词频统计和词云概述

词频统计和词云概述

import jieba
#  分词
word_list = jieba.lcut(chapter.txt[1])
word_list[:10]

import pandas as pd
df = pd.DataFrame(word_list, columns=['word'])
df.head(20)

result = df.groupby(['word']).size()
print(type(result))
freqlist = result.sort_values(ascending=False)
freqlist.head(20)

import nltk
word_list[:10]

fdist = nltk.FreqDist(word_list)  #  生成完整的词条统计词典
fdist