def from_dict(cls, obj_dict):
"""Creates a :class:`Featurizer` instance from a :obj:`dict`
The dict must have been generated with :func:`~Featurizer.to_dict`
"""
language = obj_dict['language_code']
config = FeaturizerConfig.from_dict(obj_dict["config"])
tfidf_vectorizer = _deserialize_tfidf_vectorizer(
obj_dict["tfidf_vectorizer"], language, config)
entity_utterances_to_entity_names = {
k: set(v) for k, v in
iteritems(obj_dict['entity_utterances_to_feature_names'])
}
self = cls(
language=language,
tfidf_vectorizer=tfidf_vectorizer,
pvalue_threshold=obj_dict['pvalue_threshold'],
entity_utterances_to_feature_names=
entity_utterances_to_entity_names,
best_features=obj_dict['best_features'],
config=config,
unknown_words_replacement_string=obj_dict[
"unknown_words_replacement_string"]
)
return self
def test_featurizer_config(self):
# Given
config_dict = {
"sublinear_tf": True,
}
# When
config = FeaturizerConfig.from_dict(config_dict)
serialized_config = config.to_dict()
# Then
self.assertDictEqual(config_dict, serialized_config)
def test_featurizer_config(self):
# Given
config_dict = {
"sublinear_tf": True,
"pvalue_threshold": 0.4,
"word_clusters_name": None
}
# When
config = FeaturizerConfig.from_dict(config_dict)
serialized_config = config.to_dict()
# Then
self.assertDictEqual(config_dict, serialized_config)
def test_featurizer_config(self):
# Given
tfid_vectorizer_config = TfidfVectorizerConfig()
cooccurrence_vectorizer_config = CooccurrenceVectorizerConfig()
config_dict = {
"unit_name": "featurizer",
"pvalue_threshold": 0.2,
"added_cooccurrence_feature_ratio": 0.2,
"tfidf_vectorizer_config": tfid_vectorizer_config.to_dict(),
"cooccurrence_vectorizer_config":
cooccurrence_vectorizer_config.to_dict()
}
# When
config = FeaturizerConfig.from_dict(config_dict)
serialized_config = config.to_dict()
# Then
self.assertDictEqual(config_dict, serialized_config)
def from_dict(cls, obj_dict, **shared):
"""Creates a :class:`Featurizer` instance from a :obj:`dict`
The dict must have been generated with :func:`~Featurizer.to_dict`
"""
language = obj_dict["language_code"]
config = FeaturizerConfig.from_dict(obj_dict["config"])
tfidf_vectorizer = _deserialize_tfidf_vectorizer(
obj_dict["tfidf_vectorizer"], language, config.sublinear_tf)
self = cls(
language=language,
tfidf_vectorizer=tfidf_vectorizer,
best_features=obj_dict["best_features"],
config=config,
unknown_words_replacement_string=obj_dict[
"unknown_words_replacement_string"],
builtin_entity_parser=shared.get(BUILTIN_ENTITY_PARSER),
custom_entity_parser=shared.get(CUSTOM_ENTITY_PARSER)
)
return self
def from_dict(cls, obj_dict):
"""Creates a :class:`Featurizer` instance from a :obj:`dict`
The dict must have been generated with :func:`~Featurizer.to_dict`
"""
language = obj_dict['language_code']
config = FeaturizerConfig.from_dict(obj_dict["config"])
tfidf_vectorizer = _deserialize_tfidf_vectorizer(
obj_dict["tfidf_vectorizer"], language, config.sublinear_tf)
entity_utterances_to_entity_names = {
k: set(v)
for k, v in iteritems(
obj_dict['entity_utterances_to_feature_names'])
}
self = cls(language=language,
tfidf_vectorizer=tfidf_vectorizer,
entity_utterances_to_feature_names=
entity_utterances_to_entity_names,
best_features=obj_dict['best_features'],
config=config,
unknown_words_replacement_string=obj_dict[
"unknown_words_replacement_string"])
return self