async def test_eval_data(
component_builder: ComponentBuilder,
tmp_path: Path,
project: Text,
unpacked_trained_rasa_model: Text,
):
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.yml",
"data/examples/rasa/demo-rasa-responses.yml",
],
)
_, nlu_model_directory = rasa.model.get_model_subdirectories(
unpacked_trained_rasa_model
)
interpreter = Interpreter.load(nlu_model_directory, 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) == 0
assert len(entity_results) == 46
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. "
f"Please verify the data format. "
f"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,
)
def train_nlu(
config: Text,
nlu_data: Optional[Text],
output: Text,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
additional_arguments: Optional[Dict] = None,
domain: Optional[Union[Domain, Text]] = None,
model_to_finetune: Optional[Text] = None,
finetuning_epoch_fraction: float = 1.0,
) -> Optional[Text]:
"""Trains an NLU model.
Args:
config: Path to the config file for NLU.
nlu_data: Path to the NLU training data.
output: Output path.
fixed_model_name: Name of the model to be stored.
persist_nlu_training_data: `True` if the NLU training data should be persisted
with the model.
additional_arguments: Additional training parameters which will be passed to
the `train` method of each component.
domain: Path to the optional domain file/Domain object.
model_to_finetune: Optional path to a model which should be finetuned or
a directory in case the latest trained model should be used.
finetuning_epoch_fraction: The fraction currently specified training epochs
in the model configuration which should be used for finetuning.
Returns:
Path to the model archive.
"""
if not nlu_data:
rasa.shared.utils.cli.print_error(
"No NLU data given. Please provide NLU data in order to train "
"a Rasa NLU model using the '--nlu' argument.")
return None
# training NLU only hence the training files still have to be selected
file_importer = TrainingDataImporter.load_nlu_importer_from_config(
config, domain, training_data_paths=[nlu_data])
training_data = file_importer.get_nlu_data()
if training_data.contains_no_pure_nlu_data():
rasa.shared.utils.cli.print_error(
f"Path '{nlu_data}' doesn't contain valid NLU data in it. "
f"Please verify the data format. "
f"The NLU model training will be skipped now.")
return None
return _train_graph(
file_importer,
training_type=TrainingType.NLU,
output_path=output,
model_to_finetune=model_to_finetune,
fixed_model_name=fixed_model_name,
finetuning_epoch_fraction=finetuning_epoch_fraction,
persist_nlu_training_data=persist_nlu_training_data,
**(additional_arguments or {}),
).model
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 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,
domain: Optional[Union[Domain, Text]] = None,
model_to_finetune: Optional[Text] = None,
finetuning_epoch_fraction: float = 1.0,
) -> Optional[Text]:
"""Trains an NLU model asynchronously."""
if not nlu_data:
rasa.shared.utils.cli.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, domain, training_data_paths=[nlu_data]
)
training_data = await file_importer.get_nlu_data()
if training_data.contains_no_pure_nlu_data():
rasa.shared.utils.cli.print_error(
f"Path '{nlu_data}' doesn't contain valid NLU data in it. "
f"Please verify the data format. "
f"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,
model_to_finetune=model_to_finetune,
finetuning_epoch_fraction=finetuning_epoch_fraction,
)
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)
assert isinstance(actual._importer, RetrievalModelsDataImporter)
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()
async def test_eval_data(tmp_path: Path, project: Text,
trained_rasa_model: Text):
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.yml",
"data/examples/rasa/demo-rasa-responses.yml",
],
)
processor = Agent.load(trained_rasa_model).processor
data = data_importer.get_nlu_data()
(intent_results, response_selection_results,
entity_results) = await get_eval_data(processor, data)
assert len(intent_results) == 46
assert len(response_selection_results) == 46
assert len(entity_results) == 46