{ "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": { "id": "o3Vwky4soVSS" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.metrics import accuracy_score, confusion_matrix\n", "from sklearn.ensemble import RandomForestClassifier\n" ] }, { "cell_type": "code", "source": [ "df = pd.read_csv('titanic.csv')\n" ], "metadata": { "id": "tenAbQCepQc3" }, "execution_count": 2, "outputs": [] }, { "cell_type": "code", "source": [ "print(df.head())\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "JJj_LUrhpU57", "outputId": "aa085857-0a55-4192-efc3-6331f781b6c6" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ " PassengerId Survived Pclass \\\n", "0 1 0 3 \n", "1 2 1 1 \n", "2 3 1 3 \n", "3 4 1 1 \n", "4 5 0 3 \n", "\n", " Name Sex Age SibSp \\\n", "0 Braund\\t Mr. Owen Harris male 22.0 1 \n", "1 Cumings\\t Mrs. John Bradley (Florence Briggs T... female 38.0 1 \n", "2 Heikkinen\\t Miss Laina female 26.0 0 \n", "3 Futrelle\\t Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n", "4 Allen\\t Mr. William Henry male 35.0 0 \n", "\n", " Parch Ticket Fare Cabin Embarked \n", "0 0 A/5 21171 7.2500 NaN S \n", "1 0 PC 17599 71.2833 C85 C \n", "2 0 STON/O2. 3101282 7.9250 NaN S \n", "3 0 113803 53.1000 C123 S \n", "4 0 373450 8.0500 NaN S \n" ] } ] }, { "cell_type": "code", "source": [ "print(\"\\nMissing values in each column:\")\n", "print(df.isnull().sum())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "u4yu8lOTpZ89", "outputId": "8c198352-042f-4b6c-f648-312217bd2652" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Missing values in each column:\n", "PassengerId 0\n", "Survived 0\n", "Pclass 0\n", "Name 0\n", "Sex 0\n", "Age 177\n", "SibSp 0\n", "Parch 0\n", "Ticket 0\n", "Fare 0\n", "Cabin 687\n", "Embarked 2\n", "dtype: int64\n" ] } ] }, { "cell_type": "code", "source": [ "df['Age'].fillna(df['Age'].mean(), inplace=True)\n", "df['Fare'].fillna(df['Fare'].mean(), inplace=True)\n", "df['Embarked'].fillna(df['Embarked'].mode()[0], inplace=True)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "UHKvCnbXpdZ8", "outputId": "25abb2af-93ac-4007-ace5-eec997be7497" }, "execution_count": 5, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ ":1: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " df['Age'].fillna(df['Age'].mean(), inplace=True)\n", ":2: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " df['Fare'].fillna(df['Fare'].mean(), inplace=True)\n", ":3: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " df['Embarked'].fillna(df['Embarked'].mode()[0], inplace=True)\n" ] } ] }, { "cell_type": "code", "source": [ "df = df.drop(['PassengerId', 'Name', 'Ticket', 'Cabin'], axis=1)\n" ], "metadata": { "id": "l9y3P60bpisH" }, "execution_count": 6, "outputs": [] }, { "cell_type": "code", "source": [ "df = pd.get_dummies(df, columns=['Sex', 'Embarked'], drop_first=True)\n" ], "metadata": { "id": "7prMrq5RpoF7" }, "execution_count": 7, "outputs": [] }, { "cell_type": "code", "source": [ "X = df.drop('Survived', axis=1)\n", "y = df['Survived']" ], "metadata": { "id": "8GNWlN8MprHP" }, "execution_count": 8, "outputs": [] }, { "cell_type": "code", "source": [ "print(f\"\\nX shape: {X.shape}\")\n", "print(f\"y shape: {y.shape}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "A0eJVx-3pvxl", "outputId": "95a080ee-3324-49e5-9879-195111bc3414" }, "execution_count": 9, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "X shape: (891, 8)\n", "y shape: (891,)\n" ] } ] }, { "cell_type": "code", "source": [ "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.2, random_state=42)\n", "\n", "print(f\"\\nX_train shape: {X_train.shape}\")\n", "print(f\"X_test shape: {X_test.shape}\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ELrzbUZipzZc", "outputId": "762aa35b-78db-49b1-db29-3d08108dde78" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "X_train shape: (712, 8)\n", "X_test shape: (179, 8)\n" ] } ] }, { "cell_type": "code", "source": [ "scaler = StandardScaler()\n", "X_train_scaled = scaler.fit_transform(X_train)\n", "X_test_scaled = scaler.transform(X_test)\n" ], "metadata": { "id": "jttFRkAbp4kC" }, "execution_count": 11, "outputs": [] }, { "cell_type": "code", "source": [ "sklearn_rf = RandomForestClassifier()\n", "sklearn_rf.fit(X_train_scaled, y_train)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 80 }, "id": "dxsQtfe9p8yh", "outputId": "99b62c98-9499-493b-90d7-8efe32a852be" }, "execution_count": 12, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "RandomForestClassifier()" ], "text/html": [ "
RandomForestClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ] }, "metadata": {}, "execution_count": 12 } ] }, { "cell_type": "code", "source": [ "y_pred = sklearn_rf.predict(X_test_scaled)\n" ], "metadata": { "id": "YBnx8T1rqBez" }, "execution_count": 13, "outputs": [] }, { "cell_type": "code", "source": [ "accuracy = accuracy_score(y_test, y_pred)\n", "print(f\"Accuracy: {accuracy:.4f}\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "cYtKCjT7qEVX", "outputId": "13dc1d85-3122-46c3-8bca-0153c3efd5f6" }, "execution_count": 14, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy: 0.8156\n" ] } ] }, { "cell_type": "code", "source": [ "conf_matrix = confusion_matrix(y_test, y_pred)\n" ], "metadata": { "id": "9SNH26zFqNwR" }, "execution_count": 15, "outputs": [] } ] }