe1fv16vf/++6pevXqWn6PHH39cVapU0axZszR48GAFBgZqwIABmjp1qvbu3au2bdsqX758OnbsmFatWqW5c+fq6aefVpEiRTR06FDNnDlTTzzxhNq1a6d9+/bp66+/VqFChTI1wuzp6an58+fr2WefVa1atdSjRw/5+Pjo1KlT+vLLL9W4cWO9++67+vXXX9WqVSt169ZNlSpVkoODg9auXatz586pR48ekqTFixfrvffeU+fOnVWmTBldvnxZH3zwgTw9PdW+ffsMa8js6+BhNWrUKK1fv14dO3ZUaGioateurStXrujAgQNavXq1Tp48qUKFCqlDhw6aNWuW2rVrp169eik2Nlbz5s1T2bJlbUKpdOs1uWXLFs2aNUvFihVTqVKlVL9+ffXo0UP//e9/1blzZ7300kvW26GVK1cu0x/IevPNN/Xdd9+pfv366t+/vypVqqSLFy9qz5492rJliy5evHg/nqYs8fLyUteuXfXOO+/IYrGoTJky2rBhQ7rzdefNm6cmTZqoatWq6t+/v0qXLq1z585p586d+vPPP7Vv374sndvT01OzZ89Wv379VLduXfXq1Uv58+fXvn37lJiYqMWLF8vOzk6LFi3S448/rsqVK6tv374qXry4/vrrL3333Xfy9PTUF198kVNPB3JCbt0WAYD5pN7OJqPH6dOnDcMwjD179hhBQUGGu7u74erqarRo0cL48ccf0xwvKirKaNq0qeHk5GSUKFHCmDp1qvH2228bkoyzZ89a2915i60FCxYYzZo1MwoWLGg4OTkZZcqUMUaNGmXExcXZHH/y5MlG8eLFDTs7O5vbbd15iy3DuHV7ryFDhhjFixc3HB0djRIlShh9+vRJc8uiO915a6LbhYeHp7l10MKFC43atWsbLi4uhoeHh1G1alVj9OjRxpkzZ6xtbt68aYwbN87w9fU1XFxcjJYtWxrR0dFGwYIFjYEDB6a5Hhnd/uq7774zgoKCDC8vL8PZ2dkoU6aMERoaauzevdswDMP4+++/jcGDBxsVKlQw3NzcDC8vL6N+/frGp59+aj3Gnj17jJ49exolS5Y0nJycjMKFCxsdO3a0HiOV7rjFVuq+//Y6yKgPGd2OKafc7bqlunz5sjF27FijbNmyhqOjo1GoUCGjUaNGxowZM4zr169b23344YfGY489Zjg5ORkVKlQwwsLC0r091pEjR4xmzZoZLi4uaW6X9s033xhVqlQxHB0djfLlyxsff/xxhrfYuv3Wbbc7d+6cMXjwYMPPz8/Ily+f4evra7Rq1cpYuHBhlp+P1NtepXf7tTuvdWZvsWUYhnH+/HmjS5cuhqurq5E/f35jwIABxsGDB9P8nhiGYRw/ftwICQkxfH19jXz58hnFixc3OnbsaKxevfpfz53R62f9+vVGo0aNDBcXF8PT09OoV6+e8cknn9i0iYqKMp566inrvy/+/v5Gt27djK1bt2b09CGXWAwjm++VAcB9MGzYMC1YsEAJCQkZfljjUXTp0iXlz59fU6ZM0SuvvJLb5QBArmNOLIBcc/XqVZvlCxcuaOnSpWrSpMkjHWDvfF4kWb8h6s6v3wWARxVzYgHkmoYNG6p58+aqWLGizp07pw8//FDx8fEZ3hvyUbFy5UqFh4erffv2cnd31w8//KBPPvlEbdu2zfa9cAEgryHEAsg17du31+rVq7Vw4UJZLBbVqlVLH374oZo1a5bbpeWqatWqycHBQdOmTVN8fLz1w15TpkzJ7dIA4KHBnFgAAACYDnNiAQAAYDqEWAAAAJgOc2KRp6SkpOjMmTPy8PDI0teOAgCA3GMYhi5fvqxixYrJzi5zY6yEWOQpZ86cyZHvZAcAAA/e6dOnVaJEiUy1JcQiT0n9ytHTp0/nyHezAwCA+y8+Pl5+fn7Wv+OZQYhFnpI6hcDT05MQCwCAyWRlKiAf7AIAAIDpEGIBAABgOoRYAAAAmA5zYoGHWO1RS3K7BAAArCKnh+R2CVaMxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQi2yLiIiQxWLRpUuXcrsUAADwiCHE5jCLxXLXx8SJE3O7xGxp3ry5hg0bZrOuUaNGiomJkZeXV+4UBQAAHlkOuV1AXhMTE2P9eeXKlRo/fryOHj1qXefu7m792TAMJScny8HBnJfB0dFRvr6+uV0GAAB4BDESm8N8fX2tDy8vL1ksFuvykSNH5OHhoa+//lq1a9eWk5OTfvjhBx0/flxPPvmkihQpInd3d9WtW1dbtmyxOW5AQIDeeOMNPffcc/Lw8FDJkiW1cOFC6/br169ryJAhKlq0qJydneXv76+pU6dat8+aNUtVq1aVm5ub/Pz8NGjQICUkJNicY8eOHWrevLlcXV2VP39+BQUF6Z9//lFoaKi2bdumuXPnWkeUT548me50gjVr1qhy5cpycnJSQECAZs6cmaP9AAAAkAixuWLMmDF68803FR0drWrVqikhIUHt27fX1q1bFRUVpXbt2qlTp046deqUzX4zZ85UnTp1FBUVpUGDBuk///mPdZT37bff1vr16/Xpp5/q6NGjWrZsmQICAqz72tnZ6e2339ahQ4e0ePFiffvttxo9erR1+969e9WqVStVqlRJO3fu1A8//KBOnTopOTlZc+fOVcOGDdW/f3/FxMQoJiZGfn5+afoVGRmpbt26qUePHjpw4IAmTpyocePGKTw8PMf6caekpCTFx8fbPAAAQN5nzvexTe61115TmzZtrMsFChRQ9erVrcuTJ0/W2rVrtX79eg0ZMsS6vn379ho0aJAk6b///a9mz56t7777TuXLl9epU6f02GOPqUmTJrJYLPL397c55+3zWQMCAjRlyhQNHDhQ7733niRp2rRpqlOnjnVZkipXrmz92dHRUa6urnedPjBr1iy1atVK48aNkySVK1dOhw8f1vTp0xUaGpoj/bjT1KlTNWnSpLu2AQAAeQ8jsbmgTp06NssJCQkaOXKkKlasKG9vb7m7uys6OjrNSGy1atWsP6dOU4iNjZUkhYaGau/evSpfvrxeeuklffPNNzb7btmyRa1atVLx4sXl4eGhZ599VhcuXFBiYqKk/xuJvRfR0dFq3LixzbrGjRvr2LFjSk5OzpF+3Gns2LGKi4uzPk6fPn1PfQAAAOZAiM0Fbm5uNssjR47U2rVr9cYbb2j79u3au3evqlatquvXr9u0y5cvn82yxWJRSkqKJKlWrVo6ceKEJk+erKtXr6pbt256+umnJUknT55Ux44dVa1aNa1Zs0aRkZGaN2+eJFnP4eLicl/6mp7s9iM9Tk5O8vT0tHkAAIC8jxD7ENixY4dCQ0PVuXNnVa1aVb6+vjp58mSWj+Pp6anu3bvrgw8+0MqVK7VmzRpdvHhRkZGRSklJ0cyZM9WgQQOVK1dOZ86csdm3WrVq2rp1a4bHdnR0tBlNTU/FihW1Y8eONH0rV66c7O3t77kfAAAAqZgT+xB47LHH9Nlnn6lTp06yWCwaN26cdWQys2bNmqWiRYuqZs2asrOz06pVq+Tr6ytvb2+VLVtWN27c0DvvvKNOnTppx44dev/99232Hzt2rKpWrapBgwZp4MCBcnR01HfffaeuXbuqUKFCCggI0M8//6yTJ0/K3d1dBQoUSFPDiBEjVLduXU2ePFndu3fXzp079e6779rMs72XfgAAAKRiJPYhMGvWLOXPn1+NGjVSp06dFBQUpFq1amXpGB4eHtYPZ9WtW1cnT57UV199JTs7O1WvXl2zZs3SW2+9pSpVqmjZsmVpbltVrlw5ffPNN9q3b5/q1aunhg0b6vPPP7few3bkyJGyt7dXpUqV5OPjk2a+rnRrKsCnn36qFStWqEqVKho/frxee+01mw913Us/AAAAUlkMwzByuwggp8THx8vLy0txcXF5Yn5s7VFLcrsEAACsIqeH3JfjZufvN8NbAAAAMB1CLAAAAEyHEAsAAADTIcQCAADAdAixAAAAMB1CLAAAAEyHEAsAAADTIcQCAADAdAixAAAAMB1CLAAAAEyHEAsAAADTIcQCAADAdAixAAAAMB1CLAAAAEyHEAsAAADTIcQCAADAdAixAAAAMB1CLAAAAEzHIbcLAJCxyOkhuV0CAAAPJUZiAQAAYDqEWAAAAJgOIRYAAACmQ4gFAACA6RBiAQAAYDqEWAAAAJgOIRYAAACmQ4gFAACA6RBiAQAAYDqEWAAAAJgOIRYAAACm45DbBQDIWO1RS+5p/8jpITlUCQAADxdGYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiH2ERcRESGLxaJLly7ldikAAACZlqshNjQ0VMHBwblZQqZUqFBBTk5OOnv2bG6XkqtSA2/qw8fHR+3bt9eBAweydJzw8HB5e3vfnyIBAMAjgZHYf/HDDz/o6tWrevrpp7V48eIHdt4bN248sHNl1dGjRxUTE6NNmzYpKSlJHTp00PXr13O7LAAA8Ah5aEPstm3bVK9ePTk5Oalo0aIaM2aMbt68ad2+ceNGNWnSRN7e3ipYsKA6duyo48ePW7efPHlSFotFn332mVq0aCFXV1dVr15dO3fuzFIdH374oXr16qVnn31WH330UZrtAQEBmjx5snr27Ck3NzcVL15c8+bNs2ljsVg0f/58Pf7443JxcVHp0qW1evXqNLWuXLlSgYGBcnZ21rJly5SSkqLXXntNJUqUkJOTk2rUqKGNGzda92vUqJH++9//2pzr/Pnzypcvn77//ntJ0tKlS1WnTh15eHjI19dXvXr1UmxsbJaegzsVLlxYvr6+qlWrloYNG6bTp0/ryJEj1u2zZs1S1apV5ebmJj8/Pw0aNEgJCQmSbo3m9u3bV3FxcdYR3YkTJ0qSkpKSNHLkSBUvXlxubm6qX7++IiIi7qlWAACQNz2UIfavv/5S+/btVbduXe3bt0/z58/Xhx9+qClTpljbXLlyRcOHD9fu3bu1detW2dnZqXPnzkpJSbE51iuvvKKRI0dq7969KleunHr27GkThu/m8uXLWrVqlZ555hm1adNGcXFx2r59e5p206dPV/Xq1RUVFaUxY8Zo6NCh2rx5s02bcePGqUuXLtq3b5969+6tHj16KDo62qZN6r7R0dEKCgrS3LlzNXPmTM2YMUP79+9XUFCQnnjiCR07dkyS1Lt3b61YsUKGYViPsXLlShUrVkxNmzaVdGtEd/Lkydq3b5/WrVunkydPKjQ0NFP9/zdxcXFasWKFJMnR0dG63s7OTm+//bYOHTqkxYsX69tvv9Xo0aMl3Qrec+bMkaenp2JiYhQTE6ORI0dKkoYMGaKdO3dqxYoV2r9/v7p27ap27dpZ+wsAAJDKYtyegB6w0NBQXbp0SevWrbNZ/8orr2jNmjWKjo6WxWKRJL333nv673//q7i4ONnZpc3ef//9t3x8fHTgwAFVqVJFJ0+eVKlSpbRo0SI9//zzkqTDhw+rcuXKio6OVoUKFf61vg8++EDvvfeeoqKiJEnDhg3TpUuXFB4ebm0TEBCgihUr6uuvv7au69Gjh+Lj4/XVV19JujUSO3DgQM2fP9/apkGDBqpVq5bee+89a61z5szR0KFDrW2KFy+uwYMH63//+591Xb169VS3bl3NmzdP58+fV7FixfTtt99aQ2ujRo3UrFkzvfnmm+n2affu3apbt64uX74sd3d3RUREqEWLFvrnn3/+dZ5qals3NzdJt/4jIUlPPPGEPv/88wz3W716tQYOHKi///5b0q05sanPZapTp06pdOnSOnXqlIoVK2Zd37p1a9WrV09vvPFGusdOSkpSUlKSdTk+Pl5+fn6Ki4uTp6fnXftjBrVHLbmn/SOnh+RQJQAA3D/x8fHy8vLK0t/vh3IkNjo6Wg0bNrQGWElq3LixEhIS9Oeff0qSjh07pp49e6p06dLy9PRUQECApFth6HbVqlWz/ly0aFFJyvTb6R999JGeeeYZ6/IzzzyjVatW6fLlyzbtGjZsmGb5zlHWzLSpU6eO9ef4+HidOXNGjRs3tmnTuHFj634+Pj5q27atli1bJkk6ceKEdu7cqd69e1vbR0ZGqlOnTipZsqQ8PDwUGBgoKe3zlBXbt29XZGSkwsPDVa5cOb3//vs227ds2aJWrVqpePHi8vDw0LPPPqsLFy4oMTExw2MeOHBAycnJKleunNzd3a2Pbdu22UwTudPUqVPl5eVlffj5+WW7XwAAwDweyhCbGZ06ddLFixf1wQcf6Oeff9bPP/8sSWk+YJQvXz7rz6mh+M4pB+k5fPiwfvrpJ40ePVoODg5ycHBQgwYNlJiYaH0LPaeljnBmRe/evbV69WrduHFDy5cvV9WqVVW1alVJt0ZKg4KC5OnpqWXLlmnXrl1au3atpLTPU1aUKlVK5cuXV58+fdSvXz91797duu3kyZPq2LGjqlWrpjVr1igyMtI6R/hu50xISJC9vb0iIyO1d+9e6yM6Olpz587NcL+xY8cqLi7O+jh9+nS2+wUAAMzjoQyxFStW1M6dO23meu7YsUMeHh4qUaKELly4oKNHj+rVV19Vq1atVLFiRf3zzz85WsOHH36oZs2aad++fTahavjw4frwww9t2v70009plitWrJjlNrfz9PRUsWLFtGPHDpv1O3bsUKVKlazLTz75pK5du6aNGzdq+fLlNqOwR44c0YULF/Tmm2+qadOmqlChwj1/qOtOgwcP1sGDB63hODIyUikpKZo5c6YaNGigcuXK6cyZMzb7ODo6Kjk52WZdzZo1lZycrNjYWJUtW9bm4evrm+H5nZyc5OnpafMAAAB5n0NuFxAXF6e9e/farHvhhRc0Z84cvfjiixoyZIiOHj2qCRMmaPjw4bKzs1P+/PlVsGBBLVy4UEWLFtWpU6c0ZsyYHKvpxo0bWrp0qV577TVVqVLFZlu/fv00a9YsHTp0SJUrV5Z0K1hOmzZNwcHB2rx5s1atWqUvv/zSZr9Vq1apTp06atKkiZYtW6ZffvklTRi+06hRozRhwgSVKVNGNWrUUFhYmPbu3WudPiDdGr0NDg7WuHHjFB0drZ49e1q3lSxZUo6OjnrnnXc0cOBAHTx4UJMnT77Xp8eGq6ur+vfvrwkTJig4OFhly5bVjRs39M4776hTp07asWNHmukGAQEBSkhI0NatW1W9enW5urqqXLly6t27t0JCQjRz5kzVrFlT58+f19atW1WtWjV16NAhR+sGAADmlusjsREREapZs6bNY/Lkyfrqq6/0yy+/qHr16ho4cKCef/55vfrqq5Juffp9xYoVioyMVJUqVfTyyy9r+vTpOVbT+vXrdeHCBXXu3DnNtooVK6pixYo2AXTEiBHavXu3atasqSlTpmjWrFkKCgqy2W/SpElasWKFqlWrpiVLluiTTz6xGVFNz0svvaThw4drxIgRqlq1qjZu3Kj169frscces2nXu3dv7du3T02bNlXJkiWt6318fBQeHq5Vq1apUqVKevPNNzVjxozsPCV3NWTIEEVHR2vVqlWqXr26Zs2apbfeektVqlTRsmXLNHXqVJv2jRo10sCBA9W9e3f5+Pho2rRpkqSwsDCFhIRoxIgRKl++vIKDg7Vr1y6bPgEAAEi5fHeCvCAgIEDDhg3TsGHDMmxjsVi0du1aU3w7mdll59ONDzPuTgAAeBTkmbsTAAAAAHfzyIbYxx9/3OZWTrc/MronaV7HcwIAAMwi1z/YlVsWLVqkq1evprutQIECmT7OyZMn/7WNWWZs5NRzAgAAcL89siG2ePHiuV3CQ4fnBAAAmMUjO50AAAAA5kWIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOk45HYBADIWOT0kt0sAAOChxEgsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0HHK7AAAZqz1qSbb2i5weksOVAADwcGEkFgAAAKZDiAUAAIDpEGIBAABgOoRYAAAAmA4hFgAAAKZDiAUAAIDpEGIBAABgOoRYAAAAmA4hFgAAAKZDiAUAAIDpEGIBAABgOoRYAAAAmA4hFgAAAKZDiAUAAIDpEGIBAABgOoRYAAAAmA4hFgAAAKZDiAUAAIDpEGIBAABgOoTYuwgPD5e3t3dul/HAREREyGKx6NKlS7ldCgAAwF2ZNsSGhobKYrFo4MCBabYNHjxYFotFoaGhD76w22QnFJ4/f17/+c9/VLJkSTk5OcnX11dBQUHasWNHjtbWvHlzDRs2zGZdo0aNFBMTIy8vrxw9V3aEhoYqODg4t8sAAAAPKdOGWEny8/PTihUrdPXqVeu6a9euafny5SpZsuQ9HfvGjRv3Wl62dOnSRVFRUVq8eLF+/fVXrV+/Xs2bN9eFCxfu+7kdHR3l6+sri8Vy388FAABwL0wdYmvVqiU/Pz999tln1nWfffaZSpYsqZo1a1rXbdy4UU2aNJG3t7cKFiyojh076vjx49btJ0+elMVi0cqVKxUYGChnZ2ctW7YszfnOnz+vOnXqqHPnzkpKSlJKSoqmTp2qUqVKycXFRdWrV9fq1autx2zRooUkKX/+/JkaGb506ZK2b9+ut956Sy1atJC/v7/q1aunsWPH6oknnrBp169fP/n4+MjT01MtW7bUvn37rNsnTpyoGjVqaOnSpQoICJCXl5d69Oihy5cvS7o1yrlt2zbNnTtXFotFFotFJ0+eTDNynDqdYsOGDSpfvrxcXV319NNPKzExUYsXL1ZAQIDy58+vl156ScnJydbzJyUlaeTIkSpevLjc3NxUv359RUREWLenHnfTpk2qWLGi3N3d1a5dO8XExFjrX7x4sT7//HNrfbfvDwAAYOoQK0nPPfecwsLCrMsfffSR+vbta9PmypUrGj58uHbv3q2tW7fKzs5OnTt3VkpKik27MWPGaOjQoYqOjlZQUJDNttOnT6tp06aqUqWKVq9eLScnJ02dOlVLlizR+++/r0OHDunll1/WM888o23btsnPz09r1qyRJB09elQxMTGaO3fuXfvi7u4ud3d3rVu3TklJSRm269q1q2JjY/X1118rMjJStWrVUqtWrXTx4kVrm+PHj2vdunXasGGDNmzYoG3btunNN9+UJM2dO1cNGzZU//79FRMTo5iYGPn5+aV7rsTERL399ttasWKFNm7cqIiICHXu3FlfffWVvvrqKy1dulQLFiywhndJGjJkiHbu3KkVK1Zo//796tq1q9q1a6djx47ZHHfGjBlaunSpvv/+e506dUojR46UJI0cOVLdunWzBtuYmBg1atQo3fqSkpIUHx9v8wAAAHmfQ24XcK+eeeYZjR07Vn/88YckaceOHVqxYoXNyF2XLl1s9vnoo4/k4+Ojw4cPq0qVKtb1w4YN01NPPZXmHEePHlWbNm3UuXNnzZkzRxaLRUlJSXrjjTe0ZcsWNWzYUJJUunRp/fDDD1qwYIECAwNVoEABSVLhwoUz9QExBwcHhYeHq3///nr//fdVq1YtBQYGqkePHqpWrZok6YcfftAvv/yi2NhYOTk5SZJmzJihdevWafXq1XrhhRckSSkpKQoPD5eHh4ck6dlnn9XWrVv1+uuvy8vLS46OjnJ1dZWvr+9da7px44bmz5+vMmXKSJKefvppLV26VOfOnZO7u7sqVaqkFi1a6LvvvlP37t116tQphYWF6dSpUypWrJikW6F048aNCgsL0xtvvGE97vvvv2897pAhQ/Taa69JuhXmXVxclJSU9K/1TZ06VZMmTfrX5xYAAOQtpg+xPj4+6tChg8LDw2UYhjp06KBChQrZtDl27JjGjx+vn3/+WX///bd1BPbUqVM2IbZOnTppjn/16lU1bdpUvXr10pw5c6zrf/vtNyUmJqpNmzY27a9fv24zlSGrunTpog4dOmj79u366aef9PXXX2vatGlatGiRQkNDtW/fPiUkJKhgwYJp6rx9ikRAQIA1wEpS0aJFFRsbm+V6XF1drUFTkooUKaKAgAC5u7vbrEs99oEDB5ScnKxy5crZHCcpKcmm5juPm936xo4dq+HDh1uX4+PjMxxVBgAAeYfpQ6x0a0rBkCFDJEnz5s1Ls71Tp07y9/fXBx98oGLFiiklJUVVqlTR9evXbdq5ubml2dfJyUmtW7fWhg0bNGrUKBUvXlySlJCQIEn68ssvretu3+deODs7q02bNmrTpo3GjRunfv36acKECQoNDVVCQoKKFi2a7hzR20d78+XLZ7PNYrGkmT6RGekd527HTkhIkL29vSIjI2Vvb2/T7vbgm94xDMPIcn1OTk73/HwDAADzyRMhtl27drp+/bosFkuauawXLlzQ0aNH9cEHH6hp06aSbr0ln1l2dnZaunSpevXqpRYtWigiIkLFihVTpUqV5OTkpFOnTikwMDDdfR0dHSXJ5kNP2VGpUiWtW7dO0q0Ps509e1YODg4KCAjI9jEdHR3vua701KxZU8nJyYqNjbU+39lxv+oDAAB5g+k/2CVJ9vb2io6O1uHDh9OM/uXPn18FCxbUwoUL9dtvv+nbb7+1efs5s8dftmyZqlevrpYtW+rs2bPy8PDQyJEj9fLLL2vx4sU6fvy49uzZo3feeUeLFy+WJPn7+8tisWjDhg06f/68dfQ2IxcuXFDLli318ccfa//+/Tpx4oRWrVqladOm6cknn5QktW7dWg0bNlRwcLC++eYbnTx5Uj/++KNeeeUV7d69O9N9CggI0M8//6yTJ0/aTLG4V+XKlVPv3r0VEhKizz77TCdOnNAvv/yiqVOn6ssvv8xSffv379fRo0f1999/59otzwAAwMMpT4RYSfL09JSnp2ea9XZ2dlqxYoUiIyNVpUoVvfzyy5o+fXqWj+/g4KBPPvlElStXVsuWLRUbG6vJkydr3Lhxmjp1qipWrKh27drpyy+/VKlSpSRJxYsX16RJkzRmzBgVKVLEOuUhI+7u7qpfv75mz56tZs2aqUqVKho3bpz69++vd999V9Ktt92/+uorNWvWTH379lW5cuXUo0cP/fHHHypSpEim+zNy5EjZ29urUqVK8vHx0alTp7L8nGQkLCxMISEhGjFihMqXL6/g4GDt2rUrS/fu7d+/v8qXL686derIx8cnx7/sAQAAmJvFyM5EROAhFR8fLy8vL8XFxaX7nxqzqT1qSbb2i5weksOVAABw/2Tn73eeGYkFAADAoyPbIXbp0qVq3LixihUrZr1H65w5c/T555/nWHF5zalTp6xfaJDeIyff0gcAAMjLsnV3gvnz52v8+PEaNmyYXn/9deunyL29vTVnzhzrh5Bgq1ixYtq7d+9dtwMAAODfZSvEvvPOO/rggw8UHBxs/SpT6daXBaR+dSjScnBwUNmyZXO7DAAAANPL1nSCEydOpPutVE5OTrpy5co9FwUAAADcTbZCbKlSpdJ9W3zjxo2qWLHivdYEAAAA3FW2phMMHz5cgwcP1rVr12QYhn755Rd98sknmjp1qhYtWpTTNQIAAAA2shVi+/XrJxcXF7366qtKTExUr169VKxYMc2dO1c9evTI6RoBAAAAG1kOsTdv3tTy5csVFBSk3r17KzExUQkJCSpcuPD9qA8AAABII8tzYh0cHDRw4EBdu3ZNkuTq6kqABQAAwAOVrQ921atXT1FRUTldCwAAAJAp2ZoTO2jQII0YMUJ//vmnateuLTc3N5vt1apVy5HiAAAAgPRkK8SmfnjrpZdesq6zWCwyDEMWi8X6DV4AAADA/ZCtEHvixImcrgMAAADItGyFWH9//5yuAwAAAMi0bIXYJUuW3HV7SEhItooBAAAAMiNbIXbo0KE2yzdu3FBiYqIcHR3l6upKiAUAAMB9la1bbP3zzz82j4SEBB09elRNmjTRJ598ktM1AgAAADYshmEYOXWw3bt365lnntGRI0dy6pBAlsTHx8vLy0txcXHy9PTM7XIAAEAmZOfvd7ZGYjPi4OCgM2fO5OQhAQAAgDSyNSd2/fr1NsuGYSgmJkbvvvuuGjdunCOFAQAAABnJVogNDg62WbZYLPLx8VHLli01c+bMnKgLAAAAyFC2QmxKSkpO1wEAAABkWrbmxL722mtKTExMs/7q1at67bXX7rkoAAAA4G6ydXcCe3t7xcTEqHDhwjbrL1y4oMKFCys5OTnHCgSygrsTAABgPg/s7gSGYchisaRZv2/fPhUoUCA7hwQAAAAyLUtzYvPnzy+LxSKLxaJy5crZBNnk5GQlJCRo4MCBOV4kAAAAcLsshdg5c+bIMAw999xzmjRpkry8vKzbHB0dFRAQoIYNG+Z4kQAAAMDtshRi+/TpI0kqVaqUGjVqpHz58t2XogAAAIC7ydYttgIDA60/X7t2TdevX7fZzgdqAAAAcD9l64NdiYmJGjJkiAoXLiw3Nzflz5/f5gHg3tQetUS1Ry3J7TIAAHhoZSvEjho1St9++63mz58vJycnLVq0SJMmTVKxYsW0ZAl/eAEAAHB/ZWs6wRdffKElS5aoefPm6tu3r5o2baqyZcvK399fy5YtU+/evXO6TgAAAMAqWyOxFy9eVOnSpSXdmv968eJFSVKTJk30/fff51x1AAAAQDqyFWJLly6tEydOSJIqVKigTz/9VNKtEVpvb+8cKw4AAABIT7ZCbN++fbVv3z5J0pgxYzRv3jw5Ozvr5Zdf1qhRo3K0QAAAAOBO2ZoT+/LLL1t/bt26tY4cOaLIyEiVLVtW1apVy7HiAAAAgPRkK8Te7tq1a/L395e/v39O1AMAAAD8q2xNJ0hOTtbkyZNVvHhxubu76/fff5ckjRs3Th9++GGOFggAAADcKVsh9vXXX1d4eLimTZsmR0dH6/oqVapo0aJFOVYcAAAAkJ5shdglS5Zo4cKF6t27t+zt7a3rq1evriNHjuRYcQAAAEB6shVi//rrL5UtWzbN+pSUFN24ceOeiwIAAADuJlshtlKlStq+fXua9atXr1bNmjXvuSgAAADgbrJ1d4Lx48erT58++uuvv5SSkqLPPvtMR48e1ZIlS7Rhw4acrhEAAACwkaWR2N9//12GYejJJ5/UF198oS1btsjNzU3jx49XdHS0vvjiC7Vp0+Z+1QoAAABIyuJI7GOPPaaYmBgVLlxYTZs2VYECBXTgwAEVKVLkftUHAAAApJGlkVjDMGyWv/76a125ciVHCwIAAAD+TbY+2JXqzlALAAAAPAhZCrEWi0UWiyXNOgAAAOBBytKcWMMwFBoaKicnJ0nStWvXNHDgQLm5udm0++yzz3KuQgAAAOAOWRqJ7dOnjwoXLiwvLy95eXnpmWeeUbFixazLqQ88OKGhodYR8nz58qlUqVIaPXq0rl27ltulAQAA3DdZGokNCwu7X3XgHrRr105hYWG6ceOGIiMj1adPH1ksFr311lu5XRoAAMB9cU8f7MLDwcnJSb6+vvLz81NwcLBat26tzZs3S7r1VcBTp05VqVKl5OLiourVq2v16tXWbSVKlND8+fNtjhcVFSU7Ozv98ccfkqRLly6pX79+8vHxkaenp1q2bKl9+/ZZ20+cOFE1atTQ0qVLFRAQIC8vL/Xo0UOXL1+2tgkICNCcOXNszlOjRg1NnDjRuvxv5wEAAEhFiM1jDh48qB9//FGOjo6SpKlTp2rJkiV6//33dejQIb388st65plntG3bNtnZ2alnz55avny5zTGWLVumxo0by9/fX5LUtWtXxcbG6uuvv1ZkZKRq1aqlVq1a6eLFi9Z9jh8/rnXr1mnDhg3asGGDtm3bpjfffDNLtWfmPAAAAFI2v3YWD5cNGzbI3d1dN2/eVFJSkuzs7PTuu+8qKSlJb7zxhrZs2aKGDRtKkkqXLq0ffvhBCxYsUGBgoHr37q2ZM2fq1KlTKlmypFJSUrRixQq9+uqrkqQffvhBv/zyi2JjY60f6JsxY4bWrVun1atX64UXXpB0a1Q3PDxcHh4ekqRnn31WW7du1euvv56pPmT2PHdKSkpSUlKSdTk+Pj4bzyAAADAbQmwe0KJFC82fP19XrlzR7Nmz5eDgoC5duujQoUNKTExM81XA169fV82aNSXdeku/YsWKWr58ucaMGaNt27YpNjZWXbt2lSTt27dPCQkJKliwoM0xrl69quPHj1uXAwICrAFWkooWLarY2NhM9yGz57nT1KlTNWnSpEyfBwAA5A2E2DzAzc1NZcuWlSR99NFHql69uj788ENVqVJFkvTll1+qePHiNvukjnZKUu/eva0hdvny5WrXrp01TCYkJKho0aKKiIhIc15vb2/rz/ny5bPZZrFYlJKSYl22s7NL8+UYN27csP6c2fPcaezYsRo+fLh1OT4+Xn5+fhm2BwAAeQMhNo+xs7PT//73Pw0fPly//vqrnJycdOrUKQUGBma4T69evfTqq68qMjJSq1ev1vvvv2/dVqtWLZ09e1YODg4KCAjIdl0+Pj6KiYmxLsfHx+vEiRP3fB4nJyebQA4AAB4NfLArD+ratavs7e21YMECjRw5Ui+//LIWL16s48ePa8+ePXrnnXe0ePFia/uAgAA1atRIzz//vJKTk/XEE09Yt7Vu3VoNGzZUcHCwvvnmG508eVI//vijXnnlFe3evTvTNbVs2VJLly7V9u3bdeDAAfXp00f29vY5fh4AAPBoYCQ2D3JwcNCQIUM0bdo0nThxQj4+Ppo6dap+//13eXt7q1atWvrf//5ns0/v3r01aNAghYSEyMXFxbreYrHoq6++0iuvvKK+ffvq/Pnz8vX1VbNmzVSkSJFM1zR27FidOHFCHTt2lJeXlyZPnmwzEptT5wEAAI8Gi3HnREXAxOLj4+Xl5aW4uDh5enrmdjnZVnvUEklS5PSQXK4EAID7Lzt/v5lOAAAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0HHK7AABpRU4Pye0SAAB4qDESCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATMchtwsA8H9qj1pisxw5PSSXKgEA4OHGSCwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEPiLCw8Pl7e2d588JAAAeDYTYXHD+/Hn95z//UcmSJeXk5CRfX18FBQVpx44dkiSLxaJ169blbpG3OXnypCwWi/VRsGBBtW3bVlFRUXfdr3v37vr1118fUJUAAOBRQojNBV26dFFUVJQWL16sX3/9VevXr1fz5s114cKF3C7trrZs2aKYmBht2rRJCQkJevzxx3Xp0qV02964cUMuLi4qXLjwgy0SAAA8EgixD9ilS5e0fft2vfXWW2rRooX8/f1Vr149jR07Vk888YQCAgIkSZ07d5bFYrEuS9L8+fNVpkwZOTo6qnz58lq6dGmaYw8YMEBFihSRs7OzqlSpog0bNqRbx/nz51WnTh117txZSUlJmaq9YMGC8vX1VZ06dTRjxgydO3dOP//8s3WkduXKlQoMDJSzs7OWLVuW7nSCL774QnXr1pWzs7MKFSqkzp07W7clJSVp5MiRKl68uNzc3FS/fn1FRERkqjYAAPBoIcQ+YO7u7nJ3d9e6devSDY+7du2SJIWFhSkmJsa6vHbtWg0dOlQjRozQwYMHNWDAAPXt21ffffedJCklJUWPP/64duzYoY8//liHDx/Wm2++KXt7+zTnOH36tJo2baoqVapo9erVcnJyynI/XFxcJEnXr1+3rhszZoyGDh2q6OhoBQUFpdnnyy+/VOfOndW+fXtFRUVp69atqlevnnX7kCFDtHPnTq1YsUL79+9X165d1a5dOx07dizDOpKSkhQfH2/zAAAAjwADD9zq1auN/PnzG87OzkajRo2MsWPHGvv27bNul2SsXbvWZp9GjRoZ/fv3t1nXtWtXo3379oZhGMamTZsMOzs74+jRo+meMywszPDy8jKOHDli+Pn5GS+99JKRkpKSqXpPnDhhSDKioqIMwzCMf/75x+jcubPh7u5unD171rp9zpw56Z4zVcOGDY3evXune44//vjDsLe3N/766y+b9a1atTLGjh2bYW0TJkwwJKV5xMXFZapvD5taIxfbPAAAeBTExcVl+e83I7G5oEuXLjpz5ozWr1+vdu3aKSIiQrVq1VJ4eHiG+0RHR6tx48Y26xo3bqzo6GhJ0t69e1WiRAmVK1cuw2NcvXpVTZs21VNPPaW5c+fKYrFkqe5GjRrJ3d1d+fPn1759+7Ry5UoVKVLEur1OnTp33X/v3r1q1apVutsOHDig5ORklStXzjpa7e7urm3btun48eMZHnPs2LGKi4uzPk6fPp2lPgEAAHNyyO0CHlXOzs5q06aN2rRpo3Hjxqlfv36aMGGCQkNDs3W81Lf378bJyUmtW7fWhg0bNGrUKBUvXjxL51i5cqUqVaqkggULpnvrLDc3t2zXmJCQIHt7e0VGRqaZAuHu7p7hfk5OTtmaDgEAAMyNkdiHRKVKlXTlyhVJUr58+ZScnGyzvWLFitZbcKXasWOHKlWqJEmqVq2a/vzzz7ve0srOzk5Lly5V7dq11aJFC505cyZLNfr5+alMmTLZvvdrtWrVtHXr1nS31axZU8nJyYqNjVXZsmVtHr6+vtk6HwAAyLsYiX3ALly4oK5du+q5555TtWrV5OHhod27d2vatGl68sknJUkBAQHaunWrGjduLCcnJ+XPn1+jRo1St27dVLNmTbVu3VpffPGFPvvsM23ZskWSFBgYqGbNmqlLly6aNWuWypYtqyNHjshisahdu3bW89vb22vZsmXq2bOnWrZsqYiIiAcWEidMmKBWrVqpTJky6tGjh27evKmvvvpK//3vf1WuXDn17t1bISEhmjlzpmrWrKnz589r69atqlatmjp06PBAagQAAObASOwD5u7urvr162v27Nlq1qyZqlSponHjxql///569913JUkzZ87U5s2b5efnp5o1a0qSgoODNXfuXM2YMUOVK1fWggULFBYWpubNm1uPvWbNGtWtW1c9e/ZUpUqVNHr06DQjupLk4OCgTz75RJUrV1bLli0VGxv7QPrevHlzrVq1SuvXr1eNGjXUsmVL/fLLL9btYWFhCgkJ0YgRI1S+fHkFBwdr165dKlmy5AOpDwAAmIfFMAwjt4sAckp8fLy8vLwUFxcnT0/P3C4ny2qPWmKzHDk9JJcqAQDgwcnO329GYgEAAGA6hFho4MCBNre1uv0xcODA3C4PAAAgDT7YBb322msaOXJkutvM+JY8AADI+wixUOHChVW4cOHcLgMAACDTmE4AAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQccrsAAP8ncnpIbpcAAIApMBILAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdQiwAAABMhxALAAAA0yHEAgAAwHQIsQAAADAdh9wuADCL2qOWPPBzRk4PeeDnBADADBiJBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOINYnQ0FBZLJY0j3bt2uV2aQAAAA+cQ24XgMxr166dwsLCbNY5OTnlUjUAAAC5h5FYE3FycpKvr6/NI3/+/IqIiJCjo6O2b99ubTtt2jQVLlxY586dkyQ1b95cQ4YM0ZAhQ+Tl5aVChQpp3LhxMgzDuk9SUpJGjhyp4sWLy83NTfXr11dERIR1e3h4uLy9vbVp0yZVrFhR7u7uateunWJiYqxtIiIiVK9ePbm5ucnb21uNGzfWH3/8Yd3++eefq1atWnJ2dlbp0qU1adIk3bx5U5JkGIYmTpyokiVLysnJScWKFdNLL710v55OAABgYoTYPKB58+YaNmyYnn32WcXFxSkqKkrjxo3TokWLVKRIEWu7xYsXy8HBQb/88ovmzp2rWbNmadGiRdbtQ4YM0c6dO7VixQrt379fXbt2Vbt27XTs2DFrm8TERM2YMUNLly7V999/r1OnTmnkyJGSpJs3byo4OFiBgYHav3+/du7cqRdeeEEWi0WStH37doWEhGjo0KE6fPiwFixYoPDwcL3++uuSpDVr1mj27NlasGCBjh07pnXr1qlq1ap37XtSUpLi4+NtHgAAIO+zGLcPxeGhFRoaqo8//ljOzs426//3v//pf//7n65fv6769eurXLlyOnjwoBo3bqyFCxda2zVv3lyxsbE6dOiQNVSOGTNG69ev1+HDh3Xq1CmVLl1ap06dUrFixaz7tW7dWvXq1dMbb7yh8PBw9e3bV7/99pvKlCkjSXrvvff02muv6ezZs7p48aIKFiyoiIgIBQYGpulD69at1apVK40dO9a67uOPP9bo0aN15swZzZo1SwsWLNDBgweVL1++TD0vEydO1KRJk9Ksj4uLk6enZ6aOkVm1Ry3J0eNlRuT0kAd+TgAAHrT4+Hh5eXll6e83c2JNpEWLFpo/f77NugIFCkiSHB0dtWzZMlWrVk3+/v6aPXt2mv0bNGhgDbCS1LBhQ82cOVPJyck6cOCAkpOTVa5cOZt9kpKSVLBgQeuyq6urNcBKUtGiRRUbG2utJTQ0VEFBQWrTpo1at26tbt26qWjRopKkffv2aceOHdaRV0lKTk7WtWvXlJiYqK5du2rOnDkqXbq02rVrp/bt26tTp05ycMj4ZTp27FgNHz7cuhwfHy8/P7+Mn0QAAJAnEGJNxM3NTWXLls1w+48//ihJunjxoi5evCg3N7dMHzshIUH29vaKjIyUvb29zTZ3d3frz3eOkFosFpt5tWFhYXrppZe0ceNGrVy5Uq+++qo2b96sBg0aKCEhQZMmTdJTTz2V5vzOzs7y8/PT0aNHtWXLFm3evFmDBg3S9OnTtW3btgxHZp2cnPhwGwAAjyBCbB5x/Phxvfzyy/rggw+0cuVK9enTR1u2bJGd3f9Ne/75559t9vnpp5/02GOPyd7eXjVr1lRycrJiY2PVtGnTe6qlZs2aqlmzpsaOHauGDRtq+fLlatCggWrVqqWjR4/eNYi7uLioU6dO6tSpkwYPHqwKFSrowIEDqlWr1j3VBAAA8hZCrIkkJSXp7NmzNuscHByUP39+PfPMMwoKClLfvn3Vrl07Va1aVTNnztSoUaOsbU+dOqXhw4drwIAB2rNnj9555x3NnDlTklSuXDn17t1bISEhmjlzpmrWrKnz589r69atqlatmjp06PCv9Z04cUILFy7UE088oWLFiuno0aM6duyYQkJuzescP368OnbsqJIlS+rpp5+WnZ2d9u3bp4MHD2rKlCkKDw9XcnKy6tevL1dXV3388cdycXGRv79/Dj6LAAAgLyDEmsjGjRut80tTlS9fXr169dIff/yhDRs2SLo1T3XhwoXq2bOn2rZtq+rVq0uSQkJCdPXqVdWrV0/29vYaOnSoXnjhBeuxwsLCNGXKFI0YMUJ//fWXChUqpAYNGqhjx46Zqs/V1VVHjhzR4sWLdeHCBRUtWlSDBw/WgAEDJElBQUHasGGDXnvtNb311lvKly+fKlSooH79+kmSvL299eabb2r48OFKTk5W1apV9cUXX9jMyQUAAJC4O8Ejo3nz5qpRo4bmzJmT26XcV9n5dGNmcXcCAADuj+z8/eY+sQAAADAdQiwAAABMhzmxj4jbvz4WAADA7BiJBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYDiEWAAAApkOIBQAAgOkQYgEAAGA6hFgAAACYjkNuFwCYReT0kNwuAQAA/H+MxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANPhg13IUwzDkCTFx8fnciUAACCzUv9up/4dzwxCLPKUy5cvS5L8/PxyuRIAAJBVly9flpeXV6baWoysRF7gIZeSkqIzZ87Iw8NDFoslt8u5J/Hx8fLz89Pp06fl6emZ2+U8MPT70eq39Oj2/VHtt/To9p1+Z9xvwzB0+fJlFStWTHZ2mZvtykgs8hQ7OzuVKFEit8vIUZ6eno/UP3ap6Pej51Ht+6Pab+nR7Tv9Tl9mR2BT8cEuAAAAmA4hFgAAAKZDiAUeUk5OTpowYYKcnJxyu5QHin4/Wv2WHt2+P6r9lh7dvtPvnO03H+wCAACA6TASCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQC+SiefPmKSAgQM7Ozqpfv75++eWXu7ZftWqVKlSoIGdnZ1WtWlVfffXVA6o0Z2Wl3+Hh4bJYLDYPZ2fnB1htzvj+++/VqVMnFStWTBaLRevWrfvXfSIiIlSrVi05OTmpbNmyCg8Pv+915rSs9jsiIiLN9bZYLDp79uyDKTiHTJ06VXXr1pWHh4cKFy6s4OBgHT169F/3ywu/49npe174PZ8/f76qVatmvaF/w4YN9fXXX991n7xwvbPa75y81oRYIJesXLlSw4cP14QJE7Rnzx5Vr15dQUFBio2NTbf9jz/+qJ49e+r5559XVFSUgoODFRwcrIMHDz7gyu9NVvst3fqWl5iYGOvjjz/+eIAV54wrV66oevXqmjdvXqbanzhxQh06dFCLFi20d+9eDRs2TP369dOmTZvuc6U5K6v9TnX06FGba164cOH7VOH9sW3bNg0ePFg//fSTNm/erBs3bqht27a6cuVKhvvkld/x7PRdMv/veYkSJfTmm28qMjJSu3fvVsuWLfXkk0/q0KFD6bbPK9c7q/2WcvBaGwByRb169YzBgwdbl5OTk41ixYoZU6dOTbd9t27djA4dOtisq1+/vjFgwID7WmdOy2q/w8LCDC8vrwdU3YMhyVi7du1d24wePdqoXLmyzbru3bsbQUFB97Gy+ysz/f7uu+8MScY///zzQGp6UGJjYw1JxrZt2zJsk1d+x++Umb7nxd9zwzCM/PnzG4sWLUp3W1693oZx937n5LVmJBbIBdevX1dkZKRat25tXWdnZ6fWrVtr586d6e6zc+dOm/aSFBQUlGH7h1F2+i1JCQkJ8vf3l5+f37/+Dz+vyAvX+17UqFFDRYsWVZs2bbRjx47cLueexcXFSZIKFCiQYZu8es0z03cpb/2eJycna8WKFbpy5YoaNmyYbpu8eL0z028p5641IRbIBX///beSk5NVpEgRm/VFihTJcO7f2bNns9T+YZSdfpcvX14fffSRPv/8c3388cdKSUlRo0aN9Oeffz6IknNNRtc7Pj5eV69ezaWq7r+iRYvq/fff15o1a7RmzRr5+fmpefPm2rNnT26Xlm0pKSkaNmyYGjdurCpVqmTYLi/8jt8ps33PK7/nBw4ckLu7u5ycnDRw4ECtXbtWlSpVSrdtXrreWel3Tl5rh3stHADup4YNG9r8j75Ro0aqWLGiFixYoMmTJ+diZbgfypcvr/Lly1uXGzVqpOPHj2v27NlaunRpLlaWfYMHD9bBgwf1ww8/5HYpD1xm+55Xfs/Lly+vvXv3Ki4uTqtXr1afPn20bdu2DANdXpGVfufktSbEArmgUKFCsre317lz52zWnzt3Tr6+vunu4+vrm6X2D6Ps9PtO+fLlU82aNfXbb7/djxIfGhldb09PT7m4uORSVbmjXr16pg2AQ4YM0YYNG/T999+rRIkSd22bF37Hb5eVvt/JrL/njo6OKlu2rCSpdu3a2rVrl+bOnasFCxakaZuXrndW+n2ne7nWTCcAcoGjo6Nq166trVu3WtelpKRo69atGc4jatiwoU17Sdq8efNd5x09bLLT7zslJyfrwIEDKlq06P0q86GQF653Ttm7d6/prrdhGBoyZIjWrl2rb7/9VqVKlfrXffLKNc9O3++UV37PU1JSlJSUlO62vHK903O3ft/pnq51jnw8DECWrVixwnBycjLCw8ONw4cPGy+88ILh7e1tnD171jAMw3j22WeNMWPGWNvv2LHDcHBwMGbMmGFER0cbEyZMMPLly2ccOHAgt7qQLVnt96RJk4xNmzYZx48fNyIjI40ePXoYzs7OxqFDh3KrC9ly+fJlIyoqyoiKijIkGbNmzTKioqKMP/74wzAMwxgzZozx7LPPWtv//vvvhqurqzFq1CgjOjramDdvnmFvb29s3Lgxt7qQLVnt9+zZs41169YZx44dMw4cOGAMHTrUsLOzM7Zs2ZJbXciW//znP4aXl5cRERFhxMTEWB+JiYnWNnn1dzw7fc8Lv+djxowxtm3bZpw4ccLYv3+/MWbMGMNisRjffPONYRh593pntd85ea0JsUAueuedd4ySJUsajo6ORr169YyffvrJui0wMNDo06ePTftPP/3UKFeunOHo6GhUrlzZ+PLLLx9wxTkjK/0eNmyYtW2RIkWM9u3bG3v27MmFqu9N6q2j7nyk9rVPnz5GYGBgmn1q1KhhODo6GqVLlzbCwsIeeN33Kqv9fuutt4wyZcoYzs7ORoECBYzmzZsb3377be4Ufw/S67Mkm2uYV3/Hs9P3vPB7/txzzxn+/v6Go6Oj4ePjY7Rq1coa5Awj717vrPY7J6+1xTAMI+vjtwAAAEDuYU4sAAAATIcQCwAAANMhxAIAAMB0CLEAAAAwHUIsAAAATIcQCwAAANMhxAIAAMB0CLEAgFx39uxZtWnTRm5ubvL29s5wncVi0bp16zJ1zIkTJ6pGjRr3pV4AuY8QCwC4q7Nnz+rFF19U6dKl5eTkJD8/P3Xq1CnN977fi9mzZysmJkZ79+7Vr7/+muG6mJgYPf7445k65siRI3O0RkkKDw+3BmoAucshtwsAADy8Tp48qcaNG8vb21vTp09X1apVdePGDW3atEmDBw/WkSNHcuQ8x48fV+3atfXYY4/ddZ2vr2+mj+nu7i53d/ccqQ/Aw4eRWABAhgYNGiSLxaJffvlFXbp0Ubly5VS5cmUNHz5cP/30kyTp1KlTevLJJ+Xu7i5PT09169ZN586dsznO559/rlq1asnZ2VmlS5fWpEmTdPPmTUlSQECA1qxZoyVLlshisSg0NDTddVLa6QR//vmnevbsqQIFCsjNzU116tTRzz//LCn96QSLFi1SxYoV5ezsrAoVKui9996zbjt58qQsFos+++wztWjRQq6urqpevbp27twpSYqIiFDfvn0VFxcni8Uii8WiiRMn5uCzDSArGIkFAKTr4sWL2rhxo15//XW5ubml2e7t7a2UlBRrgN22bZtu3rypwYMHq3v37oqIiJAkbd++XSEhIXr77bfVtGlTHT9+XC+88IIkacKECdq1a5dCQkLk6empuXPnysXFRdevX0+z7k4JCQkKDAxU8eLFtX79evn6+mrPnj1KSUlJtz/Lli3T+PHj9e6776pmzZqKiopS//795ebmpj59+ljbvfLKK5oxY4Yee+wxvfLKK+rZs6d+++03NWrUSHPmzNH48eN19OhRSWKkF8hFhFgAQLp+++03GYahChUqZNhm69atOnDggE6cOCE/Pz9J0pIlS1S5cmXt2rVLdevW1aRJkzRmzBhrUCxdurQmT56s0aNHa8KECfLx8ZGTk5NcXFxspgukt+52y5cv1/nz57Vr1y4VKFBAklS2bNkMa50wYYJmzpypp556SpJUqlQpHT58WAsWLLAJsSNHjlSHDh0kSZMmTVLlypX122+/qUKFCvLy8pLFYsnStAYA9wchFgCQLsMw/rVNdHS0/Pz8rAFWkipVqiRvb29FR0erbt262rdvn3bs2KHXX3/d2iY5OVnXrl1TYmKiXF1ds1Xf3r17VbNmTWuAvZsrV67o+PHjev7559W/f3/r+ps3b8rLy8umbbVq1aw/Fy1aVJIUGxt71zAP4MEjxAIA0vXYY4/JYrHc84e3EhISNGnSJOsI6O2cnZ2zfdz0phjcrQZJ+uCDD1S/fn2bbfb29jbL+fLls/5ssVgkKcMpCgByDyEWAJCuAgUKKCgoSPPmzdNLL72UZl7spUuXVLFiRZ0+fVqnT5+2jsYePnxYly5dUqVKlSRJtWrV0tGjR+/6Vn92VKtWTYsWLdLFixf/dTS2SJEiKlasmH7//Xf17t072+d0dHRUcnJytvcHkHO4OwEAIEPz5s1TcnKy6tWrpzVr1ujYsWOKjo7W22+/rYYNG6p169aqWrWqevfurT179uiXX35RSEiIAgMDVadOHUnS+PHjtWTJEk2aNEmHDh1SdHS0VqxYoVdfffWeauvZs6d8fX0VHBysHTt26Pfff9eaNWusdxO406RJkzR16lS9/fbb+vXXX3XgwAGFhYVp1qxZmT5nQECAEhIStHXrVv39999KTEy8pz4AyD5CLAAgQ6VLl9aePXvUokULjRgxQlWqVFGbNm20detWzZ8/XxaLRZ9//rny58+vZs2aqXXr1ipdurRWrlxpPUZQUJA2bNigb775RnXr1lWDBg00e/Zs+fv731Ntjo6O+uabb1S4cGG1b99eVatW1ZtvvplmekCqfv36adGiRQoLC1PVqlUVGBio8PBwlSpVKtPnbNSokQYOHKju3bvLx8dH06ZNu6c+AMg+i5GZmfsAAADAQ4SRWAAAAJgOIRYAAACmQ4gFAACA6RBiAQAAYDqEWAAAAJgOIRYAAACmQ4gFAACA6RBiAQAAYDqEWAAAAJgOIRYAAACmQ4gFAACA6RBiAQAAYDr/Dxt60cytkR3SAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Fairness & Bias Metrics***"
      ],
      "metadata": {
        "id": "CsEfqEeF0Oyk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "dp_diff_log = demographic_parity_difference(\n",
        "    y_test, log_pred, sensitive_features=g_test\n",
        ")\n",
        "\n",
        "eo_diff_log = equalized_odds_difference(\n",
        "    y_test, log_pred, sensitive_features=g_test\n",
        ")\n",
        "\n",
        "print(\"Logistic Regression Fairness Metrics\")\n",
        "print(\"Demographic Parity Difference:\", dp_diff_log)\n",
        "print(\"Equalized Odds Difference:\", eo_diff_log)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7qN0L5wYpoO0",
        "outputId": "5e2e4d2b-2df9-4dc0-ac0d-fac65fc4ab62"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Logistic Regression Fairness Metrics\n",
            "Demographic Parity Difference: 0.04356330014224752\n",
            "Equalized Odds Difference: 0.18840579710144928\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***SHAP Explainability of Logistic Regression***"
      ],
      "metadata": {
        "id": "RpuBJlZ60RWI"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "explainer_log = shap.LinearExplainer(log_model, X_train)\n",
        "shap_values_log = explainer_log.shap_values(X_train)\n",
        "\n",
        "shap.summary_plot(\n",
        "    shap_values_log,\n",
        "    X_train,\n",
        "    feature_names=selected_features\n",
        ")\n"
      ],
      "metadata": {
        "id": "2j4RvCJRpodA",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 397
        },
        "outputId": "1a57d0fb-6f2a-4053-e3e0-6f43e9403173"
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x390 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **MODEL 2: RANDOM FOREST**"
      ],
      "metadata": {
        "id": "3IpxnMWR0TKs"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Train Random Forest***"
      ],
      "metadata": {
        "id": "QwYkCyHb0Wd7"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "\n",
        "rf_model = RandomForestClassifier(\n",
        "    n_estimators=200,\n",
        "    random_state=42\n",
        ")\n",
        "\n",
        "rf_model.fit(X_train, y_train)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "JcGsrDaqv9DW",
        "outputId": "10c40b3a-4f99-403f-b26a-1556da737c0a"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestClassifier(n_estimators=200, random_state=42)"
            ],
            "text/html": [
              "<style>#sk-container-id-2 {\n",
              "  /* Definition of color scheme common for light and dark mode */\n",
              "  --sklearn-color-text: #000;\n",
              "  --sklearn-color-text-muted: #666;\n",
              "  --sklearn-color-line: gray;\n",
              "  /* Definition of color scheme for unfitted estimators */\n",
              "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
              "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
              "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
              "  --sklearn-color-unfitted-level-3: chocolate;\n",
              "  /* Definition of color scheme for fitted estimators */\n",
              "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
              "  --sklearn-color-fitted-level-1: #d4ebff;\n",
              "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
              "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
              "\n",
              "  /* Specific color for light theme */\n",
              "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
              "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
              "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
              "  --sklearn-color-icon: #696969;\n",
              "\n",
              "  @media (prefers-color-scheme: dark) {\n",
              "    /* Redefinition of color scheme for dark theme */\n",
              "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
              "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
              "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
              "    --sklearn-color-icon: #878787;\n",
              "  }\n",
              "}\n",
              "\n",
              "#sk-container-id-2 {\n",
              "  color: var(--sklearn-color-text);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 pre {\n",
              "  padding: 0;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 input.sk-hidden--visually {\n",
              "  border: 0;\n",
              "  clip: rect(1px 1px 1px 1px);\n",
              "  clip: rect(1px, 1px, 1px, 1px);\n",
              "  height: 1px;\n",
              "  margin: -1px;\n",
              "  overflow: hidden;\n",
              "  padding: 0;\n",
              "  position: absolute;\n",
              "  width: 1px;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-dashed-wrapped {\n",
              "  border: 1px dashed var(--sklearn-color-line);\n",
              "  margin: 0 0.4em 0.5em 0.4em;\n",
              "  box-sizing: border-box;\n",
              "  padding-bottom: 0.4em;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-container {\n",
              "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
              "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
              "     so we also need the `!important` here to be able to override the\n",
              "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
              "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
              "  display: inline-block !important;\n",
              "  position: relative;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-text-repr-fallback {\n",
              "  display: none;\n",
              "}\n",
              "\n",
              "div.sk-parallel-item,\n",
              "div.sk-serial,\n",
              "div.sk-item {\n",
              "  /* draw centered vertical line to link estimators */\n",
              "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
              "  background-size: 2px 100%;\n",
              "  background-repeat: no-repeat;\n",
              "  background-position: center center;\n",
              "}\n",
              "\n",
              "/* Parallel-specific style estimator block */\n",
              "\n",
              "#sk-container-id-2 div.sk-parallel-item::after {\n",
              "  content: \"\";\n",
              "  width: 100%;\n",
              "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
              "  flex-grow: 1;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-parallel {\n",
              "  display: flex;\n",
              "  align-items: stretch;\n",
              "  justify-content: center;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  position: relative;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-parallel-item {\n",
              "  display: flex;\n",
              "  flex-direction: column;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
              "  align-self: flex-end;\n",
              "  width: 50%;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
              "  align-self: flex-start;\n",
              "  width: 50%;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
              "  width: 0;\n",
              "}\n",
              "\n",
              "/* Serial-specific style estimator block */\n",
              "\n",
              "#sk-container-id-2 div.sk-serial {\n",
              "  display: flex;\n",
              "  flex-direction: column;\n",
              "  align-items: center;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  padding-right: 1em;\n",
              "  padding-left: 1em;\n",
              "}\n",
              "\n",
              "\n",
              "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
              "clickable and can be expanded/collapsed.\n",
              "- Pipeline and ColumnTransformer use this feature and define the default style\n",
              "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
              "*/\n",
              "\n",
              "/* Pipeline and ColumnTransformer style (default) */\n",
              "\n",
              "#sk-container-id-2 div.sk-toggleable {\n",
              "  /* Default theme specific background. It is overwritten whether we have a\n",
              "  specific estimator or a Pipeline/ColumnTransformer */\n",
              "  background-color: var(--sklearn-color-background);\n",
              "}\n",
              "\n",
              "/* Toggleable label */\n",
              "#sk-container-id-2 label.sk-toggleable__label {\n",
              "  cursor: pointer;\n",
              "  display: flex;\n",
              "  width: 100%;\n",
              "  margin-bottom: 0;\n",
              "  padding: 0.5em;\n",
              "  box-sizing: border-box;\n",
              "  text-align: center;\n",
              "  align-items: start;\n",
              "  justify-content: space-between;\n",
              "  gap: 0.5em;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 label.sk-toggleable__label .caption {\n",
              "  font-size: 0.6rem;\n",
              "  font-weight: lighter;\n",
              "  color: var(--sklearn-color-text-muted);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
              "  /* Arrow on the left of the label */\n",
              "  content: \"▸\";\n",
              "  float: left;\n",
              "  margin-right: 0.25em;\n",
              "  color: var(--sklearn-color-icon);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
              "  color: var(--sklearn-color-text);\n",
              "}\n",
              "\n",
              "/* Toggleable content - dropdown */\n",
              "\n",
              "#sk-container-id-2 div.sk-toggleable__content {\n",
              "  max-height: 0;\n",
              "  max-width: 0;\n",
              "  overflow: hidden;\n",
              "  text-align: left;\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-toggleable__content pre {\n",
              "  margin: 0.2em;\n",
              "  border-radius: 0.25em;\n",
              "  color: var(--sklearn-color-text);\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
              "  /* Expand drop-down */\n",
              "  max-height: 200px;\n",
              "  max-width: 100%;\n",
              "  overflow: auto;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
              "  content: \"▾\";\n",
              "}\n",
              "\n",
              "/* Pipeline/ColumnTransformer-specific style */\n",
              "\n",
              "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  color: var(--sklearn-color-text);\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "/* Estimator-specific style */\n",
              "\n",
              "/* Colorize estimator box */\n",
              "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
              "#sk-container-id-2 div.sk-label label {\n",
              "  /* The background is the default theme color */\n",
              "  color: var(--sklearn-color-text-on-default-background);\n",
              "}\n",
              "\n",
              "/* On hover, darken the color of the background */\n",
              "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
              "  color: var(--sklearn-color-text);\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "/* Label box, darken color on hover, fitted */\n",
              "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
              "  color: var(--sklearn-color-text);\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "/* Estimator label */\n",
              "\n",
              "#sk-container-id-2 div.sk-label label {\n",
              "  font-family: monospace;\n",
              "  font-weight: bold;\n",
              "  display: inline-block;\n",
              "  line-height: 1.2em;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-label-container {\n",
              "  text-align: center;\n",
              "}\n",
              "\n",
              "/* Estimator-specific */\n",
              "#sk-container-id-2 div.sk-estimator {\n",
              "  font-family: monospace;\n",
              "  border: 1px dotted var(--sklearn-color-border-box);\n",
              "  border-radius: 0.25em;\n",
              "  box-sizing: border-box;\n",
              "  margin-bottom: 0.5em;\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-estimator.fitted {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-0);\n",
              "}\n",
              "\n",
              "/* on hover */\n",
              "#sk-container-id-2 div.sk-estimator:hover {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
              "}\n",
              "\n",
              "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-2);\n",
              "}\n",
              "\n",
              "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
              "\n",
              "/* Common style for \"i\" and \"?\" */\n",
              "\n",
              ".sk-estimator-doc-link,\n",
              "a:link.sk-estimator-doc-link,\n",
              "a:visited.sk-estimator-doc-link {\n",
              "  float: right;\n",
              "  font-size: smaller;\n",
              "  line-height: 1em;\n",
              "  font-family: monospace;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  border-radius: 1em;\n",
              "  height: 1em;\n",
              "  width: 1em;\n",
              "  text-decoration: none !important;\n",
              "  margin-left: 0.5em;\n",
              "  text-align: center;\n",
              "  /* unfitted */\n",
              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
              "  color: var(--sklearn-color-unfitted-level-1);\n",
              "}\n",
              "\n",
              ".sk-estimator-doc-link.fitted,\n",
              "a:link.sk-estimator-doc-link.fitted,\n",
              "a:visited.sk-estimator-doc-link.fitted {\n",
              "  /* fitted */\n",
              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
              "  color: var(--sklearn-color-fitted-level-1);\n",
              "}\n",
              "\n",
              "/* On hover */\n",
              "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
              ".sk-estimator-doc-link:hover,\n",
              "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
              ".sk-estimator-doc-link:hover {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
              "  color: var(--sklearn-color-background);\n",
              "  text-decoration: none;\n",
              "}\n",
              "\n",
              "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
              ".sk-estimator-doc-link.fitted:hover,\n",
              "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
              ".sk-estimator-doc-link.fitted:hover {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-3);\n",
              "  color: var(--sklearn-color-background);\n",
              "  text-decoration: none;\n",
              "}\n",
              "\n",
              "/* Span, style for the box shown on hovering the info icon */\n",
              ".sk-estimator-doc-link span {\n",
              "  display: none;\n",
              "  z-index: 9999;\n",
              "  position: relative;\n",
              "  font-weight: normal;\n",
              "  right: .2ex;\n",
              "  padding: .5ex;\n",
              "  margin: .5ex;\n",
              "  width: min-content;\n",
              "  min-width: 20ex;\n",
              "  max-width: 50ex;\n",
              "  color: var(--sklearn-color-text);\n",
              "  box-shadow: 2pt 2pt 4pt #999;\n",
              "  /* unfitted */\n",
              "  background: var(--sklearn-color-unfitted-level-0);\n",
              "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
              "}\n",
              "\n",
              ".sk-estimator-doc-link.fitted span {\n",
              "  /* fitted */\n",
              "  background: var(--sklearn-color-fitted-level-0);\n",
              "  border: var(--sklearn-color-fitted-level-3);\n",
              "}\n",
              "\n",
              ".sk-estimator-doc-link:hover span {\n",
              "  display: block;\n",
              "}\n",
              "\n",
              "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
              "\n",
              "#sk-container-id-2 a.estimator_doc_link {\n",
              "  float: right;\n",
              "  font-size: 1rem;\n",
              "  line-height: 1em;\n",
              "  font-family: monospace;\n",
              "  background-color: var(--sklearn-color-background);\n",
              "  border-radius: 1rem;\n",
              "  height: 1rem;\n",
              "  width: 1rem;\n",
              "  text-decoration: none;\n",
              "  /* unfitted */\n",
              "  color: var(--sklearn-color-unfitted-level-1);\n",
              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
              "  /* fitted */\n",
              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
              "  color: var(--sklearn-color-fitted-level-1);\n",
              "}\n",
              "\n",
              "/* On hover */\n",
              "#sk-container-id-2 a.estimator_doc_link:hover {\n",
              "  /* unfitted */\n",
              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
              "  color: var(--sklearn-color-background);\n",
              "  text-decoration: none;\n",
              "}\n",
              "\n",
              "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
              "  /* fitted */\n",
              "  background-color: var(--sklearn-color-fitted-level-3);\n",
              "}\n",
              "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=200, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(n_estimators=200, random_state=42)</pre></div> </div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Evaluation & Confidence Levels***"
      ],
      "metadata": {
        "id": "60udqv_Q0YBs"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "rf_pred = rf_model.predict(X_test)\n",
        "rf_prob = rf_model.predict_proba(X_test)[:, 1]\n",
        "\n",
        "print(\"Accuracy:\", accuracy_score(y_test, rf_pred))\n",
        "print(classification_report(y_test, rf_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dVU_Am7Kv-Dd",
        "outputId": "e154b522-44e5-4884-fa90-49e52c36e687"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy: 0.88\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.93      0.93      0.93       256\n",
            "           1       0.60      0.57      0.58        44\n",
            "\n",
            "    accuracy                           0.88       300\n",
            "   macro avg       0.76      0.75      0.76       300\n",
            "weighted avg       0.88      0.88      0.88       300\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Confusion Matrix***"
      ],
      "metadata": {
        "id": "AAq9ujEH0Z_r"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "cm = confusion_matrix(y_test, rf_pred)\n",
        "sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Greens\")\n",
        "plt.title(\"Random Forest – Confusion Matrix\")\n",
        "plt.xlabel(\"Predicted\")\n",
        "plt.ylabel(\"Actual\")\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "gR08NzDsv-GP",
        "outputId": "2a2c8c9c-ca09-4a50-a1f7-6f3aaee877b9"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Feature Importance (Interpretability)***"
      ],
      "metadata": {
        "id": "ozBhel0J0fbb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "importance_df = pd.DataFrame({\n",
        "    'Feature': selected_features,\n",
        "    'Importance': rf_model.feature_importances_\n",
        "}).sort_values(by='Importance', ascending=False)\n",
        "\n",
        "print(importance_df)\n",
        "\n",
        "sns.barplot(x='Importance', y='Feature', data=importance_df)\n",
        "plt.title(\"Random Forest – Feature Importance\")\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 594
        },
        "id": "eGEyYcLYv-JL",
        "outputId": "11e0aac4-c77a-4ee9-9900-516cf10ca5da"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              Feature  Importance\n",
            "0        Transactions    0.531626\n",
            "5            Expenses    0.104533\n",
            "3             Revenue    0.100628\n",
            "2         Stock_Price    0.091226\n",
            "4  Loan_Approval_Rate    0.087061\n",
            "1    Market_Sentiment    0.084927\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***Fairness & Bias Metrics***"
      ],
      "metadata": {
        "id": "oDex3eG60iFD"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "dp_diff_rf = demographic_parity_difference(\n",
        "    y_test, rf_pred, sensitive_features=g_test\n",
        ")\n",
        "\n",
        "eo_diff_rf = equalized_odds_difference(\n",
        "    y_test, rf_pred, sensitive_features=g_test\n",
        ")\n",
        "\n",
        "print(\"Random Forest Fairness Metrics\")\n",
        "print(\"Demographic Parity Difference:\", dp_diff_rf)\n",
        "print(\"Equalized Odds Difference:\", eo_diff_rf)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iOAXH_EDv-MN",
        "outputId": "fdf8f518-ed3c-4d19-8ca1-ddef909ee091"
      },
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Random Forest Fairness Metrics\n",
            "Demographic Parity Difference: 0.06294452347083926\n",
            "Equalized Odds Difference: 0.2670807453416149\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ***SHAP Explainability of Random Forest ***"
      ],
      "metadata": {
        "id": "PwEOO4FO0ksb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "X_train_df = pd.DataFrame(X_train, columns=selected_features)\n",
        "\n",
        "explainer_rf = shap.Explainer(\n",
        "    rf_model.predict_proba,\n",
        "    X_train_df\n",
        ")\n",
        "\n",
        "shap_values_rf = explainer_rf(X_train_df)\n",
        "\n",
        "# Plot SHAP values for the \"risk\" class (class index = 1)\n",
        "shap.summary_plot(\n",
        "    shap_values_rf.values[:, :, 1],\n",
        "    X_train_df,\n",
        "    feature_names=selected_features\n",
        ")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "_zOO3lQGv-Ow",
        "outputId": "c19756ee-24c8-4d1b-fdb3-4a281fc41db1"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   0%|          | 1/700 [00:00<?, ?it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   0%|          | 3/700 [00:18<01:47,  6.48it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|          | 4/700 [00:19<01:50,  6.27it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|          | 5/700 [00:19<01:40,  6.92it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|          | 6/700 [00:19<01:34,  7.35it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|          | 7/700 [00:19<01:33,  7.41it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|          | 8/700 [00:19<01:29,  7.74it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|▏         | 9/700 [00:19<01:28,  7.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   1%|▏         | 10/700 [00:19<01:31,  7.54it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   2%|▏         | 11/700 [00:19<01:29,  7.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   2%|▏         | 12/700 [00:20<01:32,  7.44it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   2%|▏         | 13/700 [00:20<01:35,  7.19it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   2%|▏         | 14/700 [00:20<01:30,  7.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   2%|▏         | 16/700 [00:20<01:10,  9.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   3%|▎         | 18/700 [00:20<01:01, 11.01it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   3%|▎         | 20/700 [00:20<00:58, 11.66it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   3%|▎         | 22/700 [00:20<00:55, 12.32it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   3%|▎         | 24/700 [00:21<00:55, 12.27it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   4%|▎         | 26/700 [00:21<00:54, 12.34it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   4%|▍         | 28/700 [00:21<00:54, 12.33it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   4%|▍         | 30/700 [00:21<00:52, 12.77it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   5%|▍         | 32/700 [00:21<00:52, 12.65it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   5%|▍         | 34/700 [00:21<00:52, 12.76it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   5%|▌         | 36/700 [00:22<00:50, 13.13it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   5%|▌         | 38/700 [00:22<00:49, 13.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   6%|▌         | 40/700 [00:22<00:50, 13.09it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   6%|▌         | 42/700 [00:22<00:49, 13.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   6%|▋         | 44/700 [00:22<00:48, 13.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   7%|▋         | 46/700 [00:22<00:49, 13.08it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   7%|▋         | 48/700 [00:22<00:48, 13.31it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   7%|▋         | 50/700 [00:23<00:50, 12.92it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   7%|▋         | 52/700 [00:23<00:50, 12.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   8%|▊         | 54/700 [00:23<00:50, 12.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   8%|▊         | 56/700 [00:23<00:50, 12.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   8%|▊         | 58/700 [00:23<00:48, 13.12it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   9%|▊         | 60/700 [00:23<00:49, 12.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   9%|▉         | 62/700 [00:24<00:48, 13.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   9%|▉         | 64/700 [00:24<00:47, 13.38it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:   9%|▉         | 66/700 [00:24<00:49, 12.93it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  10%|▉         | 68/700 [00:24<00:47, 13.21it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  10%|█         | 70/700 [00:24<00:48, 13.06it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  10%|█         | 72/700 [00:24<00:48, 12.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  11%|█         | 74/700 [00:24<00:48, 12.81it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  11%|█         | 76/700 [00:25<00:49, 12.65it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  11%|█         | 78/700 [00:25<00:49, 12.56it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  11%|█▏        | 80/700 [00:25<00:47, 13.01it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  12%|█▏        | 82/700 [00:25<00:47, 13.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  12%|█▏        | 84/700 [00:25<00:46, 13.19it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  12%|█▏        | 86/700 [00:25<00:47, 12.88it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  13%|█▎        | 88/700 [00:26<00:47, 12.79it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  13%|█▎        | 90/700 [00:26<00:48, 12.70it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  13%|█▎        | 92/700 [00:26<00:48, 12.55it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  13%|█▎        | 94/700 [00:26<00:46, 13.00it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  14%|█▎        | 96/700 [00:26<00:47, 12.71it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  14%|█▍        | 98/700 [00:26<00:45, 13.16it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  14%|█▍        | 100/700 [00:27<00:46, 12.91it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  15%|█▍        | 102/700 [00:27<00:44, 13.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  15%|█▍        | 104/700 [00:27<00:46, 12.93it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  15%|█▌        | 106/700 [00:27<00:46, 12.90it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  15%|█▌        | 108/700 [00:27<00:45, 12.98it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  16%|█▌        | 110/700 [00:27<00:46, 12.80it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  16%|█▌        | 112/700 [00:27<00:44, 13.19it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  16%|█▋        | 114/700 [00:28<00:47, 12.35it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  17%|█▋        | 116/700 [00:28<00:47, 12.34it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  17%|█▋        | 118/700 [00:28<00:48, 12.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  17%|█▋        | 120/700 [00:28<00:46, 12.56it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  17%|█▋        | 122/700 [00:28<00:46, 12.47it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  18%|█▊        | 124/700 [00:28<00:46, 12.43it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  18%|█▊        | 126/700 [00:29<00:47, 12.02it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  18%|█▊        | 128/700 [00:29<00:47, 12.14it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  19%|█▊        | 130/700 [00:29<00:47, 12.03it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  19%|█▉        | 132/700 [00:29<00:47, 11.96it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  19%|█▉        | 134/700 [00:29<00:45, 12.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  19%|█▉        | 136/700 [00:29<00:44, 12.79it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  20%|█▉        | 138/700 [00:30<00:45, 12.24it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  20%|██        | 140/700 [00:30<00:46, 11.96it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  20%|██        | 142/700 [00:30<00:50, 11.00it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  21%|██        | 144/700 [00:30<00:55, 10.09it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  21%|██        | 146/700 [00:30<00:56,  9.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  21%|██        | 147/700 [00:31<00:57,  9.65it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  21%|██        | 148/700 [00:31<01:00,  9.15it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  21%|██▏       | 149/700 [00:31<01:01,  8.98it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  21%|██▏       | 150/700 [00:31<01:03,  8.60it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 151/700 [00:31<01:02,  8.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 152/700 [00:31<01:06,  8.22it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 153/700 [00:31<01:05,  8.33it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 154/700 [00:31<01:03,  8.56it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 155/700 [00:32<01:05,  8.30it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 156/700 [00:32<01:03,  8.62it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  22%|██▏       | 157/700 [00:32<01:02,  8.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 158/700 [00:32<01:09,  7.83it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 159/700 [00:32<01:08,  7.90it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 160/700 [00:32<01:05,  8.19it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 161/700 [00:32<01:08,  7.91it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 162/700 [00:32<01:11,  7.50it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 163/700 [00:33<01:09,  7.77it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  23%|██▎       | 164/700 [00:33<01:08,  7.81it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  24%|██▎       | 165/700 [00:33<01:10,  7.57it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  24%|██▍       | 167/700 [00:33<00:56,  9.42it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  24%|██▍       | 169/700 [00:33<00:49, 10.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  24%|██▍       | 171/700 [00:33<00:45, 11.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  25%|██▍       | 173/700 [00:33<00:44, 11.92it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  25%|██▌       | 175/700 [00:34<00:42, 12.39it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  25%|██▌       | 177/700 [00:34<00:42, 12.38it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  26%|██▌       | 179/700 [00:34<00:42, 12.31it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  26%|██▌       | 181/700 [00:34<00:40, 12.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  26%|██▌       | 183/700 [00:34<00:39, 12.96it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  26%|██▋       | 185/700 [00:34<00:40, 12.72it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  27%|██▋       | 187/700 [00:34<00:39, 13.01it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  27%|██▋       | 189/700 [00:35<00:38, 13.13it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  27%|██▋       | 191/700 [00:35<00:38, 13.19it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  28%|██▊       | 193/700 [00:35<00:40, 12.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  28%|██▊       | 195/700 [00:35<00:40, 12.41it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  28%|██▊       | 197/700 [00:35<00:42, 11.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  28%|██▊       | 199/700 [00:35<00:42, 11.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  29%|██▊       | 201/700 [00:36<00:43, 11.49it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  29%|██▉       | 203/700 [00:36<00:41, 12.01it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  29%|██▉       | 205/700 [00:36<00:42, 11.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  30%|██▉       | 207/700 [00:36<00:40, 12.12it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  30%|██▉       | 209/700 [00:36<00:40, 12.17it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  30%|███       | 211/700 [00:36<00:38, 12.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  30%|███       | 213/700 [00:37<00:38, 12.72it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  31%|███       | 215/700 [00:37<00:37, 12.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  31%|███       | 217/700 [00:37<00:37, 13.00it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  31%|███▏      | 219/700 [00:37<00:37, 12.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  32%|███▏      | 221/700 [00:37<00:38, 12.47it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  32%|███▏      | 223/700 [00:37<00:37, 12.87it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  32%|███▏      | 225/700 [00:38<00:37, 12.52it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  32%|███▏      | 227/700 [00:38<00:36, 12.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  33%|███▎      | 229/700 [00:38<00:37, 12.53it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  33%|███▎      | 231/700 [00:38<00:37, 12.35it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  33%|███▎      | 233/700 [00:38<00:36, 12.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  34%|███▎      | 235/700 [00:38<00:38, 12.18it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  34%|███▍      | 237/700 [00:39<00:37, 12.37it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  34%|███▍      | 239/700 [00:39<00:37, 12.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  34%|███▍      | 241/700 [00:39<00:36, 12.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  35%|███▍      | 243/700 [00:39<00:36, 12.41it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  35%|███▌      | 245/700 [00:39<00:37, 12.15it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  35%|███▌      | 247/700 [00:39<00:36, 12.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  36%|███▌      | 249/700 [00:39<00:37, 12.13it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  36%|███▌      | 251/700 [00:40<00:36, 12.37it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  36%|███▌      | 253/700 [00:40<00:35, 12.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  36%|███▋      | 255/700 [00:40<00:36, 12.28it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  37%|███▋      | 257/700 [00:40<00:36, 12.15it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  37%|███▋      | 259/700 [00:40<00:36, 11.98it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  37%|███▋      | 261/700 [00:40<00:35, 12.27it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  38%|███▊      | 263/700 [00:41<00:34, 12.54it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  38%|███▊      | 265/700 [00:41<00:35, 12.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  38%|███▊      | 267/700 [00:41<00:34, 12.50it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  38%|███▊      | 269/700 [00:41<00:33, 12.76it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  39%|███▊      | 271/700 [00:41<00:34, 12.49it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  39%|███▉      | 273/700 [00:41<00:33, 12.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  39%|███▉      | 275/700 [00:42<00:33, 12.72it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  40%|███▉      | 277/700 [00:42<00:34, 12.38it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  40%|███▉      | 279/700 [00:42<00:33, 12.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  40%|████      | 281/700 [00:42<00:34, 12.10it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  40%|████      | 283/700 [00:42<00:35, 11.85it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  41%|████      | 285/700 [00:42<00:36, 11.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  41%|████      | 287/700 [00:43<00:36, 11.28it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  41%|████▏     | 289/700 [00:43<00:39, 10.33it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 291/700 [00:43<00:44,  9.15it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 292/700 [00:43<00:46,  8.78it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 293/700 [00:43<00:46,  8.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 294/700 [00:44<00:50,  7.98it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 295/700 [00:44<00:50,  8.02it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 296/700 [00:44<00:50,  7.94it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  42%|████▏     | 297/700 [00:44<00:49,  8.22it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 298/700 [00:44<00:49,  8.14it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 299/700 [00:44<00:47,  8.39it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 300/700 [00:44<00:49,  8.14it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 301/700 [00:44<00:50,  7.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 302/700 [00:45<00:49,  8.03it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 303/700 [00:45<00:47,  8.37it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  43%|████▎     | 304/700 [00:45<00:45,  8.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▎     | 305/700 [00:45<00:45,  8.77it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▎     | 306/700 [00:45<00:49,  7.93it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▍     | 307/700 [00:45<00:51,  7.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▍     | 308/700 [00:45<00:48,  8.09it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▍     | 309/700 [00:45<00:46,  8.44it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▍     | 310/700 [00:46<00:48,  7.97it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  44%|████▍     | 311/700 [00:46<00:48,  8.04it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  45%|████▍     | 312/700 [00:46<00:48,  8.05it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  45%|████▍     | 313/700 [00:46<00:48,  7.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  45%|████▍     | 314/700 [00:46<00:49,  7.85it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  45%|████▌     | 315/700 [00:46<00:46,  8.37it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  45%|████▌     | 317/700 [00:46<00:38,  9.94it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  45%|████▌     | 318/700 [00:46<00:38,  9.94it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  46%|████▌     | 319/700 [00:46<00:38,  9.83it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  46%|████▌     | 320/700 [00:47<00:38,  9.85it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  46%|████▌     | 322/700 [00:47<00:34, 10.99it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  46%|████▋     | 324/700 [00:47<00:32, 11.55it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  47%|████▋     | 326/700 [00:47<00:31, 11.98it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  47%|████▋     | 328/700 [00:47<00:30, 12.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  47%|████▋     | 330/700 [00:47<00:29, 12.57it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  47%|████▋     | 332/700 [00:48<00:28, 12.70it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  48%|████▊     | 334/700 [00:48<00:29, 12.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  48%|████▊     | 336/700 [00:48<00:29, 12.34it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  48%|████▊     | 338/700 [00:48<00:30, 11.97it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  49%|████▊     | 340/700 [00:48<00:29, 12.05it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  49%|████▉     | 342/700 [00:48<00:28, 12.38it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  49%|████▉     | 344/700 [00:48<00:28, 12.53it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  49%|████▉     | 346/700 [00:49<00:30, 11.65it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  50%|████▉     | 348/700 [00:49<00:31, 11.06it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  50%|█████     | 350/700 [00:49<00:32, 10.74it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  50%|█████     | 352/700 [00:49<00:30, 11.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  51%|█████     | 354/700 [00:49<00:29, 11.70it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  51%|█████     | 356/700 [00:50<00:29, 11.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  51%|█████     | 358/700 [00:50<00:29, 11.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  51%|█████▏    | 360/700 [00:50<00:28, 11.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  52%|█████▏    | 362/700 [00:50<00:29, 11.43it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  52%|█████▏    | 364/700 [00:50<00:28, 11.90it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  52%|█████▏    | 366/700 [00:50<00:28, 11.78it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  53%|█████▎    | 368/700 [00:51<00:28, 11.79it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  53%|█████▎    | 370/700 [00:51<00:28, 11.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  53%|█████▎    | 372/700 [00:51<00:27, 12.08it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  53%|█████▎    | 374/700 [00:51<00:27, 11.76it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  54%|█████▎    | 376/700 [00:51<00:27, 11.78it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  54%|█████▍    | 378/700 [00:51<00:26, 12.20it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  54%|█████▍    | 380/700 [00:52<00:27, 11.49it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  55%|█████▍    | 382/700 [00:52<00:27, 11.47it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  55%|█████▍    | 384/700 [00:52<00:26, 11.83it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  55%|█████▌    | 386/700 [00:52<00:26, 11.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  55%|█████▌    | 388/700 [00:52<00:25, 12.23it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  56%|█████▌    | 390/700 [00:52<00:24, 12.45it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  56%|█████▌    | 392/700 [00:53<00:24, 12.52it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  56%|█████▋    | 394/700 [00:53<00:25, 12.17it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  57%|█████▋    | 396/700 [00:53<00:25, 12.01it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  57%|█████▋    | 398/700 [00:53<00:24, 12.18it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  57%|█████▋    | 400/700 [00:53<00:24, 12.08it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  57%|█████▋    | 402/700 [00:53<00:24, 12.06it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  58%|█████▊    | 404/700 [00:54<00:24, 12.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  58%|█████▊    | 406/700 [00:54<00:23, 12.47it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  58%|█████▊    | 408/700 [00:54<00:25, 11.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  59%|█████▊    | 410/700 [00:54<00:26, 10.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  59%|█████▉    | 412/700 [00:54<00:31,  9.17it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  59%|█████▉    | 413/700 [00:55<00:33,  8.59it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  59%|█████▉    | 414/700 [00:55<00:35,  8.01it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  59%|█████▉    | 415/700 [00:55<00:38,  7.34it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  59%|█████▉    | 416/700 [00:55<00:42,  6.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|█████▉    | 417/700 [00:55<00:44,  6.33it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|█████▉    | 418/700 [00:55<00:43,  6.44it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|█████▉    | 419/700 [00:56<00:43,  6.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|██████    | 420/700 [00:56<00:41,  6.76it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|██████    | 421/700 [00:56<00:39,  7.10it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|██████    | 422/700 [00:56<00:41,  6.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  60%|██████    | 423/700 [00:56<00:40,  6.84it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████    | 424/700 [00:56<00:49,  5.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████    | 425/700 [00:57<00:50,  5.46it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████    | 426/700 [00:57<00:51,  5.34it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████    | 427/700 [00:57<01:01,  4.48it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████    | 428/700 [00:57<01:02,  4.34it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████▏   | 429/700 [00:58<01:01,  4.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  61%|██████▏   | 430/700 [00:58<00:57,  4.72it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 431/700 [00:58<01:03,  4.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 432/700 [00:58<01:05,  4.10it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 433/700 [00:59<01:32,  2.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 434/700 [00:59<01:51,  2.39it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 435/700 [01:00<01:33,  2.83it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 436/700 [01:00<01:21,  3.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  62%|██████▏   | 437/700 [01:00<01:10,  3.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 438/700 [01:00<00:59,  4.39it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 439/700 [01:00<00:52,  4.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 440/700 [01:00<00:48,  5.38it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 441/700 [01:01<00:43,  5.99it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 442/700 [01:01<00:41,  6.20it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 443/700 [01:01<00:39,  6.44it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  63%|██████▎   | 444/700 [01:01<00:38,  6.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▎   | 445/700 [01:01<00:39,  6.47it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▎   | 446/700 [01:01<00:46,  5.42it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▍   | 447/700 [01:02<00:45,  5.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▍   | 448/700 [01:02<00:41,  6.12it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▍   | 449/700 [01:02<00:38,  6.49it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▍   | 450/700 [01:02<00:38,  6.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  64%|██████▍   | 451/700 [01:02<00:37,  6.71it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▍   | 452/700 [01:02<00:36,  6.79it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▍   | 453/700 [01:02<00:37,  6.56it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▍   | 454/700 [01:03<00:37,  6.55it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▌   | 455/700 [01:03<00:36,  6.62it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▌   | 456/700 [01:03<00:36,  6.72it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▌   | 457/700 [01:03<00:37,  6.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  65%|██████▌   | 458/700 [01:03<00:39,  6.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▌   | 459/700 [01:03<00:36,  6.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▌   | 460/700 [01:04<00:38,  6.23it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▌   | 461/700 [01:04<00:38,  6.15it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▌   | 462/700 [01:04<00:38,  6.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▌   | 463/700 [01:04<00:37,  6.35it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▋   | 464/700 [01:04<00:35,  6.56it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  66%|██████▋   | 465/700 [01:04<00:37,  6.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 466/700 [01:05<00:39,  5.96it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 467/700 [01:05<00:39,  5.87it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 468/700 [01:05<00:40,  5.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 469/700 [01:05<00:38,  5.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 470/700 [01:05<00:39,  5.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 471/700 [01:05<00:38,  5.92it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  67%|██████▋   | 472/700 [01:06<00:39,  5.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 473/700 [01:06<00:41,  5.52it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 474/700 [01:06<00:37,  6.04it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 475/700 [01:06<00:38,  5.88it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 476/700 [01:06<00:38,  5.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 477/700 [01:06<00:35,  6.23it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 478/700 [01:07<00:33,  6.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  68%|██████▊   | 479/700 [01:07<00:32,  6.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▊   | 480/700 [01:07<00:34,  6.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▊   | 481/700 [01:07<00:33,  6.56it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▉   | 482/700 [01:07<00:33,  6.43it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▉   | 483/700 [01:07<00:32,  6.60it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▉   | 484/700 [01:07<00:33,  6.43it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▉   | 485/700 [01:08<00:31,  6.79it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  69%|██████▉   | 486/700 [01:08<00:30,  6.99it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|██████▉   | 487/700 [01:08<00:30,  6.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|██████▉   | 488/700 [01:08<00:29,  7.21it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|██████▉   | 489/700 [01:08<00:28,  7.38it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|███████   | 490/700 [01:08<00:29,  7.10it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|███████   | 491/700 [01:08<00:28,  7.37it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|███████   | 492/700 [01:09<00:29,  7.17it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  70%|███████   | 493/700 [01:09<00:28,  7.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████   | 494/700 [01:09<00:28,  7.26it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████   | 495/700 [01:09<00:30,  6.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████   | 496/700 [01:09<00:28,  7.13it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████   | 497/700 [01:09<00:28,  7.24it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████   | 498/700 [01:09<00:28,  7.00it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████▏  | 499/700 [01:10<00:30,  6.58it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  71%|███████▏  | 500/700 [01:10<00:34,  5.80it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 501/700 [01:10<00:37,  5.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 502/700 [01:10<00:40,  4.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 503/700 [01:11<00:44,  4.44it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 504/700 [01:11<00:40,  4.84it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 505/700 [01:11<00:34,  5.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 506/700 [01:11<00:30,  6.28it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  72%|███████▏  | 507/700 [01:11<00:28,  6.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 508/700 [01:11<00:26,  7.14it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 509/700 [01:11<00:24,  7.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 510/700 [01:11<00:23,  8.09it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 511/700 [01:12<00:22,  8.46it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 512/700 [01:12<00:21,  8.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 513/700 [01:12<00:22,  8.27it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  73%|███████▎  | 514/700 [01:12<00:23,  7.84it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▎  | 515/700 [01:12<00:24,  7.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▎  | 516/700 [01:12<00:23,  7.80it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▍  | 517/700 [01:12<00:24,  7.42it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▍  | 518/700 [01:12<00:23,  7.91it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▍  | 519/700 [01:13<00:22,  7.88it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▍  | 520/700 [01:13<00:23,  7.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  74%|███████▍  | 521/700 [01:13<00:25,  7.09it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▍  | 522/700 [01:13<00:25,  6.90it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▍  | 523/700 [01:13<00:25,  6.96it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▍  | 524/700 [01:13<00:25,  7.00it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▌  | 525/700 [01:13<00:24,  7.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▌  | 526/700 [01:14<00:23,  7.31it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▌  | 527/700 [01:14<00:24,  7.03it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  75%|███████▌  | 528/700 [01:14<00:23,  7.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  76%|███████▌  | 530/700 [01:14<00:18,  9.09it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  76%|███████▌  | 532/700 [01:14<00:16, 10.10it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  76%|███████▋  | 534/700 [01:14<00:15, 10.81it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  77%|███████▋  | 536/700 [01:15<00:15, 10.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  77%|███████▋  | 538/700 [01:15<00:15, 10.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  77%|███████▋  | 540/700 [01:15<00:14, 10.72it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  77%|███████▋  | 542/700 [01:15<00:14, 11.24it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  78%|███████▊  | 544/700 [01:15<00:13, 11.62it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  78%|███████▊  | 546/700 [01:15<00:12, 11.91it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  78%|███████▊  | 548/700 [01:16<00:13, 11.13it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  79%|███████▊  | 550/700 [01:16<00:13, 11.28it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  79%|███████▉  | 552/700 [01:16<00:13, 11.22it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  79%|███████▉  | 554/700 [01:16<00:12, 11.26it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  79%|███████▉  | 556/700 [01:16<00:12, 11.46it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  80%|███████▉  | 558/700 [01:16<00:12, 11.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  80%|████████  | 560/700 [01:17<00:12, 10.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  80%|████████  | 562/700 [01:17<00:12, 11.05it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  81%|████████  | 564/700 [01:17<00:11, 11.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  81%|████████  | 566/700 [01:17<00:11, 11.60it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  81%|████████  | 568/700 [01:17<00:11, 11.90it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  81%|████████▏ | 570/700 [01:17<00:10, 11.88it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  82%|████████▏ | 572/700 [01:18<00:10, 11.65it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  82%|████████▏ | 574/700 [01:18<00:10, 11.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  82%|████████▏ | 576/700 [01:18<00:10, 11.96it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  83%|████████▎ | 578/700 [01:18<00:10, 11.78it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  83%|████████▎ | 580/700 [01:18<00:10, 11.68it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  83%|████████▎ | 582/700 [01:18<00:09, 11.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  83%|████████▎ | 584/700 [01:19<00:09, 11.69it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  84%|████████▎ | 586/700 [01:19<00:09, 11.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  84%|████████▍ | 588/700 [01:19<00:09, 11.54it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  84%|████████▍ | 590/700 [01:19<00:09, 11.04it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  85%|████████▍ | 592/700 [01:19<00:09, 11.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  85%|████████▍ | 594/700 [01:20<00:09, 11.40it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  85%|████████▌ | 596/700 [01:20<00:09, 11.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  85%|████████▌ | 598/700 [01:20<00:09, 11.32it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  86%|████████▌ | 600/700 [01:20<00:08, 11.61it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  86%|████████▌ | 602/700 [01:20<00:08, 11.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  86%|████████▋ | 604/700 [01:20<00:08, 11.83it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  87%|████████▋ | 606/700 [01:21<00:08, 11.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  87%|████████▋ | 608/700 [01:21<00:07, 11.52it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  87%|████████▋ | 610/700 [01:21<00:08, 11.19it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  87%|████████▋ | 612/700 [01:21<00:07, 11.33it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  88%|████████▊ | 614/700 [01:21<00:07, 11.63it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  88%|████████▊ | 616/700 [01:21<00:07, 11.81it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  88%|████████▊ | 618/700 [01:22<00:07, 11.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  89%|████████▊ | 620/700 [01:22<00:07, 11.25it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  89%|████████▉ | 622/700 [01:22<00:06, 11.49it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  89%|████████▉ | 624/700 [01:22<00:06, 11.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  89%|████████▉ | 626/700 [01:22<00:06, 11.90it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  90%|████████▉ | 628/700 [01:23<00:06, 11.15it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  90%|█████████ | 630/700 [01:23<00:06, 11.28it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  90%|█████████ | 632/700 [01:23<00:06, 11.11it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  91%|█████████ | 634/700 [01:23<00:05, 11.30it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  91%|█████████ | 636/700 [01:23<00:05, 11.54it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  91%|█████████ | 638/700 [01:23<00:05, 11.67it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  91%|█████████▏| 640/700 [01:24<00:05, 11.44it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  92%|█████████▏| 642/700 [01:24<00:05, 11.55it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  92%|█████████▏| 644/700 [01:24<00:05, 10.06it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  92%|█████████▏| 646/700 [01:24<00:06,  8.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  92%|█████████▏| 647/700 [01:24<00:06,  8.80it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 648/700 [01:25<00:06,  8.66it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 649/700 [01:25<00:05,  8.71it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 650/700 [01:25<00:05,  8.73it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 651/700 [01:25<00:05,  8.75it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 652/700 [01:25<00:05,  8.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 653/700 [01:25<00:05,  8.50it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  93%|█████████▎| 654/700 [01:25<00:05,  8.10it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▎| 655/700 [01:25<00:05,  7.82it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▎| 656/700 [01:25<00:05,  8.17it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▍| 657/700 [01:26<00:05,  8.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▍| 658/700 [01:26<00:04,  8.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▍| 659/700 [01:26<00:04,  8.53it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▍| 660/700 [01:26<00:04,  8.20it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  94%|█████████▍| 661/700 [01:26<00:04,  7.87it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▍| 662/700 [01:26<00:04,  7.79it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▍| 663/700 [01:26<00:04,  8.20it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▍| 664/700 [01:26<00:04,  7.95it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▌| 665/700 [01:27<00:04,  8.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▌| 666/700 [01:27<00:04,  7.88it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▌| 667/700 [01:27<00:04,  7.16it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  95%|█████████▌| 668/700 [01:27<00:04,  7.29it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▌| 669/700 [01:27<00:04,  6.99it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▌| 670/700 [01:27<00:04,  7.17it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▌| 671/700 [01:27<00:04,  6.80it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▌| 672/700 [01:28<00:04,  6.74it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▌| 673/700 [01:28<00:04,  6.54it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▋| 674/700 [01:28<00:03,  6.86it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  96%|█████████▋| 675/700 [01:28<00:03,  7.33it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  97%|█████████▋| 677/700 [01:28<00:02,  8.30it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  97%|█████████▋| 679/700 [01:28<00:02,  9.51it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  97%|█████████▋| 681/700 [01:29<00:01, 10.24it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  98%|█████████▊| 683/700 [01:29<00:01, 10.89it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  98%|█████████▊| 685/700 [01:29<00:01, 10.98it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  98%|█████████▊| 687/700 [01:29<00:01, 11.27it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  98%|█████████▊| 689/700 [01:29<00:01, 10.74it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  99%|█████████▊| 691/700 [01:29<00:00, 11.04it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  99%|█████████▉| 693/700 [01:30<00:00, 10.93it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer:  99%|█████████▉| 695/700 [01:30<00:00, 10.64it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer: 100%|█████████▉| 697/700 [01:30<00:00, 10.57it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer: 100%|█████████▉| 699/700 [01:30<00:00, 10.97it/s]/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/utils/validation.py:2732: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
            "  warnings.warn(\n",
            "ExactExplainer explainer: 701it [01:30,  7.70it/s]\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x390 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}