Tathagatd96

#tf-idf
tfidf_transformer=TfidfTransformer()

X_train_tfidf=tfidf_transformer.fit_transform(X_train_counts)
print(X_train_tfidf.shape)

Tathagatd96

#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)

Tathagatd96

#Building a pipeline

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

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

Tathagatd96

#Performance on test set

twenty_test=fetch_20newsgroups(subset='test',categories=categories,shuffle=True,random_state=42)
doc_test=twenty_test.data
predicted=text_clf.predict(doc_test)
print "Classifier Accuracy:"
print(np.mean(predicted==twenty_test.target))

Tathagatd96

#SVM Implementation

text_clf=Pipeline([('vect',CountVectorizer()),('tfidf',TfidfTransformer()),('clf',SGDClassifier(loss='hinge',alpha=1e-3,n_iter=5,random_state=42))])
text_clf.fit(twenty_train.data,twenty_train.target)
predicted=text_clf.predict(doc_test)

print "SVM Accuracy:"
print(np.mean(predicted==twenty_test.target))

Tathagatd96

2257

From: [email protected] (Michael Collier)
Subject: Converting images to HP LaserJet III?
Nntp-Posting-Host: hampton

comp.graphics

[1 1 3 3 3 3 3 2 2 2]

Tathagatd96

(2257, 35788)
4690
(2257, 35788)

Tathagatd96

'God is love'=>soc.religion.christian
'OpenGL on the GPU is fast'=>comp.graphics

Tathagatd96

Classifier Accuracy:
0.834886817577

Tathagatd96

SVM Accuracy:
0.912782956059