async def _train_nlu_async(
config: Text,
nlu_data: Text,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
):
# training NLU only hence the training files still have to be selected
file_importer = TrainingDataImporter.load_nlu_importer_from_config(
config, training_data_paths=[nlu_data])
training_datas = await file_importer.get_nlu_data()
if training_datas.is_empty():
print_error(
"No NLU data given. Please provide NLU data in order to train "
"a Rasa NLU model using the '--nlu' argument.")
return
return await _train_nlu_with_validated_data(
file_importer,
output=output,
train_path=train_path,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
)
async def _train_nlu_async(
config: Text,
nlu_data: Text,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
additional_arguments: Optional[Dict] = None,
):
if not nlu_data:
print_error(
"No NLU data given. Please provide NLU data in order to train "
"a Rasa NLU model using the '--nlu' argument.")
return
# training NLU only hence the training files still have to be selected
file_importer = TrainingDataImporter.load_nlu_importer_from_config(
config, training_data_paths=[nlu_data])
training_datas = await file_importer.get_nlu_data()
if training_datas.is_empty():
print_error(f"Path '{nlu_data}' doesn't contain valid NLU data in it. "
"Please verify the data format. "
"The NLU model training will be skipped now.")
return
return await _train_nlu_with_validated_data(
file_importer,
output=output,
train_path=train_path,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
additional_arguments=additional_arguments,
)
async def test_eval_data(component_builder, tmpdir, project):
_config = RasaNLUModelConfig({
"pipeline": [
{
"name": "WhitespaceTokenizer"
},
{
"name": "CountVectorsFeaturizer"
},
{
"name": "DIETClassifier",
"epochs": 2
},
{
"name": "ResponseSelector",
"epochs": 2
},
],
"language":
"en",
})
config_path = os.path.join(project, "config.yml")
data_importer = TrainingDataImporter.load_nlu_importer_from_config(
config_path,
training_data_paths=[
"data/examples/rasa/demo-rasa.md",
"data/examples/rasa/demo-rasa-responses.md",
],
)
(_, _, persisted_path) = await train(
_config,
path=tmpdir.strpath,
data=data_importer,
component_builder=component_builder,
persist_nlu_training_data=True,
)
interpreter = Interpreter.load(persisted_path, component_builder)
data = await data_importer.get_nlu_data()
intent_results, response_selection_results, entity_results, = get_eval_data(
interpreter, data)
assert len(intent_results) == 46
assert len(response_selection_results) == 46
assert len(entity_results) == 46
async def test_nlu_only(project: Text):
config_path = os.path.join(project, DEFAULT_CONFIG_PATH)
default_data_path = os.path.join(project, DEFAULT_DATA_PATH)
actual = TrainingDataImporter.load_nlu_importer_from_config(
config_path, training_data_paths=[default_data_path])
assert isinstance(actual, NluDataImporter)
stories = await actual.get_stories()
assert stories.is_empty()
domain = await actual.get_domain()
assert domain.is_empty()
config = await actual.get_config()
assert config
nlu_data = await actual.get_nlu_data()
assert not nlu_data.is_empty()
