{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd # pandas will be referred to as pd below\n", "import numpy\n", "import matplotlib.pyplot as plt\n", "import seaborn\n", "%matplotlib inline \n", "import warnings\n", "warnings.filterwarnings('ignore')" ] }, { "cell_type": "code", "execution_count": 193, "metadata": {}, "outputs": [], "source": [ "elec_use= pd.read_csv('electricity_use_per_person.csv')\n", "median_age= pd.read_csv('median_age_years.csv')" ] }, { "cell_type": "code", "execution_count": 194, "metadata": { "scrolled": true }, "outputs": [], "source": [ "elec_use = elec_use[['country', '1975','1980','1985','1990','1995','2000','2005','2010']]\n", "elec_use = elec_use.dropna()" ] }, { "cell_type": "code", "execution_count": 195, "metadata": {}, "outputs": [], "source": [ "median_age = median_age[['country','1975','1980' ,'1985','1990','1995','2000','2005','2010']]" ] }, { "cell_type": "code", "execution_count": 196, "metadata": {}, "outputs": [], "source": [ "melt1 = pd.melt(elec_use, id_vars=[\"country\"], value_vars=['1975','1980' ,'1985','1990','1995','2000','2005','2010'], value_name='Elec_usage')\n", "melt2 = pd.melt(median_age, id_vars=[\"country\"], value_vars=['1975','1980' ,'1985','1990','1995','2000','2005','2010'], value_name='Median_Age')\n", "#melt2.set_index('country',inplace=True)" ] }, { "cell_type": "code", "execution_count": 197, "metadata": { "scrolled": false }, "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", "
countryvariableElec_usage
99Turkey1975359.0
208Turkey1980496.0
317Turkey1985660.0
426Turkey1990930.0
535Turkey19951230.0
644Turkey20001650.0
753Turkey20052010.0
862Turkey20102490.0
\n", "
" ], "text/plain": [ " country variable Elec_usage\n", "99 Turkey 1975 359.0\n", "208 Turkey 1980 496.0\n", "317 Turkey 1985 660.0\n", "426 Turkey 1990 930.0\n", "535 Turkey 1995 1230.0\n", "644 Turkey 2000 1650.0\n", "753 Turkey 2005 2010.0\n", "862 Turkey 2010 2490.0" ] }, "execution_count": 197, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#melt2\n", "#melt2[melt2[\"country\"] == 'Turkey']\n", "melt1[melt1[\"country\"] == 'Turkey']" ] }, { "cell_type": "code", "execution_count": 198, "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", "
countryvariableMedian_Age
169Turkey197519.6
353Turkey198020.0
537Turkey198521.0
721Turkey199022.1
905Turkey199523.5
1089Turkey200024.9
1273Turkey200526.6
1457Turkey201028.3
\n", "
" ], "text/plain": [ " country variable Median_Age\n", "169 Turkey 1975 19.6\n", "353 Turkey 1980 20.0\n", "537 Turkey 1985 21.0\n", "721 Turkey 1990 22.1\n", "905 Turkey 1995 23.5\n", "1089 Turkey 2000 24.9\n", "1273 Turkey 2005 26.6\n", "1457 Turkey 2010 28.3" ] }, "execution_count": 198, "metadata": {}, "output_type": "execute_result" } ], "source": [ "melt2[melt2[\"country\"] == 'Turkey']" ] }, { "cell_type": "code", "execution_count": 199, "metadata": {}, "outputs": [], "source": [ "#melt1.set_index('country',inplace=True)\n", "#melt2.set_index('country',inplace=True)\n", "merged= pd.merge(melt1, melt2,how='inner', left_on=['country','variable'], right_on=['country','variable'])" ] }, { "cell_type": "code", "execution_count": 200, "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", "
countryvariableElec_usageMedian_Age
99Turkey1975359.019.6
208Turkey1980496.020.0
317Turkey1985660.021.0
426Turkey1990930.022.1
535Turkey19951230.023.5
644Turkey20001650.024.9
753Turkey20052010.026.6
862Turkey20102490.028.3
\n", "
" ], "text/plain": [ " country variable Elec_usage Median_Age\n", "99 Turkey 1975 359.0 19.6\n", "208 Turkey 1980 496.0 20.0\n", "317 Turkey 1985 660.0 21.0\n", "426 Turkey 1990 930.0 22.1\n", "535 Turkey 1995 1230.0 23.5\n", "644 Turkey 2000 1650.0 24.9\n", "753 Turkey 2005 2010.0 26.6\n", "862 Turkey 2010 2490.0 28.3" ] }, "execution_count": 200, "metadata": {}, "output_type": "execute_result" } ], "source": [ "merged[merged[\"country\"] == 'Turkey']" ] }, { "cell_type": "code", "execution_count": 201, "metadata": { "scrolled": true }, "outputs": [], "source": [ "data = merged.rename(columns={'variable': 'Year', 'country': 'Country'})" ] }, { "cell_type": "code", "execution_count": 202, "metadata": { "scrolled": true }, "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", "
CountryYearElec_usageMedian_Age
0Albania1975739.020.2
1Algeria1975195.016.5
2Angola1975127.016.6
3Argentina19751000.027.4
4Australia19754780.028.1
5Austria19753730.033.9
6Bahrain19752630.019.3
7Bangladesh197517.017.6
8Belgium19753890.034.3
9Benin197518.118.3
10Bolivia1975189.018.6
11Brazil1975649.019.5
12Brunei19751480.019.6
13Bulgaria19753040.033.7
14Cameroon1975175.018.4
15Canada197510400.027.5
16Chile1975742.021.5
17China1975199.020.4
18Colombia1975442.017.8
19Congo, Dem. Rep.1975167.017.8
20Congo, Rep.197564.117.9
21Costa Rica1975730.019.3
22Cote d'Ivoire1975122.017.6
23Cuba1975623.022.3
24Cyprus19751030.027.4
25Czech Republic19754030.032.7
26Denmark19753410.033.0
27Dominican Republic1975402.017.0
28Ecuador1975196.018.1
29Egypt1975236.019.2
...............
842Portugal20104960.041.6
843Qatar201014800.031.8
844Romania20102550.039.4
845Saudi Arabia20107970.025.9
846Senegal2010199.018.1
847Singapore20108680.037.3
848Slovak Republic20105200.037.3
849South Africa20104510.024.8
850South Korea20109720.038.0
851Spain20105710.040.6
852Sri Lanka2010461.030.4
853Sudan2010131.018.3
854Sweden201014900.040.7
855Switzerland20108170.041.6
856Syria20101850.021.5
857Tanzania201093.017.2
858Thailand20102310.035.5
859Togo2010123.018.6
860Trinidad and Tobago20106190.031.9
861Tunisia20101360.029.2
862Turkey20102490.028.3
863United Arab Emirates201011000.031.9
864United Kingdom20105700.039.6
865United States201013400.036.9
866Uruguay20102800.033.7
867Venezuela20103130.025.8
868Vietnam20101020.028.5
869Yemen2010250.018.0
870Zambia2010580.016.5
871Zimbabwe2010547.018.6
\n", "

872 rows × 4 columns

\n", "
" ], "text/plain": [ " Country Year Elec_usage Median_Age\n", "0 Albania 1975 739.0 20.2\n", "1 Algeria 1975 195.0 16.5\n", "2 Angola 1975 127.0 16.6\n", "3 Argentina 1975 1000.0 27.4\n", "4 Australia 1975 4780.0 28.1\n", "5 Austria 1975 3730.0 33.9\n", "6 Bahrain 1975 2630.0 19.3\n", "7 Bangladesh 1975 17.0 17.6\n", "8 Belgium 1975 3890.0 34.3\n", "9 Benin 1975 18.1 18.3\n", "10 Bolivia 1975 189.0 18.6\n", "11 Brazil 1975 649.0 19.5\n", "12 Brunei 1975 1480.0 19.6\n", "13 Bulgaria 1975 3040.0 33.7\n", "14 Cameroon 1975 175.0 18.4\n", "15 Canada 1975 10400.0 27.5\n", "16 Chile 1975 742.0 21.5\n", "17 China 1975 199.0 20.4\n", "18 Colombia 1975 442.0 17.8\n", "19 Congo, Dem. Rep. 1975 167.0 17.8\n", "20 Congo, Rep. 1975 64.1 17.9\n", "21 Costa Rica 1975 730.0 19.3\n", "22 Cote d'Ivoire 1975 122.0 17.6\n", "23 Cuba 1975 623.0 22.3\n", "24 Cyprus 1975 1030.0 27.4\n", "25 Czech Republic 1975 4030.0 32.7\n", "26 Denmark 1975 3410.0 33.0\n", "27 Dominican Republic 1975 402.0 17.0\n", "28 Ecuador 1975 196.0 18.1\n", "29 Egypt 1975 236.0 19.2\n", ".. ... ... ... ...\n", "842 Portugal 2010 4960.0 41.6\n", "843 Qatar 2010 14800.0 31.8\n", "844 Romania 2010 2550.0 39.4\n", "845 Saudi Arabia 2010 7970.0 25.9\n", "846 Senegal 2010 199.0 18.1\n", "847 Singapore 2010 8680.0 37.3\n", "848 Slovak Republic 2010 5200.0 37.3\n", "849 South Africa 2010 4510.0 24.8\n", "850 South Korea 2010 9720.0 38.0\n", "851 Spain 2010 5710.0 40.6\n", "852 Sri Lanka 2010 461.0 30.4\n", "853 Sudan 2010 131.0 18.3\n", "854 Sweden 2010 14900.0 40.7\n", "855 Switzerland 2010 8170.0 41.6\n", "856 Syria 2010 1850.0 21.5\n", "857 Tanzania 2010 93.0 17.2\n", "858 Thailand 2010 2310.0 35.5\n", "859 Togo 2010 123.0 18.6\n", "860 Trinidad and Tobago 2010 6190.0 31.9\n", "861 Tunisia 2010 1360.0 29.2\n", "862 Turkey 2010 2490.0 28.3\n", "863 United Arab Emirates 2010 11000.0 31.9\n", "864 United Kingdom 2010 5700.0 39.6\n", "865 United States 2010 13400.0 36.9\n", "866 Uruguay 2010 2800.0 33.7\n", "867 Venezuela 2010 3130.0 25.8\n", "868 Vietnam 2010 1020.0 28.5\n", "869 Yemen 2010 250.0 18.0\n", "870 Zambia 2010 580.0 16.5\n", "871 Zimbabwe 2010 547.0 18.6\n", "\n", "[872 rows x 4 columns]" ] }, "execution_count": 202, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data" ] }, { "cell_type": "code", "execution_count": 263, "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", "
CountryYearElec_usageMedian_AgeElecGroupAgeGroupAGE
99Turkey1975359.019.62.0(18, 25]0
208Turkey1980496.020.02.0(18, 25]0
317Turkey1985660.021.02.0(18, 25]0
426Turkey1990930.022.12.0(18, 25]0
535Turkey19951230.023.53.0(18, 25]0
644Turkey20001650.024.93.0(18, 25]1
753Turkey20052010.026.63.0(25, 32]1
862Turkey20102490.028.33.0(25, 32]1
\n", "
" ], "text/plain": [ " Country Year Elec_usage Median_Age ElecGroup AgeGroup AGE\n", "99 Turkey 1975 359.0 19.6 2.0 (18, 25] 0\n", "208 Turkey 1980 496.0 20.0 2.0 (18, 25] 0\n", "317 Turkey 1985 660.0 21.0 2.0 (18, 25] 0\n", "426 Turkey 1990 930.0 22.1 2.0 (18, 25] 0\n", "535 Turkey 1995 1230.0 23.5 3.0 (18, 25] 0\n", "644 Turkey 2000 1650.0 24.9 3.0 (18, 25] 1\n", "753 Turkey 2005 2010.0 26.6 3.0 (25, 32] 1\n", "862 Turkey 2010 2490.0 28.3 3.0 (25, 32] 1" ] }, "execution_count": 263, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data[data[\"Country\"] == 'Turkey']" ] }, { "cell_type": "code", "execution_count": 204, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec. use per person ranges from 6.68 and to 51400.0\n" ] }, { "data": { "text/plain": [ "count 872.000000\n", "mean 3270.140115\n", "std 4805.859468\n", "min 6.680000\n", "25% 314.000000\n", "50% 1175.000000\n", "75% 4567.500000\n", "max 51400.000000\n", "Name: Elec_usage, dtype: float64" ] }, "execution_count": 204, "metadata": {}, "output_type": "execute_result" } ], "source": [ "print ('Elec. use per person ranges from '+ str(data['Elec_usage'].min())+' and to '+ str(data['Elec_usage'].max()) )\n", "data['Elec_usage'].describe()" ] }, { "cell_type": "code", "execution_count": 205, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "872\n", "872\n" ] } ], "source": [ "# Elec. use per person column keeps continuous quantitative variables.\n", "# In order to create Elec. use per person groups, we need to generate partitions. \n", "# Below, we call the \"cut \" method. Note that the first cut is (7, 300]\n", "data['ElecGroup']= pd.cut(data.Elec_usage, [7,300,1000,5000,10000,20000,55000]) \n", "# no need to sort the data frame.\n", "\n", "print(len(data))\n", "print(len(data['ElecGroup']))" ] }, { "cell_type": "code", "execution_count": 206, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "count 871\n", "unique 6\n", "top (1000, 5000]\n", "freq 273\n", "Name: ElecGroup, dtype: object" ] }, "execution_count": 206, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data['ElecGroup']= data['ElecGroup'].astype('category')\n", "data['ElecGroup'].describe()" ] }, { "cell_type": "code", "execution_count": 207, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(7, 300] 0.246843\n", "(300, 1000] 0.219288\n", "(1000, 5000] 0.313433\n", "(5000, 10000] 0.138921\n", "(10000, 20000] 0.068886\n", "(20000, 55000] 0.012629\n", "Name: ElecGroup, dtype: float64\n" ] } ], "source": [ "ElecGroup= data['ElecGroup'].value_counts(sort= False, normalize= True) \n", "# value_counts() should make more sense now\n", "print(ElecGroup)" ] }, { "cell_type": "code", "execution_count": 208, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.countplot(x= 'ElecGroup', data= data)\n", "plt.xlabel('ElecGroup (per capita) categories)')\n", "plt.title('Counts of rows for each ElecGroup')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 209, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5, 1.0, 'Counts of rows for each ElecGroup')" ] }, "execution_count": 209, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.distplot(data['Elec_usage'].dropna(), kde= False)\n", "plt.xlabel('ElecGroup (per person) quantitative values)')\n", "plt.title('Counts of rows for each ElecGroup')" ] }, { "cell_type": "code", "execution_count": 210, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Median Age ranges from 14.3 and to 44.7\n" ] }, { "data": { "text/plain": [ "count 872.000000\n", "mean 25.344839\n", "std 7.639786\n", "min 14.300000\n", "25% 18.500000\n", "50% 23.250000\n", "75% 31.800000\n", "max 44.700000\n", "Name: Median_Age, dtype: float64" ] }, "execution_count": 210, "metadata": {}, "output_type": "execute_result" } ], "source": [ "print ('Median Age ranges from '+ str(data['Median_Age'].min())+' and to '+ str(data['Median_Age'].max()) )\n", "data['Median_Age'].describe()" ] }, { "cell_type": "code", "execution_count": 211, "metadata": {}, "outputs": [], "source": [ "data['AgeGroup']= pd.cut(data.Median_Age, [8,18,25,32,40,50]) " ] }, { "cell_type": "code", "execution_count": 212, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "count 872\n", "unique 5\n", "top (18, 25]\n", "freq 303\n", "Name: AgeGroup, dtype: object" ] }, "execution_count": 212, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data['AgeGroup']= data['AgeGroup'].astype('category')\n", "data['AgeGroup'].describe()" ] }, { "cell_type": "code", "execution_count": 213, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(8, 18] 0.213303\n", "(18, 25] 0.347477\n", "(25, 32] 0.194954\n", "(32, 40] 0.213303\n", "(40, 50] 0.030963\n", "Name: AgeGroup, dtype: float64\n" ] } ], "source": [ "MG= data['AgeGroup'].value_counts(sort= False, normalize= True)\n", "print(MG)" ] }, { "cell_type": "code", "execution_count": 214, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.countplot(x= 'AgeGroup', data= data)\n", "plt.xlabel('Median Age group')\n", "plt.title('Counts of rows for each Rate')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 215, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 215, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.regplot(x= \"Median_Age\", y= \"Elec_usage\", fit_reg= False, data= data)" ] }, { "cell_type": "code", "execution_count": 216, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(8, 18] 0.213303\n", "(18, 25] 0.347477\n", "(25, 32] 0.194954\n", "(32, 40] 0.213303\n", "(40, 50] 0.030963\n", "Name: AgeGroup, dtype: float64\n" ] } ], "source": [ "MG= data['AgeGroup'].value_counts(sort= False, normalize= True)\n", "print(MG)" ] }, { "cell_type": "code", "execution_count": 217, "metadata": {}, "outputs": [], "source": [ "def AGE (row):\n", " if row['Median_Age'] < 24 :\n", " return 0\n", " else:\n", " return 1" ] }, { "cell_type": "code", "execution_count": 218, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 455\n", "1 417\n", "Name: AGE, dtype: int64" ] }, "execution_count": 218, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data['AGE']= data.apply(lambda row : AGE(row), axis= 1)\n", "# axis=1, tells python to apply this function to each row \n", "# Arbitrary functions can be applied along the axes of a DataFrame using the apply() method\n", "data['AGE'].value_counts()" ] }, { "cell_type": "code", "execution_count": 220, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.factorplot(x= 'ElecGroup', y= 'AGE', data= data, kind= \"bar\", ci=None)\n", "plt.xlabel('ElecGroup per person')\n", "plt.ylabel('median age over 24')\n", "plt.show()\n", "# A categorical to categorical bar chart\n", "# note that a bivariate graph displays a mean on the y-axis, \n", "# so categorical response variables should not have other than two levels, they should be coded as 1 and 0.\n", "# Important: Below, the response variable gives us the proportion of the positive observations." ] }, { "cell_type": "code", "execution_count": 221, "metadata": {}, "outputs": [], "source": [ "#7,300,1000,5000,10000,20000,55000\n", "def ElecRangeGroup (row):\n", " if row['Elec_usage'] > 7.0 and row['Elec_usage']<= 300.0 :\n", " return 1\n", " if row['Elec_usage'] > 300.0 and row['Elec_usage']<= 1000.0 :\n", " return 2\n", " if row['Elec_usage'] > 1000.0 and row['Elec_usage']<= 5000.0 :\n", " return 3\n", " if row['Elec_usage'] > 5000.0 and row['Elec_usage']<= 10000.0 :\n", " return 4\n", " if row['Elec_usage'] > 10000.0 and row['Elec_usage']<= 20000.0 :\n", " return 5\n", " if row['Elec_usage'] > 20000.0 and row['Elec_usage']<= 55000.0 :\n", " return 6" ] }, { "cell_type": "code", "execution_count": 222, "metadata": {}, "outputs": [], "source": [ "data['ElecGroup'] = data.apply (lambda row: ElecRangeGroup (row),axis=1)" ] }, { "cell_type": "code", "execution_count": 224, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.factorplot(x= 'ElecGroup', y= 'AGE', data= data, kind= \"bar\", ci=None)\n", "plt.xlabel('Elec. use per person catagory')\n", "plt.ylabel('Median age over 24')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# PART II: Analysis" ] }, { "cell_type": "code", "execution_count": 226, "metadata": {}, "outputs": [], "source": [ "import statsmodels.formula.api as smf\n", "import statsmodels.stats.multicomp as multi " ] }, { "cell_type": "code", "execution_count": 232, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " ElecGroup Median_Age\n", "0 2.0 20.2\n", "1 1.0 16.5\n", "2 1.0 16.6\n", "3 2.0 27.4\n", "4 3.0 28.1\n", "5 3.0 33.9\n", "6 3.0 19.3\n", "7 1.0 17.6\n", "8 3.0 34.3\n", "9 1.0 18.3\n", "10 1.0 18.6\n", "11 2.0 19.5\n", "12 3.0 19.6\n", "13 3.0 33.7\n", "14 1.0 18.4\n", "15 5.0 27.5\n", "16 2.0 21.5\n", "17 1.0 20.4\n", "18 2.0 17.8\n", "19 1.0 17.8\n", "20 1.0 17.9\n", "21 2.0 19.3\n", "22 1.0 17.6\n", "23 2.0 22.3\n", "24 3.0 27.4\n", "25 3.0 32.7\n", "26 3.0 33.0\n", "27 2.0 17.0\n", "28 1.0 18.1\n", "29 1.0 19.2\n", ".. ... ...\n", "842 3.0 41.6\n", "843 5.0 31.8\n", "844 3.0 39.4\n", "845 4.0 25.9\n", "846 1.0 18.1\n", "847 4.0 37.3\n", "848 4.0 37.3\n", "849 3.0 24.8\n", "850 4.0 38.0\n", "851 4.0 40.6\n", "852 2.0 30.4\n", "853 1.0 18.3\n", "854 5.0 40.7\n", "855 4.0 41.6\n", "856 3.0 21.5\n", "857 1.0 17.2\n", "858 3.0 35.5\n", "859 1.0 18.6\n", "860 4.0 31.9\n", "861 3.0 29.2\n", "862 3.0 28.3\n", "863 5.0 31.9\n", "864 4.0 39.6\n", "865 5.0 36.9\n", "866 3.0 33.7\n", "867 3.0 25.8\n", "868 3.0 28.5\n", "869 1.0 18.0\n", "870 2.0 16.5\n", "871 2.0 18.6\n", "\n", "[872 rows x 2 columns]\n" ] } ], "source": [ "data3= data[['ElecGroup', 'Median_Age']]\n", "print(data3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## A) ANOVA \n", "### Please note that \"GDPCat\" is categorical, and \"Under_five_mortality\" is numeric" ] }, { "cell_type": "code", "execution_count": 233, "metadata": {}, "outputs": [], "source": [ "model1= smf.ols(formula='Median_Age ~ C(ElecGroup)', data=data3)\n", "# statsmodels.formula.api as smf\n", "# ols: ordinary least squares regression\n", "# first response var, and then explanatory variable. Note that C stands for the Categorical variable." ] }, { "cell_type": "code", "execution_count": 234, "metadata": {}, "outputs": [], "source": [ "results= model1.fit()" ] }, { "cell_type": "code", "execution_count": 235, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " OLS Regression Results \n", "==============================================================================\n", "Dep. Variable: Median_Age R-squared: 0.636\n", "Model: OLS Adj. R-squared: 0.634\n", "Method: Least Squares F-statistic: 302.0\n", "Date: Mon, 01 Apr 2019 Prob (F-statistic): 6.38e-187\n", "Time: 01:14:26 Log-Likelihood: -2566.7\n", "No. Observations: 871 AIC: 5145.\n", "Df Residuals: 865 BIC: 5174.\n", "Df Model: 5 \n", "Covariance Type: nonrobust \n", "=======================================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", "---------------------------------------------------------------------------------------\n", "Intercept 18.1972 0.315 57.695 0.000 17.578 18.816\n", "C(ElecGroup)[T.2.0] 2.5452 0.460 5.535 0.000 1.643 3.448\n", "C(ElecGroup)[T.3.0] 9.7108 0.422 23.028 0.000 8.883 10.539\n", "C(ElecGroup)[T.4.0] 16.4268 0.526 31.254 0.000 15.395 17.458\n", "C(ElecGroup)[T.5.0] 15.5161 0.675 22.979 0.000 14.191 16.841\n", "C(ElecGroup)[T.6.0] 15.9755 1.430 11.175 0.000 13.170 18.781\n", "==============================================================================\n", "Omnibus: 2.739 Durbin-Watson: 2.198\n", "Prob(Omnibus): 0.254 Jarque-Bera (JB): 2.859\n", "Skew: 0.047 Prob(JB): 0.239\n", "Kurtosis: 3.264 Cond. No. 10.0\n", "==============================================================================\n", "\n", "Warnings:\n", "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" ] } ], "source": [ "print(results.summary())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### POST-HOC TESTS ARE NEEDED: Which categories are different than others?" ] }, { "cell_type": "code", "execution_count": 236, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Multiple Comparison of Means - Tukey HSD,FWER=0.05\n", "==============================================\n", "group1 group2 meandiff lower upper reject\n", "----------------------------------------------\n", " 1.0 2.0 2.5452 1.1862 3.9042 True \n", " 1.0 3.0 9.7108 8.4646 10.9571 True \n", " 1.0 4.0 16.4268 14.8735 17.98 True \n", " 1.0 5.0 15.5161 13.5206 17.5116 True \n", " 1.0 6.0 15.9755 11.7506 20.2004 True \n", " 1.0 nan 1.2028 -12.4962 14.9018 False \n", " 2.0 3.0 7.1657 5.8764 8.4549 True \n", " 2.0 4.0 13.8816 12.2936 15.4696 True \n", " 2.0 5.0 12.9709 10.9483 14.9936 True \n", " 2.0 6.0 13.4303 9.1925 17.6682 True \n", " 2.0 nan -1.3424 -15.0454 12.3606 False \n", " 3.0 4.0 6.7159 5.2233 8.2085 True \n", " 3.0 5.0 5.8053 3.8566 7.754 True \n", " 3.0 6.0 6.2647 2.0616 10.4677 True \n", " 3.0 nan -8.5081 -22.2003 5.1842 False \n", " 4.0 5.0 -0.9106 -3.0686 1.2474 False \n", " 4.0 6.0 -0.4512 -4.7553 3.8528 False \n", " 4.0 nan -15.224 -28.9476 -1.5004 True \n", " 5.0 6.0 0.4594 -4.0233 4.9421 False \n", " 5.0 nan -14.3133 -28.094 -0.5327 True \n", " 6.0 nan -14.7727 -29.0477 -0.4978 True \n", "----------------------------------------------\n" ] } ], "source": [ "mc1 = multi.MultiComparison(data3['Median_Age'], data3['ElecGroup'])\n", "res1 = mc1.tukeyhsd()\n", "print(res1.summary())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### B) CHI SQUARE TEST OF INDEPENDENCE for CATEGORICAL TO CATEGORICAL VARIABLES" ] }, { "cell_type": "code", "execution_count": 238, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " AGE ElecGroup\n", "0 0 2.0\n", "1 0 1.0\n", "2 0 1.0\n", "3 1 2.0\n", "4 1 3.0\n", "5 1 3.0\n", "6 0 3.0\n", "7 0 1.0\n", "8 1 3.0\n", "9 0 1.0\n", "10 0 1.0\n", "11 0 2.0\n", "12 0 3.0\n", "13 1 3.0\n", "14 0 1.0\n", "15 1 5.0\n", "16 0 2.0\n", "17 0 1.0\n", "18 0 2.0\n", "19 0 1.0\n", "20 0 1.0\n", "21 0 2.0\n", "22 0 1.0\n", "23 0 2.0\n", "24 1 3.0\n", "25 1 3.0\n", "26 1 3.0\n", "27 0 2.0\n", "28 0 1.0\n", "29 0 1.0\n", ".. ... ...\n", "842 1 3.0\n", "843 1 5.0\n", "844 1 3.0\n", "845 1 4.0\n", "846 0 1.0\n", "847 1 4.0\n", "848 1 4.0\n", "849 1 3.0\n", "850 1 4.0\n", "851 1 4.0\n", "852 1 2.0\n", "853 0 1.0\n", "854 1 5.0\n", "855 1 4.0\n", "856 0 3.0\n", "857 0 1.0\n", "858 1 3.0\n", "859 0 1.0\n", "860 1 4.0\n", "861 1 3.0\n", "862 1 3.0\n", "863 1 5.0\n", "864 1 4.0\n", "865 1 5.0\n", "866 1 3.0\n", "867 1 3.0\n", "868 1 3.0\n", "869 0 1.0\n", "870 0 2.0\n", "871 0 2.0\n", "\n", "[872 rows x 2 columns]\n" ] } ], "source": [ "data4= data[['AGE', 'ElecGroup']]\n", "print(data4)" ] }, { "cell_type": "code", "execution_count": 239, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ElecGroup 1.0 2.0 3.0 4.0 5.0 6.0\n", "AGE \n", "0 209 158 81 6 0 0\n", "1 6 33 192 115 60 11\n" ] } ], "source": [ "# contingency table of observed counts\n", "ct1=pd.crosstab(data4['AGE'], data4['ElecGroup'])\n", "print (ct1) # ct1 is a two-dimentional array" ] }, { "cell_type": "code", "execution_count": 240, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ElecGroup 1.0 2.0 3.0 4.0 5.0 6.0\n", "AGE \n", "0 0.972093 0.827225 0.296703 0.049587 0.0 0.0\n", "1 0.027907 0.172775 0.703297 0.950413 1.0 1.0\n" ] } ], "source": [ "# column percentages\n", "colsum=ct1.sum(axis=0) # axis=0 to sum all columns\n", "colpct=ct1/colsum\n", "print(colpct)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "#### We are trying to find out if the mortality rate among different GDP categories is the same or not. Therefore column percentages make sense. (Explanatory variables on each column)" ] }, { "cell_type": "code", "execution_count": 241, "metadata": {}, "outputs": [], "source": [ "import scipy.stats" ] }, { "cell_type": "code", "execution_count": 242, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "chi-square value, p value, expected counts\n", "(487.1052465055917, 4.84579097311198e-103, 5, array([[112.06659013, 99.55683123, 142.29850746, 63.07003444,\n", " 31.27439724, 5.73363949],\n", " [102.93340987, 91.44316877, 130.70149254, 57.92996556,\n", " 28.72560276, 5.26636051]]))\n" ] } ], "source": [ "# chi-square\n", "print ('chi-square value, p value, expected counts')\n", "cs1= scipy.stats.chi2_contingency(ct1)\n", "print (cs1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Large X2 statistics and a small p-value states that there is a strong association between the explanatory variables and the response variables as opposed to the null hypothesis.\n" ] }, { "cell_type": "code", "execution_count": 243, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.factorplot(x= 'ElecGroup', y= 'AGE', data= data4, kind= \"bar\", ci=None)\n", "plt.xlabel('elec. usage per person category: 1 the most poor to 6 the richest')\n", "plt.ylabel('Median age levels')\n", "plt.show()\n", "# note that the y values are equal to the column percentages (colpct) for Mortal 1" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### POST-HOC TESTS ARE NEEDED: Which GDP Categories are different than the others?\n", "### chi square post hoc test: Apply chi square for each pair (all combinations of them); test with adjusted p value (bonferroni adjustment p-value: p-value / number_of_comparions)\n", "Here, we have 6 groups and there are 15 pairs; so the adjusted p-value is 0.05/15= 0,0033" ] }, { "cell_type": "code", "execution_count": 245, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_1v2 1.0 2.0\n", "AGE \n", "0 209 158\n", "1 6 33\n", "Elec_1v2 1.0 2.0\n", "AGE \n", "0 0.972093 0.827225\n", "1 0.027907 0.172775\n", "chi-square value, p value, expected counts\n", "(22.806297143283068, 1.7917765380037851e-06, 1, array([[194.34729064, 172.65270936],\n", " [ 20.65270936, 18.34729064]]))\n" ] } ], "source": [ "# We need to run chi-square tests for each of the comparisons\n", "recode_1v2 = {1: 1, 2: 2} # this is required because we are going to use only these two columns\n", "data4['Elec_1v2']= data4['ElecGroup'].map(recode_1v2)\n", "\n", "# contingency table of observed counts\n", "table_1v2=pd.crosstab(data4['AGE'], data4['Elec_1v2'])\n", "print (table_1v2)\n", "\n", "# column percentages\n", "colsum=table_1v2.sum(axis=0)\n", "colpct=table_1v2/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_1v2= scipy.stats.chi2_contingency(table_1v2)\n", "print (cs_1v2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Now, we need to run the above test for each of the remaining paired comparisons!" ] }, { "cell_type": "code", "execution_count": 246, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_1v3 1.0 3.0\n", "AGE \n", "0 209 81\n", "1 6 192\n", "Elec_1v3 1.0 3.0\n", "AGE \n", "0 0.972093 0.296703\n", "1 0.027907 0.703297\n", "chi-square value, p value, expected counts\n", "(224.7521622551614, 8.315050688248716e-51, 1, array([[127.76639344, 162.23360656],\n", " [ 87.23360656, 110.76639344]]))\n" ] } ], "source": [ "recode_1v3 = {1: 1, 3: 3}\n", "data4['Elec_1v3']= data4['ElecGroup'].map(recode_1v3)\n", "\n", "# contingency table of observed counts\n", "table_1v3=pd.crosstab(data4['AGE'], data4['Elec_1v3'])\n", "print (table_1v3)\n", "\n", "# column percentages\n", "colsum=table_1v3.sum(axis=0)\n", "colpct=table_1v3/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_1v3= scipy.stats.chi2_contingency(table_1v3)\n", "print (cs_1v3)" ] }, { "cell_type": "code", "execution_count": 247, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_1v4 1.0 4.0\n", "AGE \n", "0 209 6\n", "1 6 115\n", "Elec_1v4 1.0 4.0\n", "AGE \n", "0 0.972093 0.049587\n", "1 0.027907 0.950413\n", "chi-square value, p value, expected counts\n", "(281.95263018507967, 2.818963008671329e-63, 1, array([[137.57440476, 77.42559524],\n", " [ 77.42559524, 43.57440476]]))\n" ] } ], "source": [ "recode_1v4 = {1: 1, 4: 4}\n", "data4['Elec_1v4']= data4['ElecGroup'].map(recode_1v4)\n", "\n", "# contingency table of observed counts\n", "table_1v4=pd.crosstab(data4['AGE'], data4['Elec_1v4'])\n", "print (table_1v4)\n", "\n", "# column percentages\n", "colsum=table_1v4.sum(axis=0)\n", "colpct=table_1v4/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_1v4= scipy.stats.chi2_contingency(table_1v4)\n", "print (cs_1v4)" ] }, { "cell_type": "code", "execution_count": 248, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_1v6 1.0 6.0\n", "AGE \n", "0 209 0\n", "1 6 11\n", "Elec_1v6 1.0 6.0\n", "AGE \n", "0 0.972093 0.0\n", "1 0.027907 1.0\n", "chi-square value, p value, expected counts\n", "(128.52345794787362, 8.622214054991668e-30, 1, array([[198.82743363, 10.17256637],\n", " [ 16.17256637, 0.82743363]]))\n" ] } ], "source": [ "recode_1v6 = {1: 1, 6: 6}\n", "data4['Elec_1v6']= data4['ElecGroup'].map(recode_1v6)\n", "\n", "# contingency table of observed counts\n", "table_1v6=pd.crosstab(data4['AGE'], data4['Elec_1v6'])\n", "print (table_1v6)\n", "\n", "# column percentages\n", "colsum=table_1v6.sum(axis=0)\n", "colpct=table_1v6/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_1v6= scipy.stats.chi2_contingency(table_1v6)\n", "print (cs_1v6)" ] }, { "cell_type": "code", "execution_count": 249, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_2v3 2.0 3.0\n", "AGE \n", "0 158 81\n", "1 33 192\n", "Elec_2v3 2.0 3.0\n", "AGE \n", "0 0.827225 0.296703\n", "1 0.172775 0.703297\n", "chi-square value, p value, expected counts\n", "(124.51590444127238, 6.495642021769712e-29, 1, array([[ 98.38146552, 140.61853448],\n", " [ 92.61853448, 132.38146552]]))\n" ] } ], "source": [ "recode_2v3 = {2: 2, 3: 3}\n", "data4['Elec_2v3']= data4['ElecGroup'].map(recode_2v3)\n", "\n", "# contingency table of observed counts\n", "table_2v3=pd.crosstab(data4['AGE'], data4['Elec_2v3'])\n", "print (table_2v3)\n", "\n", "# column percentages\n", "colsum=table_2v3.sum(axis=0)\n", "colpct=table_2v3/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_2v3= scipy.stats.chi2_contingency(table_2v3)\n", "print (cs_2v3)" ] }, { "cell_type": "code", "execution_count": 250, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_2v4 2.0 4.0\n", "AGE \n", "0 158 6\n", "1 33 115\n", "Elec_2v4 2.0 4.0\n", "AGE \n", "0 0.827225 0.049587\n", "1 0.172775 0.950413\n", "chi-square value, p value, expected counts\n", "(176.54308080172652, 2.755787423749102e-40, 1, array([[100.3974359, 63.6025641],\n", " [ 90.6025641, 57.3974359]]))\n" ] } ], "source": [ "recode_2v4 = {2: 2, 4: 4}\n", "data4['Elec_2v4']= data4['ElecGroup'].map(recode_2v4)\n", "\n", "# contingency table of observed counts\n", "table_2v4=pd.crosstab(data4['AGE'], data4['Elec_2v4'])\n", "print (table_2v4)\n", "\n", "# column percentages\n", "colsum=table_2v4.sum(axis=0)\n", "colpct=table_2v4/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_2v4= scipy.stats.chi2_contingency(table_2v4)\n", "print (cs_2v4)" ] }, { "cell_type": "code", "execution_count": 251, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_2v5 2.0 5.0\n", "AGE \n", "0 158 0\n", "1 33 60\n", "Elec_2v5 2.0 5.0\n", "AGE \n", "0 0.827225 0.0\n", "1 0.172775 1.0\n", "chi-square value, p value, expected counts\n", "(130.43382402256765, 3.293304194760401e-30, 1, array([[120.2310757, 37.7689243],\n", " [ 70.7689243, 22.2310757]]))\n" ] } ], "source": [ "recode_2v5 = {2: 2, 5: 5}\n", "data4['Elec_2v5']= data4['ElecGroup'].map(recode_2v5)\n", "\n", "# contingency table of observed counts\n", "table_2v5=pd.crosstab(data4['AGE'], data4['Elec_2v5'])\n", "print (table_2v5)\n", "\n", "# column percentages\n", "colsum=table_2v5.sum(axis=0)\n", "colpct=table_2v5/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_2v5= scipy.stats.chi2_contingency(table_2v5)\n", "print (cs_2v5)" ] }, { "cell_type": "code", "execution_count": 252, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_2v6 2.0 6.0\n", "AGE \n", "0 158 0\n", "1 33 11\n", "Elec_2v6 2.0 6.0\n", "AGE \n", "0 0.827225 0.0\n", "1 0.172775 1.0\n", "chi-square value, p value, expected counts\n", "(37.06063979068546, 1.1451202748956859e-09, 1, array([[149.3960396, 8.6039604],\n", " [ 41.6039604, 2.3960396]]))\n" ] } ], "source": [ "recode_2v6 = {2: 2, 6: 6}\n", "data4['Elec_2v6']= data4['ElecGroup'].map(recode_2v6)\n", "\n", "# contingency table of observed counts\n", "table_2v6=pd.crosstab(data4['AGE'], data4['Elec_2v6'])\n", "print (table_2v6)\n", "\n", "# column percentages\n", "colsum=table_2v6.sum(axis=0)\n", "colpct=table_2v6/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_2v6= scipy.stats.chi2_contingency(table_2v6)\n", "print (cs_2v6)" ] }, { "cell_type": "code", "execution_count": 253, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_3v4 3.0 4.0\n", "AGE \n", "0 81 6\n", "1 192 115\n", "Elec_3v4 3.0 4.0\n", "AGE \n", "0 0.296703 0.049587\n", "1 0.703297 0.950413\n", "chi-square value, p value, expected counts\n", "(28.338129494062635, 1.0186955390669189e-07, 1, array([[ 60.28172589, 26.71827411],\n", " [212.71827411, 94.28172589]]))\n" ] } ], "source": [ "recode_3v4 = {3: 3, 4: 4}\n", "data4['Elec_3v4']= data4['ElecGroup'].map(recode_3v4)\n", "\n", "# contingency table of observed counts\n", "table_3v4=pd.crosstab(data4['AGE'], data4['Elec_3v4'])\n", "print (table_3v4)\n", "\n", "# column percentages\n", "colsum=table_3v4.sum(axis=0)\n", "colpct=table_3v4/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_3v4= scipy.stats.chi2_contingency(table_3v4)\n", "print (cs_3v4)" ] }, { "cell_type": "code", "execution_count": 254, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_3v5 3.0 5.0\n", "AGE \n", "0 81 0\n", "1 192 60\n", "Elec_3v5 3.0 5.0\n", "AGE \n", "0 0.296703 0.0\n", "1 0.703297 1.0\n", "chi-square value, p value, expected counts\n", "(21.94009081196581, 2.8129558697502437e-06, 1, array([[ 66.40540541, 14.59459459],\n", " [206.59459459, 45.40540541]]))\n" ] } ], "source": [ "recode_3v5 = {3: 3, 5: 5}\n", "data4['Elec_3v5']= data4['ElecGroup'].map(recode_3v5)\n", "\n", "# contingency table of observed counts\n", "table_3v5=pd.crosstab(data4['AGE'], data4['Elec_3v5'])\n", "print (table_3v5)\n", "\n", "# column percentages\n", "colsum=table_3v5.sum(axis=0)\n", "colpct=table_3v5/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_3v5= scipy.stats.chi2_contingency(table_3v5)\n", "print (cs_3v5)" ] }, { "cell_type": "code", "execution_count": 255, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_3v6 3.0 6.0\n", "AGE \n", "0 81 0\n", "1 192 11\n", "Elec_3v6 3.0 6.0\n", "AGE \n", "0 0.296703 0.0\n", "1 0.703297 1.0\n", "chi-square value, p value, expected counts\n", "(3.2266033951857707, 0.07245081307991667, 1, array([[ 77.86267606, 3.13732394],\n", " [195.13732394, 7.86267606]]))\n" ] } ], "source": [ "recode_3v6 = {3: 3, 6: 6}\n", "data4['Elec_3v6']= data4['ElecGroup'].map(recode_3v6)\n", "\n", "# contingency table of observed counts\n", "table_3v6=pd.crosstab(data4['AGE'], data4['Elec_3v6'])\n", "print (table_3v6)\n", "\n", "# column percentages\n", "colsum=table_3v6.sum(axis=0)\n", "colpct=table_3v6/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_3v6= scipy.stats.chi2_contingency(table_3v6)\n", "print (cs_3v6)" ] }, { "cell_type": "code", "execution_count": 256, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_4v5 4.0 5.0\n", "AGE \n", "0 6 0\n", "1 115 60\n", "Elec_4v5 4.0 5.0\n", "AGE \n", "0 0.049587 0.0\n", "1 0.950413 1.0\n", "chi-square value, p value, expected counts\n", "(1.7245277777777779, 0.189111262313004, 1, array([[ 4.01104972, 1.98895028],\n", " [116.98895028, 58.01104972]]))\n" ] } ], "source": [ "recode_4v5 = {4: 4, 5: 5}\n", "data4['Elec_4v5']= data4['ElecGroup'].map(recode_4v5)\n", "\n", "# contingency table of observed counts\n", "table_4v5=pd.crosstab(data4['AGE'], data4['Elec_4v5'])\n", "print (table_4v5)\n", "\n", "# column percentages\n", "colsum=table_4v5.sum(axis=0)\n", "colpct=table_4v5/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_4v5= scipy.stats.chi2_contingency(table_4v5)\n", "print (cs_4v5)" ] }, { "cell_type": "code", "execution_count": 257, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_4v6 4.0 6.0\n", "AGE \n", "0 6 0\n", "1 115 11\n", "Elec_4v6 4.0 6.0\n", "AGE \n", "0 0.049587 0.0\n", "1 0.950413 1.0\n", "chi-square value, p value, expected counts\n", "(0.0, 1.0, 1, array([[ 5.5, 0.5],\n", " [115.5, 10.5]]))\n" ] } ], "source": [ "recode_4v6 = {4: 4, 6: 6}\n", "data4['Elec_4v6']= data4['ElecGroup'].map(recode_4v6)\n", "\n", "# contingency table of observed counts\n", "table_4v6=pd.crosstab(data4['AGE'], data4['Elec_4v6'])\n", "print (table_4v6)\n", "\n", "# column percentages\n", "colsum=table_4v6.sum(axis=0)\n", "colpct=table_4v6/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_4v6= scipy.stats.chi2_contingency(table_4v6)\n", "print (cs_4v6)" ] }, { "cell_type": "code", "execution_count": 258, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Elec_5v6 5.0 6.0\n", "AGE \n", "1 60 11\n", "Elec_5v6 5.0 6.0\n", "AGE \n", "1 1 1\n", "chi-square value, p value, expected counts\n", "(0.0, 1.0, 0, array([[60., 11.]]))\n" ] } ], "source": [ "recode_5v6 = {5: 5, 6: 6}\n", "data4['Elec_5v6']= data4['ElecGroup'].map(recode_5v6)\n", "\n", "# contingency table of observed counts\n", "table_5v6=pd.crosstab(data4['AGE'], data4['Elec_5v6'])\n", "print (table_5v6)\n", "\n", "# column percentages\n", "colsum=table_5v6.sum(axis=0)\n", "colpct=table_5v6/colsum\n", "print(colpct)\n", "\n", "print ('chi-square value, p value, expected counts')\n", "cs_5v6= scipy.stats.chi2_contingency(table_5v6)\n", "print (cs_5v6)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## C) PEARSON CORRELATION BETWEEN TWO NUMERIC VARIABLES:" ] }, { "cell_type": "code", "execution_count": 260, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 260, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "seaborn.regplot(x= \"Elec_usage\", y= \"Median_Age\", fit_reg= False, data= data)" ] }, { "cell_type": "code", "execution_count": 262, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "association between Elec. usage pre person and Median Age\n", "(0.617638613515279, 7.588818646419762e-93)\n" ] } ], "source": [ "print('association between Elec. usage pre person and Median Age')\n", "print(scipy.stats.pearsonr(data['Elec_usage'], data['Median_Age']))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Bu kisim degisecek mesela coefficient positive\n", "# Interpretation of the above result: The coefficient is negative. \n", "As we can see from the scatter plot above, mortality rate decreases as the GDP increases. However this correlation is not very strong. The p-value suggests that the computed coefficient is significant. " ] }, { "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": "3.7.1" } }, "nbformat": 4, "nbformat_minor": 2 }