async def test_events_schema(monkeypatch: MonkeyPatch):
# this allows us to patch the printing part used in debug mode to collect the
# reported events
monkeypatch.setenv("RASA_TELEMETRY_DEBUG", "true")
monkeypatch.setenv("RASA_TELEMETRY_ENABLED", "true")
mock = Mock()
monkeypatch.setattr(telemetry, "print_telemetry_event", mock)
with open(TELEMETRY_EVENTS_JSON) as f:
schemas = json.load(f)["events"]
initial = asyncio.Task.all_tasks()
# Generate all known backend telemetry events, and then use events.json to
# validate their schema.
training_data = TrainingDataImporter.load_from_config(DEFAULT_CONFIG_PATH)
async with telemetry.track_model_training(training_data, "rasa"):
await asyncio.sleep(1)
await telemetry.track_telemetry_disabled()
pending = asyncio.Task.all_tasks() - initial
await asyncio.gather(*pending)
assert mock.call_count == 3
for call in mock.call_args_list:
event = call.args[0]
# `metrics_id` automatically gets added to all event but is
# not part of the schema so we need to remove it before validation
del event["properties"]["metrics_id"]
jsonschema.validate(instance=event["properties"],
schema=schemas[event["event"]])
async def test_events_schema(
monkeypatch: MonkeyPatch, default_agent: Agent, config_path: Text
):
# this allows us to patch the printing part used in debug mode to collect the
# reported events
monkeypatch.setenv("RASA_TELEMETRY_DEBUG", "true")
monkeypatch.setenv("RASA_TELEMETRY_ENABLED", "true")
mock = Mock()
monkeypatch.setattr(telemetry, "print_telemetry_event", mock)
with open(TELEMETRY_EVENTS_JSON) as f:
schemas = json.load(f)["events"]
initial = asyncio.all_tasks()
# Generate all known backend telemetry events, and then use events.json to
# validate their schema.
training_data = TrainingDataImporter.load_from_config(config_path)
with telemetry.track_model_training(training_data, "rasa"):
await asyncio.sleep(1)
telemetry.track_telemetry_disabled()
telemetry.track_data_split(0.5, "nlu")
telemetry.track_validate_files(True)
telemetry.track_data_convert("yaml", "nlu")
telemetry.track_tracker_export(5, TrackerStore(domain=None), EventBroker())
telemetry.track_interactive_learning_start(True, False)
telemetry.track_server_start([CmdlineInput()], None, None, 42, True)
telemetry.track_project_init("tests/")
telemetry.track_shell_started("nlu")
telemetry.track_rasa_x_local()
telemetry.track_visualization()
telemetry.track_core_model_test(5, True, default_agent)
telemetry.track_nlu_model_test(TrainingData())
pending = asyncio.all_tasks() - initial
await asyncio.gather(*pending)
assert mock.call_count == 15
for args, _ in mock.call_args_list:
event = args[0]
# `metrics_id` automatically gets added to all event but is
# not part of the schema so we need to remove it before validation
del event["properties"]["metrics_id"]
jsonschema.validate(
instance=event["properties"], schema=schemas[event["event"]]
)
async def _train_nlu_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Train NLU with validated training and config data."""
import rasa.nlu.train
if additional_arguments is None:
additional_arguments = {}
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(
TempDirectoryPath(tempfile.mkdtemp()))
config = await file_importer.get_config()
print_color("Training NLU model...",
color=rasa.shared.utils.io.bcolors.OKBLUE)
async with telemetry.track_model_training(file_importer,
model_type="nlu"):
await rasa.nlu.train(
config,
file_importer,
_train_path,
fixed_model_name="nlu",
persist_nlu_training_data=persist_nlu_training_data,
**additional_arguments,
)
print_color("NLU model training completed.",
color=rasa.shared.utils.io.bcolors.OKBLUE)
if train_path is None:
# Only NLU was trained
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="nlu-",
)
return _train_path
async def _train_core_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
additional_arguments: Optional[Dict] = None,
interpreter: Optional[Interpreter] = None,
) -> Optional[Text]:
"""Train Core with validated training and config data."""
import rasa.core.train
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(
TempDirectoryPath(tempfile.mkdtemp()))
# normal (not compare) training
print_color("Training Core model...",
color=rasa.shared.utils.io.bcolors.OKBLUE)
domain, config = await asyncio.gather(file_importer.get_domain(),
file_importer.get_config())
async with telemetry.track_model_training(file_importer,
model_type="core"):
await rasa.core.train(
domain_file=domain,
training_resource=file_importer,
output_path=os.path.join(_train_path,
DEFAULT_CORE_SUBDIRECTORY_NAME),
policy_config=config,
additional_arguments=additional_arguments,
interpreter=interpreter,
)
print_color("Core model training completed.",
color=rasa.shared.utils.io.bcolors.OKBLUE)
if train_path is None:
# Only Core was trained.
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="core-",
)
return _train_path
async def _train_nlu_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
additional_arguments: Optional[Dict] = None,
model_to_finetune: Optional["Text"] = None,
finetuning_epoch_fraction: float = 1.0,
) -> Optional[Text]:
"""Train NLU with validated training and config data."""
import rasa.nlu.train
if additional_arguments is None:
additional_arguments = {}
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(
TempDirectoryPath(tempfile.mkdtemp()))
config = await file_importer.get_config()
rasa.shared.utils.cli.print_color(
"Training NLU model...", color=rasa.shared.utils.io.bcolors.OKBLUE)
if model_to_finetune:
rasa.shared.utils.common.mark_as_experimental_feature(
"Incremental Training feature")
model_to_finetune = await _nlu_model_for_finetuning(
model_to_finetune,
file_importer,
finetuning_epoch_fraction,
called_from_combined_training=train_path is not None,
)
if not model_to_finetune:
rasa.shared.utils.cli.print_error_and_exit(
f"No NLU model for finetuning found. Please make sure to either "
f"specify a path to a previous model or to have a finetunable "
f"model within the directory '{output}'.")
async with telemetry.track_model_training(
file_importer,
model_type="nlu",
is_finetuning=model_to_finetune is not None,
):
await rasa.nlu.train.train(
config,
file_importer,
_train_path,
fixed_model_name="nlu",
persist_nlu_training_data=persist_nlu_training_data,
model_to_finetune=model_to_finetune,
**additional_arguments,
)
rasa.shared.utils.cli.print_color(
"NLU model training completed.",
color=rasa.shared.utils.io.bcolors.OKBLUE)
if train_path is None:
# Only NLU was trained
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="nlu-",
)
return _train_path
async def _train_core_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
additional_arguments: Optional[Dict] = None,
interpreter: Optional[Interpreter] = None,
model_to_finetune: Optional["Text"] = None,
finetuning_epoch_fraction: float = 1.0,
) -> Optional[Text]:
"""Train Core with validated training and config data."""
import rasa.core.train
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(
TempDirectoryPath(tempfile.mkdtemp()))
# normal (not compare) training
rasa.shared.utils.cli.print_color(
"Training Core model...",
color=rasa.shared.utils.io.bcolors.OKBLUE)
domain, config = await asyncio.gather(file_importer.get_domain(),
file_importer.get_config())
if model_to_finetune:
rasa.shared.utils.common.mark_as_experimental_feature(
"Incremental Training feature")
model_to_finetune = await _core_model_for_finetuning(
model_to_finetune,
file_importer=file_importer,
finetuning_epoch_fraction=finetuning_epoch_fraction,
)
if not model_to_finetune:
rasa.shared.utils.cli.print_error_and_exit(
f"No Core model for finetuning found. Please make sure to either "
f"specify a path to a previous model or to have a finetunable "
f"model within the directory '{output}'.")
async with telemetry.track_model_training(
file_importer,
model_type="core",
is_finetuning=model_to_finetune is not None,
):
await rasa.core.train.train(
domain_file=domain,
training_resource=file_importer,
output_path=os.path.join(_train_path,
DEFAULT_CORE_SUBDIRECTORY_NAME),
policy_config=config,
additional_arguments=additional_arguments,
interpreter=interpreter,
model_to_finetune=model_to_finetune,
)
rasa.shared.utils.cli.print_color(
"Core model training completed.",
color=rasa.shared.utils.io.bcolors.OKBLUE)
if train_path is None:
# Only Core was trained.
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="core-",
)
return _train_path
async def _train_async_internal(
file_importer: TrainingDataImporter,
train_path: Text,
output_path: Text,
dry_run: bool,
force_training: bool,
fixed_model_name: Optional[Text],
persist_nlu_training_data: bool,
core_additional_arguments: Optional[Dict] = None,
nlu_additional_arguments: Optional[Dict] = None,
model_to_finetune: Optional[Text] = None,
finetuning_epoch_fraction: float = 1.0,
) -> TrainingResult:
"""Trains a Rasa model (Core and NLU). Use only from `train_async`.
Args:
file_importer: `TrainingDataImporter` which supplies the training data.
train_path: Directory in which to train the model.
output_path: Output path.
dry_run: If `True` then no training will be done, and the information about
whether the training needs to be done will be printed.
force_training: If `True` retrain model even if data has not changed.
fixed_model_name: Name of model to be stored.
persist_nlu_training_data: `True` if the NLU training data should be persisted
with the model.
core_additional_arguments: Additional training parameters for core training.
nlu_additional_arguments: Additional training parameters forwarded to training
method of each NLU component.
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:
An instance of `TrainingResult`.
"""
stories, nlu_data = await asyncio.gather(file_importer.get_stories(),
file_importer.get_nlu_data())
new_fingerprint = await model.model_fingerprint(file_importer)
old_model = model.get_latest_model(output_path)
fingerprint_comparison = model.should_retrain(
new_fingerprint, old_model, train_path, force_training=force_training)
if dry_run:
code, texts = dry_run_result(fingerprint_comparison)
for text in texts:
print_warning(text) if code > 0 else print_success(text)
return TrainingResult(code=code)
if nlu_data.has_e2e_examples():
rasa.shared.utils.common.mark_as_experimental_feature(
"end-to-end training")
if stories.is_empty() and nlu_data.contains_no_pure_nlu_data():
rasa.shared.utils.cli.print_error(
"No training data given. Please provide stories and NLU data in "
"order to train a Rasa model using the '--data' argument.")
return TrainingResult()
if stories.is_empty():
rasa.shared.utils.cli.print_warning(
"No stories present. Just a Rasa NLU model will be trained.")
trained_model = await _train_nlu_with_validated_data(
file_importer,
output=output_path,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
additional_arguments=nlu_additional_arguments,
model_to_finetune=model_to_finetune,
finetuning_epoch_fraction=finetuning_epoch_fraction,
)
return TrainingResult(model=trained_model)
# We will train nlu if there are any nlu example, including from e2e stories.
if nlu_data.contains_no_pure_nlu_data(
) and not nlu_data.has_e2e_examples():
rasa.shared.utils.cli.print_warning(
"No NLU data present. Just a Rasa Core model will be trained.")
trained_model = await _train_core_with_validated_data(
file_importer,
output=output_path,
fixed_model_name=fixed_model_name,
additional_arguments=core_additional_arguments,
model_to_finetune=model_to_finetune,
finetuning_epoch_fraction=finetuning_epoch_fraction,
)
return TrainingResult(model=trained_model)
new_fingerprint = await model.model_fingerprint(file_importer)
old_model = model.get_latest_model(output_path)
if not force_training:
fingerprint_comparison = model.should_retrain(
new_fingerprint,
old_model,
train_path,
has_e2e_examples=nlu_data.has_e2e_examples(),
)
else:
fingerprint_comparison = FingerprintComparisonResult(
force_training=True)
if fingerprint_comparison.is_training_required():
async with telemetry.track_model_training(
file_importer,
model_type="rasa",
):
await _do_training(
file_importer,
output_path=output_path,
train_path=train_path,
fingerprint_comparison_result=fingerprint_comparison,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
core_additional_arguments=core_additional_arguments,
nlu_additional_arguments=nlu_additional_arguments,
old_model_zip_path=old_model,
model_to_finetune=model_to_finetune,
finetuning_epoch_fraction=finetuning_epoch_fraction,
)
trained_model = model.package_model(
fingerprint=new_fingerprint,
output_directory=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
)
return TrainingResult(model=trained_model)
rasa.shared.utils.cli.print_success(
"Nothing changed. You can use the old model stored at '{}'."
"".format(os.path.abspath(old_model)))
return TrainingResult(model=old_model)
async def _train_async_internal(
file_importer: TrainingDataImporter,
train_path: Text,
output_path: Text,
force_training: bool,
fixed_model_name: Optional[Text],
persist_nlu_training_data: bool,
core_additional_arguments: Optional[Dict] = None,
nlu_additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Rasa model (Core and NLU). Use only from `train_async`.
Args:
file_importer: `TrainingDataImporter` which supplies the training data.
train_path: Directory in which to train the model.
output_path: Output path.
force_training: If `True` retrain model even if data has not changed.
fixed_model_name: Name of model to be stored.
persist_nlu_training_data: `True` if the NLU training data should be persisted
with the model.
core_additional_arguments: Additional training parameters for core training.
nlu_additional_arguments: Additional training parameters forwarded to training
method of each NLU component.
Returns:
Path of the trained model archive.
"""
stories, nlu_data = await asyncio.gather(file_importer.get_stories(),
file_importer.get_nlu_data())
if stories.is_empty() and nlu_data.is_empty():
print_error(
"No training data given. Please provide stories and NLU data in "
"order to train a Rasa model using the '--data' argument.")
return
if stories.is_empty():
print_warning(
"No stories present. Just a Rasa NLU model will be trained.")
return await _train_nlu_with_validated_data(
file_importer,
output=output_path,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
additional_arguments=nlu_additional_arguments,
)
if nlu_data.is_empty():
print_warning(
"No NLU data present. Just a Rasa Core model will be trained.")
return await _train_core_with_validated_data(
file_importer,
output=output_path,
fixed_model_name=fixed_model_name,
additional_arguments=core_additional_arguments,
)
new_fingerprint = await model.model_fingerprint(file_importer)
old_model = model.get_latest_model(output_path)
if not force_training:
fingerprint_comparison = model.should_retrain(new_fingerprint,
old_model, train_path)
else:
fingerprint_comparison = FingerprintComparisonResult(
force_training=True)
if fingerprint_comparison.is_training_required():
async with telemetry.track_model_training(file_importer,
model_type="rasa"):
await _do_training(
file_importer,
output_path=output_path,
train_path=train_path,
fingerprint_comparison_result=fingerprint_comparison,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
core_additional_arguments=core_additional_arguments,
nlu_additional_arguments=nlu_additional_arguments,
old_model_zip_path=old_model,
)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
)
print_success("Nothing changed. You can use the old model stored at '{}'."
"".format(os.path.abspath(old_model)))
return old_model
def train(
domain: Text,
config: Text,
training_files: Optional[Union[Text, List[Text]]],
output: Text = rasa.shared.constants.DEFAULT_MODELS_PATH,
dry_run: bool = False,
force_training: bool = False,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
core_additional_arguments: Optional[Dict] = None,
nlu_additional_arguments: Optional[Dict] = None,
model_to_finetune: Optional[Text] = None,
finetuning_epoch_fraction: float = 1.0,
) -> TrainingResult:
"""Trains a Rasa model (Core and NLU).
Args:
domain: Path to the domain file.
config: Path to the config file.
training_files: List of paths to training data files.
output: Output directory for the trained model.
dry_run: If `True` then no training will be done, and the information about
whether the training needs to be done will be printed.
force_training: If `True` retrain model even if data has not changed.
fixed_model_name: Name of model to be stored.
persist_nlu_training_data: `True` if the NLU training data should be persisted
with the model.
core_additional_arguments: Additional training parameters for core training.
nlu_additional_arguments: Additional training parameters forwarded to training
method of each NLU component.
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:
An instance of `TrainingResult`.
"""
file_importer = TrainingDataImporter.load_from_config(
config, domain, training_files)
stories = file_importer.get_stories()
nlu_data = file_importer.get_nlu_data()
training_type = TrainingType.BOTH
if nlu_data.has_e2e_examples():
rasa.shared.utils.common.mark_as_experimental_feature(
"end-to-end training")
training_type = TrainingType.END_TO_END
if stories.is_empty() and nlu_data.contains_no_pure_nlu_data():
rasa.shared.utils.cli.print_error(
"No training data given. Please provide stories and NLU data in "
"order to train a Rasa model using the '--data' argument.")
return TrainingResult(code=1)
domain = file_importer.get_domain()
if domain.is_empty():
rasa.shared.utils.cli.print_warning(
"Core training was skipped because no valid domain file was found. "
"Only an NLU-model was created. Please specify a valid domain using "
"the '--domain' argument or check if the provided domain file exists."
)
training_type = TrainingType.NLU
elif stories.is_empty():
rasa.shared.utils.cli.print_warning(
"No stories present. Just a Rasa NLU model will be trained.")
training_type = TrainingType.NLU
# We will train nlu if there are any nlu example, including from e2e stories.
elif nlu_data.contains_no_pure_nlu_data(
) and not nlu_data.has_e2e_examples():
rasa.shared.utils.cli.print_warning(
"No NLU data present. Just a Rasa Core model will be trained.")
training_type = TrainingType.CORE
with telemetry.track_model_training(file_importer, model_type="rasa"):
return _train_graph(
file_importer,
training_type=training_type,
output_path=output,
fixed_model_name=fixed_model_name,
model_to_finetune=model_to_finetune,
force_full_training=force_training,
persist_nlu_training_data=persist_nlu_training_data,
finetuning_epoch_fraction=finetuning_epoch_fraction,
dry_run=dry_run,
**(core_additional_arguments or {}),
**(nlu_additional_arguments or {}),
)
def _train_graph(
file_importer: TrainingDataImporter,
training_type: TrainingType,
output_path: Text,
fixed_model_name: Text,
model_to_finetune: Optional[Text] = None,
force_full_training: bool = False,
dry_run: bool = False,
**kwargs: Any,
) -> TrainingResult:
if model_to_finetune:
model_to_finetune = rasa.model.get_model_for_finetuning(
model_to_finetune)
if not model_to_finetune:
rasa.shared.utils.cli.print_error_and_exit(
f"No model for finetuning found. Please make sure to either "
f"specify a path to a previous model or to have a finetunable "
f"model within the directory '{output_path}'.")
rasa.shared.utils.common.mark_as_experimental_feature(
"Incremental Training feature")
is_finetuning = model_to_finetune is not None
config = file_importer.get_config()
recipe = Recipe.recipe_for_name(config.get("recipe"))
config, _missing_keys, _configured_keys = recipe.auto_configure(
file_importer.get_config_file_for_auto_config(),
config,
training_type,
)
model_configuration = recipe.graph_config_for_recipe(
config,
kwargs,
training_type=training_type,
is_finetuning=is_finetuning,
)
rasa.engine.validation.validate(model_configuration)
with tempfile.TemporaryDirectory() as temp_model_dir:
model_storage = _create_model_storage(is_finetuning, model_to_finetune,
Path(temp_model_dir))
cache = LocalTrainingCache()
trainer = GraphTrainer(model_storage, cache, DaskGraphRunner)
if dry_run:
fingerprint_status = trainer.fingerprint(
model_configuration.train_schema, file_importer)
return _dry_run_result(fingerprint_status, force_full_training)
model_name = _determine_model_name(fixed_model_name, training_type)
full_model_path = Path(output_path, model_name)
with telemetry.track_model_training(
file_importer, model_type=training_type.model_type):
trainer.train(
model_configuration,
file_importer,
full_model_path,
force_retraining=force_full_training,
is_finetuning=is_finetuning,
)
rasa.shared.utils.cli.print_success(
f"Your Rasa model is trained and saved at '{full_model_path}'."
)
return TrainingResult(str(full_model_path), 0)
async def _train_nlu_with_validated_data(
file_importer: TrainingDataImporter,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
persist_nlu_training_data: bool = False,
retrain_nlu: Union[bool, List[Text]] = True,
additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Train NLU with validated training and config data."""
import rasa.nlu.train
if additional_arguments is None:
additional_arguments = {}
with ExitStack() as stack:
if train_path:
# If the train path was provided, do nothing on exit.
_train_path = train_path
else:
# Otherwise, create a temp train path and clean it up on exit.
_train_path = stack.enter_context(TempDirectoryPath(tempfile.mkdtemp()))
# bf mod
config = await file_importer.get_nlu_config(retrain_nlu)
async with telemetry.track_model_training(file_importer, model_type="nlu"):
for lang in config:
if config[lang]:
print_color(
"Start training <{}> NLU model ...".format(lang),
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
await rasa.nlu.train(
config[lang],
file_importer,
_train_path,
fixed_model_name="nlu-{}".format(lang),
persist_nlu_training_data=persist_nlu_training_data,
**additional_arguments,
)
else:
print_color(
"NLU data for language <{}> didn't change, skipping training...".format(
lang
),
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
# /bf mod
print_color(
"NLU model training completed.", color=rasa.shared.utils.io.bcolors.OKBLUE
)
if train_path is None:
# Only NLU was trained
new_fingerprint = await model.model_fingerprint(file_importer)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output,
train_path=_train_path,
fixed_model_name=fixed_model_name,
model_prefix="nlu-",
)
return _train_path
async def _train_async_internal(
file_importer: TrainingDataImporter,
train_path: Text,
output_path: Text,
force_training: bool,
fixed_model_name: Optional[Text],
persist_nlu_training_data: bool,
core_additional_arguments: Optional[Dict] = None,
nlu_additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Rasa model (Core and NLU). Use only from `train_async`.
Args:
file_importer: `TrainingDataImporter` which supplies the training data.
train_path: Directory in which to train the model.
output_path: Output path.
force_training: If `True` retrain model even if data has not changed.
fixed_model_name: Name of model to be stored.
persist_nlu_training_data: `True` if the NLU training data should be persisted
with the model.
core_additional_arguments: Additional training parameters for core training.
nlu_additional_arguments: Additional training parameters forwarded to training
method of each NLU component.
Returns:
Path of the trained model archive.
"""
stories, nlu_data = await asyncio.gather(
file_importer.get_stories(), file_importer.get_nlu_data()
)
# if stories.is_empty() and nlu_data.can_train_nlu_model():
# print_error(
# "No training data given. Please provide stories and NLU data in "
# "order to train a Rasa model using the '--data' argument."
# )
# return
# if stories.is_empty():
# print_warning("No stories present. Just a Rasa NLU model will be trained.")
# return await _train_nlu_with_validated_data(
# file_importer,
# output=output_path,
# fixed_model_name=fixed_model_name,
# persist_nlu_training_data=persist_nlu_training_data,
# additional_arguments=nlu_additional_arguments,
# )
# if nlu_data.can_train_nlu_model():
# print_warning("No NLU data present. Just a Rasa Core model will be trained.")
# return await _train_core_with_validated_data(
# file_importer,
# output=output_path,
# fixed_model_name=fixed_model_name,
# additional_arguments=core_additional_arguments,
# )
new_fingerprint = await model.model_fingerprint(file_importer)
old_model = model.get_latest_model(output_path)
if not force_training:
fingerprint_comparison = model.should_retrain(
new_fingerprint, old_model, train_path
)
else:
fingerprint_comparison = FingerprintComparisonResult(force_training=True)
# bf mod >
if fingerprint_comparison.nlu == True: # replace True with list of all langs
fingerprint_comparison.nlu = list(new_fingerprint.get("nlu-config", {}).keys())
domain = await file_importer.get_domain()
core_untrainable = domain.is_empty() or stories.is_empty()
nlu_untrainable = [l for l, d in nlu_data.items() if d.is_empty()]
fingerprint_comparison.core = fingerprint_comparison.core and not core_untrainable
fingerprint_comparison.nlu = [
l for l in fingerprint_comparison.nlu if l not in nlu_untrainable
]
if core_untrainable:
print_color(
"Skipping Core training since domain or stories are empty.",
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
for lang in nlu_untrainable:
print_color(
"No NLU data found for language <{}>, skipping training...".format(lang),
color=rasa.shared.utils.io.bcolors.OKBLUE,
)
# </ bf mod
if fingerprint_comparison.is_training_required():
async with telemetry.track_model_training(file_importer, model_type="rasa"):
await _do_training(
file_importer,
output_path=output_path,
train_path=train_path,
fingerprint_comparison_result=fingerprint_comparison,
fixed_model_name=fixed_model_name,
persist_nlu_training_data=persist_nlu_training_data,
core_additional_arguments=core_additional_arguments,
nlu_additional_arguments=nlu_additional_arguments,
old_model_zip_path=old_model,
)
return model.package_model(
fingerprint=new_fingerprint,
output_directory=output_path,
train_path=train_path,
fixed_model_name=fixed_model_name,
)
print_success(
"Nothing changed. You can use the old model stored at '{}'."
"".format(os.path.abspath(old_model))
)
return old_model
