def remove_frequent_and_infrequent_words(newsgroup):
vectorizer = CountVectorizer(max_df=0.5, min_df=10)
vectors = vectorizer.fit_transform(newsgroup['data'])
vocabulary = voc.get_top_n_words(newsgroup['data'],
len(vectorizer.vocabulary_))
vectorizer = CountVectorizer()
vectors = vectorizer.fit_transform(newsgroup['data'])
vocabulary_with_freq_and_infreq = voc.get_top_n_words(
newsgroup['data'], len(vectorizer.vocabulary_))
i = 0
while i < len(vocabulary_with_freq_and_infreq):
vocabulary_with_freq_and_infreq[i] = vocabulary_with_freq_and_infreq[
i][0]
if i < len(vocabulary):
vocabulary[i] = vocabulary[i][0]
i += 1
print(len(vocabulary))
print(len(vocabulary_with_freq_and_infreq))
remove = []
i = 0
while i < len(vocabulary_with_freq_and_infreq):
if vocabulary_with_freq_and_infreq[i] not in vocabulary:
remove.append(vocabulary_with_freq_and_infreq[i])
i += 1
remove = "|".join(remove)
i = 0
while i < len(newsgroup['data']):
newsgroup['data'][i] = re.sub(r'\b(' + remove + ')\s', ' ',
newsgroup['data'][i])
i += 1
print("Document: ", i, "/", len(newsgroup['data']))
"""
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_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_tfidf_vocabulary(nbr, str_list):
i = 0
avg_f1 = 0
avg_accuracy = 0
while i < 10:
dataset = Dataset(categories)
dataset.split_train_bayers(nbr)
vectorizer = TfidfVectorizer(
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 TF-IDF voc Avg f1: " + avg_f1.__str__(),
"NB TF-IDF voc 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 print_v2_test_docs_vocabulary_labeled(categories):
i = 0
removed_test = 0
print("Printing docs...")
while i < len(categories):
with open(
'../assets/20newsgroups/test2vocabulary_labeled/newsgroups_test_'
+ categories[i] + '.txt', 'w') as f:
lines = [
line.rstrip('\n') for line in
open('../assets/20newsgroups/test/newsgroups_test_' +
categories[i] + '.txt')
]
j = 0
dataset = Dataset(categories)
vectorizer = CountVectorizer(
vocabulary=voc.get_vocabulary_only_labeled(categories))
vectors = vectorizer.fit_transform(dataset.train['data'])
vocabulary = vectorizer.vocabulary_
while j < len(lines):
lines[j] = re.sub(r'[^\w]', " ", lines[j])
lines[j] = re.sub(r'\b[a-zA-Z]\b', " ", lines[j])
lines[j] = re.sub(r'[ \t]+', " ",
lines[j]) # remove extra space or tab
lines[j] = lines[j].strip() + "\n"
remove_doc = 1
words = lines[j].split()
for word in words:
if word in vocabulary.keys():
remove_doc = 0
break
size = len(lines[j])
# lines[j] = lines[j][1:size]
if len(lines[j]) > 4 and not remove_doc:
f.write(lines[j])
else:
removed_test += 1
j += 1
f.close()
i += 1
print("Printing finished")
print("Removed testing doc:", removed_test)
categories = [
'alt.atheism', 'comp.graphics', 'rec.autos', 'sci.space',
'talk.politics.guns'
]
# initialize dataset
dataset = Dataset(categories)
dataset.load_preprocessed(categories)
dataset.split_train_bayers(100)
print_v2_test_docs_vocabulary_labeled(categories)
dataset.load_preprocessed_test_vocabulary_labeled_in_use(categories)
# feature extraction
vectorizer = TfidfVectorizer(
vocabulary=voc.get_vocabulary_only_labeled(categories))
vectors = vectorizer.fit_transform(dataset.train['data'])
print(len(vectorizer.vocabulary_))
clf = MultinomialNB().fit(vectors.todense(), dataset.train['target'])
test_vec = vectorizer.transform(dataset.test['data'])
pred = clf.predict(test_vec.todense())
print('f1 score Naive Bayes: ',
metrics.f1_score(dataset.test['target'], pred, average='macro'))
print('clf score Naive Bayes: ',
clf.score(test_vec.todense(), dataset.test['target']))
np.set_printoptions(precision=2)
# Plot non-normalized confusion matrix
plot_confusion_matrix(
dataset.test['target'],
