{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "#import packages\n", "import pandas as pd\n", "import numpy as np\n", "import sys\n", "%matplotlib inline\n", "import matplotlib as mpl\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "#import file containing function\n", "sys.path.append(r'.\\common_function') #add path to default module search path\n", "from EDA_function import *\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "** load data from seaborn " ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['anagrams',\n", " 'anscombe',\n", " 'attention',\n", " 'brain_networks',\n", " 'car_crashes',\n", " 'diamonds',\n", " 'dots',\n", " 'exercise',\n", " 'flights',\n", " 'fmri',\n", " 'gammas',\n", " 'geyser',\n", " 'iris',\n", " 'mpg',\n", " 'penguins',\n", " 'planets',\n", " 'taxis',\n", " 'tips',\n", " 'titanic']" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "sns.get_dataset_names()" ] }, { "cell_type": "code", "execution_count": 3, "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", "
survivedpclasssexagesibspparchfareembarkedclasswhoadult_maledeckembark_townalivealone
003male22.0107.2500SThirdmanTrueNaNSouthamptonnoFalse
111female38.01071.2833CFirstwomanFalseCCherbourgyesFalse
213female26.0007.9250SThirdwomanFalseNaNSouthamptonyesTrue
311female35.01053.1000SFirstwomanFalseCSouthamptonyesFalse
403male35.0008.0500SThirdmanTrueNaNSouthamptonnoTrue
\n", "
" ], "text/plain": [ " survived pclass sex age sibsp parch fare embarked class \\\n", "0 0 3 male 22.0 1 0 7.2500 S Third \n", "1 1 1 female 38.0 1 0 71.2833 C First \n", "2 1 3 female 26.0 0 0 7.9250 S Third \n", "3 1 1 female 35.0 1 0 53.1000 S First \n", "4 0 3 male 35.0 0 0 8.0500 S Third \n", "\n", " who adult_male deck embark_town alive alone \n", "0 man True NaN Southampton no False \n", "1 woman False C Cherbourg yes False \n", "2 woman False NaN Southampton yes True \n", "3 woman False C Southampton yes False \n", "4 man True NaN Southampton no True " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = sns.load_dataset('titanic')\n", "df_copy =df.copy() # keep a copy just in case\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'\\n1. overall EDA\\n2. further EDA on data variation and dup\\n3. further EDA on data missing or inf (inlier)\\n4. further EDA on data with outlier \\n5. further EDA on feature correlation\\n6. further EAD on feature selection\\n'" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "'''\n", "1. overall EDA\n", "2. further EDA on data variation and dup\n", "3. further EDA on data missing or inf (inlier)\n", "4. further EDA on data with outlier \n", "5. further EDA on feature correlation\n", "6. further EAD on feature selection\n", "'''" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1mGet list of column, data type and see if there are data missing\u001b[0m\n", "\n", "RangeIndex: 891 entries, 0 to 890\n", "Data columns (total 15 columns):\n", "survived 891 non-null int64\n", "pclass 891 non-null int64\n", "sex 891 non-null object\n", "age 714 non-null float64\n", "sibsp 891 non-null int64\n", "parch 891 non-null int64\n", "fare 891 non-null float64\n", "embarked 889 non-null object\n", "class 891 non-null category\n", "who 891 non-null object\n", "adult_male 891 non-null bool\n", "deck 203 non-null category\n", "embark_town 889 non-null object\n", "alive 891 non-null object\n", "alone 891 non-null bool\n", "dtypes: bool(2), category(2), float64(2), int64(4), object(5)\n", "memory usage: 80.6+ KB\n" ] }, { "data": { "text/plain": [ "None" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1mGet descriptive statistics for numeric column \u001b[0m\n" ] }, { "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", "
survivedpclassagesibspparchfare
count891.000000891.000000714.000000891.000000891.000000891.000000
mean0.3838382.30864229.6991180.5230080.38159432.204208
std0.4865920.83607114.5264971.1027430.80605749.693429
min0.0000001.0000000.4200000.0000000.0000000.000000
25%0.0000002.00000020.1250000.0000000.0000007.910400
50%0.0000003.00000028.0000000.0000000.00000014.454200
75%1.0000003.00000038.0000001.0000000.00000031.000000
max1.0000003.00000080.0000008.0000006.000000512.329200
\n", "
" ], "text/plain": [ " survived pclass age sibsp parch fare\n", "count 891.000000 891.000000 714.000000 891.000000 891.000000 891.000000\n", "mean 0.383838 2.308642 29.699118 0.523008 0.381594 32.204208\n", "std 0.486592 0.836071 14.526497 1.102743 0.806057 49.693429\n", "min 0.000000 1.000000 0.420000 0.000000 0.000000 0.000000\n", "25% 0.000000 2.000000 20.125000 0.000000 0.000000 7.910400\n", "50% 0.000000 3.000000 28.000000 0.000000 0.000000 14.454200\n", "75% 1.000000 3.000000 38.000000 1.000000 0.000000 31.000000\n", "max 1.000000 3.000000 80.000000 8.000000 6.000000 512.329200" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# 1. overall EDA\n", "eda_overall(df)" ] }, { "cell_type": "code", "execution_count": 6, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
survivedpclasssexagesibspparchfareembarkedclasswhoadult_maledeckembark_townalivealone
41302maleNaN000.0000SSecondmanTrueNaNSouthamptonnoTrue
46602maleNaN000.0000SSecondmanTrueNaNSouthamptonnoTrue
67402maleNaN000.0000SSecondmanTrueNaNSouthamptonnoTrue
73202maleNaN000.0000SSecondmanTrueNaNSouthamptonnoTrue
48102maleNaN000.0000SSecondmanTrueNaNSouthamptonnoTrue
27702maleNaN000.0000SSecondmanTrueNaNSouthamptonnoTrue
78403male25.00007.0500SThirdmanTrueNaNSouthamptonnoTrue
88403male25.00007.0500SThirdmanTrueNaNSouthamptonnoTrue
77303maleNaN007.2250CThirdmanTrueNaNCherbourgnoTrue
2603maleNaN007.2250CThirdmanTrueNaNCherbourgnoTrue
52203maleNaN007.2250CThirdmanTrueNaNCherbourgnoTrue
35403maleNaN007.2250CThirdmanTrueNaNCherbourgnoTrue
59803maleNaN007.2250CThirdmanTrueNaNCherbourgnoTrue
83203maleNaN007.2292CThirdmanTrueNaNCherbourgnoTrue
56803maleNaN007.2292CThirdmanTrueNaNCherbourgnoTrue
53103maleNaN007.2292CThirdmanTrueNaNCherbourgnoTrue
85903maleNaN007.2292CThirdmanTrueNaNCherbourgnoTrue
52403maleNaN007.2292CThirdmanTrueNaNCherbourgnoTrue
32003male22.00007.2500SThirdmanTrueNaNSouthamptonnoTrue
25003maleNaN007.2500SThirdmanTrueNaNSouthamptonnoTrue
47003maleNaN007.2500SThirdmanTrueNaNSouthamptonnoTrue
21203male22.00007.2500SThirdmanTrueNaNSouthamptonnoTrue
42503maleNaN007.2500SThirdmanTrueNaNSouthamptonnoTrue
27413femaleNaN007.7500QThirdwomanFalseNaNQueenstownyesTrue
26003maleNaN007.7500QThirdmanTrueNaNQueenstownnoTrue
36813femaleNaN007.7500QThirdwomanFalseNaNQueenstownyesTrue
19813femaleNaN007.7500QThirdwomanFalseNaNQueenstownyesTrue
19603maleNaN007.7500QThirdmanTrueNaNQueenstownnoTrue
79003maleNaN007.7500QThirdmanTrueNaNQueenstownnoTrue
42803maleNaN007.7500QThirdmanTrueNaNQueenstownnoTrue
................................................
36403maleNaN1015.5000QThirdmanTrueNaNQueenstownnoFalse
24113femaleNaN1015.5000QThirdwomanFalseNaNQueenstownyesFalse
34713femaleNaN1016.1000SThirdwomanFalseNaNSouthamptonyesFalse
43113femaleNaN1016.1000SThirdwomanFalseNaNSouthamptonyesFalse
46913female0.752119.2583CThirdchildFalseNaNCherbourgyesFalse
64413female0.752119.2583CThirdchildFalseNaNCherbourgyesFalse
45103maleNaN1019.9667SThirdmanTrueNaNSouthamptonnoFalse
49003maleNaN1019.9667SThirdmanTrueNaNSouthamptonnoFalse
40502male34.001021.0000SSecondmanTrueNaNSouthamptonnoFalse
47602male34.001021.0000SSecondmanTrueNaNSouthamptonnoFalse
40903femaleNaN3125.4667SThirdwomanFalseNaNSouthamptonnoFalse
22903femaleNaN3125.4667SThirdwomanFalseNaNSouthamptonnoFalse
48503femaleNaN3125.4667SThirdwomanFalseNaNSouthamptonnoFalse
13312female29.001026.0000SSecondwomanFalseNaNSouthamptonyesFalse
5312female29.001026.0000SSecondwomanFalseNaNSouthamptonyesFalse
6401maleNaN0027.7208CFirstmanTrueNaNCherbourgnoTrue
29501maleNaN0027.7208CFirstmanTrueNaNCherbourgnoTrue
7413male32.000056.4958SThirdmanTrueNaNSouthamptonyesTrue
83813male32.000056.4958SThirdmanTrueNaNSouthamptonyesTrue
69213maleNaN0056.4958SThirdmanTrueNaNSouthamptonyesTrue
64313maleNaN0056.4958SThirdmanTrueNaNSouthamptonyesTrue
64111female24.000069.3000CFirstwomanFalseBCherbourgyesTrue
36911female24.000069.3000CFirstwomanFalseBCherbourgyesTrue
84603maleNaN8269.5500SThirdmanTrueNaNSouthamptonnoFalse
79203femaleNaN8269.5500SThirdwomanFalseNaNSouthamptonnoFalse
86303femaleNaN8269.5500SThirdwomanFalseNaNSouthamptonnoFalse
20103maleNaN8269.5500SThirdmanTrueNaNSouthamptonnoFalse
32403maleNaN8269.5500SThirdmanTrueNaNSouthamptonnoFalse
15903maleNaN8269.5500SThirdmanTrueNaNSouthamptonnoFalse
18003femaleNaN8269.5500SThirdwomanFalseNaNSouthamptonnoFalse
\n", "

160 rows × 15 columns

\n", "
" ], "text/plain": [ " survived pclass sex age sibsp parch fare embarked class \\\n", "413 0 2 male NaN 0 0 0.0000 S Second \n", "466 0 2 male NaN 0 0 0.0000 S Second \n", "674 0 2 male NaN 0 0 0.0000 S Second \n", "732 0 2 male NaN 0 0 0.0000 S Second \n", "481 0 2 male NaN 0 0 0.0000 S Second \n", "277 0 2 male NaN 0 0 0.0000 S Second \n", "784 0 3 male 25.00 0 0 7.0500 S Third \n", "884 0 3 male 25.00 0 0 7.0500 S Third \n", "773 0 3 male NaN 0 0 7.2250 C Third \n", "26 0 3 male NaN 0 0 7.2250 C Third \n", "522 0 3 male NaN 0 0 7.2250 C Third \n", "354 0 3 male NaN 0 0 7.2250 C Third \n", "598 0 3 male NaN 0 0 7.2250 C Third \n", "832 0 3 male NaN 0 0 7.2292 C Third \n", "568 0 3 male NaN 0 0 7.2292 C Third \n", "531 0 3 male NaN 0 0 7.2292 C Third \n", "859 0 3 male NaN 0 0 7.2292 C Third \n", "524 0 3 male NaN 0 0 7.2292 C Third \n", "320 0 3 male 22.00 0 0 7.2500 S Third \n", "250 0 3 male NaN 0 0 7.2500 S Third \n", "470 0 3 male NaN 0 0 7.2500 S Third \n", "212 0 3 male 22.00 0 0 7.2500 S Third \n", "425 0 3 male NaN 0 0 7.2500 S Third \n", "274 1 3 female NaN 0 0 7.7500 Q Third \n", "260 0 3 male NaN 0 0 7.7500 Q Third \n", "368 1 3 female NaN 0 0 7.7500 Q Third \n", "198 1 3 female NaN 0 0 7.7500 Q Third \n", "196 0 3 male NaN 0 0 7.7500 Q Third \n", "790 0 3 male NaN 0 0 7.7500 Q Third \n", "428 0 3 male NaN 0 0 7.7500 Q Third \n", ".. ... ... ... ... ... ... ... ... ... \n", "364 0 3 male NaN 1 0 15.5000 Q Third \n", "241 1 3 female NaN 1 0 15.5000 Q Third \n", "347 1 3 female NaN 1 0 16.1000 S Third \n", "431 1 3 female NaN 1 0 16.1000 S Third \n", "469 1 3 female 0.75 2 1 19.2583 C Third \n", "644 1 3 female 0.75 2 1 19.2583 C Third \n", "451 0 3 male NaN 1 0 19.9667 S Third \n", "490 0 3 male NaN 1 0 19.9667 S Third \n", "405 0 2 male 34.00 1 0 21.0000 S Second \n", "476 0 2 male 34.00 1 0 21.0000 S Second \n", "409 0 3 female NaN 3 1 25.4667 S Third \n", "229 0 3 female NaN 3 1 25.4667 S Third \n", "485 0 3 female NaN 3 1 25.4667 S Third \n", "133 1 2 female 29.00 1 0 26.0000 S Second \n", "53 1 2 female 29.00 1 0 26.0000 S Second \n", "64 0 1 male NaN 0 0 27.7208 C First \n", "295 0 1 male NaN 0 0 27.7208 C First \n", "74 1 3 male 32.00 0 0 56.4958 S Third \n", "838 1 3 male 32.00 0 0 56.4958 S Third \n", "692 1 3 male NaN 0 0 56.4958 S Third \n", "643 1 3 male NaN 0 0 56.4958 S Third \n", "641 1 1 female 24.00 0 0 69.3000 C First \n", "369 1 1 female 24.00 0 0 69.3000 C First \n", "846 0 3 male NaN 8 2 69.5500 S Third \n", "792 0 3 female NaN 8 2 69.5500 S Third \n", "863 0 3 female NaN 8 2 69.5500 S Third \n", "201 0 3 male NaN 8 2 69.5500 S Third \n", "324 0 3 male NaN 8 2 69.5500 S Third \n", "159 0 3 male NaN 8 2 69.5500 S Third \n", "180 0 3 female NaN 8 2 69.5500 S Third \n", "\n", " who adult_male deck embark_town alive alone \n", "413 man True NaN Southampton no True \n", "466 man True NaN Southampton no True \n", "674 man True NaN Southampton no True \n", "732 man True NaN Southampton no True \n", "481 man True NaN Southampton no True \n", "277 man True NaN Southampton no True \n", "784 man True NaN Southampton no True \n", "884 man True NaN Southampton no True \n", "773 man True NaN Cherbourg no True \n", "26 man True NaN Cherbourg no True \n", "522 man True NaN Cherbourg no True \n", "354 man True NaN Cherbourg no True \n", "598 man True NaN Cherbourg no True \n", "832 man True NaN Cherbourg no True \n", "568 man True NaN Cherbourg no True \n", "531 man True NaN Cherbourg no True \n", "859 man True NaN Cherbourg no True \n", "524 man True NaN Cherbourg no True \n", "320 man True NaN Southampton no True \n", "250 man True NaN Southampton no True \n", "470 man True NaN Southampton no True \n", "212 man True NaN Southampton no True \n", "425 man True NaN Southampton no True \n", "274 woman False NaN Queenstown yes True \n", "260 man True NaN Queenstown no True \n", "368 woman False NaN Queenstown yes True \n", "198 woman False NaN Queenstown yes True \n", "196 man True NaN Queenstown no True \n", "790 man True NaN Queenstown no True \n", "428 man True NaN Queenstown no True \n", ".. ... ... ... ... ... ... \n", "364 man True NaN Queenstown no False \n", "241 woman False NaN Queenstown yes False \n", "347 woman False NaN Southampton yes False \n", "431 woman False NaN Southampton yes False \n", "469 child False NaN Cherbourg yes False \n", "644 child False NaN Cherbourg yes False \n", "451 man True NaN Southampton no False \n", "490 man True NaN Southampton no False \n", "405 man True NaN Southampton no False \n", "476 man True NaN Southampton no False \n", "409 woman False NaN Southampton no False \n", "229 woman False NaN Southampton no False \n", "485 woman False NaN Southampton no False \n", "133 woman False NaN Southampton yes False \n", "53 woman False NaN Southampton yes False \n", "64 man True NaN Cherbourg no True \n", "295 man True NaN Cherbourg no True \n", "74 man True NaN Southampton yes True \n", "838 man True NaN Southampton yes True \n", "692 man True NaN Southampton yes True \n", "643 man True NaN Southampton yes True \n", "641 woman False B Cherbourg yes True \n", "369 woman False B Cherbourg yes True \n", "846 man True NaN Southampton no False \n", "792 woman False NaN Southampton no False \n", "863 woman False NaN Southampton no False \n", "201 man True NaN Southampton no False \n", "324 man True NaN Southampton no False \n", "159 man True NaN Southampton no False \n", "180 woman False NaN Southampton no False \n", "\n", "[160 rows x 15 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#further EDA on data variation and dup\n", "eda_showDup(df, 'fare')\n", "\n", "#df1 =df.drop_duplicates()" ] }, { "cell_type": "code", "execution_count": 7, "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", "
columncountunique/total
6fare24816.533333
3age885.866667
4sibsp70.466667
5parch70.466667
11deck70.466667
1pclass30.200000
7embarked30.200000
8class30.200000
9who30.200000
12embark_town30.200000
0survived20.133333
2sex20.133333
10adult_male20.133333
13alive20.133333
14alone20.133333
\n", "
" ], "text/plain": [ " column count unique/total\n", "6 fare 248 16.533333\n", "3 age 88 5.866667\n", "4 sibsp 7 0.466667\n", "5 parch 7 0.466667\n", "11 deck 7 0.466667\n", "1 pclass 3 0.200000\n", "7 embarked 3 0.200000\n", "8 class 3 0.200000\n", "9 who 3 0.200000\n", "12 embark_town 3 0.200000\n", "0 survived 2 0.133333\n", "2 sex 2 0.133333\n", "10 adult_male 2 0.133333\n", "13 alive 2 0.133333\n", "14 alone 2 0.133333" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#check data variation\n", "eda_feature_variance_ratio (df)" ] }, { "cell_type": "code", "execution_count": 8, "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", "
TotalPercent
deck6880.772166
age1770.198653
embark_town20.002245
embarked20.002245
\n", "
" ], "text/plain": [ " Total Percent\n", "deck 688 0.772166\n", "age 177 0.198653\n", "embark_town 2 0.002245\n", "embarked 2 0.002245" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#3 further EDA on data missing or inf (inlier)\n", "eda_getMissingData(df)" ] }, { "cell_type": "code", "execution_count": 9, "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", "
Inf countInf Ratio
survived00.0
pclass00.0
age00.0
sibsp00.0
parch00.0
fare00.0
\n", "
" ], "text/plain": [ " Inf count Inf Ratio\n", "survived 0 0.0\n", "pclass 0 0.0\n", "age 0 0.0\n", "sibsp 0 0.0\n", "parch 0 0.0\n", "fare 0 0.0" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "eda_getInfData(df) " ] }, { "cell_type": "code", "execution_count": 10, "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", "
companyrevnueprofit
0A1000.0-inf
1Binf200.0
2C4000.01000.0
\n", "
" ], "text/plain": [ " company revnue profit\n", "0 A 1000.0 -inf\n", "1 B inf 200.0\n", "2 C 4000.0 1000.0" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#let us intentionaly create some inf to see it function work properly\n", "company = ['A', 'B', 'C']\n", "revnue = [1000, np.inf, 4000]\n", "profit = [-np.inf, 200, 1000]\n", "df_test = pd.DataFrame({'company':company, 'revnue':revnue, 'profit':profit})\n", "df_test\n" ] }, { "cell_type": "code", "execution_count": 11, "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", "
Inf countInf Ratio
revnue10.333333
profit10.333333
\n", "
" ], "text/plain": [ " Inf count Inf Ratio\n", "revnue 1 0.333333\n", "profit 1 0.333333" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "eda_getInfData(df_test)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "outlier standard is out of 1.5 standard deviation \n", "\n", "['pclass', 'age', 'sibsp', 'parch', 'fare']\n" ] } ], "source": [ "#4. outlier analysis please note: the result contains some discrete variable, use it with business sense\n", "eda_getOutLier(df, 1.5)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "#take a look at age, pclass, sibsp, parch are discrete variable \n", "eda_getHistPlot(df,'age')\n", "\n" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "#bulk plot with age and fare\n", "eda_getBulkPlot(df, ['age', 'fare'], eda_getHistPlot )" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAADuCAYAAAAjmZDVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAEE9JREFUeJzt3X+MXWWdx/H3tx3UVlwqMhDSooNOs2pi/MGEkLh/wAAbKBsLURI2ZG1Il8YNumw0WREQSlJdTciyhSBsAaG47CJx19C4RBdazGb/0HW6svgDs9wlVYYSGAVB6BYz8N0/5kyZaZ/OTHvvmXMPfb+Sm3u+z3lm+v2j6afPOec+NzITSZL2t6TpBiRJ/cmAkCQVGRCSpCIDQpJUZEBIkooMCElSkQEhSSoyICRJRQaEJKlooOkGunHcccfl0NBQ021IUqvs3Lnz15k5ON+8VgfE0NAQY2NjTbchSa0SEb9cyDwvMUmSigwISVKRASFJKjIgJElFBoTUY2NjY4yOjrJz586mW5G6YkBIPbZx40Zee+01rr322qZbkbpiQEg9NDY2xksvvQTASy+95CpCrWZASD20cePGWbWrCLWZASH10PTq4WC11Ca1BkRE7IqIn0TEIxExVo0dGxEPRsTj1fvbq/GIiBsjohMRj0bER+rsTarD0UcfPWcttclirCDOyMwPZeZIVV8BbM/M1cD2qgY4F1hdvTYAtyxCb1JP7X+J6brrrmumEakHmrjEtBbYWh1vBc6fMX53TvkBsCIiTmygP+mwjYyM7Fs1HH300ZxyyikNdyQdvroDIoF/i4idEbGhGjshM58GqN6Pr8ZXAk/O+NnxakxqlY0bN7JkyRJXD2q9undz/Whm7o6I44EHI+IXc8yNwlgeMGkqaDYAvPOd7+xNl1IPjYyMsGPHjqbbkLpW6woiM3dX788C3wZOBZ6ZvnRUvT9bTR8HTprx46uA3YXfuSUzRzJzZHBw3u3MJUmHqbaAiIi3RsTbpo+BPwZ+CmwD1lXT1gH3V8fbgE9WTzOdBrwwfSlKkrT46rzEdALw7YiY/nP+MTO/GxE/Au6LiPXAr4ALq/kPAGuADrAHuKTG3iRJ86gtIDLzCeCDhfHfAGcWxhO4rK5+JEmHxk9SS5KKDAhJUpEBIUkqMiAkSUUGhCSpyICQJBUZEJKkIgNCklRkQEiSigwISVKRASFJKjIgJElFBoQkqciAkCQVGRCSpCIDQpJUZEBIkooMCElSkQEhSSoyICRJRQaEJKnIgJAkFRkQkqQiA0KSVGRASJKKDAhJUpEBIUkqMiAkSUUGhCSpyICQJBXVHhARsTQifhwR36nqkyPihxHxeER8MyLeVI2/uao71fmhunuTJB3cYqwgLgcem1F/FbghM1cDzwPrq/H1wPOZOQzcUM2TJDWk1oCIiFXAecDtVR3AKPCtaspW4PzqeG1VU50/s5ovSWpA3SuIvwP+Gnitqt8B/DYzJ6t6HFhZHa8EngSozr9QzZ8lIjZExFhEjE1MTNTZuyQd0WoLiIj4E+DZzNw5c7gwNRdw7vWBzC2ZOZKZI4ODgz3oVJJUMlDj7/4o8LGIWAO8BfgDplYUKyJioFolrAJ2V/PHgZOA8YgYAI4BnquxP0nSHGpbQWTmFzJzVWYOARcBOzLzYuBh4BPVtHXA/dXxtqqmOr8jMw9YQUiSFkcTn4P4PPDZiOgwdY/hjmr8DuAd1fhngSsa6E2SVKnzEtM+mfl94PvV8RPAqYU5e4ELF6MfSdL8/CS1JKnIgJAkFRkQkqQiA0KSVGRASJKKDAhJUpEBIUkqMiAkSUUGhCSpyICQJBUZEJKkIgNCklRkQEiSigwISVKRASFJKjIgJElFBoQkqciAkCQVGRCSpCIDQpJUZEBIkooMCElSkQEhSSoyICRJRQaEJKnIgJAkFRkQkqQiA0KSVGRASJKKDAhJUlFtARERb4mI/4yI/46In0XEddX4yRHxw4h4PCK+GRFvqsbfXNWd6vxQXb1JkuZX5wriFWA0Mz8IfAg4JyJOA74K3JCZq4HngfXV/PXA85k5DNxQzZMkNaS2gMgpL1XlUdUrgVHgW9X4VuD86nhtVVOdPzMioq7+JElzq/UeREQsjYhHgGeBB4H/BX6bmZPVlHFgZXW8EngSoDr/AvCOwu/cEBFjETE2MTFRZ/uSdESrNSAy89XM/BCwCjgVeF9pWvVeWi3kAQOZWzJzJDNHBgcHe9esJGmWRXmKKTN/C3wfOA1YERED1alVwO7qeBw4CaA6fwzw3GL0J0k6UJ1PMQ1GxIrqeBlwFvAY8DDwiWraOuD+6nhbVVOd35GZB6wgJEmLY2D+KYftRGBrRCxlKojuy8zvRMTPgXsjYhPwY+COav4dwDciosPUyuGiGnuTJM2jtoDIzEeBDxfGn2DqfsT+43uBC+vqR5J0aPwktSSpyICQJBUZEJKkogUFRET8UURcUh0PRsTJ9bYlSWravAEREdcCnwe+UA0dBfxDnU1JbXbPPfdw+umnc++99zbditSVhawgLgA+BrwMkJm7gbfV2ZTUZrfddhsAt956a8OdSN1ZSED8vvrAWgJExFvrbUlqr3vuuWdW7SpCbbaQgLgvIv6eqS0yLgUeAm6rty2pnaZXD9NcRajN5v2gXGZeHxFnAy8Cfwhck5kP1t6ZJKlRcwZEtU3G9zLzLKa265YkHSHmvMSUma8CeyLimEXqR2q1Sy+9dFb9qU99qqFOpO4t5B7EXuAnEXFHRNw4/aq7MamNLr744ln1RRe556TaayGb9f1r9ZI0j06nc0A9PDzcUDdSdxZyk3rrfHMkTdm0adMB9V133dVMM1KX5g2IiFgN/A3wfuAt0+OZ+e4a+5JaadeuXXPWUpss5B7EncAtwCRwBnA38I06m5LaamhoaM5aapOFBMSyzNwORGb+MjM3AqP1tiW109VXXz1nLbXJgp5iioglwOMR8emIuAA4vua+pFYaHh7et2oYGhryBrVa7aABERHTl5HuB5YDfwmcAvwZsK7+1qR2OvvsswE455xzGu5E6s5cK4hTIuJdwMVMbfG9B/gc8OfA/yxCb1Ir3XnnnQDcfvvtDXcidWeugLgV+C7wXmBn9Rqb8S5pPzt27GBychKAyclJHn744YY7kg5fTO3kPceEiFsy8y8WqZ9DMjIykmNjZpX6x1lnnbUvIAAGBgZ46KGHGuxIOlBE7MzMkfnmzXuTul/DQepHM8OhVEttsqDvpJa0MBExZy21iQEh9dBRRx01Zy21iQEh9dD+j7aee+65DXUidc+AkHroPe95z6zaD8qpzQwIqYduuummWfXmzZsb6kTqngEh9ZBPMemNpLaAiIiTIuLhiHgsIn4WEZdX48dGxIMR8Xj1/vZqPKpvq+tExKMR8ZG6epPqMjAwMGcttUmdK4hJ4HOZ+T7gNOCyiHg/cAWwPTNXA9urGuBcYHX12sDUFuNSq1x55ZWz6quuuqqhTqTu1RYQmfl0Zv5Xdfw74DFgJbAWmP6Wuq3A+dXxWuDunPIDYEVEnFhXf1IdRkdH960aBgYGOOOMMxruSDp8i3IPIiKGgA8DPwROyMynYSpEeH3r8JXAkzN+bLwa2/93bYiIsYgYm5iYqLNt6bBMryJcPajtar9AGhFHA/8M/FVmvjjHJ0tLJw7YKCoztwBbYGovpl71KfXK6Ogoo6N+p5bar9YVREQcxVQ43JOZ/1INPzN96ah6f7YaHwdOmvHjq4DddfYnSTq4Op9iCuAO4LHM/NsZp7bx+hcOrWPqC4mmxz9ZPc10GvDC9KUoSdLiq/MS00eZ+va5n0TEI9XYlcBXgPsiYj3wK+DC6twDwBqgw9SXE11SY2+SpHnUFhCZ+R+U7ysAnFmYn8BldfUjSTo0fpJaklRkQEiSigwISVKRASFJKjIgpB7rdDqcd955dDqdpluRumJASD22adMmXn75ZTZt2tR0K1JXDAiphzqdDrt27QJg165driLUagaE1EP7rxpcRajNDAiph6ZXDwerpTYxIKQeGhoamrOW2sSAkHroggsumFV//OMfb6gTqXsGhNRDX/va12bVN998c0OdSN0zIKQeeuWVV2bVe/fubagTqXsGhCSpyICQJBUZEJKkIgNC6iEfc9UbiQEh9ZCPueqNxICQesjHXPVGYkBIPeRjrnojMSAkSUUGhNRDS5cunbOW2sSAkHroqquumlVfffXVDXUidc+AkCQVGRBSD335y1+eVX/pS19qqBOpewaE1EOTk5Nz1lKbGBBSD3mTWm8kBoTUQ5k5Zy21iQEh9dBrr702Zy21iQEhSSqqLSAi4usR8WxE/HTG2LER8WBEPF69v70aj4i4MSI6EfFoRHykrr4kSQtT5wriLuCc/cauALZn5mpge1UDnAusrl4bgFtq7EuqzYoVK+aspTapLSAy89+B5/YbXgtsrY63AufPGL87p/wAWBERJ9bVm1SX66+/fs5aapPFvgdxQmY+DVC9H1+NrwSenDFvvBo7QERsiIixiBibmJiotVlJOpL1y03qKIwVnw/MzC2ZOZKZI4ODgzW3JR2aL37xi7Pqa665pqFOpO4tdkA8M33pqHp/thofB06aMW8VsHuRe5O69vTTT8+qd+/2r7Haa7EDYhuwrjpeB9w/Y/yT1dNMpwEvTF+KkiQ1Y6CuXxwR/wScDhwXEePAtcBXgPsiYj3wK+DCavoDwBqgA+wBLqmrL0nSwtQWEJn5pwc5dWZhbgKX1dWLJOnQ9ctNaklSnzEgJElFBoQkqciAkCQVGRCSpCIDQpJUVNtjrjry3HTTTXQ6nabb6DuXX3550y00anh4mM985jNNt6HD4ApCklQUbf7O3JGRkRwbG2u6DWmfNWvWsGfPnn318uXLeeCBBxrsSDpQROzMzJH55rmCkHroxhtvnLOW2sSAkHpoeHh43/Hy5ctn1VLbGBBSj61evZolS5a4elDrGRBSjy1fvpwPfOADrh7UegaEJKnIgJAkFRkQkqQiA0KSVGRASJKKDAhJUpGb9XXJDeq0v+m/D0f6Jn06UNs2LjQgutTpdHjkp4/x6vJjm25FfWLJ76f2N9v5xDMNd6J+snTPc023cMgMiB54dfmx/N971zTdhqQ+tuwX7du00XsQkqQiA0KSVGRASJKKDAhJUpE3qbv01FNPsXTPC628ASVp8Szd8xueemqy6TYOiSsISVKRAdGllStXAtF0G+ojS/a+yJK9LzbdhvpOVP9etEdfXWKKiHOAzcBS4PbM/ErDLc3LL4XR/jqd3wEw/O4TGu5E/eWE1v170TcBERFLgZuBs4Fx4EcRsS0zf95sZ3Nr08fmtTimt9jYvHlzw51I3embgABOBTqZ+QRARNwLrAX6OiD0OvelmuJeTLO1bf8hva6f7kGsBJ6cUY9XY7NExIaIGIuIsYmJiUVrTlqoZcuWsWzZsqbbkLrWTyuI0p3ePGAgcwuwBWBkZOSA82qO/0uU3lj6aQUxDpw0o14F7G6oF0k64vVTQPwIWB0RJ0fEm4CLgG0N9yRJR6y+ucSUmZMR8Wnge0w95vr1zPxZw21J0hGrbwICIDMfANyzQpL6QD9dYpIk9REDQpJUZEBIkooMCElSUWS297NmETEB/LLpPqSC44BfN92EdBDvyszB+Sa1OiCkfhURY5k50nQfUje8xCRJKjIgJElFBoRUjy1NNyB1y3sQkqQiVxCSpCIDQpJUZEBIkooMCElSkQEhSSr6fyXrCvn8Aw6uAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# use boxplot to show outlier\n", "eda_getBulkPlot(df, ['age', 'fare'], eda_getOutlierBoxPlot)\n" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'\\nhandle outlier\\nthis will depend on your business senario. You can do following \\n* remove outlier\\n* cap outlier\\n* replace with mean, median\\n* future analyze with target variable to see if it is consistent with other value to determine next step\\n https://www.kaggle.com/code/pmarcelino/comprehensive-data-exploration-with-python/notebook\\n\\n'" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "'''\n", "handle outlier\n", "this will depend on your business senario. You can do following \n", "* remove outlier\n", "* cap outlier\n", "* replace with mean, median\n", "* future analyze with target variable to see if it is consistent with other value to determine next step\n", " https://www.kaggle.com/code/pmarcelino/comprehensive-data-exploration-with-python/notebook\n", "\n", "'''\n", "\n" ] }, { "cell_type": "code", "execution_count": 17, "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", "
survivedpclassagesibspparchfareadult_malealone
survived1.000000-0.338481-0.077221-0.0353220.0816290.257307-0.557080-0.203367
pclass-0.3384811.000000-0.3692260.0830810.018443-0.5495000.0940350.135207
age-0.077221-0.3692261.000000-0.308247-0.1891190.0960670.2803280.198270
sibsp-0.0353220.083081-0.3082471.0000000.4148380.159651-0.253586-0.584471
parch0.0816290.018443-0.1891190.4148381.0000000.216225-0.349943-0.583398
fare0.257307-0.5495000.0960670.1596510.2162251.000000-0.182024-0.271832
adult_male-0.5570800.0940350.280328-0.253586-0.349943-0.1820241.0000000.404744
alone-0.2033670.1352070.198270-0.584471-0.583398-0.2718320.4047441.000000
\n", "
" ], "text/plain": [ " survived pclass age sibsp parch fare \\\n", "survived 1.000000 -0.338481 -0.077221 -0.035322 0.081629 0.257307 \n", "pclass -0.338481 1.000000 -0.369226 0.083081 0.018443 -0.549500 \n", "age -0.077221 -0.369226 1.000000 -0.308247 -0.189119 0.096067 \n", "sibsp -0.035322 0.083081 -0.308247 1.000000 0.414838 0.159651 \n", "parch 0.081629 0.018443 -0.189119 0.414838 1.000000 0.216225 \n", "fare 0.257307 -0.549500 0.096067 0.159651 0.216225 1.000000 \n", "adult_male -0.557080 0.094035 0.280328 -0.253586 -0.349943 -0.182024 \n", "alone -0.203367 0.135207 0.198270 -0.584471 -0.583398 -0.271832 \n", "\n", " adult_male alone \n", "survived -0.557080 -0.203367 \n", "pclass 0.094035 0.135207 \n", "age 0.280328 0.198270 \n", "sibsp -0.253586 -0.584471 \n", "parch -0.349943 -0.583398 \n", "fare -0.182024 -0.271832 \n", "adult_male 1.000000 0.404744 \n", "alone 0.404744 1.000000 " ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#5. feature correlation only show numberic varialbe, no categorical\n", "df.corr()\n" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "survived 1.000000\n", "fare 0.257307\n", "parch 0.081629\n", "sibsp -0.035322\n", "age -0.077221\n", "alone -0.203367\n", "pclass -0.338481\n", "adult_male -0.557080\n", "Name: survived, dtype: float64\n" ] } ], "source": [ "#custom function to list target column in descending order, fare play big part for survival\n", "eda_getCorrelation (df, 'survived')" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "#take close look using pairplot\n", "eda_getPairPlot(df,['survived','age', 'fare'])" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "#using heat map to show some collinearity \n", "eda_getCorrlationHeatMap (df)" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "eda_getTopKCorrelatedColumnHeatMap (df, 5, 'survived' )\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1 num__fare\n", "2 cat__x0_female\n", "3 cat__x0_male\n", "4 cat__x1_C\n", "6 cat__x1_S\n", "8 cat__x2_child\n", "9 cat__x2_man\n", "10 cat__x2_woman\n", "11 cat__x3_Cherbourg\n", "13 cat__x3_Southampton\n", "dtype: object" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#6. select K best features\n", "#classification use f_classif, regression use f_regression\n", "eda_getKBestFeatures(df, 10,['age', 'fare'], ['sex', 'embarked', 'who', 'embark_town'], 'survived', f_classif )" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }