Question

我正在尝试删除标点符号并计算话。我的部分代码有效，但我的代码似乎不完整。

def word_distribution(text_string):    
words_list = text_string.split()
words_list = [words_list[i].lower() for i in range(len(words_list))]

for i in range(len(words_list)):
    if not words_list[i].isalpha():
        word = words_list[i]
        for j in word:
            if j != "\'" and  not j.isalpha():
                id = word.find(j)
                words_list[i] = word.replace(word[id],"")

words_dict = {}
for word in words_list:
    if word in words_dict:
        words_dict[word] += 1
    else:
        words_dict[word] = 1    
result = words_dict
return result

word_distribution("Hello,, hello, hi, Hurray!!!, Hurray,  What's up!,Today 
 is Saturday, Saturday, saturday. Funday.")

我正在尝试像{'hello'：2，'hi'：1}这样的单词的字典。它适用于问候词，但适用于Hurray，它给我的输出类似于hurray !!!'：1，'hurray'：1而不是Hurray：2。我不知道为什么会这样。

任何对为什么这样的行为表示赞赏的输入。

Answer 1

您可以使用正则表达式用非字母字符分隔句子。并可以获得结果

import re

def word_distribution(s):
    res = re.split(r'\W+', s)
    counter = {}
    for word in res:
        if not counter.get(word):
            counter[word] = 1
        else:
            counter[word] += 1
    return counter
s = "Hello,, hello, hi, Hurray!!!, Hurray,  What's up!,Today is Saturday, Saturday, saturday. Funday."
print(word_distribution(s))```
#Output:
#{'Hello': 1, 'hello': 1, 'hi': 1, 'Hurray': 2, 'What': 1, 's': 1, 'up': 1, 'Today': 1, 'is': 1, 'Saturday': 2, 'saturday': 1, 'Funday': 1, '': 1}

Answer 2

import re
from collections import Counter

def word_distribution(text_string):
    regex = re.compile('[^a-zA-Z]')
    return Counter(regex.sub('', word.lower()) for word in text_string.split())


s = "Hello,, hello, hi, Hurray!!!, Hurray,  What's up!,Today is Saturday, Saturday, saturday. Funday."

print(word_distribution(s)) #Counter({'saturday': 3, 'hello': 2, 'hurray': 2, 'whats': 1, 'funday': 1, 'is': 1, 'hi': 1, 'uptoday': 1})

计算python

2 个答案: