Python统计中文词频的四种方法小结

import jieba
txt = open("词频统计文本.txt", "r").read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1: #排除单个字符的分词结果
        continue
    else:
        counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word,count))
print ('已统计数量排前10的词')

import jieba
from collections import Counter
with open("词频统计文本.txt", "r",encoding="utf-8") as f:
    words = jieba.lcut(f.read())
    words = [item for item in words if len(item)>1]
counts = Counter(words)
for word,count in counts.most_common(10):
    print(word,count)
print ('已统计数量排前10的词')

import jieba,os
from nltk.probability import FreqDist
with open("词频统计文本.txt","r",encoding="utf-8") as f:
    text = f.read()
words = jieba.lcut(text)
lst = [i for i in words if len(i)>1]
freq = FreqDist(lst)
for item in freq.most_common(10):
    word,count=item
    print(f"{word:<10}\t{count:<5}")
print ('已统计数量排前10的词')

import jieba,os
with open("词频统计文本.txt","r",encoding="utf-8") as f:
    text = f.read()
words = jieba.lcut(text)
lst = [(key,words.count(key)) for key in set(words) if len(key)>1]
items = sorted(lst,key=lambda x:x[1],reverse=True)
for i in range(10):
    word, count = items[i]
    if len(word) == 1: #排除单个字符的分词结果
        continue
    else:
        print(f"{word:<10}\t{count:<5}")
print ('已统计数量排前10的词')