Python英文词频统计代码

以下是Python实现统计英文文章词频的方法，按照词频从高到低输出前十位的代码实现：

引用:

def words_list():
    with open(r'file_path', 'r') as f:  # 将file_path替换成文章路径
        words = f.read().split()
    return words


def word_dic(words):
    word_dict = {}
    for word in words:
        if word_dict.get(word):  # 如果字典中已经有该单词，次数加1
            word_dict[word] += 1
        else:
            word_dict[word] = 1  # 如果没有出现过，这个单词的计数为1
    return word_dict


def word_fre(word_dict):
    fre_dict = {}
    for key, value in word_dict.items():
        if value in fre_dict:
            fre_dict[value].append(key)  # 如果该单词出现次数已存在，将这个单词添加到次数的数组中
        else:
            fre_dict[value] = [key]  # 如果该单词出现次数不存在，创建次数为key的数组，并将该单词添加进去
    return fre_dict


def word_sort(fre_dict):
    fre_list = list(fre_dict.keys())
    fre_list.sort(reverse=True)
    word_sort_list = []
    for fre in fre_list:
        words = fre_dict[fre]
        if len(words) == 1:
            word_sort_list.append(words + ':' + str(fre))
        else:
            for word in words:
                word_sort_list.append(word + ':' + str(fre))
    return word_sort_list


print(word_sort(word_fre(word_dic(words_list())))[-10:])  # 输出频率前十的单词

引用：

import collections

def words_list():
    with open(r'file_path', 'r') as f:  # 将file_path替换成文章路径
        words = f.read().split()
    return words

words = words_list()
w = collections.Counter(words)
for word,cnt in w.most_common(10):
    print(word + ':' + str(cnt))