python - pandas 多索引中的上采样

Question

我正在尝试在分组的 DataFrame 中进行上采样，但不确定如何使其仅在组内进行上采样。我有一个看起来像这样的数据框:

cat      weekstart                  date      
0.0      2016-07-04 00:00:00+00:00  2016-07-04    1
                                    2016-07-06    1
                                    2016-07-07    2
         2016-08-15 00:00:00+00:00  2016-08-16    1
                                    2016-08-19    1
         2016-09-19 00:00:00+00:00  2016-09-20    1
                                    2016-09-21    1
         2016-12-19 00:00:00+00:00  2016-12-19    1
                                    2016-12-21    1

1.0      2016-07-25 00:00:00+00:00  2016-07-26    2
         2016-08-01 00:00:00+00:00  2016-08-03    1
         2016-08-08 00:00:00+00:00  2016-08-12    1

如果我做类似 df.unstack().fillna(0).stack() 的事情会导致:

cat      weekstart                  date      
0.0      2016-07-04 00:00:00+00:00  2016-1-1      0 
                                           .
                                           .
                                           .
                                    2016-07-04    1
                                    2016-07-06    1
                                    2016-07-07    2

因为日期列中的最小值是 2016-1-1。不过，我所追求的只是在每个“猫”和“周开始”内采样工作日，例如:

 cat      weekstart                  date      
 0.0      2016-07-04 00:00:00+00:00  2016-07-04    1
                                     2016-07-05    0 
                                     2016-07-06    1
                                     2016-07-07    2
                                     2016-07-8     0
          2016-08-15 00:00:00+00:00  2016-08-15    0
                                     2016-08-16    1
                                     2016-08-17    0
                                     2016-08-18    0
                                    2016-08-19    1

我尝试过使用:

 level_values = df.index.get_level_values
 df.groupby(
            [level_values(i) for i in [0, 1]] + [pd.Grouper('B', level=-1)]
            )
    .sum()

但它没有按预期工作。

Answer 1

我认为您需要使用 reindex 的自定义功能由 bdate_range 创建的 MultiIndex :

def f(x):
    lvl0 = x.index.get_level_values(0)[0]
    lvl1 = x.index.get_level_values(1)[0]
    lvl2 = pd.bdate_range(start=lvl1, periods=5)
    mux = pd.MultiIndex.from_product([[lvl0], [lvl1], lvl2], names=x.index.names)
    return (x.reindex(mux, fill_value=0))

s1 = s.groupby(['cat','weekstart'], group_keys=False).apply(f)

<小时/>

print (s1)

cat  weekstart   date      
0.0  2016-07-04  2016-07-04    1
                 2016-07-05    0
                 2016-07-06    1
                 2016-07-07    2
                 2016-07-08    0
     2016-08-15  2016-08-15    0
                 2016-08-16    1
                 2016-08-17    0
                 2016-08-18    0
                 2016-08-19    1
     2016-09-19  2016-09-19    0
                 2016-09-20    1
                 2016-09-21    1
                 2016-09-22    0
                 2016-09-23    0
     2016-12-19  2016-12-19    1
                 2016-12-20    0
                 2016-12-21    1
                 2016-12-22    0
                 2016-12-23    0
1.0  2016-07-25  2016-07-25    0
                 2016-07-26    2
                 2016-07-27    0
                 2016-07-28    0
                 2016-07-29    0
     2016-08-01  2016-08-01    0
                 2016-08-02    0
                 2016-08-03    1
                 2016-08-04    0
                 2016-08-05    0
     2016-08-08  2016-08-08    0
                 2016-08-09    0
                 2016-08-10    0
                 2016-08-11    0
                 2016-08-12    1
Name: a, dtype: int64

设置:

d = {(0.0, pd.Timestamp('2016-07-04 00:00:00'), pd.Timestamp('2016-07-07 00:00:00')): 2, (1.0, pd.Timestamp('2016-07-25 00:00:00'), pd.Timestamp('2016-07-26 00:00:00')): 2, (0.0, pd.Timestamp('2016-08-15 00:00:00'), pd.Timestamp('2016-08-16 00:00:00')): 1, (0.0, pd.Timestamp('2016-07-04 00:00:00'), pd.Timestamp('2016-07-04 00:00:00')): 1, (0.0, pd.Timestamp('2016-09-19 00:00:00'), pd.Timestamp('2016-09-20 00:00:00')): 1, (0.0, pd.Timestamp('2016-09-19 00:00:00'), pd.Timestamp('2016-09-21 00:00:00')): 1, (0.0, pd.Timestamp('2016-12-19 00:00:00'), pd.Timestamp('2016-12-19 00:00:00')): 1, (1.0, pd.Timestamp('2016-08-08 00:00:00'), pd.Timestamp('2016-08-12 00:00:00')): 1, (0.0, pd.Timestamp('2016-07-04 00:00:00'), pd.Timestamp('2016-07-06 00:00:00')): 1, (1.0, pd.Timestamp('2016-08-01 00:00:00'), pd.Timestamp('2016-08-03 00:00:00')): 1, (0.0, pd.Timestamp('2016-12-19 00:00:00'), pd.Timestamp('2016-12-21 00:00:00')): 1, (0.0, pd.Timestamp('2016-08-15 00:00:00'), pd.Timestamp('2016-08-19 00:00:00')): 1}
s = pd.Series(d).rename_axis(['cat','weekstart','date'])    
print (s)
cat  weekstart   date      
0.0  2016-07-04  2016-07-04    1
                 2016-07-06    1
                 2016-07-07    2
     2016-08-15  2016-08-16    1
                 2016-08-19    1
     2016-09-19  2016-09-20    1
                 2016-09-21    1
     2016-12-19  2016-12-19    1
                 2016-12-21    1
1.0  2016-07-25  2016-07-26    2
     2016-08-01  2016-08-03    1
     2016-08-08  2016-08-12    1
dtype: int64