Untitled Python Project

import numpy as np

import pandas as pd

## 提取数据并处理列名 df=pd.read_csv('/datasets/data1/effect_tb.csv',header=None,names=["date","uid","click","type"],encoding='gb18030')

!ls /datasets/data1

effect_tb.csv

# 查看信息 df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 0 entries
Data columns (total 4 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   date    0 non-null      object
 1   uid     0 non-null      object
 2   click   0 non-null      object
 3   type    0 non-null      object
dtypes: object(4)
memory usage: 0.0+ bytes

#重复值 df.duplicated().sum()

#查看缺失值 df.isnull().sum()

#实验组2 df[(df["type"]==3)]["click"].mean()

#实验组1 df[(df["type"]==2)]["click"].mean()

#对照组 df[(df["type"]==1)]["click"].mean()

#检测 # 用户数 n_old = len(df[df.type == 1]) # 对照组 n_new = len(df[df.type == 3]) # 策略二

#点击数 c_old = df[(df.type ==1)&(df.click == 1)]["uid"].count() c_new = df[(df.type ==3)&(df.click == 1)]["uid"].count()

import statsmodels.stats.proportion as sp z_score, p = sp.proportions_ztest([c_old, c_new],[n_old, n_new], alternative = "smaller") print("检验统计量z：",z_score,"，p值：", p)

检验统计量z： -59.66600946268368 ，p值： 0.0

# 查α=0.05对应的z分位数 from scipy.stats import norm z_alpha = norm.ppf(0.05) z_alpha

# 策略一检验f z_score, p = sp.proportions_ztest([c_old, len(df[df.type ==2][df.click == 1])], [n_old, len(df[df.type == 2])], alternative = "smaller") print("检验统计量z：",z_score,"，p值：", p)

检验统计量z： -14.362726203811503 ，p值： 4.433468512724253e-47

D:\software\anaconda\lib\site-packages\ipykernel_launcher.py:2: UserWarning: Boolean Series key will be reindexed to match DataFrame index.

df_ka = pd.DataFrame(columns = ['用户数','点击数'],index = ['对照','策略2'], data=[[n_old,c_old],[n_new,c_new]]) df_ka['未点击'] = df_ka["用户数"]- df_ka['点击数'] df_ka

df_ka2=df_ka[["点击数","未点击"]]

from scipy import stats

stats.chi2_contingency(observed=df_ka2)

# 用户数 n_new2 = len(df[df.type == 2]) # 策略二 #点击数 c_new2 = df[(df.type ==2)&(df.click == 1)]["uid"].count()

df_ka3 = pd.DataFrame(columns = ['用户数','点击数'],index = ['对照','策略1'], data=[[n_old,c_old],[n_new2,c_new2]]) df_ka3['未点击'] = df_ka3["用户数"]- df_ka3['点击数'] df_ka3

stats.chi2_contingency(observed=df_ka3)