{ "cells": [ { "cell_type": "markdown", "id": "310c258e", "metadata": {}, "source": [ "# Machine Learning Activity: Feature Selection and Model Comparison\n", "\n", "In this notebook, you will train a **Random Forest classifier** using the **Diabetes** or **Titanic** dataset.\n", "You will analyze the effect of **feature selection** and compare **Random Forest, Logistic Regression, and Naïve Bayes classifiers**.\n", "\n", "## Objectives\n", "1. Train a **Random Forest classifier**.\n", "2. Investigate feature selection using:\n", " - **Manual feature importance analysis**.\n", " - **Principal Component Analysis (PCA)**.\n", "3. Train **Logistic Regression** and **Naïve Bayes** for comparison.\n", "4. Evaluate models using **accuracy, precision, recall, and F1-score**.\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "f77f9100", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 768 entries, 0 to 767\n", "Data columns (total 10 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 PatientId 768 non-null int64 \n", " 1 Pregnancies 768 non-null int64 \n", " 2 Glucose 768 non-null int64 \n", " 3 BloodPressure 768 non-null int64 \n", " 4 SkinThickness 768 non-null int64 \n", " 5 Insulin 768 non-null int64 \n", " 6 BMI 768 non-null float64\n", " 7 DiabetesPedigreeFunction 768 non-null float64\n", " 8 Age 768 non-null int64 \n", " 9 Outcome 768 non-null int64 \n", "dtypes: float64(2), int64(8)\n", "memory usage: 60.1 KB\n", "None\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
\n", "
" ], "text/plain": [ " PatientId Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n", "0 1 6 148 72 35 0 \n", "1 2 1 85 66 29 0 \n", "2 3 8 183 64 0 0 \n", "3 4 1 89 66 23 94 \n", "4 5 0 137 40 35 168 \n", "\n", " BMI DiabetesPedigreeFunction Age Outcome \n", "0 33.6 0.627 50 1 \n", "1 26.6 0.351 31 0 \n", "2 23.3 0.672 32 1 \n", "3 28.1 0.167 21 0 \n", "4 43.1 2.288 33 1 " ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler, LabelEncoder\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.decomposition import PCA\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n", "\n", "# Load dataset (Uncomment the one you want to use)\n", "df = pd.read_csv('diabetes.csv') # Diabetes dataset\n", "#df = pd.read_csv('titanic.csv') # Titanic dataset\n", "\n", "# Display basic info\n", "print(df.info())\n", "\n", "df.head()\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "ef428d8d", "metadata": {}, "outputs": [], "source": [ "# Handle missing values (if any)\n", "df.dropna(inplace=True)\n", "\n", "# Encode categorical features (if using Titanic dataset)\n", "if 'Sex' in df.columns:\n", " df['Sex'] = LabelEncoder().fit_transform(df['Sex'])\n", "\n", "# Define features and target\n", "X = df.drop(columns=['Outcome']) if 'Outcome' in df.columns else df.drop(columns=['Survived'])\n", "y = df['Outcome'] if 'Outcome' in df.columns else df['Survived']\n", "\n", "# Split data\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }