def _set_lm_features(self,
message: Message,
attribute: Text = TEXT) -> None:
"""Adds the precomputed word vectors to the messages features."""
doc = self._get_doc(message, attribute)
if doc is None:
return
sequence_features = doc[SEQUENCE_FEATURES]
sentence_features = doc[SENTENCE_FEATURES]
final_sequence_features = Features(
sequence_features,
FEATURE_TYPE_SEQUENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sequence_features)
final_sentence_features = Features(
sentence_features,
FEATURE_TYPE_SENTENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sentence_features)
def _set_spacy_features(self,
message: Message,
attribute: Text = TEXT) -> None:
"""Adds the spacy word vectors to the messages features."""
doc = self.get_doc(message, attribute)
if doc is None:
return
# in case an empty spaCy model was used, no vectors are present
if doc.vocab.vectors_length == 0:
logger.debug(
"No features present. You are using an empty spaCy model.")
return
sequence_features = self._features_for_doc(doc)
sentence_features = self._calculate_sentence_features(
sequence_features, self.pooling_operation)
final_sequence_features = Features(
sequence_features,
FEATURE_TYPE_SEQUENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sequence_features)
final_sentence_features = Features(
sentence_features,
FEATURE_TYPE_SENTENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sentence_features)
def process(self, message: Message, **kwargs: Any) -> None:
mitie_feature_extractor = self._mitie_feature_extractor(**kwargs)
tokens = train_utils.tokens_without_cls(message)
features = self.features_for_tokens(tokens, mitie_feature_extractor)
final_features = Features(
features, TEXT, self.component_config[FEATURIZER_CLASS_ALIAS])
message.add_features(final_features)
def process(
self, message: Message, *, tf_hub_module: Any = None, **kwargs: Any
) -> None:
features = self._compute_features([message], tf_hub_module)[0]
final_features = Features(
features, TEXT, self.component_config[FEATURIZER_CLASS_ALIAS]
)
message.add_features(final_features)
def _text_features_with_regex(self, message: Message,
attribute: Text) -> None:
if self.known_patterns:
features = self._features_for_patterns(message, attribute)
if features is not None:
final_features = Features(
features, attribute,
self.component_config[FEATURIZER_CLASS_ALIAS])
message.add_features(final_features)
def process_training_example(self, example: Message, attribute: Text,
mitie_feature_extractor: Any):
tokens = train_utils.tokens_without_cls(example, attribute)
if tokens is not None:
features = self.features_for_tokens(tokens,
mitie_feature_extractor)
final_features = Features(
features, attribute,
self.component_config[FEATURIZER_CLASS_ALIAS])
example.add_features(final_features)
def _create_sparse_features(self, message: Message) -> None:
"""Convert incoming messages into sparse features using the configured
features."""
import scipy.sparse
# [:-1] to remove CLS token
tokens = message.get(TOKENS_NAMES[TEXT])[:-1]
sentence_features = self._tokens_to_features(tokens)
one_hot_feature_vector = self._features_to_one_hot(sentence_features)
sparse_features = scipy.sparse.coo_matrix(one_hot_feature_vector)
final_features = Features(
sparse_features, TEXT, self.component_config[FEATURIZER_CLASS_ALIAS]
)
message.add_features(final_features)
def process(self, message: Message, **kwargs: Any) -> None:
"""Process incoming message and compute and set features"""
if self.vectorizers is None:
logger.error("There is no trained CountVectorizer: "
"component is either not trained or "
"didn't receive enough training data")
return
attribute = TEXT
message_tokens = self._get_processed_message_tokens_by_attribute(
message, attribute)
# features shape (1, seq, dim)
features = self._create_sequence(attribute, [message_tokens])
if features[0] is not None:
final_features = Features(
features[0], attribute,
self.component_config[FEATURIZER_CLASS_ALIAS])
message.add_features(final_features)
def _set_features(
self,
message: Message,
sequence_features: np.ndarray,
sentence_features: np.ndarray,
attribute: Text,
):
final_sequence_features = Features(
sequence_features,
FEATURE_TYPE_SEQUENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sequence_features)
final_sentence_features = Features(
sentence_features,
FEATURE_TYPE_SENTENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sentence_features)
def _text_features_with_regex(self, message: Message, attribute: Text) -> None:
if self.known_patterns:
sequence_features, sentence_features = self._features_for_patterns(
message, attribute
)
if sequence_features is not None:
final_sequence_features = Features(
sequence_features,
FEATURE_TYPE_SEQUENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sequence_features)
if sentence_features is not None:
final_sentence_features = Features(
sentence_features,
FEATURE_TYPE_SENTENCE,
attribute,
self.component_config[FEATURIZER_CLASS_ALIAS],
)
message.add_features(final_sentence_features)
def _set_spacy_features(self,
message: Message,
attribute: Text = TEXT) -> None:
"""Adds the spacy word vectors to the messages features."""
doc = self.get_doc(message, attribute)
if doc is None:
return
# in case an empty spaCy model was used, no vectors are present
if doc.vocab.vectors_length == 0:
logger.debug(
"No features present. You are using an empty spaCy model.")
return
features = self._features_for_doc(doc)
cls_token_vec = self._calculate_cls_vector(features,
self.pooling_operation)
features = np.concatenate([features, cls_token_vec])
final_features = Features(
features, attribute, self.component_config[FEATURIZER_CLASS_ALIAS])
message.add_features(final_features)
