Question

def hello_worddict(doc):
    string_alpha = ""
    list_of_noalpha = []
    worddict = {}
    newlist = []

    for char in doc:
        if char.isalpha():
            string_alpha += char
        elif char == "'" or char == "-":
            if (string_alpha[-1]).isalpha():
                string_alpha += char
            else:
                string_alpha += " "
                list_of_noalpha.append(char)
        alpha_list = string_alpha.split()

        def remover(char):
            for word in alpha_list:
                if word[-1] == char:
                    del(alpha_list[lpha_list.index(word)])
                    word = word[0:-1]
                    n = alpha_list.append(word)
                    list_of_noalpha.append(char)
        (return what????)

当这样调用时：

hello_worddict("Male, rool, rool, hello 'bro !!!!! \jKr22vy")

应该返回：

output = {"'": 1, 'vy': 1, '!': 5, '2': 2, 'bro': 1, 'rool': 2, 'Male': 1, 'hello': 1, 'Kr': 1, ',': 3}

Answer 1

永远记住Python附带了大量电池。除了字符串中反斜杠的问题之外，这里有一个简单的分割方法：

import re
import collections

def hello_worddict(doc):
    return collections.Counter(
        w for w in re.split(r'(\d+|[a-zA-Z]+|.)', s) if w.strip())

我无法确定以下代码的返回功能是这样的

1 个答案: