Python PANDES基于滚动周期测试值的再现性

基于上述数据帧，我正在尝试解决以下问题： 在（比如）5天的时间内，我想检查

ColN\u ext

值是否按组显示在特定行的前后

ColN

i、 e.我正在尝试创建一个标志：

---

df['flag']=[NaN，0，1，NaN，NaN]

。任何帮助都将不胜感激。

我可以通过定义自定义函数来做到这一点：

import pandas as pd
import numpy as np
df = pd.DataFrame()
df['ColN']=['AAA', 'AAA', 'AAA', 'AAA', 'ABC']
df['ColN_dt']=['03-01-2018', '03-04-2018', '03-05-2018', \
           '03-08-2018', '03-12-2018']
df['ColN_ext']=['A', 'B', 'B', 'B', 'B']
df['ColN_dt'] = pd.to_datetime(df['ColN_dt'])

将numpy导入为np
作为pd进口熊猫
flag_list=[]
def create_标志（dt、lookupdf）：
stdt=dt-lkfwd
enddt=dt+lkfwd
bckset_ext=set（lookupdf.loc[（lookupdf['ColN_dt']>=stdt）&\
（lookupdf['ColN_dt']dt）和\
（lookupdf['ColN_dt']
import numpy as np
import pandas as pd

flag_list = []

def create_flag(dt, lookupdf):
    stdt = dt - lkfwd
    enddt = dt + lkfwd
    bckset_ext = set(lookupdf.loc[(lookupdf['ColN_dt'] >= stdt) & \
                 (lookupdf['ColN_dt'] < dt)]['ColN_ext'])
    fwdset_ext = set(lookupdf.loc[(lookupdf['ColN_dt'] > dt) & \
                 (lookupdf['ColN_dt'] <= enddt)]['ColN_ext'])
    flag_list.append(bool(bckset_ext.intersection(fwdset_ext)))
    return None

# Define the rolling days
lkfwd = pd.Timedelta(days=5)
df = pd.DataFrame()
df['ColN']=['AAA', 'AAA', 'AAA', 'AAA', 'AAA', 'AAA', 'AAA', 'ABC']
df['ColN_dt']=['03-12-2018', '03-13-2018', '03-13-2018', '03-01-2018', '03-05-2018', '03-04-2018', '03-08-2018', '02-04-2018']
df['ColN_ext']=['A', 'B', 'A', 'A', 'B', 'B', 'C', 'A']

df['ColN_dt'] = pd.to_datetime(df['ColN_dt'])
dfs = df.sort_values(by=['ColN', 'ColN_dt']).reset_index(drop=True)

dfg = dfs.groupby('ColN')

for _, grpdf in dfg:
    grpdf['ColN_dt'].apply(create_flag, args=(grpdf,))

dfs['flag'] = flag_list