python文件链接:
http://pan.baidu.com/s/1kVl9W3d
元文件
链接:http://pan.baidu.com/s/1i5GMe49
密码:14i7
====================================
import pandas as pd
import numpy as np
df = pd.read_csv('movie_data.csv')
#数据预处理
from sklearn.feature_extraction.text import CountVectorizer
count = CountVectorizer()
docs = np.array(['How are you?','Fine,thank you','And you?'])
#print(count.fit_transform(docs))
bag = count.fit_transform(docs)
print(count.vocabulary_)
print(bag.toarray())
##对单词进行向量表示
from sklearn.feature_extraction.text import TfidfTransformer
tfidf = TfidfTransformer()
print(tfidf.fit_transform(count.fit_transform(docs)).toarray())
##对数据进行预处理
df.loc[0, 'review'][-50:]