def get_data(self, language):
lookup_tables = []
composite_entities = []
cmdline_args = create_argument_parser().parse_args()
files = utils.list_files(cmdline_args.data)
for file in files:
fformat = _guess_format(file)
file_content = utils.read_json_file(file)
if fformat == DIALOGFLOW_ENTITIES:
entity = file_content['name']
dialogflowReader = DialogflowReader()
examples_js = dialogflowReader._read_examples_js(fn=file, language=language, fformat=fformat)
lookup_table = self._extract_lookup_tables(entity, examples_js)
if(lookup_table):
lookup_tables.append(lookup_table)
composite_entity = self._extract_composite_entities(
entity,
examples_js)
if(composite_entity):
composite_entities.append(composite_entity)
if fformat == RASA_NLU:
rasa_nlu_data = file_content['rasa_nlu_data']
composite_entities = rasa_nlu_data['composite_entities']
lookup_tables = rasa_nlu_data['lookup_tables']
return lookup_tables, composite_entities
def load(
cls,
model_dir=None, # type: Optional[Text]
model_metadata=None, # type: Optional[Metadata]
cached_component=None, # type: Optional[CompositeEntitiesMapper]
**kwargs # type: **Any
):
# type: (...) -> CompositeEntitiesMapper
meta = model_metadata.for_component(cls.name)
file_name = meta.get("composite_entities_file",
COMPOSITE_ENTITIES_FILE_NAME)
composite_entities_file = os.path.join(model_dir, file_name)
if os.path.isfile(composite_entities_file):
composite_entities = utils.read_json_file(composite_entities_file)
else:
composite_entities = {
'lookup_tables': [],
'composite_entities': []
}
warnings.warn("Failed to load composite entities file from '{}'"
"".format(composite_entities_file))
return cls(meta, composite_entities)
def __init__(self, filename=None, env_vars=None, cmdline_args=None):
if filename is None and os.path.isfile(DEFAULT_CONFIG_LOCATION):
filename = DEFAULT_CONFIG_LOCATION
self.override(DEFAULT_CONFIG)
if filename is not None:
try:
file_config = utils.read_json_file(filename)
except ValueError as e:
raise InvalidConfigError("Failed to read configuration file "
"'{}'. Error: {}".format(filename, e))
self.override(file_config)
if env_vars is not None:
env_config = self.create_env_config(env_vars)
self.override(env_config)
if cmdline_args is not None:
cmdline_config = self.create_cmdline_config(cmdline_args)
self.override(cmdline_config)
if isinstance(self.__dict__['pipeline'], six.string_types):
from rasa_nlu import registry
if self.__dict__['pipeline'] in registry.registered_pipeline_templates:
self.__dict__['pipeline'] = registry.registered_pipeline_templates[self.__dict__['pipeline']]
else:
raise InvalidConfigError("No pipeline specified and unknown pipeline template " +
"'{}' passed. Known pipeline templates: {}".format(
self.__dict__['pipeline'],
", ".join(registry.registered_pipeline_templates.keys())))
for key, value in self.items():
setattr(self, key, value)
def test_url_data_format():
data = u"""
{
"rasa_nlu_data": {
"entity_synonyms": [
{
"value": "nyc",
"synonyms": ["New York City", "nyc", "the big apple"]
}
],
"common_examples" : [
{
"text": "show me flights to New York City",
"intent": "unk",
"entities": [
{
"entity": "destination",
"start": 19,
"end": 32,
"value": "NYC"
}
]
}
]
}
}"""
fname = utils.create_temporary_file(data.encode("utf-8"),
suffix="_tmp_training_data.json",
mode="w+b")
data = utils.read_json_file(fname)
assert data is not None
validate_rasa_nlu_data(data)
def test_url_data_format():
data = u"""
{
"rasa_nlu_data": {
"entity_synonyms": [
{
"value": "nyc",
"synonyms": ["New York City", "nyc", "the big apple"]
}
],
"common_examples" : [
{
"text": "show me flights to New York City",
"intent": "unk",
"entities": [
{
"entity": "destination",
"start": 19,
"end": 32,
"value": "NYC"
}
]
}
]
}
}"""
fname = utils.create_temporary_file(data.encode("utf-8"),
suffix="_tmp_training_data.json",
mode="w+b")
data = utils.read_json_file(fname)
assert data is not None
validate_rasa_nlu_data(data)
def _read_examples_js(self, fn, language, fformat):
"""Infer and load the example file based on the root filename and root format."""
examples_type = "usersays" if fformat == DIALOGFLOW_INTENT else "entries"
examples_fn_ending = "_{}_{}.json".format(examples_type, language)
examples_fn = fn.replace(".json", examples_fn_ending)
if os.path.isfile(examples_fn):
return utils.read_json_file(examples_fn)
else:
return None
def _read_examples_js(self, fn, language, fformat):
"""Infer and load the example file based on the root filename and root format."""
examples_type = "usersays" if fformat == DIALOGFLOW_INTENT else "entries"
examples_fn_ending = "_{}_{}.json".format(examples_type, language)
examples_fn = fn.replace(".json", examples_fn_ending)
if os.path.isfile(examples_fn):
return utils.read_json_file(examples_fn)
else:
return None
def load(model_dir):
# type: (Text) -> 'Metadata'
"""Loads the metadata from a models directory."""
try:
metadata_file = os.path.join(model_dir, 'metadata.json')
data = utils.read_json_file(metadata_file)
return Metadata(data, model_dir)
except Exception as e:
abspath = os.path.abspath(os.path.join(model_dir, 'metadata.json'))
raise InvalidProjectError("Failed to load model metadata "
"from '{}'. {}".format(abspath, e))
def load(model_dir):
# type: (Text) -> 'Metadata'
"""Loads the metadata from a models directory."""
try:
metadata_file = os.path.join(model_dir, 'metadata.json')
data = utils.read_json_file(metadata_file)
return Metadata(data, model_dir)
except Exception as e:
abspath = os.path.abspath(os.path.join(model_dir, 'metadata.json'))
raise InvalidProjectError("Failed to load model metadata "
"from '{}'. {}".format(abspath, e))
def load(cls, model_dir, model_metadata, cached_component, **kwargs):
# type: (Text, Metadata, Optional[EntitySynonymMapper], **Any) -> EntitySynonymMapper
if model_dir and model_metadata.get("entity_synonyms"):
entity_synonyms_file = os.path.join(
model_dir, model_metadata.get("entity_synonyms"))
if os.path.isfile(entity_synonyms_file):
synonyms = utils.read_json_file(entity_synonyms_file)
return EntitySynonymMapper(synonyms)
else:
warnings.warn("Failed to load synonyms file from '{}'".format(
entity_synonyms_file))
return EntitySynonymMapper()
def load(cls,
model_dir=None,
model_metadata=None,
cached_component=None,
**kwargs):
meta = model_metadata.for_component(cls.name)
file_name = meta.get('regex_file', REGEX_FEATURIZER_FILE_NAME)
regex_file = os.path.join(model_dir, file_name)
if os.path.exists(regex_file):
known_patterns = utils.read_json_file(regex_file)
return cls(meta, known_patterns=known_patterns)
else:
return cls(meta)
def load(cls,
model_dir: Optional[Text] = None,
model_metadata: Optional['Metadata'] = None,
cached_component: Optional['RegexFeaturizer'] = None,
**kwargs: Any) -> 'RegexFeaturizer':
meta = model_metadata.for_component(cls.name)
file_name = meta.get("regex_file", REGEX_FEATURIZER_FILE_NAME)
regex_file = os.path.join(model_dir, file_name)
if os.path.exists(regex_file):
known_patterns = utils.read_json_file(regex_file)
return RegexFeaturizer(meta, known_patterns=known_patterns)
else:
return RegexFeaturizer(meta)
def load(cls,
meta: Dict[Text, Any],
model_dir: Optional[Text] = None,
model_metadata: Optional['Metadata'] = None,
cached_component: Optional['RegexFeaturizer'] = None,
**kwargs: Any) -> 'RegexFeaturizer':
file_name = meta.get("file")
regex_file = os.path.join(model_dir, file_name)
if os.path.exists(regex_file):
known_patterns = utils.read_json_file(regex_file)
return RegexFeaturizer(meta, known_patterns=known_patterns)
else:
return RegexFeaturizer(meta)
def load(cls,
meta: Dict[Text, Any],
model_dir: Optional[Text] = None,
model_metadata: Optional['Metadata'] = None,
cached_component: Optional['RegexFeaturizer'] = None,
**kwargs: Any
) -> 'RegexFeaturizer':
file_name = meta.get("file")
regex_file = os.path.join(model_dir, file_name)
if os.path.exists(regex_file):
known_patterns = utils.read_json_file(regex_file)
return RegexFeaturizer(meta, known_patterns=known_patterns)
else:
return RegexFeaturizer(meta)
def load(cls,
model_dir=None,
model_metadata=None,
cached_component=None,
**kwargs):
meta = model_metadata.for_component(cls.name)
file_name = meta.get('composite_entities_file',
COMPOSITE_ENTITIES_FILE_NAME)
composite_entities_file = os.path.join(model_dir, file_name)
if os.path.isfile(composite_entities_file):
composite_entities = utils.read_json_file(composite_entities_file)
else:
composite_entities = []
warnings.warn('Failed to load composite entities'
'file from "{}"'.format(composite_entities_file))
return cls(meta, composite_entities)
def load(model_dir: Text):
"""Loads the metadata from a models directory.
Args:
model_dir (str): the directory where the model is saved.
Returns:
Metadata: A metadata object describing the model
"""
try:
metadata_file = os.path.join(model_dir, 'metadata.json')
data = utils.read_json_file(metadata_file)
return Metadata(data, model_dir)
except Exception as e:
abspath = os.path.abspath(os.path.join(model_dir, 'metadata.json'))
raise InvalidProjectError("Failed to load model metadata "
"from '{}'. {}".format(abspath, e))
def load(model_dir):
# type: (Text) -> 'Metadata'
"""Loads the metadata from a models directory.
Args:
model_dir (str): the directory where the model is saved.
Returns:
Metadata: A metadata object describing the model
"""
try:
metadata_file = os.path.join(model_dir, 'metadata.json')
data = utils.read_json_file(metadata_file)
return Metadata(data, model_dir)
except Exception as e:
abspath = os.path.abspath(os.path.join(model_dir, 'metadata.json'))
raise InvalidProjectError("Failed to load model metadata "
"from '{}'. {}".format(abspath, e))
def load(cls,
model_dir=None, # type: Optional[Text]
model_metadata=None, # type: Optional[Metadata]
cached_component=None, # type: Optional[RegexFeaturizer]
**kwargs # type: **Any
):
# type: (...) -> RegexFeaturizer
meta = model_metadata.for_component(cls.name)
file_name = meta.get("regex_file", REGEX_FEATURIZER_FILE_NAME)
regex_file = os.path.join(model_dir, file_name)
if os.path.exists(regex_file):
known_patterns = utils.read_json_file(regex_file)
return RegexFeaturizer(meta, known_patterns=known_patterns)
else:
return RegexFeaturizer(meta)
def load(cls,
model_dir=None, # type: Optional[Text]
model_metadata=None, # type: Optional[Metadata]
cached_component=None, # type: Optional[RegexFeaturizer]
**kwargs # type: **Any
):
# type: (...) -> RegexFeaturizer
if model_dir and model_metadata.get("regex_featurizer"):
regex_file = os.path.join(model_dir,
model_metadata.get("regex_featurizer"))
if os.path.isfile(regex_file):
known_patterns = utils.read_json_file(regex_file)
return RegexFeaturizer(known_patterns)
else:
warnings.warn("Failed to load regex pattern file "
"'{}'".format(regex_file))
return RegexFeaturizer()
def load(
cls,
model_dir=None, # type: Optional[Text]
model_metadata=None, # type: Optional[Metadata]
cached_component=None, # type: Optional[RegexFeaturizer]
**kwargs # type: **Any
):
# type: (...) -> RegexFeaturizer
meta = model_metadata.for_component(cls.name)
file_name = meta.get("regex_file", REGEX_FEATURIZER_FILE_NAME)
regex_file = os.path.join(model_dir, file_name)
if os.path.exists(regex_file):
known_patterns = utils.read_json_file(regex_file)
return RegexFeaturizer(meta, known_patterns=known_patterns)
else:
return RegexFeaturizer(meta)
def load(cls,
model_dir: Optional[Text] = None,
model_metadata: Optional[Metadata] = None,
cached_component: Optional['EntitySynonymMapper'] = None,
**kwargs: Any) -> 'EntitySynonymMapper':
meta = model_metadata.for_component(cls.name)
file_name = meta.get("synonyms_file")
if not file_name:
synonyms = None
return cls(meta, synonyms)
entity_synonyms_file = os.path.join(model_dir, file_name)
if os.path.isfile(entity_synonyms_file):
synonyms = utils.read_json_file(entity_synonyms_file)
else:
synonyms = None
warnings.warn("Failed to load synonyms file from '{}'"
"".format(entity_synonyms_file))
return cls(meta, synonyms)
def load(
cls,
model_dir=None, # type: Text
model_metadata=None, # type: Metadata
cached_component=None, # type: Optional[DucklingHTTPExtractor]
**kwargs # type: **Any
):
# type: (...) -> DucklingHTTPExtractor
persisted = os.path.join(model_dir, model_metadata.get(cls.name))
config = kwargs.get("config", {})
dimensions = None
if os.path.isfile(persisted):
persisted_data = utils.read_json_file(persisted)
dimensions = persisted_data["dimensions"]
return DucklingHTTPExtractor(config.get("duckling_http_url"),
model_metadata.get("language"),
dimensions)
def read(self, fn, **kwargs):
# type: ([Text]) -> TrainingData
"""Loads training data stored in the Dialogflow data format."""
language = kwargs["language"]
fformat = kwargs["fformat"]
if fformat not in {DIALOGFLOW_INTENT, DIALOGFLOW_ENTITIES}:
raise ValueError("fformat must be either {}, or {}".format(DIALOGFLOW_INTENT, DIALOGFLOW_ENTITIES))
root_js = utils.read_json_file(fn)
examples_js = self._read_examples_js(fn, language, fformat)
if not examples_js:
logger.warning("No training examples found for dialogflow file {}!".format(fn))
return TrainingData()
elif fformat == DIALOGFLOW_INTENT:
return self._read_intent(root_js, examples_js)
elif fformat == DIALOGFLOW_ENTITIES:
return self._read_entities(examples_js)
def load(cls,
model_dir=None, # type: Optional[Text]
model_metadata=None, # type: Optional[Metadata]
cached_component=None, # type: Optional[EntitySynonymMapper]
**kwargs # type: **Any
):
# type: (...) -> EntitySynonymMapper
meta = model_metadata.for_component(cls.name)
file_name = meta.get("synonyms_file", ENTITY_SYNONYMS_FILE_NAME)
entity_synonyms_file = os.path.join(model_dir, file_name)
if os.path.isfile(entity_synonyms_file):
synonyms = utils.read_json_file(entity_synonyms_file)
else:
synonyms = None
warnings.warn("Failed to load synonyms file from '{}'"
"".format(entity_synonyms_file))
return EntitySynonymMapper(meta, synonyms)
def load(
cls,
model_dir=None, # type: Optional[Text]
model_metadata=None, # type: Optional[Metadata]
cached_component=None, # type: Optional[Component]
**kwargs # type: **Any
):
from rasa_nlu.utils import read_json_file
meta = model_metadata.for_component(cls.name)
file_name = meta.get("gazette_file", FUZZY_GAZETTE_FILE)
path = os.path.join(model_dir, file_name)
if os.path.isfile(path):
gazette = read_json_file(path)
else:
gazette = None
warnings.warn("Failed to load gazette file from '{}'"
"".format(path))
return FuzzyGazette(meta, gazette)
def load(cls,
model_dir=None, # type: Text
model_metadata=None, # type: Metadata
cached_component=None, # type:Optional[DucklingExtractor]
**kwargs # type: **Any
):
# type: (...) -> DucklingExtractor
persisted = os.path.join(model_dir,
model_metadata.get("ner_duckling_persisted"))
if cached_component:
duckling = cached_component.duckling
else:
language = model_metadata.get("language")
duckling = cls.create_duckling_wrapper(language)
if os.path.isfile(persisted):
persisted_data = utils.read_json_file(persisted)
return DucklingExtractor(duckling, persisted_data["dimensions"])
else:
return DucklingExtractor(duckling)
def load(cls,
meta: Dict[Text, Any],
model_dir: Optional[Text] = None,
model_metadata: Optional[Metadata] = None,
cached_component: Optional['EntitySynonymMapper'] = None,
**kwargs: Any
) -> 'EntitySynonymMapper':
file_name = meta.get("file")
if not file_name:
synonyms = None
return cls(meta, synonyms)
entity_synonyms_file = os.path.join(model_dir, file_name)
if os.path.isfile(entity_synonyms_file):
synonyms = utils.read_json_file(entity_synonyms_file)
else:
synonyms = None
warnings.warn("Failed to load synonyms file from '{}'"
"".format(entity_synonyms_file))
return cls(meta, synonyms)
def read(self, fn: Text, **kwargs: Any) -> 'TrainingData':
"""Loads training data stored in the Dialogflow data format."""
from rasa_nlu.training_data import TrainingData
language = kwargs["language"]
fformat = kwargs["fformat"]
if fformat not in {DIALOGFLOW_INTENT, DIALOGFLOW_ENTITIES}:
raise ValueError("fformat must be either {}, or {}"
"".format(DIALOGFLOW_INTENT, DIALOGFLOW_ENTITIES))
root_js = utils.read_json_file(fn)
examples_js = self._read_examples_js(fn, language, fformat)
if not examples_js:
logger.warning("No training examples found for dialogflow file {}!"
"".format(fn))
return TrainingData()
elif fformat == DIALOGFLOW_INTENT:
return self._read_intent(root_js, examples_js)
elif fformat == DIALOGFLOW_ENTITIES:
return self._read_entities(root_js, examples_js)
def _read_composite_entities(self):
"""Read the defined composite patterns from the train file. We have
to manually load the file, as rasa strips our custom information.
"""
try:
file = self._get_train_file_cmd()
except:
try:
file = self._get_train_file_http()
except:
warnings.warn('The CompositeEntityExtractor could not load '
'the train file.')
return []
file_content = utils.read_json_file(file)
rasa_nlu_data = file_content['rasa_nlu_data']
try:
composite_entities = rasa_nlu_data['composite_entities']
except KeyError:
composite_entities = []
if not composite_entities:
warnings.warn(
'CompositeEntityExtractor was added to the '
'pipeline but no composite entites have been defined.')
return composite_entities
def test_example_training_data_is_valid():
demo_json = 'data/examples/rasa/demo-rasa.json'
data = utils.read_json_file(demo_json)
validate_rasa_nlu_data(data)
def test_example_training_data_is_valid():
demo_json = 'data/examples/rasa/demo-rasa.json'
data = utils.read_json_file(demo_json)
validate_rasa_nlu_data(data)
