数据分析之AB testing实战(附Python代码)（二）

import pandas as pd
---------------------------------------------------------
# 读取数据，查看前5行
df = pd.read_csv("ab_test.csv")
df.head()
---------------------------------------------------------
# 数据预览，查看数据有多少行、多少列
df.shape
---------------------------------------------------------
# 查看数据中是否有空值
df.isnull().any()
df.info()
---------------------------------------------------------
# 查看数据中的错误行
print((True) != (True))
print((True) != (False))
print((False) != (True))
print((False) != (False))
"""
true  != true   fasle    treatment  new_page
true  != false  true     treatment  old_page
false != true   true     control    new_page
false != false  false    control    old_page
"""
# 下面这句代码，展示的就是group=treatment且landing_page=old_page和group=control且landing_page=new_page，这样的错误行；
num_error = df[((df.group == "treatment")!=(df.landing_page == "new_page"))].shape[0]
num_error
---------------------------------------------------------
# 去掉错误行后，再次查看是否还存在错误行
print("没有删除错误行之前的记录数：", df.shape[0])
df2 = df[~((df.landing_page == "new_page")&(df.group == "control"))]
df3 = df2[~((df2.landing_page == "old_page")&(df2.group == "treatment"))]
print("删除错误行之后的记录数：", df3.shape[0])
print("错误行共有",str(df.shape[0]-df3.shape[0]),"条记录")
num_error2 = df3[((df3.group == "treatment")!=(df3.landing_page == "new_page"))].shape[0]
num_error2
---------------------------------------------------------
# 查看是否有重复行
print("数据的记录数为：", df3.user_id.shape[0])
print("将user_id去重计数后的记录数为：", df3.user_id.nunique())
"""
通过上述分析，可以看出：user_id中有一条记录数是重复的。接下来，我们可以找出这条重复的记录，并去重。
"""
---------------------------------------------------------
# 查看重复的行
df3[df3.user_id.duplicated(keep=False)]
#  去除重复的行
df4 = df3.drop_duplicates(subset=["user_id"],keep="first")
df4.shape[0]
---------------------------------------------------------
# 我们来看一下control组的转化率
control_converted = df4.query('group=="control"').converted.mean()
control_converted
# 再来看一下treatment组的转化率
treatment_converted = df4.query('group=="treatment"').converted.mean()
treatment_converted
"""
自己下去思考一下：根据上述结果，老页面的转化率比新页面的转换率好，是不是就可以说明老页面好呢？
"""
---------------------------------------------------------
# 进行独立两样本的假设检验
import statsmodels.stats.proportion as ssp
converted_old = df4[df4.landing_page == "old_page"].converted.sum()
converted_new = df4[df4.landing_page == "new_page"].converted.sum()
n_old = len(df4[df4.landing_page == "old_page"])
n_new = len(df4[df4.landing_page == "new_page"])
data = pd.DataFrame({"converted":[converted_old, converted_new],
                     "total":[n_old ,n_new]})
display(data)
z_score, p_value = ssp.proportions_ztest(count=data.converted, nobs=data.total, alternative="smaller")
print("Z值为：", z_score)
print("P值为：", p_value)
---------------------------------------------------------