AB_TESTING/AB_TESTING.py at main · halepeneklioglu/AB_TESTING · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
import pandas as pd
from scipy.stats import shapiro, levene, ttest_ind

pd.set_option('display.max_columns', None)
pd.set_option('display.expand_frame_repr', False)
pd.set_option('display.float_format', lambda x: '%.5f' % x)

dataframe_control = pd.read_excel("ab_testing.xlsx", sheet_name="Control Group")
dataframe_test = pd.read_excel("ab_testing.xlsx", sheet_name="Test Group")

df_control = dataframe_control.copy()
df_test = dataframe_test.copy()

def check_df(dataframe, head=5):
    print("##################### Shape #####################")
    print(dataframe.shape)
    print("##################### Types #####################")
    print(dataframe.dtypes)
    print("##################### Head #####################")
    print(dataframe.head())
    print("##################### Tail #####################")
    print(dataframe.tail())
    print("##################### NA #####################")
    print(dataframe.isnull().sum())
    print("##################### Quantiles #####################")
    print(dataframe.quantile([0, 0.05, 0.50, 0.95, 0.99, 1]).T)


check_df(df_control)
check_df(df_test)

df_control["group"] = "control"
df_test["group"] = "test"

df_control.head()
df_test.head()

df = pd.concat([df_control, df_test], axis=0, ignore_index=True)

df.groupby("group").agg({"Purchase": "mean"})

test_stat, pvalue = shapiro(df.loc[df["group"] == "control", "Purchase"])
print('Test Stat = %.4f, p-value = %.4f' % (test_stat, pvalue))
# p-value = 0.5891

test_stat, pvalue = shapiro(df.loc[df["group"] == "test", "Purchase"])
print('Test Stat = %.4f, p-value = %.4f' % (test_stat, pvalue))
# p-value = 0.1541

test_stat, pvalue = levene(df.loc[df["group"] == "control", "Purchase"],
                           df.loc[df["group"] == "test", "Purchase"])
print('Test Stat = %.4f, p-value = %.4f' % (test_stat, pvalue))
# p-value = 0.1083

test_stat, pvalue = ttest_ind(df.loc[df["group"] == "control", "Purchase"],
                              df.loc[df["group"] == "test", "Purchase"],
                              equal_var=True)

print('Test Stat = %.4f, p-value = %.4f' % (test_stat, pvalue))
# p-value = 0.3493