data_train = datasets.fetch_20newsgroups(subset = 'train', shuffle = True,  random_state = 2016, remove = ('headers', 'footers', 'quotes'))
data_test = datasets.fetch_20newsgroups(subset = 'test', shuffle = True, random_state = 2016, remove = ('headers', 'footers', 'quotes'))
categories = data_train.target_names

target_map = {}

for i in range(len(categories)):
    if 'comp.' in categories[i]:
        target_map[i] = 0
    elif 'rec.' in categories[i]:
        target_map[i] = 1
    elif 'sci.' in categories[i]:
        target_map[i] = 2
    elif 'misc.forsale' in categories[i]:
        target_map[i] = 3
    elif 'talk.politics' in categories[i]:
        target_map[i] = 4
    else:
        target_map[i] = 5

y_temp = data_train.target
y_train = []

for y in y_temp:
    y_train.append(target_map[y])

y_temp = data_test.target
y_test = []

for y in y_temp:
    y_test.append(target_map[y])

count_vectorizer = feature_extraction.text.CountVectorizer(min_df = 0.01, max_df = 0.5, stop_words = 'english')
x_train = count_vectorizer.fit_transform(data_train.data)
x_test = count_vectorizer.transform(data_test.data)

feature_names= count_vectorizer.get_feature_names()

mnb_alpha_001  = naive_bayes.MultinomialNB(alpha = 0.01)

mnb_alpha_001.fit(x_train, y_train)

y_pred_001  = mnb_alpha_001.predict(x_test)

print('Accuracy Of MNB With Alpha = 0.01  : ', metrics.accuracy_score(y_test,y_pred_001))

diff = mnb_alpha_001.feature_log_prob_[1,:] - mnb_alpha_001.feature_log_prob_[0,:]
name_diff = {}
for i in range(len(feature_names)):
    name_diff[feature_names[i]] = diff[i]
names_diff_sorted = sorted(name_diff.items(), key = operator.itemgetter(1), reverse = True)
for i in range(10):
    print(names_diff_sorted[i])