import pandas as pd #importing packages import os as os #pd.describe_option() #describe options for customizing #pd.get_option("display.memory_usage")#setting some options os.getcwd() #current working directory os.chdir('/home/ajay/Desktop') os.getcwd() a=os.getcwd() os.listdir(a) names2=["age","workclass","fnlwgt","education","education-num","marital-status","occupation","relationship","race","sex","capital-gain","capital-loss","hours-per-week","native-country","income"] len(names2) adult=pd.read_csv("adult.data",header=None) len(adult) adult.columns adult.info() adult.head(8) adult.columns= names2 adult.head(30) adult.describe() #numerical summaries workclass=adult.groupby("workclass") len(workclass) workclass.sum() workclass.count() workclass.describe() race=adult.groupby("race") race.sum() race.mean() pd.crosstab(adult.race, adult.workclass) pd.crosstab(adult.race, adult.sex) pd.crosstab(adult.income, adult.sex) pd.crosstab(adult.income, adult.race) adult.corr(method='pearson', min_periods=1)