sklearn_ex1.py 文件源码

def case1():
    from sklearn import datasets
    news = datasets.fetch_20newsgroups(subset='all')
    # print len(news.data)
    # print len(news.target)

    # print '*'*10
    # print news.data[0]
    # print '*'*10
    # print news.target[0]
    from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
    vec = CountVectorizer()
    x = vec.fit_transform(news.data)
    # print x.shape
    # print x[:2]
    print x[:10,:10].toarray()
    TFIDF = TfidfTransformer()
    x_tfidf = TFIDF.fit_transform(x)
    print x_tfidf[:10,:10].toarray()


    from sklearn.cross_validation import train_test_split
    Xtrain, Xtest, ytrain,ytest =train_test_split(x,news.target,test_size = 0.3,random_state=233)

    tf_Xtrain, tf_Xtest, tf_ytrain,tf_ytest =train_test_split(x_tfidf,news.target,test_size = 0.3,random_state=233)


    from sklearn.naive_bayes import MultinomialNB
    mnb =MultinomialNB()
    tf_mnb = MultinomialNB()

    mmb.fit(Xtrain,ytrain)
    tf_mnb.fit(tf_Xtrain,tf_ytrain)