def words(word,number):
if number<len(word):
result={}
for key,value in word.items():
common_num=sorted(set(word.values()), reverse=True)[:number]
if value in common_num:
result.update({key:value})
word.clear()
word.update(result)
new_word_count={}
common_word=[]
common=[]
for key, value in word.items():
if value in common_word:
common.append(value)
common_word.append(value)
new_word_count=dict(word)
for key,value in new_word_count.items():
if value in common:
del word[key]
示例:
>>> word={'a': 2, 'b': 2, 'c' : 3, 'd: 3, 'e': 4, 'f' : 4, 'g' : 5}
>>> words(word,3)
我的输出:{'g':5}
预期输出:{'g':5,'e':4,'f':4}
知道为什么我得到这个输出
答案 0 :(得分:3)
嗯,没有任何特殊的进口,有更简单的方法来完成你想要做的事情。你可以通过跟踪和存储保存的值,然后删除,然后重新添加,在你可以简化很多事情时参与其中。即使有解释性评论,这也要短得多:
def common_words(word_count, number):
# Early out when no filtering needed
if number >= len(word_count):
return
# Get the top number+1 keys based on their values
top = sorted(word_count, key=word_count.get, reverse=True)[:number+1]
# We kept one more than we needed to figure out what the tie would be
tievalue = word_count[top.pop()]
# If there is a tie, we keep popping until the tied values are gone
while top and tievalue == word_count[top[-1]]:
top.pop()
# top is now the keys we should retain, easy to compute keys to delete
todelete = word_count.keys() - top
for key in todelete:
del word_count[key]
有一些更好的方法可以避免在word_count
中重复查找(排序items
,而不是keys
等),但这更容易理解IMO,以及word_count
中的额外查找是有界的和线性的,所以这不是什么大问题。
答案 1 :(得分:1)
虽然在评论中作者提到避免Counter()
,但对于那些有兴趣了解如何应用它的人来说,这是@ShadowRanger建议的简短解决方案:
import collections as ct
word={'a': 2, 'b': 2, 'c' : 3, 'd': 3, 'e': 4, 'f' : 4, 'g' : 5}
words = ct.Counter(word)
words.most_common(3)
# [('g', 5), ('f', 4), ('e', 4)]