{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU" }, "cells": [ { "cell_type": "code", "execution_count": 23, "metadata": { "id": "QIy-FDAliLBP" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.impute import SimpleImputer\n", "from sklearn.preprocessing import LabelEncoder\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.ensemble import AdaBoostClassifier\n", "from sklearn.metrics import accuracy_score" ] }, { "cell_type": "code", "source": [ "titanic = pd.read_csv('/content/Titanic-Dataset.csv')" ], "metadata": { "id": "bDWIWwewiMJU" }, "execution_count": 24, "outputs": [] }, { "cell_type": "code", "source": [ "X = titanic.drop(['PassengerId', 'Name', 'Ticket', 'Cabin', 'Survived'], axis=1)\n", "y = titanic['Survived']\n", "\n", "num_cols = X.select_dtypes(include=np.number).columns\n", "cat_cols = X.select_dtypes(include='object').columns\n", "\n", "imputer_num = SimpleImputer(strategy='median')\n", "X[num_cols] = imputer_num.fit_transform(X[num_cols])\n", "\n", "imputer_cat = SimpleImputer(strategy='most_frequent')\n", "X[cat_cols] = imputer_cat.fit_transform(X[cat_cols])" ], "metadata": { "id": "mhc7OH2Aib9C" }, "execution_count": 25, "outputs": [] }, { "cell_type": "code", "source": [ "for col in cat_cols:\n", " le = LabelEncoder()\n", " X[col] = le.fit_transform(X[col])" ], "metadata": { "id": "wI0jRCM6ib_h" }, "execution_count": 26, "outputs": [] }, { "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", "\n", "\n", "weak_tree = DecisionTreeClassifier(max_depth=4, random_state=42)\n", "weak_tree.fit(X_train, y_train)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 80 }, "id": "rupyd3Qtiirc", "outputId": "7f68ec8e-9c1f-414d-fe15-5a074e88ad23" }, "execution_count": 27, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "DecisionTreeClassifier(max_depth=4, random_state=42)" ], "text/html": [ "
DecisionTreeClassifier(max_depth=4, random_state=42)
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": 27 } ] }, { "cell_type": "code", "source": [ "tree_accuracy = accuracy_score(y_test, weak_tree.predict(X_test))\n", "print(f'Accuracy of the weak learner (Decision Tree): {tree_accuracy*100:.2f}%')\n", "\n", "\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "dJvnhhzJiMLg", "outputId": "6ad35135-a7cb-4bfe-f4a9-46e45b488578" }, "execution_count": 28, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy of the weak learner (Decision Tree): 79.89%\n" ] } ] }, { "cell_type": "code", "source": [ "ada_boost = AdaBoostClassifier(\n", " estimator=weak_tree,\n", " n_estimators=100,\n", " learning_rate=1.0,\n", " random_state=42\n", ")\n", "ada_boost.fit(X_train, y_train)\n", "\n", "\n", "ada_accuracy = accuracy_score(y_test, ada_boost.predict(X_test))\n", "print(f'Accuracy of AdaBoost model: {ada_accuracy*100:.2f}%')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "VuXnUQHliMhK", "outputId": "63d21958-5b0d-4e3f-fdbb-03aff1216eb5" }, "execution_count": 29, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy of AdaBoost model: 81.56%\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "1fV6_tAuiMin" }, "execution_count": 29, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "eLNGh7CniMj_" }, "execution_count": 29, "outputs": [] } ] }