def train(self, data: TrainingData, **kwargs: Any) -> "Interpreter":
"""Trains the underlying pipeline using the provided training data."""
self.training_data = data
self.training_data.validate()
context = kwargs
for component in self.pipeline:
updates = component.provide_context()
if updates:
context.update(updates)
# Before the training starts: check that all arguments are provided
if not self.skip_validation:
components.validate_required_components_from_data(
self.pipeline, self.training_data)
# data gets modified internally during the training - hence the copy
working_data: TrainingData = copy.deepcopy(data)
for i, component in enumerate(self.pipeline):
if isinstance(component, (EntityExtractor, IntentClassifier)):
working_data = working_data.without_empty_e2e_examples()
logger.info(f"Starting to train component {component.name}")
component.prepare_partial_processing(self.pipeline[:i], context)
updates = component.train(working_data, self.config, **context)
logger.info("Finished training component.")
if updates:
context.update(updates)
return Interpreter(self.pipeline, context)
def train(self, data: TrainingData, **kwargs: Any) -> "Interpreter":
"""Trains the underlying pipeline using the provided training data."""
self.training_data = data
self.training_data.validate()
context = kwargs ##这里的context是什么？
for component in self.pipeline:
updates = component.provide_context(
) ##provide_context()函数 ：The updated component configuration.
if updates:
context.update(updates)
# Before the training starts: check that all arguments are provided
if not self.skip_validation:
components.validate_required_components_from_data( ##检测response_selector
self.pipeline, self.training_data)
# data gets modified internally during the training - hence the copy
working_data = copy.deepcopy(data)
for i, component in enumerate(self.pipeline):
logger.info(f"Starting to train component {component.name}")
component.prepare_partial_processing(self.pipeline[:i], context)
updates = component.train(working_data, self.config, **context)
logger.info("Finished training component.")
if updates:
context.update(updates)
return Interpreter(self.pipeline, context)
def train(self, data: TrainingData, **kwargs: Any) -> "Interpreter":
"""Trains the underlying pipeline using the provided training data."""
self.training_data = data
self.training_data.validate()
context = kwargs
for component in self.pipeline:
updates = component.provide_context()
if updates:
context.update(updates)
# Before the training starts: check that all arguments are provided
if not self.skip_validation:
components.validate_required_components_from_data(
self.pipeline, self.training_data)
# Warn if there is an obvious case of competing entity extractors
components.warn_of_competing_extractors(self.pipeline)
components.warn_of_competition_with_regex_extractor(
self.pipeline, self.training_data)
# data gets modified internally during the training - hence the copy
working_data: TrainingData = copy.deepcopy(data)
for i, component in enumerate(self.pipeline):
logger.info(f"Starting to train component {component.name}")
component.prepare_partial_processing(self.pipeline[:i], context)
component.train(working_data, self.config, **context)
logger.info("Finished training component.")
return Interpreter(self.pipeline, context)
def test_validate_required_components_from_data(
config_path: Text, data_path: Text,
expected_warning_excerpts: List[Text]):
loaded_config = config.load(config_path)
trainer = Trainer(loaded_config)
training_data = load_data(data_path)
with pytest.warns(UserWarning) as record:
components.validate_required_components_from_data(
trainer.pipeline, training_data)
assert len(record) == 1
assert all([excerpt in record[0].message.args[0]]
for excerpt in expected_warning_excerpts)
