Groupby shift apply 测试 计算每小时 各站的出入人数

ridership_df = pd.DataFrame({
    'UNIT': ['R051', 'R079', 'R051', 'R079', 'R051', 'R079', 'R051', 'R079', 'R051'],
    'TIMEn': ['00:00:00', '02:00:00', '04:00:00', '06:00:00', '08:00:00', '10:00:00', '12:00:00', '14:00:00', '16:00:00'],
    'ENTRIESn': [3144312, 8936644, 3144335, 8936658, 3144353, 8936687, 3144424, 8936819, 3144594],
    'EXITSn': [1088151, 13755385,  1088159, 13755393,  1088177, 13755598, 1088231, 13756191,  1088275]
})

def hourly_for_group(entries_and_exits):
    return entries_and_exits - entries_and_exits.shift()
    
def get_hourly_entries_and_exits(entries_and_exits):
    return entries_and_exits.groupby('UNIT')[['ENTRIESn','EXITSn']].apply(hourly_for_group)

print get_hourly_entries_and_exits(ridership_df)

   ENTRIESn  EXITSn
0       NaN     NaN
1       NaN     NaN
2      23.0     8.0
3      14.0     8.0
4      18.0    18.0
5      29.0   205.0
6      71.0    54.0
7     132.0   593.0
8     170.0    44.0