pandas如何找到连续/不连续的0

import pandas as pd

df = pd.DataFrame({
    'names': ['A','B','C','D','E','F','G','H','I','J','K','L'],
    'col1': [0, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0],
    'col2': [0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0]})

names   col1    col2
A   0   0
B   1   0
C   0   0
D   1   0
E   1   1
F   1   0
G   0   1
H   0   0
I   0   1
J   1   0
K   0   0
L   0   0


def f(col, threshold=3):
    mask = col.groupby((col != col.shift()).cumsum()).transform('count').lt(threshold)
    mask &= col.eq(0)
    col.update(col.loc[mask].replace(0,1))
    return col

In [79]: df.apply(f, threshold=3)
Out[79]:
       col1  col2
names
A         1     0
B         1     0
C         1     0
D         1     0
E         1     1
F         1     1
G         0     1
H         0     1
I         0     1
J         1     0
K         1     0
L         1     0

step by step

In [84]: col = df['col2']

In [85]: col
Out[85]:
names
A    0
B    0
C    0
D    0
E    1
F    0
G    1
H    0
I    1
J    0
K    0
L    0
Name: col2, dtype: int64

In [86]: (col != col.shift()).cumsum()
Out[86]:
names
A    1
B    1
C    1
D    1
E    2
F    3
G    4
H    5
I    6
J    7
K    7
L    7
Name: col2, dtype: int32

In [87]: col.groupby((col != col.shift()).cumsum()).transform('count')
Out[87]:
names
A    4
B    4
C    4
D    4
E    1
F    1
G    1
H    1
I    1
J    3
K    3
L    3
Name: col2, dtype: int64

In [88]: col.groupby((col != col.shift()).cumsum()).transform('count').lt(3)
Out[88]:
names
A    False
B    False
C    False
D    False
E     True
F     True
G     True
H     True
I     True
J    False
K    False
L    False
Name: col2, dtype: bool

In [89]: col.groupby((col != col.shift()).cumsum()).transform('count').lt(3) & col.eq(0)
Out[89]:
names
A    False
B    False
C    False
D    False
E    False
F     True
G    False
H     True
I    False
J    False
K    False
L    False
Name: col2, dtype: bool

reference: https://datascience.stackexchange.com/questions/20587/find-the-consecutive-zeros-in-a-dataframe-and-do-a-conditional-replacement