python机器学习第一天——python 高频词处理

 获取文本段前二十个高频词

import csv
import jieba
import sklearn

from sklearn.feature_extraction.text import CountVectorizer
file=open("/Users/yin/Desktop/词频/comment.csv")
reader= csv.reader(file)

data=[]

for info in reader:
    data.append(info)

word=[]

for row in data:
    text=row[0]
    ret = jieba.lcut(text)
    ret=";".join(ret)
    word.append(ret)

vect = CountVectorizer(max_features=20)
X=vect.fit_transform(word)

keywords=vect.get_feature_names()
print(keywords)