{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":84896,"databundleVersionId":10305135,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:17.277547Z","iopub.execute_input":"2025-07-28T12:47:17.27793Z","iopub.status.idle":"2025-07-28T12:47:17.654477Z","shell.execute_reply.started":"2025-07-28T12:47:17.277896Z","shell.execute_reply":"2025-07-28T12:47:17.653458Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nimport seaborn as sns\nimport matplotlib.pyplot as plt \nimport plotly.express as px\nfrom sklearn.preprocessing import MinMaxScaler, StandardScaler, RobustScaler\nimport warnings\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:17.655869Z","iopub.execute_input":"2025-07-28T12:47:17.656322Z","iopub.status.idle":"2025-07-28T12:47:20.274503Z","shell.execute_reply.started":"2025-07-28T12:47:17.656282Z","shell.execute_reply":"2025-07-28T12:47:20.273513Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Ignore all warnings\nwarnings.filterwarnings('ignore')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:20.27935Z","iopub.execute_input":"2025-07-28T12:47:20.279697Z","iopub.status.idle":"2025-07-28T12:47:20.284229Z","shell.execute_reply.started":"2025-07-28T12:47:20.279668Z","shell.execute_reply":"2025-07-28T12:47:20.283174Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data = pd.read_csv('/kaggle/input/playground-series-s4e12/train.csv')\ntest_data = pd.read_csv('/kaggle/input/playground-series-s4e12/test.csv')\nsample_submission = pd.read_csv('/kaggle/input/playground-series-s4e12/sample_submission.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:20.285359Z","iopub.execute_input":"2025-07-28T12:47:20.285696Z","iopub.status.idle":"2025-07-28T12:47:34.352307Z","shell.execute_reply.started":"2025-07-28T12:47:20.285668Z","shell.execute_reply":"2025-07-28T12:47:34.351122Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:34.353249Z","iopub.execute_input":"2025-07-28T12:47:34.353511Z","iopub.status.idle":"2025-07-28T12:47:35.177142Z","shell.execute_reply.started":"2025-07-28T12:47:34.353488Z","shell.execute_reply":"2025-07-28T12:47:35.176093Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# EDA : exploratory Data Analysis","metadata":{}},{"cell_type":"code","source":"train_data.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:35.178489Z","iopub.execute_input":"2025-07-28T12:47:35.178818Z","iopub.status.idle":"2025-07-28T12:47:35.945169Z","shell.execute_reply.started":"2025-07-28T12:47:35.178796Z","shell.execute_reply":"2025-07-28T12:47:35.944187Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 1- Handling Missing Values","metadata":{}},{"cell_type":"code","source":"train_data.isnull().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:35.946124Z","iopub.execute_input":"2025-07-28T12:47:35.94645Z","iopub.status.idle":"2025-07-28T12:47:36.725936Z","shell.execute_reply.started":"2025-07-28T12:47:35.946422Z","shell.execute_reply":"2025-07-28T12:47:36.724933Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# missing percentage\nmissings = train_data.isnull().mean()*100\nmissings","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:36.726885Z","iopub.execute_input":"2025-07-28T12:47:36.727154Z","iopub.status.idle":"2025-07-28T12:47:37.454637Z","shell.execute_reply.started":"2025-07-28T12:47:36.727131Z","shell.execute_reply":"2025-07-28T12:47:37.453515Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# handling Age ( mean, mode, median)\nsns.boxplot(x=train_data['Age'])\nplt.title(\"BoxPlot of Age\")\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:37.457712Z","iopub.execute_input":"2025-07-28T12:47:37.457992Z","iopub.status.idle":"2025-07-28T12:47:37.748354Z","shell.execute_reply.started":"2025-07-28T12:47:37.457971Z","shell.execute_reply":"2025-07-28T12:47:37.747199Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(train_data['Age'].mean())\nprint(train_data['Age'].median())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:37.749421Z","iopub.execute_input":"2025-07-28T12:47:37.749694Z","iopub.status.idle":"2025-07-28T12:47:37.78621Z","shell.execute_reply.started":"2025-07-28T12:47:37.749674Z","shell.execute_reply":"2025-07-28T12:47:37.78525Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:37.787196Z","iopub.execute_input":"2025-07-28T12:47:37.787581Z","iopub.status.idle":"2025-07-28T12:47:38.496142Z","shell.execute_reply.started":"2025-07-28T12:47:37.787529Z","shell.execute_reply":"2025-07-28T12:47:38.495259Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for col in train_data.columns:\n    print(train_data[col].value_counts(normalize=True))\n    print(\"-------------\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:38.4972Z","iopub.execute_input":"2025-07-28T12:47:38.497541Z","iopub.status.idle":"2025-07-28T12:47:40.426219Z","shell.execute_reply.started":"2025-07-28T12:47:38.497514Z","shell.execute_reply":"2025-07-28T12:47:40.425022Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:40.427667Z","iopub.execute_input":"2025-07-28T12:47:40.427954Z","iopub.status.idle":"2025-07-28T12:47:41.163604Z","shell.execute_reply.started":"2025-07-28T12:47:40.427933Z","shell.execute_reply":"2025-07-28T12:47:41.16242Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"del train_data['id']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:41.165907Z","iopub.execute_input":"2025-07-28T12:47:41.16628Z","iopub.status.idle":"2025-07-28T12:47:41.172232Z","shell.execute_reply.started":"2025-07-28T12:47:41.166245Z","shell.execute_reply":"2025-07-28T12:47:41.171256Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Changing data type of (Number of Dependents & revious Claims ) columns from numerical to category","metadata":{}},{"cell_type":"code","source":"train_data['Number of Dependents'] = train_data['Number of Dependents'].astype('category')\ntrain_data['Previous Claims'] = train_data['Previous Claims'].astype('category')\n\n\ntrain_data.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:41.173269Z","iopub.execute_input":"2025-07-28T12:47:41.173688Z","iopub.status.idle":"2025-07-28T12:47:41.958841Z","shell.execute_reply.started":"2025-07-28T12:47:41.173664Z","shell.execute_reply":"2025-07-28T12:47:41.957774Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# N","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:41.959938Z","iopub.execute_input":"2025-07-28T12:47:41.960401Z","iopub.status.idle":"2025-07-28T12:47:41.964939Z","shell.execute_reply.started":"2025-07-28T12:47:41.960367Z","shell.execute_reply":"2025-07-28T12:47:41.96415Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"num = train_data.select_dtypes(include=['int64', 'float64']).columns\ncat = train_data.select_dtypes(include=['object', 'category']).columns\nprint(num.tolist())\nprint(cat.tolist())\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:41.965871Z","iopub.execute_input":"2025-07-28T12:47:41.966082Z","iopub.status.idle":"2025-07-28T12:47:42.615471Z","shell.execute_reply.started":"2025-07-28T12:47:41.966065Z","shell.execute_reply":"2025-07-28T12:47:42.614463Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\"\"\"\nnumerical_columns = ['Age' ,'Annual Income' ,'' ]\ncat \ntrain_data.fillna(train_data.mean(), inplace=True)\n#gender, Marital Status\n\"\"\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:42.616669Z","iopub.execute_input":"2025-07-28T12:47:42.616931Z","iopub.status.idle":"2025-07-28T12:47:42.622481Z","shell.execute_reply.started":"2025-07-28T12:47:42.616911Z","shell.execute_reply":"2025-07-28T12:47:42.621643Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for col in num:\n    plt.figure(figsize=(15,8))\n    sns.histplot(x=train_data[col] , kde=True , bins = 25, data =train_data)\n    plt.title(f\"Histogram of {col}\")\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:47:42.623324Z","iopub.execute_input":"2025-07-28T12:47:42.623615Z","iopub.status.idle":"2025-07-28T12:48:18.794842Z","shell.execute_reply.started":"2025-07-28T12:47:42.623589Z","shell.execute_reply":"2025-07-28T12:48:18.793797Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"mean = train_data['Health Score'].mean()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:18.795839Z","iopub.execute_input":"2025-07-28T12:48:18.796178Z","iopub.status.idle":"2025-07-28T12:48:18.815757Z","shell.execute_reply.started":"2025-07-28T12:48:18.796147Z","shell.execute_reply":"2025-07-28T12:48:18.814631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"std = train_data['Health Score'].std()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:18.816642Z","iopub.execute_input":"2025-07-28T12:48:18.817341Z","iopub.status.idle":"2025-07-28T12:48:18.828112Z","shell.execute_reply.started":"2025-07-28T12:48:18.817306Z","shell.execute_reply":"2025-07-28T12:48:18.827119Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data['Health Score'].isna().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:18.829423Z","iopub.execute_input":"2025-07-28T12:48:18.829845Z","iopub.status.idle":"2025-07-28T12:48:18.852432Z","shell.execute_reply.started":"2025-07-28T12:48:18.829813Z","shell.execute_reply":"2025-07-28T12:48:18.851632Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n#np.random.uniform(mean-std ,mean+std , size = train_data['Health Score'].isna().sum() )\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:18.853423Z","iopub.execute_input":"2025-07-28T12:48:18.853685Z","iopub.status.idle":"2025-07-28T12:48:18.858894Z","shell.execute_reply.started":"2025-07-28T12:48:18.853665Z","shell.execute_reply":"2025-07-28T12:48:18.857816Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_data.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:18.860248Z","iopub.execute_input":"2025-07-28T12:48:18.861135Z","iopub.status.idle":"2025-07-28T12:48:19.42Z","shell.execute_reply.started":"2025-07-28T12:48:18.861092Z","shell.execute_reply":"2025-07-28T12:48:19.419054Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#test_data.fillna(test_data.mean() , inplace=True )\n# missing percentage\nfor col in num:\n    print(f\"Column Name : {col}\")\n    print(f\" Number of Missing Before Cleaning {train_data[col].isnull().mean()*100}\")\n    \n    m = train_data[col].mean()\n    s = train_data[col].std()\n    si = train_data[col].isna().sum()\n\n    #pd.Series\n    train_data[col] = train_data[col].fillna(pd.Series(np.random.uniform(m-s , m+s , size = int(si))\n                                                      , index = train_data[train_data[col].isna()].index ) )\n    \n    print(f\"Number of missing after Handling : {train_data[col].isnull().mean()*100}\")\n    print(\"________\")\n    \n    #loc , iloc","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:19.420955Z","iopub.execute_input":"2025-07-28T12:48:19.421312Z","iopub.status.idle":"2025-07-28T12:48:20.055777Z","shell.execute_reply.started":"2025-07-28T12:48:19.421282Z","shell.execute_reply":"2025-07-28T12:48:20.054445Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for col in num:\n    plt.figure(figsize=(15,8))\n    sns.histplot(x=train_data[col] , kde=True , bins = 25 , data= train_data)\n    plt.title(f\"Histogram of {col}\")\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:20.057058Z","iopub.execute_input":"2025-07-28T12:48:20.057362Z","iopub.status.idle":"2025-07-28T12:48:55.861273Z","shell.execute_reply.started":"2025-07-28T12:48:20.057333Z","shell.execute_reply":"2025-07-28T12:48:55.859926Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## **` After Handling missing values with random choices between mean and standard deviation, this resulted to smooth data , with no missing values or outliers , and normally distributed. Which is the meaning of a Clean Data ! `**\n\n### Health score column after handling Missing data with Mean Value\n![image.png](attachment:7d16bcb3-08e2-4ed1-8d67-eea09d95d7e7.png)\n\n### Credit score column after handling Missing data with Mean Value\n![image.png](attachment:cb264f72-66df-4087-ac19-46684a6e90a7.png)\n","metadata":{},"attachments":{"cb264f72-66df-4087-ac19-46684a6e90a7.png":{"image/png":"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"},"7d16bcb3-08e2-4ed1-8d67-eea09d95d7e7.png":{"image/png":"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"}}},{"cell_type":"code","source":"train_data['Marital Status'].mode()[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:55.865978Z","iopub.execute_input":"2025-07-28T12:48:55.866305Z","iopub.status.idle":"2025-07-28T12:48:55.965955Z","shell.execute_reply.started":"2025-07-28T12:48:55.86628Z","shell.execute_reply":"2025-07-28T12:48:55.964922Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for col in cat:\n    print(f\"Column Name : {col}\")\n    print(train_data[col].isnull().mean()*100)\n    \n    train_data[col] = train_data[col].fillna(train_data[col].mode()[0])\n    print(f\"Number of missing after Handling : {train_data[col].isnull().mean()*100}\")\n    print(\"________\")\n    \n    ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:55.96698Z","iopub.execute_input":"2025-07-28T12:48:55.967323Z","iopub.status.idle":"2025-07-28T12:48:59.649526Z","shell.execute_reply.started":"2025-07-28T12:48:55.967302Z","shell.execute_reply":"2025-07-28T12:48:59.648437Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## **`After considering Data distribution , we found out that filling these two colmns 'Number of Dependents' , 'Credit Score' with mean value would have a negative effective and cause the data to have too much outliers, so we need to handle it with a different way!`**\n","metadata":{}},{"cell_type":"markdown","source":"# Step 2 - Detecting Outlier using Histogram, BoxPlot, Scatter Plot , IQR , MAD","metadata":{}},{"cell_type":"markdown","source":"## 1- BoxPlot","metadata":{}},{"cell_type":"code","source":"num","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:59.650341Z","iopub.execute_input":"2025-07-28T12:48:59.650585Z","iopub.status.idle":"2025-07-28T12:48:59.656805Z","shell.execute_reply.started":"2025-07-28T12:48:59.65054Z","shell.execute_reply":"2025-07-28T12:48:59.655789Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# supplot\nplt.figure(figsize=(20,15))\nfor i , col in enumerate(num , start=1):\n    plt.subplot(5,2 , i)\n    sns.boxplot(x=train_data[col])\n    plt.title(f\"Boxplot of {col}\")\nplt.tight_layout()    \nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:48:59.65825Z","iopub.execute_input":"2025-07-28T12:48:59.658598Z","iopub.status.idle":"2025-07-28T12:49:01.268805Z","shell.execute_reply.started":"2025-07-28T12:48:59.658543Z","shell.execute_reply":"2025-07-28T12:49:01.267813Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 2- Histogram","metadata":{}},{"cell_type":"code","source":"for col in num :\n    fig = px.histogram( train_data , x = col , title = f'Histogram for {col} distribution')\n    fig.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:49:58.336066Z","iopub.execute_input":"2025-07-28T12:49:58.336357Z","iopub.status.idle":"2025-07-28T12:50:00.290516Z","shell.execute_reply.started":"2025-07-28T12:49:58.336335Z","shell.execute_reply":"2025-07-28T12:50:00.2896Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 3- IQR ","metadata":{}},{"cell_type":"code","source":"num","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:52:14.532251Z","iopub.execute_input":"2025-07-28T12:52:14.532598Z","iopub.status.idle":"2025-07-28T12:52:14.539545Z","shell.execute_reply.started":"2025-07-28T12:52:14.532546Z","shell.execute_reply":"2025-07-28T12:52:14.538407Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for col in num :\n    print(f\"Column Name : {col}\")\n    Q1 = train_data[col].quantile(0.25)\n    Q3 = train_data[col].quantile(0.75)\n    IQR = Q3 - Q1\n    lower = Q1 - ( 1.5 *IQR )\n    upper = Q3 + (1.5 * IQR )\n    print (f\" Q1 : {Q1} , Q3 : {Q3} \\nLower bound is : {lower} \\nUpper Bound is : {upper}\")\n    outlier = train_data[(train_data[col] < lower) | (train_data[col] > upper ) ]\n    print(f\"Number of outlier : {outlier.shape[0]}\")\n    print(\"____________________\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T12:55:07.563139Z","iopub.execute_input":"2025-07-28T12:55:07.563488Z","iopub.status.idle":"2025-07-28T12:55:08.013795Z","shell.execute_reply.started":"2025-07-28T12:55:07.563465Z","shell.execute_reply":"2025-07-28T12:55:08.012973Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## 4- MAD ","metadata":{}},{"cell_type":"code","source":"# Define function to detect outlier \ndef mad_outliers( column_name , threshold = 3.5 ): # threshold = 3.5 Defult value\n    med = train_data[column_name].median()\n    abs_deviation = abs ( train_data[column_name] - med )\n    mad = abs_deviation.median()\n    modified_z_score = 0.6745 * (train_data[column_name] - med ) / mad\n    outliers =  train_data[(modified_z_score < -threshold) | (modified_z_score > threshold )]\n    print(f\"Outlier size in {column_name} is : {outliers.shape[0]}\")\n    return outliers\n\nfor col in num :\n    mad_outliers(col )\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:05:48.292878Z","iopub.execute_input":"2025-07-28T13:05:48.293194Z","iopub.status.idle":"2025-07-28T13:05:48.74042Z","shell.execute_reply.started":"2025-07-28T13:05:48.293173Z","shell.execute_reply":"2025-07-28T13:05:48.739321Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Step 3 - Handling Outlier","metadata":{}},{"cell_type":"code","source":"df = train_data.copy()\ndf","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:14:37.476244Z","iopub.execute_input":"2025-07-28T13:14:37.476636Z","iopub.status.idle":"2025-07-28T13:14:38.164179Z","shell.execute_reply.started":"2025-07-28T13:14:37.476608Z","shell.execute_reply":"2025-07-28T13:14:38.162711Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def mad_outliers( column_name , threshold = 3.5 ): # threshold = 3.5 Defult value\n    med = df[column_name].median()\n    abs_deviation = abs ( df[column_name] - med )\n    mad = abs_deviation.median()\n    modified_z_score = 0.6745 * (df[column_name] - med ) / mad\n    outliers =  (modified_z_score < -threshold) | (modified_z_score > threshold )\n    print(f\"Outlier size in {column_name} is : {outliers.shape[0]}\")\n    return outliers","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:14:41.940197Z","iopub.execute_input":"2025-07-28T13:14:41.9405Z","iopub.status.idle":"2025-07-28T13:14:41.946389Z","shell.execute_reply.started":"2025-07-28T13:14:41.940479Z","shell.execute_reply":"2025-07-28T13:14:41.945371Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"income_outlier = mad_outliers('Annual Income')\nincome_outlier","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:14:44.364165Z","iopub.execute_input":"2025-07-28T13:14:44.364484Z","iopub.status.idle":"2025-07-28T13:14:44.423105Z","shell.execute_reply.started":"2025-07-28T13:14:44.364462Z","shell.execute_reply":"2025-07-28T13:14:44.421838Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = df[~income_outlier]\ndf","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:16:17.524269Z","iopub.execute_input":"2025-07-28T13:16:17.524648Z","iopub.status.idle":"2025-07-28T13:16:17.730032Z","shell.execute_reply.started":"2025-07-28T13:16:17.524623Z","shell.execute_reply":"2025-07-28T13:16:17.72921Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"__________________________________________\n# Step 4 - Encoding Categorical column","metadata":{}},{"cell_type":"code","source":"cat","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:18:18.977149Z","iopub.execute_input":"2025-07-28T13:18:18.9775Z","iopub.status.idle":"2025-07-28T13:18:18.986699Z","shell.execute_reply.started":"2025-07-28T13:18:18.977468Z","shell.execute_reply":"2025-07-28T13:18:18.984865Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:19:23.409479Z","iopub.execute_input":"2025-07-28T13:19:23.40983Z","iopub.status.idle":"2025-07-28T13:19:23.414591Z","shell.execute_reply.started":"2025-07-28T13:19:23.409808Z","shell.execute_reply":"2025-07-28T13:19:23.413594Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"LE = LabelEncoder()\nfor col in cat :\n    train_data[col] = LE.fit_transform(train_data[col])\n\ntrain_data","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:20:22.297652Z","iopub.execute_input":"2025-07-28T13:20:22.298097Z","iopub.status.idle":"2025-07-28T13:20:26.343471Z","shell.execute_reply.started":"2025-07-28T13:20:22.298063Z","shell.execute_reply":"2025-07-28T13:20:26.342659Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Step 5 - Scalling Numerical columns","metadata":{}},{"cell_type":"code","source":"num","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:21:28.294132Z","iopub.execute_input":"2025-07-28T13:21:28.29442Z","iopub.status.idle":"2025-07-28T13:21:28.300794Z","shell.execute_reply.started":"2025-07-28T13:21:28.2944Z","shell.execute_reply":"2025-07-28T13:21:28.299457Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:21:08.289261Z","iopub.execute_input":"2025-07-28T13:21:08.289639Z","iopub.status.idle":"2025-07-28T13:21:08.295475Z","shell.execute_reply.started":"2025-07-28T13:21:08.289607Z","shell.execute_reply":"2025-07-28T13:21:08.294037Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"SC = StandardScaler()\n\nfor col in num :\n    train_data[[col]] = SC.fit_transform(train_data[[col]])\n\ntrain_data","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:22:29.020933Z","iopub.execute_input":"2025-07-28T13:22:29.022476Z","iopub.status.idle":"2025-07-28T13:22:29.259404Z","shell.execute_reply.started":"2025-07-28T13:22:29.02235Z","shell.execute_reply":"2025-07-28T13:22:29.258418Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Step 6 : Splitting the data","metadata":{}},{"cell_type":"code","source":"X = train_data.drop('Premium Amount' , axis = 1)\ny = train_data['Premium Amount']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:27:49.222654Z","iopub.execute_input":"2025-07-28T13:27:49.222958Z","iopub.status.idle":"2025-07-28T13:27:49.347946Z","shell.execute_reply.started":"2025-07-28T13:27:49.222937Z","shell.execute_reply":"2025-07-28T13:27:49.346636Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:27:52.446115Z","iopub.execute_input":"2025-07-28T13:27:52.446449Z","iopub.status.idle":"2025-07-28T13:27:52.466093Z","shell.execute_reply.started":"2025-07-28T13:27:52.446427Z","shell.execute_reply":"2025-07-28T13:27:52.465217Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:27:57.746384Z","iopub.execute_input":"2025-07-28T13:27:57.746704Z","iopub.status.idle":"2025-07-28T13:27:57.753755Z","shell.execute_reply.started":"2025-07-28T13:27:57.746682Z","shell.execute_reply":"2025-07-28T13:27:57.752886Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nX_train , X_test , y_train , y_test = train_test_split(X , y , test_size = 0.25 , random_state = 42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:28:03.032988Z","iopub.execute_input":"2025-07-28T13:28:03.033404Z","iopub.status.idle":"2025-07-28T13:28:03.722827Z","shell.execute_reply.started":"2025-07-28T13:28:03.033374Z","shell.execute_reply":"2025-07-28T13:28:03.721881Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(\"X_train : \" , X_train.shape)\nprint(\"X_test : \" , X_test.shape)\nprint(\"y_train : \" , y_train.shape)\nprint(\"y_test : \" , y_test.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-28T13:28:20.072623Z","iopub.execute_input":"2025-07-28T13:28:20.073377Z","iopub.status.idle":"2025-07-28T13:28:20.078612Z","shell.execute_reply.started":"2025-07-28T13:28:20.073348Z","shell.execute_reply":"2025-07-28T13:28:20.077721Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Step 7 - Modelling\n## regression techniques  (linear regression , SVR , RF , KNN  ","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}