{ "cells": [ { "cell_type": "code", "execution_count": 3, "id": "8a2f6552", "metadata": { "id": "8a2f6552" }, "outputs": [], "source": [ "\n", "# Import necessary libraries\n", "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, GridSearchCV\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.feature_selection import SelectKBest, chi2, RFE\n", "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "7d8a0652", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "id": "7d8a0652", "outputId": "2b08a8fa-ec36-45f3-b8f9-3214d111bd0e" }, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " 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, Mr. Owen Harris male 22.0 1 \n", "1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n", "2 Heikkinen, Miss. Laina female 26.0 0 \n", "3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n", "4 Allen, 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 " ], "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked
0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS
1211Cumings, Mrs. John Bradley (Florence Briggs Th...female38.010PC 1759971.2833C85C
2313Heikkinen, Miss. Lainafemale26.000STON/O2. 31012827.9250NaNS
3411Futrelle, Mrs. Jacques Heath (Lily May Peel)female35.01011380353.1000C123S
4503Allen, Mr. William Henrymale35.0003734508.0500NaNS
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "data", "summary": "{\n \"name\": \"data\",\n \"rows\": 891,\n \"fields\": [\n {\n \"column\": \"PassengerId\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 257,\n \"min\": 1,\n \"max\": 891,\n \"num_unique_values\": 891,\n \"samples\": [\n 710,\n 440,\n 841\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Survived\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Pclass\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 1,\n \"max\": 3,\n \"num_unique_values\": 3,\n \"samples\": [\n 3,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Name\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 891,\n \"samples\": [\n \"Moubarek, Master. Halim Gonios (\\\"William George\\\")\",\n \"Kvillner, Mr. Johan Henrik Johannesson\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sex\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"female\",\n \"male\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.526497332334044,\n \"min\": 0.42,\n \"max\": 80.0,\n \"num_unique_values\": 88,\n \"samples\": [\n 0.75,\n 22.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"SibSp\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 0,\n \"max\": 8,\n \"num_unique_values\": 7,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Parch\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 6,\n \"num_unique_values\": 7,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Ticket\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 681,\n \"samples\": [\n \"11774\",\n \"248740\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Fare\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 49.693428597180905,\n \"min\": 0.0,\n \"max\": 512.3292,\n \"num_unique_values\": 248,\n \"samples\": [\n 11.2417,\n 51.8625\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Cabin\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 147,\n \"samples\": [\n \"D45\",\n \"B49\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Embarked\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"S\",\n \"C\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 4 } ], "source": [ "\n", "# Reading dataset\n", "data = pd.read_csv(\"Titanic-Dataset.csv\")\n", "data.head()\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "513fc326", "metadata": { "id": "513fc326" }, "outputs": [], "source": [ "\n", "# Drop unnecessary columns if they exist\n", "for col in ['Cabin', 'Name', 'Ticket']:\n", " if col in data.columns:\n", " data.drop(col, axis=1, inplace=True)\n", "\n", "# Handle missing values\n", "if 'Age' in data.columns:\n", " data['Age'] = data['Age'].fillna(data['Age'].mean())\n", "\n", "if 'Embarked' in data.columns:\n", " data['Embarked'] = data['Embarked'].fillna(data['Embarked'].mode()[0])\n", "\n", "data.dropna(inplace=True)\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "70784452", "metadata": { "id": "70784452" }, "outputs": [], "source": [ "\n", "# Convert categorical variables to numeric\n", "data = pd.get_dummies(data, columns=['Sex', 'Embarked'], drop_first=True)\n" ] }, { "cell_type": "code", "execution_count": 7, "id": "ad7d3db6", "metadata": { "id": "ad7d3db6" }, "outputs": [], "source": [ "\n", "# Define features and target variable\n", "X = data.drop(['Survived', 'PassengerId'], axis=1)\n", "y = data['Survived']\n" ] }, { "cell_type": "code", "execution_count": 8, "id": "8dfa7131", "metadata": { "id": "8dfa7131" }, "outputs": [], "source": [ "\n", "# Split and scale the data\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "scaler = StandardScaler()\n", "X_train_scaled = scaler.fit_transform(X_train)\n", "X_test_scaled = scaler.transform(X_test)\n" ] }, { "cell_type": "code", "execution_count": 9, "id": "1acc275b", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "1acc275b", "outputId": "a51cfab0-6a18-4725-a2e2-95ebc993dc1b" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Best parameters: {'C': 0.01}\n", "Accuracy: 0.7988826815642458\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.79 0.89 0.84 105\n", " 1 0.81 0.68 0.74 74\n", "\n", " accuracy 0.80 179\n", " macro avg 0.80 0.78 0.79 179\n", "weighted avg 0.80 0.80 0.80 179\n", "\n" ] } ], "source": [ "\n", "# Apply Logistic Regression with GridSearchCV\n", "param_grid = {'C': [0.01, 0.1, 1, 10]}\n", "grid = GridSearchCV(LogisticRegression(), param_grid, cv=5)\n", "grid.fit(X_train_scaled, y_train)\n", "\n", "y_pred = grid.predict(X_test_scaled)\n", "print(\"Best parameters:\", grid.best_params_)\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n", "print(\"Classification Report:\")\n", "print(classification_report(y_test, y_pred))\n" ] }, { "cell_type": "code", "execution_count": 10, "id": "685b7b58", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 410 }, "id": "685b7b58", "outputId": "f173d7b9-7e92-4e4f-fec6-1a6d3ec5fa15" }, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ], "source": [ "\n", "# Plot Confusion Matrix\n", "cm = confusion_matrix(y_test, y_pred)\n", "plt.figure(figsize=(4, 4))\n", "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', cbar=False)\n", "plt.title(\"Confusion Matrix\")\n", "plt.xlabel(\"Predicted\")\n", "plt.ylabel(\"Actual\")\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": 11, "id": "01d792c0", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "01d792c0", "outputId": "3beeb579-b05c-4950-8d2b-1d119166b9ba" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy after SelectKBest: 0.7932960893854749\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.80 0.86 0.83 105\n", " 1 0.78 0.70 0.74 74\n", "\n", " accuracy 0.79 179\n", " macro avg 0.79 0.78 0.78 179\n", "weighted avg 0.79 0.79 0.79 179\n", "\n" ] } ], "source": [ "\n", "# Feature Selection using SelectKBest\n", "selector = SelectKBest(score_func=chi2, k=5)\n", "X_new = selector.fit_transform(X, y)\n", "\n", "X_train_kb, X_test_kb, y_train_kb, y_test_kb = train_test_split(X_new, y, test_size=0.2, random_state=42)\n", "\n", "grid.fit(X_train_kb, y_train_kb)\n", "y_pred_kb = grid.predict(X_test_kb)\n", "\n", "print(\"Accuracy after SelectKBest:\", accuracy_score(y_test_kb, y_pred_kb))\n", "print(\"Classification Report:\")\n", "print(classification_report(y_test_kb, y_pred_kb))\n" ] }, { "cell_type": "code", "execution_count": 12, "id": "8dede2ed", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "8dede2ed", "outputId": "8f313f4b-fe89-434b-bef4-eb8580e285b8" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy after RFE: 0.770949720670391\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.81 0.79 0.80 105\n", " 1 0.71 0.74 0.73 74\n", "\n", " accuracy 0.77 179\n", " macro avg 0.76 0.77 0.77 179\n", "weighted avg 0.77 0.77 0.77 179\n", "\n" ] } ], "source": [ "\n", "# Feature Selection using RFE\n", "rfe_selector = RFE(estimator=LogisticRegression(max_iter=1000), n_features_to_select=5)\n", "X_rfe = rfe_selector.fit_transform(X, y)\n", "\n", "X_train_rfe, X_test_rfe, y_train_rfe, y_test_rfe = train_test_split(X_rfe, y, test_size=0.2, random_state=42)\n", "\n", "grid.fit(X_train_rfe, y_train_rfe)\n", "y_pred_rfe = grid.predict(X_test_rfe)\n", "\n", "print(\"Accuracy after RFE:\", accuracy_score(y_test_rfe, y_pred_rfe))\n", "print(\"Classification Report:\")\n", "print(classification_report(y_test_rfe, y_pred_rfe))\n" ] } ], "metadata": { "colab": { "provenance": [] }, "language_info": { "name": "python" }, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "nbformat": 4, "nbformat_minor": 5 }