def restore_model_trained(parameter_pathfile='',
model_pathfile='',
dataset_pathfile='',
embedding_filepath='',
model_folder=''):
if model_folder == '':
parameters = pickle.load(open(parameter_pathfile, 'rb'))
token_to_vector = utils_nlp.load_pretrained_token_embeddings(
embedding_filepath)
dataset = pickle.load(open(dataset_pathfile, 'rb'))
name_entity = NER(parameters, dataset, token_to_vector)
name_entity.restore_model_trained(
model_pathfile,
dataset_pathfile,
embedding_filepath,
character_dimension=parameters['character_embedding_dimension'],
token_dimension=parameters['token_embedding_dimension'])
else:
parameter_pathfile = os.path.join(model_folder, 'parameters.pickle')
dataset_pathfile = os.path.join(model_folder, 'dataset.pickle')
model_pathfile = os.path.join(model_folder, 'model.ckpt')
parameters = pickle.load(open(parameter_pathfile, 'rb'))
token_to_vector = utils_nlp.load_pretrained_token_embeddings(
embedding_filepath)
dataset = pickle.load(open(dataset_pathfile, 'rb'))
name_entity = NER(parameters, dataset, token_to_vector)
name_entity.restore_model_trained(
model_pathfile,
dataset_pathfile,
embedding_filepath,
character_dimension=parameters['character_embedding_dimension'],
token_dimension=parameters['token_embedding_dimension'])
return name_entity
def load_pretrained_token_embeddings(self, sess, dataset, parameters):
if parameters['token_pretrained_embedding_filepath'] == '':
return
# Load embeddings
start_time = time.time()
print('Load token embeddings... ', end='', flush=True)
token_to_vector = utils_nlp.load_pretrained_token_embeddings(
parameters)
initial_weights = sess.run(self.token_embedding_weights.read_value())
number_of_loaded_word_vectors = 0
number_of_token_original_case_found = 0
number_of_token_lowercase_found = 0
number_of_token_digits_replaced_with_zeros_found = 0
number_of_token_lowercase_and_digits_replaced_with_zeros_found = 0
for token in dataset.token_to_index.keys():
if token in token_to_vector.keys():
initial_weights[
dataset.token_to_index[token]] = token_to_vector[token]
number_of_token_original_case_found += 1
elif parameters['check_for_lowercase'] and token.lower(
) in token_to_vector.keys():
initial_weights[dataset.token_to_index[
token]] = token_to_vector[token.lower()]
number_of_token_lowercase_found += 1
elif parameters['check_for_digits_replaced_with_zeros'] and re.sub(
'\d', '0', token) in token_to_vector.keys():
initial_weights[
dataset.token_to_index[token]] = token_to_vector[re.sub(
'\d', '0', token)]
number_of_token_digits_replaced_with_zeros_found += 1
elif parameters['check_for_lowercase'] and parameters[
'check_for_digits_replaced_with_zeros'] and re.sub(
'\d', '0', token.lower()) in token_to_vector.keys():
initial_weights[
dataset.token_to_index[token]] = token_to_vector[re.sub(
'\d', '0', token.lower())]
number_of_token_lowercase_and_digits_replaced_with_zeros_found += 1
else:
continue
number_of_loaded_word_vectors += 1
elapsed_time = time.time() - start_time
print('done ({0:.2f} seconds)'.format(elapsed_time))
print("number_of_token_original_case_found: {0}".format(
number_of_token_original_case_found))
print("number_of_token_lowercase_found: {0}".format(
number_of_token_lowercase_found))
print("number_of_token_digits_replaced_with_zeros_found: {0}".format(
number_of_token_digits_replaced_with_zeros_found))
print(
"number_of_token_lowercase_and_digits_replaced_with_zeros_found: {0}"
.format(
number_of_token_lowercase_and_digits_replaced_with_zeros_found
))
print('number_of_loaded_word_vectors: {0}'.format(
number_of_loaded_word_vectors))
print("dataset.vocabulary_size: {0}".format(dataset.vocabulary_size))
sess.run(self.token_embedding_weights.assign(initial_weights))
def load_dataset(self,
dataset_filepaths,
parameters,
token_to_vector=None):
'''
dataset_filepaths : dictionary with keys 'train', 'valid', 'test', 'deploy'
'''
start_time = time.time()
print('Load dataset... ', end='', flush=True)
if parameters['token_pretrained_embedding_filepath'] != '':
if token_to_vector == None:
token_to_vector = utils_nlp.load_pretrained_token_embeddings(
parameters)
else:
token_to_vector = {}
if self.verbose:
print("len(token_to_vector): {0}".format(len(token_to_vector)))
# Load pretraining dataset to ensure that index to label is compatible to the pretrained model,
# and that token embeddings that are learned in the pretrained model are loaded properly.
all_tokens_in_pretraining_dataset = []
all_characters_in_pretraining_dataset = []
if parameters['use_pretrained_model']:
pretraining_dataset = pickle.load(
open(
os.path.join(parameters['pretrained_model_folder'],
'dataset.pickle'), 'rb'))
all_tokens_in_pretraining_dataset = pretraining_dataset.index_to_token.values(
)
all_characters_in_pretraining_dataset = pretraining_dataset.index_to_character.values(
)
remap_to_unk_count_threshold = 1
self.UNK_TOKEN_INDEX = 0
self.PADDING_CHARACTER_INDEX = 0
self.tokens_mapped_to_unk = []
self.UNK = 'UNK'
self.unique_labels = []
labels = {}
tokens = {}
label_count = {}
token_count = {}
character_count = {}
for dataset_type in ['train', 'valid', 'test', 'deploy']:
labels[dataset_type], tokens[dataset_type], token_count[dataset_type], label_count[dataset_type], character_count[dataset_type] \
= self._parse_dataset(dataset_filepaths.get(dataset_type, None))
if self.verbose: print("dataset_type: {0}".format(dataset_type))
if self.verbose:
print("len(token_count[dataset_type]): {0}".format(
len(token_count[dataset_type])))
token_count['all'] = {}
for token in list(token_count['train'].keys()) + list(
token_count['valid'].keys()) + list(
token_count['test'].keys()) + list(
token_count['deploy'].keys()):
token_count['all'][token] = token_count['train'][
token] + token_count['valid'][token] + token_count['test'][
token] + token_count['deploy'][token]
if parameters['load_all_pretrained_token_embeddings']:
for token in token_to_vector:
if token not in token_count['all']:
token_count['all'][token] = -1
token_count['train'][token] = -1
for token in all_tokens_in_pretraining_dataset:
if token not in token_count['all']:
token_count['all'][token] = -1
token_count['train'][token] = -1
character_count['all'] = {}
for character in list(character_count['train'].keys()) + list(
character_count['valid'].keys()) + list(
character_count['test'].keys()) + list(
character_count['deploy'].keys()):
character_count['all'][character] = character_count['train'][
character] + character_count['valid'][
character] + character_count['test'][
character] + character_count['deploy'][character]
for character in all_characters_in_pretraining_dataset:
if character not in character_count['all']:
character_count['all'][character] = -1
character_count['train'][character] = -1
for dataset_type in dataset_filepaths.keys():
if self.verbose: print("dataset_type: {0}".format(dataset_type))
if self.verbose:
print("len(token_count[dataset_type]): {0}".format(
len(token_count[dataset_type])))
label_count['all'] = {}
for character in list(label_count['train'].keys()) + list(
label_count['valid'].keys()) + list(
label_count['test'].keys()) + list(
label_count['deploy'].keys()):
label_count['all'][character] = label_count['train'][
character] + label_count['valid'][character] + label_count[
'test'][character] + label_count['deploy'][character]
token_count['all'] = utils.order_dictionary(token_count['all'],
'value_key',
reverse=True)
label_count['all'] = utils.order_dictionary(label_count['all'],
'key',
reverse=False)
character_count['all'] = utils.order_dictionary(character_count['all'],
'value',
reverse=True)
if self.verbose:
print('character_count[\'all\']: {0}'.format(
character_count['all']))
token_to_index = {}
token_to_index[self.UNK] = self.UNK_TOKEN_INDEX
iteration_number = 0
number_of_unknown_tokens = 0
if self.verbose:
print("parameters['remap_unknown_tokens_to_unk']: {0}".format(
parameters['remap_unknown_tokens_to_unk']))
if self.verbose:
print("len(token_count['train'].keys()): {0}".format(
len(token_count['train'].keys())))
for token, count in token_count['all'].items():
if iteration_number == self.UNK_TOKEN_INDEX: iteration_number += 1
if parameters['remap_unknown_tokens_to_unk'] == 1 and \
(token_count['train'][token] == 0 or \
parameters['load_only_pretrained_token_embeddings']) and \
not utils_nlp.is_token_in_pretrained_embeddings(token, token_to_vector, parameters) and \
token not in all_tokens_in_pretraining_dataset:
if self.verbose: print("token: {0}".format(token))
if self.verbose:
print("token.lower(): {0}".format(token.lower()))
if self.verbose:
print("re.sub('\d', '0', token.lower()): {0}".format(
re.sub('\d', '0', token.lower())))
token_to_index[token] = self.UNK_TOKEN_INDEX
number_of_unknown_tokens += 1
self.tokens_mapped_to_unk.append(token)
else:
token_to_index[token] = iteration_number
iteration_number += 1
if self.verbose:
print("number_of_unknown_tokens: {0}".format(
number_of_unknown_tokens))
infrequent_token_indices = []
for token, count in token_count['train'].items():
if 0 < count <= remap_to_unk_count_threshold:
infrequent_token_indices.append(token_to_index[token])
if self.verbose:
print("len(token_count['train']): {0}".format(
len(token_count['train'])))
if self.verbose:
print("len(infrequent_token_indices): {0}".format(
len(infrequent_token_indices)))
# Ensure that both B- and I- versions exist for each label
labels_without_bio = set()
for label in label_count['all'].keys():
new_label = utils_nlp.remove_bio_from_label_name(label)
labels_without_bio.add(new_label)
for label in labels_without_bio:
if label == 'O':
continue
if parameters['tagging_format'] == 'bioes':
prefixes = ['B-', 'I-', 'E-', 'S-']
else:
prefixes = ['B-', 'I-']
for prefix in prefixes:
l = prefix + label
if l not in label_count['all']:
label_count['all'][l] = 0
label_count['all'] = utils.order_dictionary(label_count['all'],
'key',
reverse=False)
if parameters['use_pretrained_model']:
self.unique_labels = sorted(
list(pretraining_dataset.label_to_index.keys()))
# Make sure labels are compatible with the pretraining dataset.
for label in label_count['all']:
if label not in pretraining_dataset.label_to_index:
raise AssertionError(
"The label {0} does not exist in the pretraining dataset. "
.format(label) +
"Please ensure that only the following labels exist in the dataset: {0}"
.format(', '.join(self.unique_labels)))
label_to_index = pretraining_dataset.label_to_index.copy()
else:
label_to_index = {}
iteration_number = 0
for label, count in label_count['all'].items():
label_to_index[label] = iteration_number
iteration_number += 1
self.unique_labels.append(label)
if self.verbose:
print('self.unique_labels: {0}'.format(self.unique_labels))
character_to_index = {}
iteration_number = 0
for character, count in character_count['all'].items():
if iteration_number == self.PADDING_CHARACTER_INDEX:
iteration_number += 1
character_to_index[character] = iteration_number
iteration_number += 1
if self.verbose:
print('token_count[\'train\'][0:10]: {0}'.format(
list(token_count['train'].items())[0:10]))
token_to_index = utils.order_dictionary(token_to_index,
'value',
reverse=False)
if self.verbose: print('token_to_index: {0}'.format(token_to_index))
index_to_token = utils.reverse_dictionary(token_to_index)
if parameters['remap_unknown_tokens_to_unk'] == 1:
index_to_token[self.UNK_TOKEN_INDEX] = self.UNK
if self.verbose: print('index_to_token: {0}'.format(index_to_token))
if self.verbose:
print('label_count[\'train\']: {0}'.format(label_count['train']))
label_to_index = utils.order_dictionary(label_to_index,
'value',
reverse=False)
if self.verbose: print('label_to_index: {0}'.format(label_to_index))
index_to_label = utils.reverse_dictionary(label_to_index)
if self.verbose: print('index_to_label: {0}'.format(index_to_label))
character_to_index = utils.order_dictionary(character_to_index,
'value',
reverse=False)
index_to_character = utils.reverse_dictionary(character_to_index)
if self.verbose:
print('character_to_index: {0}'.format(character_to_index))
if self.verbose:
print('index_to_character: {0}'.format(index_to_character))
if self.verbose:
print('labels[\'train\'][0:10]: {0}'.format(labels['train'][0:10]))
if self.verbose:
print('tokens[\'train\'][0:10]: {0}'.format(tokens['train'][0:10]))
if self.verbose:
# Print sequences of length 1 in train set
for token_sequence, label_sequence in zip(tokens['train'],
labels['train']):
if len(label_sequence) == 1 and label_sequence[0] != 'O':
print("{0}\t{1}".format(token_sequence[0],
label_sequence[0]))
self.token_to_index = token_to_index
self.index_to_token = index_to_token
self.index_to_character = index_to_character
self.character_to_index = character_to_index
self.index_to_label = index_to_label
self.label_to_index = label_to_index
if self.verbose:
print("len(self.token_to_index): {0}".format(
len(self.token_to_index)))
if self.verbose:
print("len(self.index_to_token): {0}".format(
len(self.index_to_token)))
self.tokens = tokens
self.labels = labels
token_indices, label_indices, character_indices_padded, character_indices, token_lengths, characters, label_vector_indices = self._convert_to_indices(
dataset_filepaths.keys())
self.token_indices = token_indices
self.label_indices = label_indices
self.character_indices_padded = character_indices_padded
self.character_indices = character_indices
self.token_lengths = token_lengths
self.characters = characters
self.label_vector_indices = label_vector_indices
self.number_of_classes = max(self.index_to_label.keys()) + 1
self.vocabulary_size = max(self.index_to_token.keys()) + 1
self.alphabet_size = max(self.index_to_character.keys()) + 1
if self.verbose:
print("self.number_of_classes: {0}".format(self.number_of_classes))
if self.verbose:
print("self.alphabet_size: {0}".format(self.alphabet_size))
if self.verbose:
print("self.vocabulary_size: {0}".format(self.vocabulary_size))
# unique_labels_of_interest is used to compute F1-scores.
self.unique_labels_of_interest = list(self.unique_labels)
self.unique_labels_of_interest.remove('O')
self.unique_label_indices_of_interest = []
for lab in self.unique_labels_of_interest:
self.unique_label_indices_of_interest.append(label_to_index[lab])
self.infrequent_token_indices = infrequent_token_indices
if self.verbose:
print('self.unique_labels_of_interest: {0}'.format(
self.unique_labels_of_interest))
if self.verbose:
print('self.unique_label_indices_of_interest: {0}'.format(
self.unique_label_indices_of_interest))
elapsed_time = time.time() - start_time
print('done ({0:.2f} seconds)'.format(elapsed_time))
return token_to_vector
def load_dataset(self,
dataset_filepaths,
parameters,
token_to_vector=None):
'''
dataset_filepaths : dictionary with keys 'train', 'valid', 'test', 'deploy'
Load word vectors từ file đã chuẩn bị sẵn
'''
start_time = time.time()
print('Load dataset... ', end='', flush=True)
if parameters['token_pretrained_embedding_filepath'] != '':
if token_to_vector == None:
token_to_vector = utils_nlp.load_pretrained_token_embeddings(
parameters)
else:
token_to_vector = {}
if self.verbose:
print("len(token_to_vector): {0}".format(len(token_to_vector)))
# Load pretraining dataset to ensure that index to label is compatible to the pretrained model,
# and that token embeddings that are learned in the pretrained model are loaded properly.
all_tokens_in_pretraining_dataset = []
all_characters_in_pretraining_dataset = []
if parameters['use_pretrained_model']:
pretraining_dataset = pickle.load(
open(
os.path.join(parameters['pretrained_model_folder'],
'dataset.pickle'), 'rb'))
all_tokens_in_pretraining_dataset = pretraining_dataset.index_to_token.values(
) # Những token lưu ở đợt train trước
all_characters_in_pretraining_dataset = pretraining_dataset.index_to_character.values(
) # Những character lưu ở đợt train trước
remap_to_unk_count_threshold = 1
self.UNK_TOKEN_INDEX = 0 # Index của những unknow token
self.PADDING_CHARACTER_INDEX = 0
self.tokens_mapped_to_unk = [] # những unknown token
self.UNK = 'UNK'
self.unique_labels = [] # Các nhãn tồn tại trong dataset
labels = {} # nhãn {all: ...., train: ..., test: ...}
tokens = {} # token {all: ...., train: ..., test: ...}
label_count = {} # Đếm số nhãn {all: ...., train: ..., test: ...}
token_count = {} # Đếm số token {all: ...., train: ..., test: ...}
character_count = {} # Đếm số ký tự {all: ...., train: ..., test: ...}
for dataset_type in ['train', 'valid', 'test', 'deploy']:
labels[dataset_type], tokens[dataset_type], token_count[dataset_type], label_count[dataset_type], character_count[dataset_type] \
= self._parse_dataset(dataset_filepaths.get(dataset_type, None))
if self.verbose: print("dataset_type: {0}".format(dataset_type))
if self.verbose:
print("len(token_count[dataset_type]): {0}".format(
len(token_count[dataset_type])))
# Tính tổng hợp lại cho tất cả các dataset
token_count['all'] = {}
for token in list(token_count['train'].keys()) + list(
token_count['valid'].keys()) + list(
token_count['test'].keys()) + list(
token_count['deploy'].keys()):
token_count['all'][token] = token_count['train'][
token] + token_count['valid'][token] + token_count['test'][
token] + token_count['deploy'][token]
# Thêm những token ở pretrained trước với giá trị -1
if parameters['load_all_pretrained_token_embeddings']:
for token in token_to_vector:
if token not in token_count['all']:
token_count['all'][token] = -1
token_count['train'][token] = -1
for token in all_tokens_in_pretraining_dataset:
if token not in token_count['all']:
token_count['all'][token] = -1
token_count['train'][token] = -1
# Tính tổng hợp lại cho tất cả các dataset
character_count['all'] = {}
for character in list(character_count['train'].keys()) + list(
character_count['valid'].keys()) + list(
character_count['test'].keys()) + list(
character_count['deploy'].keys()):
character_count['all'][character] = character_count['train'][
character] + character_count['valid'][
character] + character_count['test'][
character] + character_count['deploy'][character]
# Thêm những token ở pretrained trước với giá trị -1
for character in all_characters_in_pretraining_dataset:
if character not in character_count['all']:
character_count['all'][character] = -1
character_count['train'][character] = -1
for dataset_type in dataset_filepaths.keys():
if self.verbose: print("dataset_type: {0}".format(dataset_type))
if self.verbose:
print("len(token_count[dataset_type]): {0}".format(
len(token_count[dataset_type])))
# Tính tổng hợp lại các nhãn ở đợt train trước
label_count['all'] = {}
for character in list(label_count['train'].keys()) + list(
label_count['valid'].keys()) + list(
label_count['test'].keys()) + list(
label_count['deploy'].keys()):
label_count['all'][character] = label_count['train'][
character] + label_count['valid'][character] + label_count[
'test'][character] + label_count['deploy'][character]
token_count['all'] = utils.order_dictionary(
token_count['all'], 'value_key', reverse=True
) # Sort token count theo các token có freq cao đến thấp, token desc
label_count['all'] = utils.order_dictionary(
label_count['all'], 'key',
reverse=False) # Sort label count theo label asc
character_count['all'] = utils.order_dictionary(
character_count['all'], 'value', reverse=True
) # Sort character count theo các character có freq cao đến thấp
if self.verbose:
print('character_count[\'all\']: {0}'.format(
character_count['all']))
token_to_index = {}
token_to_index[self.UNK] = self.UNK_TOKEN_INDEX
iteration_number = 0
number_of_unknown_tokens = 0
if self.verbose:
print("parameters['remap_unknown_tokens_to_unk']: {0}".format(
parameters['remap_unknown_tokens_to_unk']))
if self.verbose:
print("len(token_count['train'].keys()): {0}".format(
len(token_count['train'].keys())))
for token, count in token_count['all'].items():
if iteration_number == self.UNK_TOKEN_INDEX: iteration_number += 1
'''
UNK_TOKEN: token không xuất hiện trong pretraining_dataset và trong word vectors
'''
if parameters['remap_unknown_tokens_to_unk'] == 1 and \
(token_count['train'][token] == 0 or \
parameters['load_only_pretrained_token_embeddings']) and \
not utils_nlp.is_token_in_pretrained_embeddings(token, token_to_vector, parameters) and \
token not in all_tokens_in_pretraining_dataset:
if self.verbose: print("token: {0}".format(token))
if self.verbose:
print("token.lower(): {0}".format(token.lower()))
if self.verbose:
print("re.sub('\d', '0', token.lower()): {0}".format(
re.sub('\d', '0', token.lower())))
token_to_index[token] = self.UNK_TOKEN_INDEX
number_of_unknown_tokens += 1
self.tokens_mapped_to_unk.append(token)
else:
token_to_index[token] = iteration_number
iteration_number += 1
if self.verbose:
print("number_of_unknown_tokens: {0}".format(
number_of_unknown_tokens))
infrequent_token_indices = [
] # Các token xuất hiện thấp trong train dataset
for token, count in token_count['train'].items():
if 0 < count <= remap_to_unk_count_threshold:
infrequent_token_indices.append(token_to_index[token])
if self.verbose:
print("len(token_count['train']): {0}".format(
len(token_count['train'])))
if self.verbose:
print("len(infrequent_token_indices): {0}".format(
len(infrequent_token_indices)))
# Ensure that both B- and I- versions exist for each label
# Bỏ các tiền tố B-, O-, I-...
labels_without_bio = set()
for label in label_count['all'].keys():
new_label = utils_nlp.remove_bio_from_label_name(label)
labels_without_bio.add(new_label)
# Kết hợp các ENTITY vs các tiền tố B-, I-,... và thêm vào label count
for label in labels_without_bio:
if label == 'O':
continue
if parameters['tagging_format'] == 'bioes':
prefixes = ['B-', 'I-', 'E-', 'S-']
else:
prefixes = ['B-', 'I-']
for prefix in prefixes:
l = prefix + label
if l not in label_count['all']:
label_count['all'][l] = 0
# Sắp xếp label_count theo label asc
label_count['all'] = utils.order_dictionary(label_count['all'],
'key',
reverse=False)
if parameters['use_pretrained_model']:
self.unique_labels = sorted(
list(pretraining_dataset.label_to_index.keys()))
# Make sure labels are compatible with the pretraining dataset.
for label in label_count['all']:
if label not in pretraining_dataset.label_to_index:
raise AssertionError(
"The label {0} does not exist in the pretraining dataset. "
.format(label) +
"Please ensure that only the following labels exist in the dataset: {0}"
.format(', '.join(self.unique_labels)))
label_to_index = pretraining_dataset.label_to_index.copy()
else:
label_to_index = {}
iteration_number = 0
for label, count in label_count['all'].items():
label_to_index[label] = iteration_number
iteration_number += 1
self.unique_labels.append(label)
if self.verbose:
print('self.unique_labels: {0}'.format(self.unique_labels))
character_to_index = {}
iteration_number = 0
for character, count in character_count['all'].items():
if iteration_number == self.PADDING_CHARACTER_INDEX:
iteration_number += 1
character_to_index[character] = iteration_number
iteration_number += 1
if self.verbose:
print('token_count[\'train\'][0:10]: {0}'.format(
list(token_count['train'].items())[0:10]))
token_to_index = utils.order_dictionary(token_to_index,
'value',
reverse=False)
if self.verbose: print('token_to_index: {0}'.format(token_to_index))
index_to_token = utils.reverse_dictionary(token_to_index)
if parameters['remap_unknown_tokens_to_unk'] == 1:
index_to_token[self.UNK_TOKEN_INDEX] = self.UNK
if self.verbose: print('index_to_token: {0}'.format(index_to_token))
if self.verbose:
print('label_count[\'train\']: {0}'.format(label_count['train']))
label_to_index = utils.order_dictionary(label_to_index,
'value',
reverse=False)
if self.verbose: print('label_to_index: {0}'.format(label_to_index))
index_to_label = utils.reverse_dictionary(label_to_index)
if self.verbose: print('index_to_label: {0}'.format(index_to_label))
character_to_index = utils.order_dictionary(character_to_index,
'value',
reverse=False)
index_to_character = utils.reverse_dictionary(character_to_index)
if self.verbose:
print('character_to_index: {0}'.format(character_to_index))
if self.verbose:
print('index_to_character: {0}'.format(index_to_character))
if self.verbose:
print('labels[\'train\'][0:10]: {0}'.format(labels['train'][0:10]))
if self.verbose:
print('tokens[\'train\'][0:10]: {0}'.format(tokens['train'][0:10]))
if self.verbose:
# Print sequences of length 1 in train set
for token_sequence, label_sequence in zip(tokens['train'],
labels['train']):
if len(label_sequence) == 1 and label_sequence[0] != 'O':
print("{0}\t{1}".format(token_sequence[0],
label_sequence[0]))
self.token_to_index = token_to_index # {token: index sau khi sắp xếp theo freq từ cao đến thấp, 0 nếu là unk token}
self.index_to_token = index_to_token # Ngược token_to_index
self.index_to_character = index_to_character # Ngược character_to_index
self.character_to_index = character_to_index # { character: index sau khi sắp xếp freq từ cao đến thấp}
self.index_to_label = index_to_label # Ngược label_to_index
self.label_to_index = label_to_index # {label: index sau khi sắp xếp asc}
if self.verbose:
print("len(self.token_to_index): {0}".format(
len(self.token_to_index)))
if self.verbose:
print("len(self.index_to_token): {0}".format(
len(self.index_to_token)))
self.tokens = tokens
self.labels = labels
token_indices, label_indices, character_indices_padded, character_indices, token_lengths, characters, label_vector_indices = self._convert_to_indices(
dataset_filepaths.keys())
self.token_indices = token_indices
self.label_indices = label_indices
self.character_indices_padded = character_indices_padded
self.character_indices = character_indices
self.token_lengths = token_lengths
self.characters = characters
self.label_vector_indices = label_vector_indices
self.number_of_classes = max(self.index_to_label.keys()) + 1
self.vocabulary_size = max(self.index_to_token.keys()) + 1
self.alphabet_size = max(self.index_to_character.keys()) + 1
if self.verbose:
print("self.number_of_classes: {0}".format(self.number_of_classes))
if self.verbose:
print("self.alphabet_size: {0}".format(self.alphabet_size))
if self.verbose:
print("self.vocabulary_size: {0}".format(self.vocabulary_size))
# unique_labels_of_interest is used to compute F1-scores.
self.unique_labels_of_interest = list(self.unique_labels)
self.unique_labels_of_interest.remove('O')
self.unique_label_indices_of_interest = []
for lab in self.unique_labels_of_interest:
self.unique_label_indices_of_interest.append(label_to_index[lab])
self.infrequent_token_indices = infrequent_token_indices
if self.verbose:
print('self.unique_labels_of_interest: {0}'.format(
self.unique_labels_of_interest))
if self.verbose:
print('self.unique_label_indices_of_interest: {0}'.format(
self.unique_label_indices_of_interest))
elapsed_time = time.time() - start_time
print('done ({0:.2f} seconds)'.format(elapsed_time))
return token_to_vector
