# Base
# -----------------------------------
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
# Hypothesis Testing
# -----------------------------------
import scipy.stats as stats
#import the dataset
df = pd.read_csv('/work/Voodoo_Test_Business_Case.csv', delimiter = ';')
#check the dataset
df.columns
df.info()
# We can observe that the dataset is composed of 372834 observations and 18 features.
# Moreover, there is no missing data.
df.head()
#Number of Unique User
df.user_id.nunique()
# Summary Stats: publisher_revenue
df.describe([0.01, 0.05, 0.10, 0.20, 0.80, 0.90, 0.95, 0.99])[["publisher_revenue"]].T
#histogram
sns.distplot(df['publisher_revenue']);
# Summary Stats: session_number_
df.describe([0.01, 0.05, 0.10, 0.20, 0.80, 0.90, 0.95, 0.99])[["session_number_"]].T
#histogram
sns.distplot(df['session_number_']);
df['session_number_'].plot.box(figsize=(5,10))
df.groupby('ab_cohort_name')['user_id'].count()
df.groupby("ab_cohort_name").publisher_revenue.describe()
df.groupby("ab_cohort_name").session_number_.describe()
# Let's create different datasets for each groups we want to test.
data_control = df[df['ab_cohort_name'] == "control"] #only users that are in the control group.
data_xHigh = df[df['ab_cohort_name'] == "xHigh"] #only users that are in the xHigh group.
data_xxHigh = df[df['ab_cohort_name'] == "xxHigh"] #only users that are in the xxHigh group.
#We first compare the 'control' group's revenue with those generated from the 'xHigh' group.
t_stat, p_val= stats.ttest_ind(data_control['publisher_revenue'], data_xHigh['publisher_revenue'])
t_stat , p_val
#Then we compare the 'control' group's revenue with those generated from the 'xxHigh' group.
t_stat, p_val= stats.ttest_ind(data_control['publisher_revenue'], data_xxHigh['publisher_revenue'])
t_stat , p_val
#Finally we compare the 'xHigh' group's revenue with those generated from the 'xxHigh' group.
t_stat, p_val= stats.ttest_ind(data_xHigh['publisher_revenue'], data_xxHigh['publisher_revenue'])
t_stat , p_val
