‘ustr2024 190030960_ds_lab4ipynb- Colaboratory import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import warnings warnings. filterwarnings("ignore") data_2@15=pd.read_csv('2015.csv') data_2016=pd.read_csv('2016.csv') data_2017=pd.read_csv('2@17.csv') data_2018-pd.read_csv('2018.csv') data_2019=pd.read_csv('2019.csv') data_2015.columns=[each.split()[@] if(len(each.split())>2) else each.replace( data_2016.columns=[each.split()[@] if(len(each.split())>2) else each.replace( data_2017. colunns=[each.replace("."," ") for each in data_2017.colunns] data_2016. colunns=[each. split()[@] if(len(each.split())>2) else each.replace(” ", data_2015.info() Rangelndex: 158 entries, @ to 157 Data columns (total 12 columns): # Column Non-Null Count type country 158 non-null object @ 1 Region 158 non-null object 2 Happiness Rank 158 non-null —intoa 3 Happiness_Score 158 non-null —float 64 4 Standard_Error 158 non-null —float64 5 Economy 158 non-null —floatea 6 Family 158 non-null floate4 7 Health 158 non-null floatea 8 Freedom 158 non-null floatea 9 Trust 158 non-null floatea 1@ Generosity 158 non-null —floate4 11 Dystopia Residual 158 non-null —floatea dtypes: floatea(9), int64(1), object(2) memory usage: 14.9+ KB data_2015.head() hitpsscolab research google comidrveltylotiasAbkzO186o05ZgKBu_SkDOVZIHSCroTE leDHUDOBDVPEprintMode=true a‘ustr2024 190030960_ds_lab4ipynb- Colaboratory Country Region Happiness_Rank Happiness_Score Standard Error Economy Family Western 0 Switzerland Europe 1 7.587 0.03411 1.39651 1.34951 region_lists=list(data_2015[ ‘Region’ ] .unique()) region_lists [‘Western Europe’, ‘North America’, ‘australia and New Zealand’, ‘Middle East and Northern Africa’, ‘Latin America and Caribbean’, "Southeastern Asia’, “central and Eastern Europe’, ‘Eastern Asia’, "Sub-Saharan Africa’, “Southern Asia’ ] print("Are There Missing Data? print (data_2015.isnul1().sum()) ,data_2015.isnul1().any().any()) Are There Missing Data? : False Country @ Region Happiness_Rank Happiness_Score Standard_Error Econony Family Health Freedom Trust Generosity Dystopia Residual ctype: intea region_lists=list(data_2015[ ‘Region’ ] .unique()) region_happiness_ratio=[] for each in region_lists: region=data_2015[data_2015[ ‘Region’ ]==each] region_happiness_rate=sum(region.Happiness_Score)/len(region) region_happiness_ratio. append(region_happiness_rate) data-pd.DataFrame({" region’ :region_lists, 'region_happiness_ratio' :region_happiness_ratioy) new_index=(datal ‘region_happiness_ratio' ].sort_values(ascending-False) ) .index.values sorted_data =data.reindex(new_index) sorted_data hitpsscolab research google comidrveltylotiasAbkzO186o05ZgKBu_SkDOVZIHSCroTE leDHUDOBDVPEprintMode=true‘ustr2024 5 #barplot plt.figu 190030960_ds_lab4ipynb- Colaboratory region region_happiness_ratio Australia and New Zealand 7.285000 North America 7.273000 Western Europe 6.689619 Latin America and Caribbean 6.144682 Easter Asia 5.626167 Middle East and Northern Africa 5.406900 Central and Eastern Europe 5.332931 Southeastem Asia 5.317444 re(Figsize=(12,1@)) sns.barplot(x=sorted_data[ ‘region’ ], y=sorted_data[ ‘region_happiness_ratio' ],palette=sns. cube plt.xtic! ks (rotation = 98) plt.xlabel(‘region') plt.ylabel( ‘region Happiness Ration’) plt.title('Happiness rate for regions’) plt. show 0. ch google comirva toy tiasAbkzO136008ZoKBu_SkbOvZiscrolTo=JeDHUBOSOVp&printMode=tme se‘ustr2024 Happiness rate for regions *190030950_ds_Iabé.ipynb -Colaboratory + Ration region_economy_ratio=[] for each in region_lists: region=data_2015[data_2015[ ‘Region’ region_economy_rat: each] um region. Economy) /len(region) region_economy_ratio. append(region_econony_rate) | | . li region_lists=list(data_2015[ ‘Region’ ].unique()) data_economy=pd.DataFrame({ ‘region’ :region_lists, 'region_econony_ratio’ :region_economy_ratio} new_index_economy=(data_econony[ 'region_economy_ratio' ].sort_values(ascending=True)).index.va sorted_data_econony =data_economy.reindex(new_index) sorted_data_economy region region_econony_ratio 2 Australia and New Zealand 1 North America Western Europe Latin America and Caribbean Eastern Asia Middle East and Northern Africa Central and Eastern Europe Southeastern Asia ‘Southemn Asia ee aaer eo ‘Sub-Saharan Arica f,ax1eplt. subplots (figsize=(12,10)) 1.291880 1.360400 1.298596 0.876815 1.151780 1.066973 0.942438 0.789054 0.560486 0.380473 sns.barplot (x=sorted_data_economy| ‘region’ ],y=sorted_data_economy| 'region_econony_ratio'],pal plt.xticks(rotation=98) plt.xlabel(' Region’) Alt viahel('Raoinn Franamy RatiatY hitpsieola.research.google.comidrive/ yl iasAbkz0[86o08ZeKBu_SkbOvZi#scrolITo=)1eDHUSO3eVp&printMode=truo 40‘ustr2024 190030960_ds_lab4ipynb- Colaboratory plt.title('Econony rate for regions') plt.show() Economy rate for regions u a c Bos as 0 00 7 rr rr er er i g § i 2 i é 3 a 5 3 € = é € € » ad € 8 f € € | 7 5 8 g “ 5 a g 8 i i p oF 8 ; i BE a & g 8 3 3S = Region #Point plot sorted_data[ ‘region_happiness_ratio' ]=sorted_data[ ‘region _happiness_ratio' ]/max(sorted_data[' sorted _data_econony[ ‘region_econony ratio’ ]=sorted_data_economy| ‘region economy ratio’ ]/max(s data=pd. concat([sorted_data, sorted_data_econony[ 'region_economy_ratio’ }],axis=1) rue) data.sort_values('region_happiness_ratio' , inplac hitpsscolab research google comidrveltylotiasAbkzO186o05ZgKBu_SkDOVZIHSCroTE leDHUDOBDVPEprintMode=true‘ustr2024 190030960_ds_lab4ipynb- Colaboratory f,ax1 = plt.subplots(figsize =(20,18)) sns.pointplot(x='region’ ,y='region_happiness_ratio' ,data-data, color="1ime‘ ,alpha=@.8) sns.pointplot(x='region' ,y='region_economy_ratio’ ,data=data, color='red',alpha=.8) plt.text(7.55,0.6, ‘happiness score ratio’ ,color='red’,fontsize = 17,style = italic’) plt.text(7.55,0.55, ‘economy ratio’ ,color='lime',fontsize = 18,style = ‘italic') plt.xticks(rotation=45) plt.xlabel( Region’, fontsize = 15, color: plt.ylabel( ‘Values’, fontsize = 15, color: blue) blue") plt.title('Happiness Score VS Economy Rate’ ,fontsize = 20,color='blue') plt.grid() plt.show() leDHUDOBDVPEprintMode=true‘ustr2024 *190030950_ds_Iabé.ipynb -Colaboratory #jointplot datafrane=pd.pivot_table(data_2015, index=' Region’ ,values=["Happiness_Score”, "Family"]) datafrane[ "Happiness_Score" ]=dataframe| "Happiness _Score” ]/nax(datafrane[ "Happiness_Score”]) datafrane[ "Family" ]=dataframe[ "Family"]/max(dataframe["Family"]) sns. jointplot (datafrane. Family, dataframe.Happiness_Score, kind="kde" ,height=7, space=@) plt.savefig( ‘graph. png") plt.show() a 10 Happiness Score 04 oz oa 06 08 10 12 Family data_2015[ data_2016[ data_2017[ data_concat=pd. concat ([data_2015, data_2016, data_2017], axis=0, sort=False) df=pd.pivot_table(data_concat, index=' Year’ ,values="Happiness_Score”) dF Happiness_Score Year 2015 5.375734 2016 5.382185 hitpsseola.research,google.comidrve/teyltiasAbkz0186008ZsKBu_SkbOvZi#scroITo=)1eDHUSO3eVp&printMode=truo 18‘ustr2024 *190030950_ds_Iabé.ipynb -Colaboratory tviolinplot datafrane2=pd.pivot_table(data_2015, index=' Region’ , values=["Happiness_Score” "Trust datatrane2["Happiness_Score" ]=datafrane2[ "Happiness Score" ]/nax(datafrane2[ "Happiness_Score"] datafrane2[ "Trust" ]=dataframe2[ "Trust" ]/max(datafrane2[ "Trust" ]) pal=sns. cubehelix_palette(2,rot=.5,dark=.3) sns.violinplot (data-dataframe2, palette=pal,,inne plt.show() points") D 2 10 08 06 os 02 09 Happiness Score ust |eOHUBOS0Vp&printMode=tme