{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "a1b2c3d4-0001-4000-8000-000000000001", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler, LabelEncoder\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report" ] }, { "cell_type": "code", "execution_count": 3, "id": "a1b2c3d4-0002-4000-8000-000000000002", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "csv file read\n", " User ID Gender Age EstimatedSalary Purchased\n", "0 15624510 Male 19 19000 0\n", "1 15810944 Male 35 20000 0\n", "2 15668575 Female 26 43000 0\n", "3 15603246 Female 27 57000 0\n", "4 15804002 Male 19 76000 0\n", "(19, 5)\n" ] } ], "source": [ "# Load dataset\n", "df = pd.read_csv(\"data/user_data.csv\")\n", "print(\"csv file read\")\n", "print(df.head())\n", "print(df.shape)" ] }, { "cell_type": "code", "execution_count": 4, "id": "a1b2c3d4-0003-4000-8000-000000000003", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Gender Age EstimatedSalary Purchased\n", "0 1 19 19000 0\n", "1 1 35 20000 0\n", "2 0 26 43000 0\n", "3 0 27 57000 0\n", "4 1 19 76000 0\n" ] } ], "source": [ "# Remove unnecessary column\n", "df = df.drop(columns=['User ID'])\n", "\n", "# Encode categorical variable: Gender (Male=1, Female=0)\n", "le = LabelEncoder()\n", "df['Gender'] = le.fit_transform(df['Gender'])\n", "\n", "print(df.head())" ] }, { "cell_type": "code", "execution_count": 5, "id": "a1b2c3d4-0004-4000-8000-000000000004", "metadata": {}, "outputs": [], "source": [ "# Separate features (X) and target (y)\n", "X = df[['Gender', 'Age', 'EstimatedSalary']].values\n", "y = df['Purchased'].values" ] }, { "cell_type": "code", "execution_count": 6, "id": "a1b2c3d4-0005-4000-8000-000000000005", "metadata": {}, "outputs": [], "source": [ "# Apply feature scaling\n", "scaler = StandardScaler()\n", "X = scaler.fit_transform(X)" ] }, { "cell_type": "code", "execution_count": 7, "id": "a1b2c3d4-0006-4000-8000-000000000006", "metadata": {}, "outputs": [], "source": [ "# Split dataset into training and testing sets\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.2, random_state=42\n", ")" ] }, { "cell_type": "code", "execution_count": 8, "id": "a1b2c3d4-0007-4000-8000-000000000007", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
LogisticRegression()
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.
" ], "text/plain": [ "LogisticRegression()" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Create and train Logistic Regression model\n", "model = LogisticRegression()\n", "model.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 9, "id": "a1b2c3d4-0008-4000-8000-000000000008", "metadata": {}, "outputs": [], "source": [ "# Predict on test set\n", "predictions = model.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 10, "id": "a1b2c3d4-0009-4000-8000-000000000009", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 1.0\n", "\n", "Confusion Matrix:\n", "[[4]]\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 1.00 1.00 4\n", "\n", " accuracy 1.00 4\n", " macro avg 1.00 1.00 1.00 4\n", "weighted avg 1.00 1.00 1.00 4\n", "\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\222-G\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:407: UserWarning: A single label was found in 'y_true' and 'y_pred'. For the confusion matrix to have the correct shape, use the 'labels' parameter to pass all known labels.\n", " warnings.warn(\n" ] } ], "source": [ "# Evaluate performance\n", "accuracy = accuracy_score(y_test, predictions)\n", "print(\"Accuracy:\", accuracy)\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, predictions))\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, predictions))" ] }, { "cell_type": "code", "execution_count": 11, "id": "a1b2c3d4-0010-4000-8000-000000000010", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Age Salary Actual Predicted\n", "0 19 19000 0 0\n", "1 27 58000 0 0\n", "2 26 52000 0 0\n", "3 35 20000 0 0\n" ] } ], "source": [ "# Display sample predictions: Age, Salary, Actual, Predicted\n", "# Inverse-transform scaled X_test to recover original Age and Salary values\n", "X_test_original = scaler.inverse_transform(X_test)\n", "\n", "results = pd.DataFrame({\n", " 'Age': X_test_original[:, 1].astype(int),\n", " 'Salary': X_test_original[:, 2].astype(int),\n", " 'Actual': y_test,\n", " 'Predicted': predictions\n", "})\n", "\n", "print(results.head())" ] } ], "metadata": { "kernelspec": { "display_name": "Python [conda env:base] *", "language": "python", "name": "conda-base-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.13.5" } }, "nbformat": 4, "nbformat_minor": 5 }