gistfile1.txt

#Classifier Training


clf=MultinomialNB().fit(X_train_tfidf,twenty_train.target)

docs_new=['God is love','OpenGL on the GPU is fast']
X_new_counts=count_vect.transform(docs_new)
X_new_tfidf=tfidf_transformer.transform(X_new_counts)

predicted=clf.predict(X_new_tfidf)

for doc,category in zip(docs_new,predicted):
    print('%r=>%s'%(doc,twenty_train.target_names[category]))
    
    
#Building a pipeline

text_clf=Pipeline([('vect',CountVectorizer()),('tfidf',TfidfTransformer()),('clf',MultinomialNB())])

text_clf=text_clf.fit(twenty_train.data,twenty_train.target)

clf = Pipeline([
    ('vec', CountVectorizer(analyzer=analyzer)),
    ('tfidf', TfidfTransformer(use_idf=False)),
    ('clf', LinearSVC(loss='l2', penalty='l1', dual=False, C=100)),
])