选项 2 对我来说听起来最合乎逻辑,尤其是使用 defaultdict 它应该很容易做到:)
import pprint
import collections
data = '''ID1 ID2 ID3
ID1 ID4 ID5
ID3 ID5 ID7 ID6'''
groups = collections.defaultdict(set)
for row in data.split('\n'):
cols = row.split()
for groupcol in cols:
for col in cols:
if col is not groupcol:
groups[groupcol].add(col)
pprint.pprint(dict(groups))
结果:
{'ID1': set(['ID2', 'ID3', 'ID4', 'ID5']),
'ID2': set(['ID1', 'ID3']),
'ID3': set(['ID1', 'ID2', 'ID5', 'ID6', 'ID7']),
'ID4': set(['ID1', 'ID5']),
'ID5': set(['ID1', 'ID3', 'ID4', 'ID6', 'ID7']),
'ID6': set(['ID3', 'ID5', 'ID7']),
'ID7': set(['ID3', 'ID5', 'ID6'])}