擅长:python、mysql、java
<pre><code>df = pd.DataFrame({'Intersections': {0: 1, 1: 1, 2: 6, 3: 6, 4: 12, 5: 12, 6: 1, 7: 1},
'term_x': {0: 'boxers',1: 'briefs',2: 'babies',3: 'costumes',4: 'babies',
5: 'clothes',6: 'babies',7: 'clothings'}, 'term_y': {0: 'briefs',1: 'boxers',
2: 'costumes',3: 'babies',4: 'clothes',5: 'babies',6: 'clothings',7: 'babies'}})
#create a column to combine team_x and team_y in a sorted order
df['team_xy'] = df.apply(lambda x: str(sorted([x.term_x,x.term_y])), axis=1)
#drop duplicates on the combined fields.
df.drop_duplicates(subset='team_xy',inplace=True)
df
Out[916]:
Intersections term_x term_y team_xy
0 1 boxers briefs ['boxers', 'briefs']
2 6 babies costumes ['babies', 'costumes']
4 12 babies clothes ['babies', 'clothes']
6 1 babies clothings ['babies', 'clothings']
</code></pre>