def remove_stop_postag(dataset, output_dir):
utils.mkdir(output_dir)
stack = os.listdir(dataset)
# print 'loading data in ' + dataset
total_doc = 0
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)): # neu la thu muc thi day vao strong stack
utils.push_data_to_stack(stack, file_path, file_name)
else:
with open(file_path, 'r', encoding='utf-8') as fr:
data = unicodedata.normalize('NFKC', fr.read().strip())
original_content = tokenizer.predict(data)
content = map(lambda x: ViPosTagger.postagging(x),
spliter.split(original_content))
clean_content = []
for info in content:
sen = []
for i in xrange(len(info[0])):
if is_exist(info[1][i]):
sen.append(info[0][i])
clean_content.append(u' '.join(sen))
with open(os.path.join(output_dir, os.path.basename(file_name)),
'w', encoding='utf-8') as fw:
if len(clean_content) > 0:
fw.write(u'\n'.join(clean_content))
else: fw.write(original_content)
total_doc += 1
def load_dataset_from_disk(dataset):
list_samples = {k: [] for k in my_map.name2label.keys()}
print(list_samples)
print 'load_data in ' + dataset
# return list file and folder in dir
stack = os.listdir(dataset)
while len(stack) > 0:
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
# where is file_path
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
print('%s' % file_path)
sys.stdout.flush()
with open(file_path, 'r', encoding='utf-16') as fp:
content = unicodedata.normalize('NFKC', fp.read())
#tokenizer content
content = r.run(tokenizer.predict(content))
#dir name of file_path
dir_name = utils.get_dir_name(file_path)
list_samples[dir_name].append(content)
print('')
return list_samples
def load_document_content(dataset, documents):
stack = os.listdir(dataset)
while (len(stack) > 0):
file_name = stack.pop()
file_path = dataset + '/' + file_name
if (os.path.isdir(file_path)
): # neu la thu muc thi day vao strong stack
utils.push_data_to_stack(stack, file_path, file_name)
else:
with open(file_path, 'r', encoding='utf-8') as f:
try:
raw_content = unicodedata.normalize(
'NFKC',
f.read().strip()).split(u'\n')
new_content = []
for i, sen in enumerate(raw_content):
if i == 0:
# highlight title
sen = u'<h2>' + sen + u'</h2>'
elif i == 1:
sen = u'<h5>' + sen + u'</h5>'
else:
sen = sen + u'<br>'
new_content.append(sen)
documents.update(
{raw_content[0].lower(): u'\n'.join(new_content)})
except:
continue
def build_vocab(dataset, output_vocab, root_dir, title_map):
vectorizer = TfidfVectorizer(ngram_range=(1, 1),
max_df=0.6,
min_df=1,
stop_words=utils.load_data_from_list(
os.path.join(root_dir, 'stopwords.txt')))
stack = os.listdir(dataset)
contents = []
titles = []
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)
): # neu la thu muc thi day vao strong stack
utils.push_data_to_stack(stack, file_path, file_name)
else:
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
base = os.path.basename(file_name)
titles.append(title_map[base])
contents.append(content.lower())
# change vectorizer to ensure length of document greater than 0
if len(contents) < 50:
vectorizer.max_df = 1.0
vectorizer.fit(contents)
with open(output_vocab, 'w', encoding='utf-8') as f:
vocab = {w: i for i, w in enumerate(vectorizer.vocabulary_.keys())}
f.write(u'\n'.join(vocab.keys()))
return contents, titles
def update_title_map(dataset, title_map):
stack = os.listdir(dataset)
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)
): # neu la thu muc thi day vao strong stack
utils.push_data_to_stack(stack, file_path, file_name)
else:
with open(file_path, 'r', encoding='utf-8') as f:
data = unicodedata.normalize('NFKC', f.read().strip())
title = data.lower().split(u'\n')[0]
base = os.path.basename(file_name)
title_map.update({base: title})
def load_data_from_file(dataset):
data = {}
stack = os.listdir(dataset)
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
img = cv2.imread(file_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
loan_id = file_name.split('_')[2].split('.')[0]
data[loan_id] = gray
return data
def load_data_from_file(dataset):
data = {}
stack = os.listdir(dataset)
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
img = cv.imread(file_path)
loan_id = file_name.split('_')[2].split('.')[0]
img = padding_img(img, max_width, max_height)
img = padding_img(img, final_width, final_height)
data[loan_id] = img
return data
def load_dataset(dataset):
list_samples = {k: [] for k in my_map.name2label.keys()}
stack = os.listdir(dataset)
print 'loading data in ' + dataset
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
print(file_path)
with open(file_path, 'r', encoding='utf-16') as fp:
content = unicodedata.normalize('NFKC', fp.read())
content = r.run(tokenizer.predict(content))
dir_name = utils.get_dir_name(file_path)
list_samples[dir_name].append(content)
return list_samples
def parse_training_data(dataset, output):
docs = []
utils.mkdir(output)
stack = os.listdir(dataset)
print 'loading data in ' + dataset
while (len(stack) > 0):
file_name = stack.pop()
file_path = dataset + '/' + file_name
if (os.path.isdir(file_path)
): # neu la thu muc thi day vao strong stack
utils.push_data_to_stack(stack, file_path, file_name)
else: # nguoc lai tien hanh readfile
with open(file_path, 'r', encoding='utf-8') as ff:
content = ff.read()
bs = BeautifulSoup(content)
docs.append([bs.text])
# with open(output + '/' + file_name, 'w', encoding='utf-8') as f:
# f.write(bs.text)
return docs
def load_data_from_file(dataset):
data = {}
stack = os.listdir(dataset)
max_h, max_w = 0, 0
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
img = cv.imread(file_path)
loan_id = file_name.split('_')[2].split('.')[0]
data[loan_id] = img
if img.shape[0] > max_h:
max_h = img.shape[0]
if img.shape[1] > max_w:
max_w = img.shape[1]
# print(f'{max_h} {max_w}')
return data
def count_tokens():
print('count tokens...')
statistic = {name: {} for name in my_map.name2label.keys()}
stack = os.listdir(tokenized_dataset)
print 'loading data in ' + dataset
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(tokenized_dataset, file_name)
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
print('\r%s' % (file_path)),
sys.stdout.flush()
with open(file_path, 'r', encoding='utf-8') as fp:
label = utils.get_dir_name(file_path)
for sen in fp:
sen = sen.strip()
tag = ViPosTagger.postagging(sen)
tokens = [
tag[0][i] for i in xrange(len(tag[0]))
if tag[1][i] == u'N'
]
update_count_tokens(statistic, label, tokens)
def tokenizer_dataset():
utils.mkdir(tokenized_dataset)
stack = os.listdir(dataset)
print 'loading data in ' + dataset
while (len(stack) > 0):
file_name = stack.pop()
file_path = os.path.join(dataset, file_name)
if (os.path.isdir(file_path)):
utils.push_data_to_stack(stack, file_path, file_name)
else:
print('\r%s' % (file_path)),
sys.stdout.flush()
with open(file_path, 'r', encoding='utf-16') as fp:
content = unicodedata.normalize('NFKC', fp.read())
content = r.run(tokenizer.predict(content))
dir_name = utils.get_dir_name(file_path)
output_dir = os.path.join(tokenized_dataset, dir_name)
utils.mkdir(output_dir)
name = os.path.basename(file_path)
with open(os.path.join(output_dir, name),
'w',
encoding='utf-8') as fw:
fw.write(content)
print('')
