TestTopic.py

from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.datasets import fetch_20newsgroups
import numpy as np


categories = ['alt.atheism', 'soc.religion.christian',
              'comp.graphics', 'sci.med']

twenty_train = fetch_20newsgroups(subset='train',
    categories=categories, shuffle=True, random_state=42)
text_clf = Pipeline([('vect', CountVectorizer()),
                     ('tfidf', TfidfTransformer()),
                     ('clf', MultinomialNB()),
])
text_clf = text_clf.fit(twenty_train.data, twenty_train.target)

twenty_test = fetch_20newsgroups(subset='test',
    categories=categories, shuffle=True, random_state=42)
docs_test = twenty_test.data
predicted = text_clf.predict(docs_test)
print np.mean(predicted == twenty_test.target)