import pandas as pd

data = pd.read_csv("nyt1.csv")
data.describe()

print data.shape
data.head()

%pylab inline
data.hist(figsize=(10,8))

##YOUR ANSWER HERE

data1 = data[data.Impressions > 0]

##YOUR ANSWERS HERE
data1['CTR'] = #DEFINE CTR
data1['AgeGroup'] = #DEFINE AgeGroup
data1.head()

print data1.shape
data1.describe()

impressionsByAgeSignIn = data1.groupby(['AgeGroup','Signed_In'])['Clicks'].sum()
impressionsByAgeSignIn.plot(kind='bar')

loggedInCTRsByAgeGroup = data1[(data1.CTR > 0) & (data1.Signed_In > 0)].groupby('AgeGroup').CTR

loggedInCTRsByAgeGroup.describe()

from scipy.stats import ttest_ind

groups = [s for s in loggedInCTRsByAgeGroup]

def run_pairwise_tests(groups):
    for g in groups:
        for g2 in groups:
            if g[0] < g2[0]:
                yield g[0], g2[0], ttest_ind(g[1], g2[1])[1]
            
testResults = pd.DataFrame(run_pairwise_tests(groups))

## YOUR ANSWERS HERE