def run_naive_bayes_bow_runtime_vocabulary(nbr, str_list):
i = 0
avg_f1 = 0
avg_accuracy = 0
while i < 10:
dataset = Dataset(categories)
dataset.load_preprocessed(categories)
dataset.split_train_bayers(nbr)
print_v2_test_docs_vocabulary_labeled(categories)
dataset.load_preprocessed_test_vocabulary_labeled_in_use(categories)
vectorizer = CountVectorizer(
vocabulary=Vocabulary.get_vocabulary(categories))
vectors = vectorizer.fit_transform(dataset.train['data'])
clf = MultinomialNB().fit(vectors.todense(), dataset.train['target'])
test_vec = vectorizer.transform(dataset.test['data'])
pred = clf.predict(test_vec.todense())
avg_f1 += metrics.f1_score(dataset.test['target'],
pred,
average='macro')
avg_accuracy += clf.score(test_vec.todense(), dataset.test['target'])
i += 1
avg_accuracy = avg_accuracy / 10
avg_f1 = avg_f1 / 10
str_list.extend([
"NB BOW runtime voc Avg f1: " + avg_f1.__str__(),
"NB BOW runtime voc Avg acc: " + avg_accuracy.__str__()
])
print("Avg f1: " + avg_f1.__str__())
print("Avg acc: " + avg_accuracy.__str__())
def run_naive_bayes_bow(nbr, str_list):
i = 0
avg_f1 = 0
avg_accuracy = 0
while i < 10:
dataset = Dataset(categories)
dataset.split_train_bayers(nbr)
vectorizer = CountVectorizer()
vectors = vectorizer.fit_transform(dataset.train['data'])
clf = MultinomialNB().fit(vectors.todense(), dataset.train['target'])
test_vec = vectorizer.transform(dataset.test['data'])
pred = clf.predict(test_vec.todense())
avg_f1 += metrics.f1_score(dataset.test['target'],
pred,
average='macro')
avg_accuracy += clf.score(test_vec.todense(), dataset.test['target'])
i += 1
avg_accuracy = avg_accuracy / 10
avg_f1 = avg_f1 / 10
str_list.extend([
"NB BOW Avg f1: " + avg_f1.__str__(),
"NB BOW Avg acc: " + avg_accuracy.__str__()
])
print("Avg f1: " + avg_f1.__str__())
print("Avg acc: " + avg_accuracy.__str__())