Pandas 同元素多列去重的实例

G1 G2
a b
b a
c d
d c
e f

G1 G2
a b
c d
e f

#-*- coding: utf-8 -*-
data = {'G1':['a','b','c','d','e'],'G2':['b','a','d','c','f']}
data = pd.DataFrame(data)
data['G3'] = data['G1'] + '|' + data['G2']
p = []
for i in data['G3'].tolist():
  tmp = sorted(i.split('|')) # The most important part,sort 
  p.append(tmp[0] + '|' + tmp[1])
data['G3'] = pd.Series(p)
data = data.drop_duplicates('G3')