{ "cells": [ { "cell_type": "code", "execution_count": 212, "id": "16cea173-32ee-4641-a729-1642051ed227", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from matplotlib import pyplot as plt\n", "import seaborn as sns\n", "\n", "df = pd.read_csv('healthcare-dataset-stroke-data.csv')\n" ] }, { "cell_type": "code", "execution_count": 213, "id": "96d68c51-e5d3-4dba-89fc-823f32d498f8", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idgenderagehypertensionheart_diseaseever_marriedwork_typeResidence_typeavg_glucose_levelbmismoking_statusstroke
09046Male67.001YesPrivateUrban228.6936.6formerly smoked1
151676Female61.000YesSelf-employedRural202.21NaNnever smoked1
231112Male80.001YesPrivateRural105.9232.5never smoked1
360182Female49.000YesPrivateUrban171.2334.4smokes1
41665Female79.010YesSelf-employedRural174.1224.0never smoked1
556669Male81.000YesPrivateUrban186.2129.0formerly smoked1
653882Male74.011YesPrivateRural70.0927.4never smoked1
710434Female69.000NoPrivateUrban94.3922.8never smoked1
827419Female59.000YesPrivateRural76.15NaNUnknown1
960491Female78.000YesPrivateUrban58.5724.2Unknown1
\n", "
" ], "text/plain": [ " id gender age hypertension heart_disease ever_married \\\n", "0 9046 Male 67.0 0 1 Yes \n", "1 51676 Female 61.0 0 0 Yes \n", "2 31112 Male 80.0 0 1 Yes \n", "3 60182 Female 49.0 0 0 Yes \n", "4 1665 Female 79.0 1 0 Yes \n", "5 56669 Male 81.0 0 0 Yes \n", "6 53882 Male 74.0 1 1 Yes \n", "7 10434 Female 69.0 0 0 No \n", "8 27419 Female 59.0 0 0 Yes \n", "9 60491 Female 78.0 0 0 Yes \n", "\n", " work_type Residence_type avg_glucose_level bmi smoking_status \\\n", "0 Private Urban 228.69 36.6 formerly smoked \n", "1 Self-employed Rural 202.21 NaN never smoked \n", "2 Private Rural 105.92 32.5 never smoked \n", "3 Private Urban 171.23 34.4 smokes \n", "4 Self-employed Rural 174.12 24.0 never smoked \n", "5 Private Urban 186.21 29.0 formerly smoked \n", "6 Private Rural 70.09 27.4 never smoked \n", "7 Private Urban 94.39 22.8 never smoked \n", "8 Private Rural 76.15 NaN Unknown \n", "9 Private Urban 58.57 24.2 Unknown \n", "\n", " stroke \n", "0 1 \n", "1 1 \n", "2 1 \n", "3 1 \n", "4 1 \n", "5 1 \n", "6 1 \n", "7 1 \n", "8 1 \n", "9 1 " ] }, "execution_count": 213, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head(10)" ] }, { "cell_type": "code", "execution_count": 214, "id": "d43bbff1-a182-4734-9b2f-0d2737115eb4", "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", " \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", "
idagehypertensionheart_diseaseavg_glucose_levelbmistroke
count5110.0000005110.0000005110.0000005110.0000005110.0000004909.0000005110.000000
mean36517.82935443.2266140.0974560.054012106.14767728.8932370.048728
std21161.72162522.6126470.2966070.22606345.2835607.8540670.215320
min67.0000000.0800000.0000000.00000055.12000010.3000000.000000
25%17741.25000025.0000000.0000000.00000077.24500023.5000000.000000
50%36932.00000045.0000000.0000000.00000091.88500028.1000000.000000
75%54682.00000061.0000000.0000000.000000114.09000033.1000000.000000
max72940.00000082.0000001.0000001.000000271.74000097.6000001.000000
\n", "
" ], "text/plain": [ " id age hypertension heart_disease \\\n", "count 5110.000000 5110.000000 5110.000000 5110.000000 \n", "mean 36517.829354 43.226614 0.097456 0.054012 \n", "std 21161.721625 22.612647 0.296607 0.226063 \n", "min 67.000000 0.080000 0.000000 0.000000 \n", "25% 17741.250000 25.000000 0.000000 0.000000 \n", "50% 36932.000000 45.000000 0.000000 0.000000 \n", "75% 54682.000000 61.000000 0.000000 0.000000 \n", "max 72940.000000 82.000000 1.000000 1.000000 \n", "\n", " avg_glucose_level bmi stroke \n", "count 5110.000000 4909.000000 5110.000000 \n", "mean 106.147677 28.893237 0.048728 \n", "std 45.283560 7.854067 0.215320 \n", "min 55.120000 10.300000 0.000000 \n", "25% 77.245000 23.500000 0.000000 \n", "50% 91.885000 28.100000 0.000000 \n", "75% 114.090000 33.100000 0.000000 \n", "max 271.740000 97.600000 1.000000 " ] }, "execution_count": 214, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe()" ] }, { "cell_type": "code", "execution_count": 215, "id": "a1bd713a-0c3f-4da6-b092-e7ac2b55f89d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "id 0\n", "gender 0\n", "age 0\n", "hypertension 0\n", "heart_disease 0\n", "ever_married 0\n", "work_type 0\n", "Residence_type 0\n", "avg_glucose_level 0\n", "bmi 201\n", "smoking_status 0\n", "stroke 0\n", "dtype: int64" ] }, "execution_count": 215, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 216, "id": "f04727cf-ccdb-4103-b968-db01ea791eff", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "5110" ] }, "execution_count": 216, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "len(df) # number of rows = 5110" ] }, { "cell_type": "code", "execution_count": 217, "id": "47e74751-7eaa-4921-9399-f39ab04ff4e9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "id 0.000000\n", "gender 0.000000\n", "age 0.000000\n", "hypertension 0.000000\n", "heart_disease 0.000000\n", "ever_married 0.000000\n", "work_type 0.000000\n", "Residence_type 0.000000\n", "avg_glucose_level 0.000000\n", "bmi 3.933464\n", "smoking_status 0.000000\n", "stroke 0.000000\n", "dtype: float64\n" ] } ], "source": [ "print((df.isnull().sum() / len(df)) * 100) # null values for bmi = 4% so no need to delete column # bmi column is numeric" ] }, { "cell_type": "code", "execution_count": 218, "id": "40a3e3ae-2379-43ff-af6f-43215b047281", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "id False\n", "gender False\n", "age False\n", "hypertension False\n", "heart_disease False\n", "ever_married False\n", "work_type False\n", "Residence_type False\n", "avg_glucose_level False\n", "bmi False\n", "smoking_status False\n", "stroke False\n", "dtype: bool\n" ] } ], "source": [ "threshold = 30\n", "print((df.isnull().mean() * 100) > threshold) # no columns has null values bigger than 30% so no need ro delete column # best approaches for nulls < 5 % are mean or median or mode." ] }, { "cell_type": "code", "execution_count": 219, "id": "a16647cb-eab2-47d2-b9f6-592b6c2181dc", "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", " \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", " \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", "
idgenderagehypertensionheart_diseaseever_marriedwork_typeResidence_typeavg_glucose_levelbmismoking_statusstroke
09046Male67.001YesPrivateUrban228.6936.6formerly smoked1
151676Female61.000YesSelf-employedRural202.2128.1never smoked1
231112Male80.001YesPrivateRural105.9232.5never smoked1
360182Female49.000YesPrivateUrban171.2334.4smokes1
41665Female79.010YesSelf-employedRural174.1224.0never smoked1
.......................................
510518234Female80.010YesPrivateUrban83.7528.1never smoked0
510644873Female81.000YesSelf-employedUrban125.2040.0never smoked0
510719723Female35.000YesSelf-employedRural82.9930.6never smoked0
510837544Male51.000YesPrivateRural166.2925.6formerly smoked0
510944679Female44.000YesGovt_jobUrban85.2826.2Unknown0
\n", "

5110 rows × 12 columns

\n", "
" ], "text/plain": [ " id gender age hypertension heart_disease ever_married \\\n", "0 9046 Male 67.0 0 1 Yes \n", "1 51676 Female 61.0 0 0 Yes \n", "2 31112 Male 80.0 0 1 Yes \n", "3 60182 Female 49.0 0 0 Yes \n", "4 1665 Female 79.0 1 0 Yes \n", "... ... ... ... ... ... ... \n", "5105 18234 Female 80.0 1 0 Yes \n", "5106 44873 Female 81.0 0 0 Yes \n", "5107 19723 Female 35.0 0 0 Yes \n", "5108 37544 Male 51.0 0 0 Yes \n", "5109 44679 Female 44.0 0 0 Yes \n", "\n", " work_type Residence_type avg_glucose_level bmi smoking_status \\\n", "0 Private Urban 228.69 36.6 formerly smoked \n", "1 Self-employed Rural 202.21 28.1 never smoked \n", "2 Private Rural 105.92 32.5 never smoked \n", "3 Private Urban 171.23 34.4 smokes \n", "4 Self-employed Rural 174.12 24.0 never smoked \n", "... ... ... ... ... ... \n", "5105 Private Urban 83.75 28.1 never smoked \n", "5106 Self-employed Urban 125.20 40.0 never smoked \n", "5107 Self-employed Rural 82.99 30.6 never smoked \n", "5108 Private Rural 166.29 25.6 formerly smoked \n", "5109 Govt_job Urban 85.28 26.2 Unknown \n", "\n", " stroke \n", "0 1 \n", "1 1 \n", "2 1 \n", "3 1 \n", "4 1 \n", "... ... \n", "5105 0 \n", "5106 0 \n", "5107 0 \n", "5108 0 \n", "5109 0 \n", "\n", "[5110 rows x 12 columns]" ] }, "execution_count": 219, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#data_after_handle_missing_values_by_mean = df['bmi'].fillna(df['bmi'].mean(), inplace=False) # to handle nulls by mean for numeric data (not affect data. inplace = false)\n", "#print(data_after_handle_missing_values_by_mean)\n", "\n", "#data_after_handle_missing_values_by_median = df['bmi'].fillna(df['bmi'].median(), inplace=True) # to handle nulls by median for numeric data (not affect data. inplace = true)\n", "#print(data_after_handle_missing_values_by_median)\n", "\n", "df['bmi'] = df['bmi'].fillna(df['bmi'].median()) # to handle nulls by median for numeric data (inplace = true)\n", "df" ] }, { "cell_type": "code", "execution_count": 220, "id": "abb1cac8-d050-4c3b-98a3-c4c8811a05d0", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "id 0.0\n", "gender 0.0\n", "age 0.0\n", "hypertension 0.0\n", "heart_disease 0.0\n", "ever_married 0.0\n", "work_type 0.0\n", "Residence_type 0.0\n", "avg_glucose_level 0.0\n", "bmi 0.0\n", "smoking_status 0.0\n", "stroke 0.0\n", "dtype: float64\n" ] } ], "source": [ "print((df.isnull().sum() / len(df)) * 100)" ] }, { "cell_type": "code", "execution_count": 221, "id": "7b3b995f-fbfa-4f35-96f0-151504802f94", "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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idgenderagehypertensionheart_diseaseever_marriedwork_typeResidence_typeavg_glucose_levelbmismoking_statusstroke
09046Male67.001YesPrivateUrban228.6936.6formerly smoked1
151676Female61.000YesSelf-employedRural202.2128.1never smoked1
231112Male80.001YesPrivateRural105.9232.5never smoked1
360182Female49.000YesPrivateUrban171.2334.4smokes1
41665Female79.010YesSelf-employedRural174.1224.0never smoked1
556669Male81.000YesPrivateUrban186.2129.0formerly smoked1
653882Male74.011YesPrivateRural70.0927.4never smoked1
710434Female69.000NoPrivateUrban94.3922.8never smoked1
827419Female59.000YesPrivateRural76.1528.1Unknown1
960491Female78.000YesPrivateUrban58.5724.2Unknown1
\n", "
" ], "text/plain": [ " id gender age hypertension heart_disease ever_married \\\n", "0 9046 Male 67.0 0 1 Yes \n", "1 51676 Female 61.0 0 0 Yes \n", "2 31112 Male 80.0 0 1 Yes \n", "3 60182 Female 49.0 0 0 Yes \n", "4 1665 Female 79.0 1 0 Yes \n", "5 56669 Male 81.0 0 0 Yes \n", "6 53882 Male 74.0 1 1 Yes \n", "7 10434 Female 69.0 0 0 No \n", "8 27419 Female 59.0 0 0 Yes \n", "9 60491 Female 78.0 0 0 Yes \n", "\n", " work_type Residence_type avg_glucose_level bmi smoking_status \\\n", "0 Private Urban 228.69 36.6 formerly smoked \n", "1 Self-employed Rural 202.21 28.1 never smoked \n", "2 Private Rural 105.92 32.5 never smoked \n", "3 Private Urban 171.23 34.4 smokes \n", "4 Self-employed Rural 174.12 24.0 never smoked \n", "5 Private Urban 186.21 29.0 formerly smoked \n", "6 Private Rural 70.09 27.4 never smoked \n", "7 Private Urban 94.39 22.8 never smoked \n", "8 Private Rural 76.15 28.1 Unknown \n", "9 Private Urban 58.57 24.2 Unknown \n", "\n", " stroke \n", "0 1 \n", "1 1 \n", "2 1 \n", "3 1 \n", "4 1 \n", "5 1 \n", "6 1 \n", "7 1 \n", "8 1 \n", "9 1 " ] }, "execution_count": 221, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head(10)" ] }, { "cell_type": "code", "execution_count": 222, "id": "621acc9b-0bc3-4974-a29a-a6ae6ac6ae5d", "metadata": {}, "outputs": [], "source": [ "# handling outliers\n", "#detect outliers and replace with null value\n", "data = df.copy()\n", "\n", "def replace_outliers_with_null(column):\n", " Q1 = column.quantile(0.25)\n", " Q3 = column.quantile(0.75)\n", " IQR = Q3 - Q1\n", " lower_bound = Q1 - 1.5 * IQR\n", " upper_bound = Q3 + 1.5 * IQR\n", " \n", " return column.where((column < lower_bound) | (column > upper_bound), np.nan)\n" ] }, { "cell_type": "code", "execution_count": 223, "id": "01327e2a-0db6-4776-8a3b-83b034d62f45", "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", " \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", " \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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idgenderagehypertensionheart_diseaseever_marriedwork_typeResidence_typeavg_glucose_levelbmismoking_statusstrokeid_outlierage_outlierhypertension_outlierheart_disease_outlieravg_glucose_level_outlierbmi_outlierstroke_outlier
09046Male67.001YesPrivateUrban228.6936.6formerly smoked1NaNNaNNaN1.0228.69NaN1.0
151676Female61.000YesSelf-employedRural202.2128.1never smoked1NaNNaNNaNNaN202.21NaN1.0
231112Male80.001YesPrivateRural105.9232.5never smoked1NaNNaNNaN1.0NaNNaN1.0
360182Female49.000YesPrivateUrban171.2334.4smokes1NaNNaNNaNNaN171.23NaN1.0
41665Female79.010YesSelf-employedRural174.1224.0never smoked1NaNNaN1.0NaN174.12NaN1.0
............................................................
50916369Male59.010YesPrivateRural95.0530.9never smoked0NaNNaN1.0NaNNaNNaNNaN
509332235Female45.010YesGovt_jobRural95.0228.1smokes0NaNNaN1.0NaNNaNNaNNaN
510068398Male82.010YesSelf-employedRural71.9728.3never smoked0NaNNaN1.0NaNNaNNaNNaN
510322127Female18.000NoPrivateUrban82.8546.9Unknown0NaNNaNNaNNaNNaN46.9NaN
510518234Female80.010YesPrivateUrban83.7528.1never smoked0NaNNaN1.0NaNNaNNaNNaN
\n", "

1296 rows × 19 columns

\n", "
" ], "text/plain": [ " id gender age hypertension heart_disease ever_married \\\n", "0 9046 Male 67.0 0 1 Yes \n", "1 51676 Female 61.0 0 0 Yes \n", "2 31112 Male 80.0 0 1 Yes \n", "3 60182 Female 49.0 0 0 Yes \n", "4 1665 Female 79.0 1 0 Yes \n", "... ... ... ... ... ... ... \n", "5091 6369 Male 59.0 1 0 Yes \n", "5093 32235 Female 45.0 1 0 Yes \n", "5100 68398 Male 82.0 1 0 Yes \n", "5103 22127 Female 18.0 0 0 No \n", "5105 18234 Female 80.0 1 0 Yes \n", "\n", " work_type Residence_type avg_glucose_level bmi smoking_status \\\n", "0 Private Urban 228.69 36.6 formerly smoked \n", "1 Self-employed Rural 202.21 28.1 never smoked \n", "2 Private Rural 105.92 32.5 never smoked \n", "3 Private Urban 171.23 34.4 smokes \n", "4 Self-employed Rural 174.12 24.0 never smoked \n", "... ... ... ... ... ... \n", "5091 Private Rural 95.05 30.9 never smoked \n", "5093 Govt_job Rural 95.02 28.1 smokes \n", "5100 Self-employed Rural 71.97 28.3 never smoked \n", "5103 Private Urban 82.85 46.9 Unknown \n", "5105 Private Urban 83.75 28.1 never smoked \n", "\n", " stroke id_outlier age_outlier hypertension_outlier \\\n", "0 1 NaN NaN NaN \n", "1 1 NaN NaN NaN \n", "2 1 NaN NaN NaN \n", "3 1 NaN NaN NaN \n", "4 1 NaN NaN 1.0 \n", "... ... ... ... ... \n", "5091 0 NaN NaN 1.0 \n", "5093 0 NaN NaN 1.0 \n", "5100 0 NaN NaN 1.0 \n", "5103 0 NaN NaN NaN \n", "5105 0 NaN NaN 1.0 \n", "\n", " heart_disease_outlier avg_glucose_level_outlier bmi_outlier \\\n", "0 1.0 228.69 NaN \n", "1 NaN 202.21 NaN \n", "2 1.0 NaN NaN \n", "3 NaN 171.23 NaN \n", "4 NaN 174.12 NaN \n", "... ... ... ... \n", "5091 NaN NaN NaN \n", "5093 NaN NaN NaN \n", "5100 NaN NaN NaN \n", "5103 NaN NaN 46.9 \n", "5105 NaN NaN NaN \n", "\n", " stroke_outlier \n", "0 1.0 \n", "1 1.0 \n", "2 1.0 \n", "3 1.0 \n", "4 1.0 \n", "... ... \n", "5091 NaN \n", "5093 NaN \n", "5100 NaN \n", "5103 NaN \n", "5105 NaN \n", "\n", "[1296 rows x 19 columns]" ] }, "execution_count": 223, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# print outliers\n", "for col in data.select_dtypes(include=np.number).columns: # for loop for numerical columns\n", " data[f'{col}_outlier'] = replace_outliers_with_null(data[col])\n", " \n", "out_liers_only = data[data.filter(like='_outlier').any(axis = 1)]\n", "out_liers_only" ] }, { "cell_type": "code", "execution_count": 224, "id": "bfe98077-5441-442c-8d78-04c4d699760a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "id 0\n", "gender 0\n", "age 0\n", "hypertension 0\n", "heart_disease 0\n", "ever_married 0\n", "work_type 0\n", "Residence_type 0\n", "avg_glucose_level 0\n", "bmi 0\n", "smoking_status 0\n", "stroke 0\n", "id_outlier 5110\n", "age_outlier 5110\n", "hypertension_outlier 4612\n", "heart_disease_outlier 4834\n", "avg_glucose_level_outlier 4483\n", "bmi_outlier 4984\n", "stroke_outlier 4861\n", "dtype: int64" ] }, "execution_count": 224, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# sum of null values in each column\n", "null_count = data.isnull().sum()\n", "null_count" ] }, { "cell_type": "code", "execution_count": 225, "id": "080a1a40-75fc-4de8-9be8-792e8ae34e11", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "original data: \n", "5110\n", "cleaned data: (without ouliers)\n", "3814\n" ] } ], "source": [ "# remove outliers rows\n", "outliers_data = df.select_dtypes(include=np.number).copy()\n", "\n", "def remove_out_liers_IQR(outliers_data):\n", " Q1 = outliers_data.quantile(0.25)\n", " Q3 = outliers_data.quantile(0.75)\n", " IQR = Q3 - Q1\n", " lower_bound = Q1 - 1.5 * IQR\n", " upper_bound = Q3 + 1.5 * IQR\n", " data_to_be_clean = outliers_data[~((outliers_data < lower_bound) | (outliers_data > upper_bound)).any(axis = 1)]\n", " return data_to_be_clean\n", "\n", "cleaned_data = remove_out_liers_IQR(outliers_data)\n", "print(\"original data: \")\n", "print(len(outliers_data))\n", "print(\"cleaned data: (without ouliers)\")\n", "print(len(cleaned_data))" ] }, { "cell_type": "code", "execution_count": 226, "id": "c0cfbaaa-5ee8-4237-9bbc-e5c0f715f8d0", "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", " \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", "
idagehypertensionheart_diseaseavg_glucose_levelbmistroke
249306693.00095.1218.00
251165238.000110.8917.60
2525654370.00069.0435.90
2534613614.000161.2819.10
2555280052.00077.5917.70
2571526632.00077.6732.30
2591046079.00077.0835.00
2616388437.000162.9639.40
2623789337.00073.5026.10
2636785540.00095.0442.40
\n", "
" ], "text/plain": [ " id age hypertension heart_disease avg_glucose_level bmi stroke\n", "249 30669 3.0 0 0 95.12 18.0 0\n", "251 16523 8.0 0 0 110.89 17.6 0\n", "252 56543 70.0 0 0 69.04 35.9 0\n", "253 46136 14.0 0 0 161.28 19.1 0\n", "255 52800 52.0 0 0 77.59 17.7 0\n", "257 15266 32.0 0 0 77.67 32.3 0\n", "259 10460 79.0 0 0 77.08 35.0 0\n", "261 63884 37.0 0 0 162.96 39.4 0\n", "262 37893 37.0 0 0 73.50 26.1 0\n", "263 67855 40.0 0 0 95.04 42.4 0" ] }, "execution_count": 226, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cleaned_data.head(10)" ] }, { "cell_type": "code", "execution_count": 227, "id": "f3f87c13-a00a-4d97-a38c-3863536a7d8c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "gender Female Male Other\n", "heart_disease \n", "0 2881 1952 1\n", "1 113 163 0\n" ] } ], "source": [ "# visualize \n", "gender_class_count = df.groupby(['heart_disease' , 'gender']).size().unstack(fill_value=0)\n", "print(gender_class_count)" ] }, { "cell_type": "code", "execution_count": 239, "id": "f0860eb0-69dc-407a-98c5-efd02ad2fac0", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "gender_class_count.plot(kind='bar')\n", "\n", "# Adding title and labels\n", "plt.title('Heart Disease Count by Gender')\n", "plt.xlabel('Heart Disease')\n", "plt.ylabel('Count')\n", "plt.legend(title='Gender', labels=['Male (1)', 'Female (2)' , 'other (3)'])\n", "plt.xticks(rotation=20)\n", "plt.grid(axis = 'y')\n", "\n", "# Display the plot\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "id": "f3caf833-fbf9-441a-9083-e5080311bfef", "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": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }