背景：有一个list，里面的每一个元素都是dict，根据某一个key进行去重，在这里，key代表question
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# created by fhqplzj on 2017/12/07 上午11:38
from itertools import groupby
from operator import itemgetter
import pandas as pd
def distinct(items):
questions = map(itemgetter('question'), items)
df = pd.DataFrame({
'items': items,
'questions': questions
})
return df.drop_duplicates(['questions'])['items'].tolist()
def distinct2(items):
exist_questions = set()
result = []
for item in items:
question = item['question']
if question not in exist_questions:
exist_questions.add(question)
result.append(item)
return result
def distinct3(items):
key = itemgetter('question')
items = sorted(items, key=key)
return [next(v) for _, v in groupby(items, key=key)]
def distinct4(items):
from itertools import compress
mask = (~pd.Series(map(itemgetter('question'), items)).duplicated()).tolist()
return list(compress(items, mask))
if __name__ == '__main__':
data = [
{'question': 'a', 'ans': 'b'},
{'question': 'b', 'ans': 'd'},
{'question': 'a', 'ans': 'p'},
{'question': 'b', 'ans': 'e'}
]
print distinct4(data)
以上这篇python去重,一个由dict组成的list的去重示例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。