Training and validation

training-validation.py

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn import metrics

vectorizer = TfidfVectorizer()
vectors = vectorizer.fit_transform(newsgroups_train_enriched)
clf = MultinomialNB(alpha=.01)
clf.fit(vectors, newsgroups_train.target)

newsgroups_test = fetch_20newsgroups(subset='test', remove=('headers', 'footers', 'quotes'), categories=categories)
vectors_test = vectorizer.transform(newsgroups_test.data)
pred = clf.predict(vectors_test)
print(metrics.f1_score(pred, newsgroups_test.target, average='macro'))