Feature Extraction

print("Extracting features from the training dataset using a sparse vectorizer")
t0 = time()

vectorizer = TfidfVectorizer(max_df = 0.5, max_features = 10000,
                                 min_df = 2, stop_words = 'english',
                                 use_idf = True)
    
X = vectorizer.fit_transform(dataset.data)

print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X.shape)
print()