async def train_comparison_models(
story_file: Text,
domain: Text,
output_path: Text = "",
exclusion_percentages: Optional[List] = None,
policy_configs: Optional[List] = None,
runs: int = 1,
dump_stories: bool = False,
additional_arguments: Optional[Dict] = None,
):
"""Train multiple models for comparison of policies"""
from rasa import model
from rasa.importers.importer import TrainingDataImporter
exclusion_percentages = exclusion_percentages or []
policy_configs = policy_configs or []
for r in range(runs):
logging.info("Starting run {}/{}".format(r + 1, runs))
for current_run, percentage in enumerate(exclusion_percentages, 1):
for policy_config in policy_configs:
file_importer = TrainingDataImporter.load_core_importer_from_config(
policy_config, domain, [story_file])
config_name = os.path.splitext(
os.path.basename(policy_config))[0]
logging.info("Starting to train {} round {}/{}"
" with {}% exclusion"
"".format(config_name, current_run,
len(exclusion_percentages), percentage))
with TempDirectoryPath(tempfile.mkdtemp()) as train_path:
_, new_fingerprint = await asyncio.gather(
train(
domain,
file_importer,
train_path,
policy_config=policy_config,
exclusion_percentage=percentage,
additional_arguments=additional_arguments,
dump_stories=dump_stories,
),
model.model_fingerprint(file_importer),
)
output_dir = os.path.join(output_path, "run_" + str(r + 1))
model_name = config_name + PERCENTAGE_KEY + str(percentage)
model.package_model(
fingerprint=new_fingerprint,
output_directory=output_dir,
train_path=train_path,
fixed_model_name=model_name,
)
async def train_core_async(
domain: Union[Domain, Text],
config: Text,
stories: Text,
output: Text,
train_path: Optional[Text] = None,
fixed_model_name: Optional[Text] = None,
additional_arguments: Optional[Dict] = None,
) -> Optional[Text]:
"""Trains a Core model.
Args:
domain: Path to the domain file.
config: Path to the config file for Core.
stories: Path to the Core training data.
output: Output path.
train_path: If `None` the model will be trained in a temporary
directory, otherwise in the provided directory.
fixed_model_name: Name of model to be stored.
uncompress: If `True` the model will not be compressed.
additional_arguments: Additional training parameters.
Returns:
If `train_path` is given it returns the path to the model archive,
otherwise the path to the directory with the trained model files.
"""
file_importer = TrainingDataImporter.load_core_importer_from_config(
config, domain, [stories]
)
domain = await file_importer.get_domain()
if domain.is_empty():
print_error(
"Core training was skipped because no valid domain file was found. "
"Please specify a valid domain using '--domain' argument or check if the provided domain file exists."
)
return None
if not await file_importer.get_stories():
print_error(
"No stories given. Please provide stories in order to "
"train a Rasa Core model using the '--stories' argument."
)
return
return await _train_core_with_validated_data(
file_importer,
output=output,
train_path=train_path,
fixed_model_name=fixed_model_name,
additional_arguments=additional_arguments,
)
async def test_core_only(project: Text):
config_path = os.path.join(project, DEFAULT_CONFIG_PATH)
domain_path = os.path.join(project, DEFAULT_DOMAIN_PATH)
default_data_path = os.path.join(project, DEFAULT_DATA_PATH)
actual = TrainingDataImporter.load_core_importer_from_config(
config_path, domain_path, training_data_paths=[default_data_path])
assert isinstance(actual, CoreDataImporter)
stories = await actual.get_stories()
assert not stories.is_empty()
domain = await actual.get_domain()
assert not domain.is_empty()
config = await actual.get_config()
assert config
nlu_data = await actual.get_nlu_data()
assert nlu_data.is_empty()
async def train_comparison_models(
story_file: Text,
domain: Text,
output_path: Text = "",
exclusion_percentages: Optional[List] = None,
policy_configs: Optional[List] = None,
runs: int = 1,
dump_stories: bool = False,
kwargs: Optional[Dict] = None,
):
"""Train multiple models for comparison of policies"""
from rasa.core import config
from rasa import model
from rasa.importers.importer import TrainingDataImporter
exclusion_percentages = exclusion_percentages or []
policy_configs = policy_configs or []
for r in range(runs):
logging.info("Starting run {}/{}".format(r + 1, runs))
for current_run, percentage in enumerate(exclusion_percentages, 1):
for policy_config in policy_configs:
policies = config.load(policy_config)
if len(policies) > 1:
raise ValueError(
"You can only specify one policy per model for comparison"
)
file_importer = TrainingDataImporter.load_core_importer_from_config(
policy_config, domain, [story_file])
policy_name = type(policies[0]).__name__
logging.info("Starting to train {} round {}/{}"
" with {}% exclusion"
"".format(policy_name, current_run,
len(exclusion_percentages), percentage))
with TempDirectoryPath(tempfile.mkdtemp()) as train_path:
await train(
domain,
file_importer,
train_path,
policy_config=policy_config,
exclusion_percentage=current_run,
kwargs=kwargs,
dump_stories=dump_stories,
)
new_fingerprint = await model.model_fingerprint(
file_importer)
output_dir = os.path.join(output_path, "run_" + str(r + 1))
model_name = policy_name + str(current_run)
model.package_model(
fingerprint=new_fingerprint,
output_directory=output_dir,
train_path=train_path,
fixed_model_name=model_name,
)
