PandasPythonForDataScience

PythonForDataScienceCheatSheetPandasBasicsLearnPythonforDataScienceInteractivelyatwww.DataCamp.comPandasDataCampLearnPythonforDataScienceInteractivelySeriesDataFrame47-53dcbaAone-dimensionallabeledarraycapableofholdinganydatatypeIndexIndexColumnsAtwo-dimensionallabeleddatastructurewithcolumnsofpotentiallydifferenttypesThePandaslibraryisbuiltonNumPyandprovideseasy-to-usedatastructuresanddataanalysistoolsforthePythonprogramminglanguage.>>>importpandasaspdUsethefollowingimportconvention:PandasDataStructures>>>s=pd.Series([3,-5,7,4],index=['a','b','c','d'])>>>data={'Country':['Belgium','India','Brazil'],'Capital':['Brussels','NewDelhi','Brasília'],'Population':[11190846,1303171035,207847528]}>>>df=pd.DataFrame(data,columns=['Country','Capital','Population'])Selection>>>s['b']Getoneelement-5>>>df[1:]GetsubsetofaDataFrameCountryCapitalPopulation1IndiaNewDelhi13031710352BrazilBrasília207847528ByPosition>>>df.iloc([0],[0])Selectsinglevaluebyrow&'Belgium'column>>>df.iat([0],[0])'Belgium'ByLabel>>>df.loc([0],['Country'])Selectsinglevaluebyrow&'Belgium'columnlabels>>>df.at([0],['Country'])'Belgium'ByLabel/Position>>>df.ix[2]SelectsinglerowofCountryBrazilsubsetofrowsCapitalBrasíliaPopulation207847528>>>df.ix[:,'Capital']Selectasinglecolumnof0Brusselssubsetofcolumns1NewDelhi2Brasília>>>df.ix[1,'Capital']Selectrowsandcolumns'NewDelhi'BooleanIndexing>>>s[~(s>1)]Seriesswherevalueisnot>1>>>s[(s<-1)|(s>2)]swherevalueis<-1or>2>>>df[df['Population']>1200000000]UsefiltertoadjustDataFrameSetting>>>s['a']=6SetindexaofSeriessto6ApplyingFunctions>>>f=lambdax:x*2>>>df.apply(f)Applyfunction>>>df.applymap(f)Applyfunctionelement-wiseRetrievingSeries/DataFrameInformation>>>df.shape(rows,columns)>>>df.indexDescribeindex>>>df.columnsDescribeDataFramecolumns>>>df.info()InfoonDataFrame>>>df.count()Numberofnon-NAvaluesGettingAlsoseeNumPyArraysSelecting,BooleanIndexing&SettingBasicInformationSummary>>>df.sum()Sumofvalues>>>df.cumsum()Cummulativesumofvalues>>>df.min()/df.max()Minimum/maximumvalues>>>df.idxmin()/df.idxmax()Minimum/Maximumindexvalue>>>df.describe()Summarystatistics>>>df.mean()Meanofvalues>>>df.median()MedianofvaluesDropping>>>s.drop(['a','c'])Dropvaluesfromrows(axis=0)>>>df.drop('Country',axis=1)Dropvaluesfromcolumns(axis=1)DataAlignment>>>s.add(s3,fill_value=0)a10.0b-5.0c5.0d7.0>>>s.sub(s3,fill_value=2)>>>s.div(s3,fill_value=4)>>>s.mul(s3,fill_value=3)>>>s3=pd.Series([7,-2,3],index=['a','c','d'])>>>s+s3a10.0bNaNc5.0d7.0ArithmeticOperationswithFillMethodsInternalDataAlignmentNAvaluesareintroducedintheindicesthatdon’toverlap:Youcanalsodotheinternaldataalignmentyourselfwiththehelpofthefillmethods:Sort&Rank>>>df.sort_index()Sortbylabelsalonganaxis>>>df.sort_values(by='Country')Sortbythevaluesalonganaxis>>>df.rank()AssignrankstoentriesBelgiumBrusselsIndiaNewDelhiBrazilBrasília012CountryCapital111908461303171035207847528PopulationI/OReadandWritetoCSV>>>pd.read_csv('file.csv',header=None,nrows=5)>>>df.to_csv('myDataFrame.csv')ReadandWritetoExcel>>>pd.read_excel('file.xlsx')>>>pd.to_excel('dir/myDataFrame.xlsx',sheet_name='Sheet1')Readmultiplesheetsfromthesamefile>>>xlsx=pd.ExcelFile('file.xls')>>>df=pd.read_excel(xlsx,'Sheet1')>>>help(pd.Series.loc)AskingForHelpReadandWritetoSQLQueryorDatabaseTable>>>fromsqlalchemyimportcreate_engine>>>engine=create_engine('sqlite:///:memory:')>>>pd.read_sql("SELECT*FROMmy_table;",engine)>>>pd.read_sql_table('my_table',engine)>>>pd.read_sql_query("SELECT*FROMmy_table;",engine)>>>pd.to_sql('myDf',engine)read_sql()isaconveniencewrapperaroundread_sql_table()andread_sql_query()