- Use pandas.Series.str.split将字符串拆分为
list
.
# use str split on the column
df.mgrs_grids = df.mgrs_grids.str.split(',')
# display(df)
driver_code journey_code mgrs_grids
0 7211863 7211863-140 [18TWL927129, 18TWL888113, 18TWL888113, 18TWL887113, 18TWL888113, 18TWL887113, 18TWL887113, 18TWL887113, 18TWL903128]
1 7211863 7211863-105 [18TWL927129, 18TWL939112, 18TWL939112, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL960111, 18TWL960112]
2 7211863 7211863-50 [18TWL927129, 18TWL889085, 18TWL889085, 18TWL888085, 18TWL888085, 18TWL888085, 18TWL888085, 18TWL888085, 18TWL890085]
3 7211863 7211863-109 [18TWL927129, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952105, 18TWL951103]
print(type(df.loc[0, 'mgrs_grids']))
[out]:
list
每个值单独行
- 创建一列列表后。
- Use pandas.DataFrame.explode为列表中的每个值创建单独的行。
# get a separate row for each value
df = df.explode('mgrs_grids').reset_index(drop=True)
# display(df.hea())
driver_code journey_code mgrs_grids
0 7211863 7211863-140 18TWL927129
1 7211863 7211863-140 18TWL888113
2 7211863 7211863-140 18TWL888113
3 7211863 7211863-140 18TWL887113
4 7211863 7211863-140 18TWL888113
Update
- Here is another option, which combines the
'journey_code'
to the front of 'mgrs_grids'
, and then splits the string into a list.
- 该列表被分配回
'mgrs_grids'
,但也可以分配给新列。
# add the journey code to mgrs_grids and then split
df.mgrs_grids = (df.journey_code + ',' + df.mgrs_grids).str.split(',')
# display(df.head())
driver_code journey_code mgrs_grids
0 7211863 7211863-140 [7211863-140, 18TWL927129, 18TWL888113, 18TWL888113, 18TWL887113, 18TWL888113, 18TWL887113, 18TWL887113, 18TWL887113, 18TWL903128]
1 7211863 7211863-105 [7211863-105, 18TWL927129, 18TWL939112, 18TWL939112, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL939113, 18TWL960111, 18TWL960112]
2 7211863 7211863-50 [7211863-50, 18TWL927129, 18TWL889085, 18TWL889085, 18TWL888085, 18TWL888085, 18TWL888085, 18TWL888085, 18TWL888085, 18TWL890085]
3 7211863 7211863-109 [7211863-109, 18TWL927129, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952106, 18TWL952105, 18TWL951103]
# output to nested list
df.mgrs_grids.tolist()
[out]:
[['7211863-140', '18TWL927129', '18TWL888113', '18TWL888113', '18TWL887113', '18TWL888113', '18TWL887113', '18TWL887113', '18TWL887113', '18TWL903128'],
['7211863-105', '18TWL927129', '18TWL939112', '18TWL939112', '18TWL939113', '18TWL939113', '18TWL939113', '18TWL939113', '18TWL939113', '18TWL939113', '18TWL960111', '18TWL960112'],
['7211863-50', '18TWL927129', '18TWL889085', '18TWL889085', '18TWL888085', '18TWL888085', '18TWL888085', '18TWL888085', '18TWL888085', '18TWL890085'],
['7211863-109', '18TWL927129', '18TWL952106', '18TWL952106', '18TWL952106', '18TWL952106', '18TWL952106', '18TWL952106', '18TWL952106', '18TWL952105', '18TWL951103']]