{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "14dcdb65", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 2, "id": "6e1a28d6", "metadata": {}, "outputs": [], "source": [ "df= pd.read_csv('Social_Network_Ads.csv')" ] }, { "cell_type": "code", "execution_count": 3, "id": "f307f899", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(400, 5)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.shape" ] }, { "cell_type": "code", "execution_count": 4, "id": "bfd3f0a7", "metadata": {}, "outputs": [ { "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", "
User IDGenderAgeEstimatedSalaryPurchased
015624510Male19190000
115810944Male35200000
215668575Female26430000
315603246Female27570000
415804002Male19760000
\n", "
" ], "text/plain": [ " 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" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head()" ] }, { "cell_type": "code", "execution_count": 5, "id": "367f68ac", "metadata": {}, "outputs": [], "source": [ "df.drop(['User ID'],axis=1,inplace=True)" ] }, { "cell_type": "code", "execution_count": 6, "id": "a4cbd32d", "metadata": {}, "outputs": [ { "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", "
GenderAgeEstimatedSalaryPurchased
0Male19190000
1Male35200000
2Female26430000
3Female27570000
4Male19760000
\n", "
" ], "text/plain": [ " Gender Age EstimatedSalary Purchased\n", "0 Male 19 19000 0\n", "1 Male 35 20000 0\n", "2 Female 26 43000 0\n", "3 Female 27 57000 0\n", "4 Male 19 76000 0" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head()" ] }, { "cell_type": "code", "execution_count": 7, "id": "79b711cd", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Purchased\n", "0 257\n", "1 143\n", "Name: count, dtype: int64" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.Purchased.value_counts()" ] }, { "cell_type": "code", "execution_count": 8, "id": "95801afd", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Gender\n", "Female 204\n", "Male 196\n", "Name: count, dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.Gender.value_counts()" ] }, { "cell_type": "code", "execution_count": 9, "id": "4320d700", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Gender object\n", "Age int64\n", "EstimatedSalary int64\n", "Purchased int64\n", "dtype: object" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.dtypes" ] }, { "cell_type": "code", "execution_count": 10, "id": "7fdabb03", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Gender 0\n", "Age 0\n", "EstimatedSalary 0\n", "Purchased 0\n", "dtype: int64" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 11, "id": "605b7da5", "metadata": {}, "outputs": [ { "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", "
AgeEstimatedSalaryPurchased
count400.000000400.000000400.000000
mean37.65500069742.5000000.357500
std10.48287734096.9602820.479864
min18.00000015000.0000000.000000
25%29.75000043000.0000000.000000
50%37.00000070000.0000000.000000
75%46.00000088000.0000001.000000
max60.000000150000.0000001.000000
\n", "
" ], "text/plain": [ " Age EstimatedSalary Purchased\n", "count 400.000000 400.000000 400.000000\n", "mean 37.655000 69742.500000 0.357500\n", "std 10.482877 34096.960282 0.479864\n", "min 18.000000 15000.000000 0.000000\n", "25% 29.750000 43000.000000 0.000000\n", "50% 37.000000 70000.000000 0.000000\n", "75% 46.000000 88000.000000 1.000000\n", "max 60.000000 150000.000000 1.000000" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe()" ] }, { "cell_type": "code", "execution_count": 18, "id": "6b60855e", "metadata": {}, "outputs": [ { "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", "
AgeEstimatedSalary
01919000
13520000
22643000
32757000
41976000
\n", "
" ], "text/plain": [ " Age EstimatedSalary\n", "0 19 19000\n", "1 35 20000\n", "2 26 43000\n", "3 27 57000\n", "4 19 76000" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X=df.drop(['Gender','Purchased'],axis=1)\n", "Y= df['Purchased']\n", "X.head()\n", "\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "a026b20d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training and testing split was successful.\n" ] } ], "source": [ "from sklearn.model_selection import train_test_split\n", "# Shuffle and split the data into training and testing subsets\n", "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state = 42)\n", "\n", "# Success\n", "print(\"Training and testing split was successful.\")" ] }, { "cell_type": "code", "execution_count": 20, "id": "1b403e52", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training accuracy: 64.0625\n" ] } ], "source": [ "from sklearn.linear_model import LogisticRegression\n", "basemodel= LogisticRegression()\n", "basemodel.fit(X_train,y_train)\n", "print(\"Training accuracy:\", basemodel.score(X_train,y_train)*100)" ] }, { "cell_type": "code", "execution_count": 21, "id": "33e720a2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Testing accuracy: 65.0\n" ] } ], "source": [ "y_predict= basemodel.predict(X_test)\n", "print(\"Testing accuracy:\", basemodel.score(X_test,y_test)*100)" ] }, { "cell_type": "code", "execution_count": 22, "id": "90d5c0c4", "metadata": {}, "outputs": [], "source": [ "from sklearn.preprocessing import MinMaxScaler\n", "scaler=MinMaxScaler()" ] }, { "cell_type": "code", "execution_count": 23, "id": "cc071b5a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training and testing split was successful.\n" ] } ], "source": [ "X=df[['Age','EstimatedSalary']]\n", "X_scaled= scaler.fit_transform(X)\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X_scaled, Y, test_size=0.2, random_state = 42)\n", "print(\"Training and testing split was successful.\")" ] }, { "cell_type": "code", "execution_count": 24, "id": "3c78c9db", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training accuracy: 80.9375\n", "Testing accuracy: 87.5\n" ] } ], "source": [ "model= LogisticRegression()\n", "model.fit(X_train,y_train)\n", "y_predict= model.predict(X_test)\n", "print(\"Training accuracy:\", model.score(X_train,y_train)*100)\n", "print(\"Testing accuracy:\", model.score(X_test,y_test)*100)" ] }, { "cell_type": "code", "execution_count": 25, "id": "37c241e7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.875\n" ] } ], "source": [ "from sklearn.metrics import accuracy_score\n", "Acc=accuracy_score(y_test,y_predict)\n", "print(Acc)" ] }, { "cell_type": "code", "execution_count": 26, "id": "b5f6e55a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[51 1]\n", " [ 9 19]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "cm= confusion_matrix(y_test,y_predict)\n", "print(cm)" ] }, { "cell_type": "code", "execution_count": 27, "id": "be4e2329", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "precision: [0.85 0.95]\n", "Recall: [0.98076923 0.67857143]\n", "fscore: [0.91071429 0.79166667]\n", "support: [52 28]\n" ] } ], "source": [ "from sklearn.metrics import precision_recall_fscore_support\n", "prf= precision_recall_fscore_support(y_test,y_predict)\n", "print('precision:',prf[0])\n", "print('Recall:',prf[1])\n", "print('fscore:',prf[2])\n", "print('support:',prf[3])" ] }, { "cell_type": "code", "execution_count": 28, "id": "6a19f5b8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.85 0.98 0.91 52\n", " 1 0.95 0.68 0.79 28\n", "\n", " accuracy 0.88 80\n", " macro avg 0.90 0.83 0.85 80\n", "weighted avg 0.89 0.88 0.87 80\n", "\n" ] } ], "source": [ "from sklearn.metrics import classification_report\n", "cr= classification_report(y_test,y_predict)\n", "print(cr)" ] }, { "cell_type": "code", "execution_count": null, "id": "02579d16", "metadata": {}, "outputs": [], "source": [] } ], "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": "3.11.5" } }, "nbformat": 4, "nbformat_minor": 5 }