from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB

data = datasets.fetch_20newsgroups()
X = data.data
y = data.target

x_train, x_test, y_train, y_test = train_test_split(X, y, random_state=1, test_size=0.3)

vectorizer = TfidfVectorizer(stop_words="english")
x_train_vec = vectorizer.fit_transform(x_train)
x_test_vec = vectorizer.transform(x_test)

model = MultinomialNB()
model.fit(x_train_vec, y_train)

y_pred = model.predict(x_test_vec)

for i in range(9):
    print("\nText:", x_test[i][:100], "...")
    print("Actual:", data.target_names[y_test[i]])
    print("Predicted:", data.target_names[y_pred[i]])