def run_lp_bow_runtime_vocabulary(nbr, str_list, neighbors):
i = 0
avg_f1 = 0
avg_accuracy = 0
while i < 10:
dataset = Dataset(categories)
dataset.load_preprocessed(categories)
dataset.split_train_true(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 = LabelSpreading(kernel='knn', n_neighbors=neighbors).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(["KNN BOW runtime voc Avg f1: " + avg_f1.__str__(), "KNN BOW runtime vod Avg acc: "
+ avg_accuracy.__str__()])
print("Avg f1: " + avg_f1.__str__())
print("Avg acc: " + avg_accuracy.__str__())
def run_lp_bow_vocabulary(nbr, str_list, gamma):
i = 0
avg_f1 = 0
avg_accuracy = 0
while i < 10:
dataset = Dataset(categories)
dataset.split_train_true(nbr)
vectorizer = CountVectorizer(
vocabulary=Vocabulary.get_vocabulary(categories))
vectors = vectorizer.fit_transform(dataset.train['data'])
clf = LabelPropagation(kernel='rbf',
gamma=gamma).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([
"RBF BOW voc Avg f1: " + avg_f1.__str__(),
"RBF BOW voc Avg acc: " + avg_accuracy.__str__()
])
print("Avg f1: " + avg_f1.__str__())
print("Avg acc: " + avg_accuracy.__str__())
def run_lp_tfidf(nbr, str_list, neighbors):
i = 0
avg_f1 = 0
avg_accuracy = 0
while i < 10:
dataset = Dataset(categories)
dataset.split_train_true(nbr)
vectorizer = TfidfVectorizer()
vectors = vectorizer.fit_transform(dataset.train['data'])
clf = LabelSpreading(kernel='knn', n_neighbors=neighbors).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(["KNN TF-IDF Avg f1: " + avg_f1.__str__(), "KNN TF-IDF Avg acc: " + avg_accuracy.__str__()])
print("Avg f1: " + avg_f1.__str__())
print("Avg acc: " + avg_accuracy.__str__())
'sci.space',
'soc.religion.christian',
'talk.politics.guns',
'talk.politics.mideast',
'talk.politics.misc',
'talk.religion.misc']
"""
categories = [
'rec.autos', 'rec.motorcycles', 'rec.sport.baseball', 'rec.sport.hockey'
]
# initialize dataset
dataset = Dataset(categories)
dataset.load_preprocessed(categories)
dataset.split_train_true(10)
print_v2_test_docs_vocabulary_labeled(categories)
dataset.load_preprocessed_test_vocabulary_labeled_in_use(categories)
dataset_knn = Dataset(categories)
dataset_knn.load_preprocessed_vocabulary_in_use(categories)
dataset_knn.split_train_true(10)
print_v2_test_docs_vocabulary_labeled(categories)
dataset_knn.load_preprocessed_test_vocabulary_labeled_in_use(categories)
# feature extraction
vectorizer_rbf = TfidfVectorizer(
vocabulary=voc.get_vocabulary_only_labeled(categories))
vectorizer_knn = TfidfVectorizer(
vocabulary=voc.get_vocabulary_only_labeled(categories))
vectors = vectorizer_rbf.fit_transform(dataset.train['data'])
'sci.space',
'soc.religion.christian',
'talk.politics.guns',
'talk.politics.mideast',
'talk.politics.misc',
'talk.religion.misc']
"""
categories = ['rec.autos',
'rec.motorcycles',
'rec.sport.baseball',
'rec.sport.hockey']
# initialize dataset
dataset_rbf = Dataset(categories)
dataset_rbf.split_train_true(100)
dataset_knn = Dataset(categories)
dataset_knn.split_train_true(100)
# feature extraction
vectorizer_rbf = TfidfVectorizer()
vectorizer_knn = TfidfVectorizer()
vectors_rbf = vectorizer_rbf.fit_transform(dataset_rbf.train['data'])
vectors_knn = vectorizer_knn.fit_transform(dataset_knn.train['data'])
# classification
# use max_iter=10 when 20 categories
clf_rbf = LabelPropagation(kernel='rbf', gamma=5).fit(vectors_rbf.todense(), dataset_rbf.train['target'])
clf_knn = LabelSpreading(kernel='knn', n_neighbors=10).fit(vectors_knn.todense(), dataset_knn.train['target'])
test_vec_rbf = vectorizer_rbf.transform(dataset_rbf.test['data'])
test_vec_knn = vectorizer_knn.transform(dataset_knn.test['data'])