def _gen_examples():
examples = []
examples.append(
classifier_data_lib.InputExample(
guid=0, text_a='Really good.', label='pos'))
examples.append(
classifier_data_lib.InputExample(guid=1, text_a='So bad.', label='neg'))
return examples
def _get_single_story_features(self, story_headline, articles):
"""Converts a list of articles to a tensorflow Example."""
def get_text_snippet(article):
if article.text_b:
return " [SEP] ".join([article.text_a, article.text_b])
else:
return article.text_a
story_features = collections.OrderedDict()
story_headline_feature = classifier_data_lib.convert_single_example(
ex_index=self.ex_index,
example=classifier_data_lib.InputExample(guid=self.guid,
text_a=story_headline,
label=self.label),
label_list=[self.label],
max_seq_length=self.len_title,
tokenizer=self.tokenizer)
if self.include_text_snippet_in_example:
story_headline_feature.label_id = story_headline
self._add_feature_with_suffix(feature=story_headline_feature,
suffix="a",
story_features=story_features)
for (article_index, article) in enumerate(articles):
if article_index == self.max_num_articles:
break
article_feature = classifier_data_lib.convert_single_example(
ex_index=self.ex_index,
example=article,
label_list=[self.label],
max_seq_length=self.len_passage,
tokenizer=self.tokenizer)
if self.include_text_snippet_in_example:
article_feature.label_id = get_text_snippet(article)
suffix = chr(ord("b") + article_index)
self._add_feature_with_suffix(feature=article_feature,
suffix=suffix,
story_features=story_features)
# Adds empty features as placeholder.
for article_index in range(len(articles), self.max_num_articles):
suffix = chr(ord("b") + article_index)
empty_article = classifier_data_lib.InputExample(guid=self.guid,
text_a="",
label=self.label)
empty_feature = classifier_data_lib.convert_single_example(
ex_index=self.ex_index,
example=empty_article,
label_list=[self.label],
max_seq_length=self.len_passage,
tokenizer=self.tokenizer)
if self.include_text_snippet_in_example:
empty_feature.label_id = ""
self._add_feature_with_suffix(feature=empty_feature,
suffix=suffix,
story_features=story_features)
return story_features
def _get_article_content_from_json(self, file_path):
"""Returns (url, InputExample) keeping content extracted from file_path."""
with tf.io.gfile.GFile(file_path, "r") as article_json_file:
article = json.load(article_json_file)
if self.include_article_title_in_passage:
return article["url"], classifier_data_lib.InputExample(
guid=self.guid,
text_a=article["title"],
text_b=article["maintext"],
label=self.label)
else:
return article["url"], classifier_data_lib.InputExample(
guid=self.guid, text_a=article["maintext"], label=self.label)
def __to_feature(self, text, label):
example = classifier_data_lib.InputExample(guid=None,
text_a=text.numpy(),
text_b=None,
label=label.numpy())
feature = classifier_data_lib.convert_single_example(
0, example, self.label_list, self.max_seq_length, self.tokenizer)
return feature.input_ids, feature.input_mask, feature.segment_ids, feature.label_id
def _create_examples(self, lines, set_type):
"""Creates examples for the training and dev sets."""
examples = []
for (i, line) in enumerate(lines):
guid = "%s-%s" % (set_type, i)
text_a = self.process_text_fn(line[0])
examples.append(
classifier_data_lib.InputExample(
guid=guid, text_a=text_a, example_id=i))
return examples
def to_feature(text,
label,
label_list=label_list,
max_seq_length=max_seq_length,
tokenizer=tokenizer):
example = classifier_data_lib.InputExample(guid=None,
text_a=text.numpy(),
text_b=None,
label=label.numpy())
feature = classifier_data_lib.convert_single_example(
0, example, label_list, max_seq_length, tokenizer)
return (feature.input_ids, feature.input_mask, feature.segment_ids,
feature.label_id)
def from_folder(cls,
filename,
model_spec='average_word_vec',
is_training=True,
class_labels=None,
shuffle=True,
cache_dir=None):
"""Loads text with labels and preproecess text according to `model_spec`.
Assume the text data of the same label are in the same subdirectory. each
file is one text.
Args:
filename: Name of the file.
model_spec: Specification for the model.
is_training: Whether the loaded data is for training or not.
class_labels: Class labels that should be considered. Name of the
subdirectory not in `class_labels` will be ignored. If None, all the
subdirectories will be considered.
shuffle: boolean, if shuffle, random shuffle data.
cache_dir: The cache directory to save preprocessed data. If None,
generates a temporary directory to cache preprocessed data.
Returns:
TextDataset containing text, labels and other related info.
"""
model_spec = ms.get(model_spec)
data_root = os.path.abspath(filename)
folder_name = os.path.basename(data_root)
is_cached, tfrecord_file, meta_data_file, vocab_file = cls._get_cache_info(
cache_dir, folder_name, model_spec, is_training)
# If cached, directly loads data from cache directory.
if is_cached:
return cls._load_data(tfrecord_file, meta_data_file, model_spec)
# Gets paths of all text.
if class_labels:
all_text_paths = []
for class_label in class_labels:
all_text_paths.extend(
list(
tf.io.gfile.glob(
os.path.join(data_root, class_label) + r'/*')))
else:
all_text_paths = list(tf.io.gfile.glob(data_root + r'/*/*'))
all_text_size = len(all_text_paths)
if all_text_size == 0:
raise ValueError('Text size is zero')
if shuffle:
random.shuffle(all_text_paths)
# Gets label and its index.
if class_labels:
label_names = sorted(class_labels)
else:
label_names = sorted(
name for name in os.listdir(data_root)
if os.path.isdir(os.path.join(data_root, name)))
# Generates text examples from folder.
examples = []
for i, path in enumerate(all_text_paths):
with tf.io.gfile.GFile(path, 'r') as f:
text = f.read()
guid = '%s-%d' % (folder_name, i)
label = os.path.basename(os.path.dirname(path))
examples.append(
classifier_data_lib.InputExample(guid, text, None, label))
# Saves preprocessed data and other assets into files.
cls._save_data(examples, model_spec, label_names, tfrecord_file,
meta_data_file, vocab_file, is_training)
# Loads data from cache directory.
return cls._load_data(tfrecord_file, meta_data_file, model_spec)
def from_csv(cls,
filename,
text_column,
label_column,
fieldnames=None,
model_spec='average_word_vec',
is_training=True,
delimiter=',',
quotechar='"',
shuffle=False,
cache_dir=None):
"""Loads text with labels from the csv file and preproecess text according to `model_spec`.
Args:
filename: Name of the file.
text_column: String, Column name for input text.
label_column: String, Column name for labels.
fieldnames: A sequence, used in csv.DictReader. If fieldnames is omitted,
the values in the first row of file f will be used as the fieldnames.
model_spec: Specification for the model.
is_training: Whether the loaded data is for training or not.
delimiter: Character used to separate fields.
quotechar: Character used to quote fields containing special characters.
shuffle: boolean, if shuffle, random shuffle data.
cache_dir: The cache directory to save preprocessed data. If None,
generates a temporary directory to cache preprocessed data.
Returns:
TextDataset containing text, labels and other related info.
"""
model_spec = ms.get(model_spec)
csv_name = os.path.basename(filename)
is_cached, tfrecord_file, meta_data_file, vocab_file = cls._get_cache_info(
cache_dir, csv_name, model_spec, is_training)
# If cached, directly loads data from cache directory.
if is_cached:
return cls._load_data(tfrecord_file, meta_data_file, model_spec)
lines = cls._read_csv(filename, fieldnames, delimiter, quotechar)
if shuffle:
random.shuffle(lines)
# Gets labels.
label_set = set()
for line in lines:
label_set.add(line[label_column])
label_names = sorted(label_set)
# Generates text examples from csv file.
examples = []
for i, line in enumerate(lines):
text, label = line[text_column], line[label_column]
guid = '%s-%d' % (csv_name, i)
examples.append(
classifier_data_lib.InputExample(guid, text, None, label))
# Saves preprocessed data and other assets into files.
cls._save_data(examples, model_spec, label_names, tfrecord_file,
meta_data_file, vocab_file, is_training)
# Loads data from cache directory.
return cls._load_data(tfrecord_file, meta_data_file, model_spec)
