python英文文本高频词统计

统计出现频率最高的20个词，代码：

def getText():
    txt = open('comment.text','r',encoding='utf-8').read()
    txt = txt.lower()
    for ch in '`~!@#$%^&*()_+-={}[];":,./<>?|':
        txt = txt.replace(ch," ")
    return txt


commentText = getText()
words = commentText.split()
# print(words)
counts = {}
for word in words:
    counts[word] = counts.get(word,0)+1
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
print("出现频率最高的20个词：")
print("单词         出现次数")
for i in range(20):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))

结果：