Python文本词频统计（英文）

text文件下载: https://python123.io/resources/pye/hamlet.txt

代码：

# CalHamletV1.py
def get_text():
    txt = open("hamlet.txt", "r").read()
    txt = txt.lower()                           # 将获取到的文章字母变成小写
    for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':       # \：转义字符 \：\
        txt = txt.replace(ch, " ")              # 把乱七八糟的字符用空格替换掉
    return txt


hamletTxt = get_text()
words = hamletTxt.split()                       # 将文章切片
counts = {}                                     # 建立一个空字典
for word in words:
    counts[word] = counts.get(word, 0) + 1      # 为键赋值，若单词存在则值加一，不存在则值为0，顺道加一
items = list(counts.items())                    # 将字典类型变成列表类型
items.sort(key=lambda x:x[1], reverse=True)     # 由大到小排序
for i in range(10):                             # 输出10次，即出现次数最多的10个单词
    word, count = items[i]
    print("{0:<30}{1:>7}".format(word, count))

效果：

the                              1138
and                               965
to                                754
of                                669
you                               550
i                                 542
a                                 542
my                                514
hamlet                            462
in                                436

Process finished with exit code 0