sklearn----native bayers

from time import time
from sklearn.naive_bayes import MultinomialNB
from sklearn.datasets import load_files
from sklearn.feature_extraction.text import TfidfVectorizer

print("loading train dataset...")
t = time()
new_train = load_files('C:/Users/Jamson/PycharmProjects/my_sklearn/dataset/379/train')
print("summary: {0} documents in {1} categories".format(len(new_train.data), len(new_train.target_names)))
print("done in {0} seconds".format(time() - t))

print("vectorizing train dataset ...")
t = time()
vectorizer = TfidfVectorizer(encoding='latin-1')
X_train = vectorizer.fit_transform((d for d in new_train.data))
print("done in {0} seconds.".format(time() - t))

print("train models ...")
t = time()
y_train = new_train.target
clf = MultinomialNB(alpha=0.0001)
clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
print("train score: {0}".format(train_score