def validate_required_components_from_data(
pipeline: List["Component"], data: TrainingData
) -> None:
"""Validates that all components are present in the pipeline based on data.
Args:
pipeline: The list of the :class:`rasa.nlu.components.Component`s.
data: The :class:`rasa.shared.nlu.training_data.training_data.TrainingData`.
"""
if data.response_examples and not any_components_in_pipeline(
["ResponseSelector"], pipeline
):
rasa.shared.utils.io.raise_warning(
"You have defined training data with examples for training a response "
"selector, but your NLU pipeline does not include a response selector "
"component. To train a model on your response selector data, add a "
"'ResponseSelector' to your pipeline."
)
if data.entity_examples and not any_components_in_pipeline(
TRAINABLE_EXTRACTORS, pipeline
):
rasa.shared.utils.io.raise_warning(
"You have defined training data consisting of entity examples, but "
"your NLU pipeline does not include an entity extractor trained on "
"your training data. To extract non-pretrained entities, add one of "
f"{TRAINABLE_EXTRACTORS} to your pipeline."
)
if data.entity_examples and not any_components_in_pipeline(
{"DIETClassifier", "CRFEntityExtractor"}, pipeline
):
if data.entity_roles_groups_used():
rasa.shared.utils.io.raise_warning(
"You have defined training data with entities that have roles/groups, "
"but your NLU pipeline does not include a 'DIETClassifier' or a "
"'CRFEntityExtractor'. To train entities that have roles/groups, "
"add either 'DIETClassifier' or 'CRFEntityExtractor' to your "
"pipeline."
)
if data.regex_features and not any_components_in_pipeline(
["RegexFeaturizer", "RegexEntityExtractor"], pipeline
):
rasa.shared.utils.io.raise_warning(
"You have defined training data with regexes, but "
"your NLU pipeline does not include a 'RegexFeaturizer' or a "
"'RegexEntityExtractor'. To use regexes, include either a "
"'RegexFeaturizer' or a 'RegexEntityExtractor' in your pipeline."
)
if data.lookup_tables and not any_components_in_pipeline(
["RegexFeaturizer", "RegexEntityExtractor"], pipeline
):
rasa.shared.utils.io.raise_warning(
"You have defined training data consisting of lookup tables, but "
"your NLU pipeline does not include a 'RegexFeaturizer' or a "
"'RegexEntityExtractor'. To use lookup tables, include either a "
"'RegexFeaturizer' or a 'RegexEntityExtractor' in your pipeline."
)
if data.lookup_tables:
if not any_components_in_pipeline(
["CRFEntityExtractor", "DIETClassifier"], pipeline
):
rasa.shared.utils.io.raise_warning(
"You have defined training data consisting of lookup tables, but "
"your NLU pipeline does not include any components that use these "
"features. To make use of lookup tables, add a 'DIETClassifier' or a "
"'CRFEntityExtractor' with the 'pattern' feature to your pipeline."
)
elif any_components_in_pipeline(["CRFEntityExtractor"], pipeline):
crf_components = [c for c in pipeline if c.name == "CRFEntityExtractor"]
# check to see if any of the possible CRFEntityExtractors will
# featurize `pattern`
has_pattern_feature = False
for crf in crf_components:
crf_features = crf.component_config.get("features")
# iterate through [[before],[word],[after]] features
has_pattern_feature = "pattern" in itertools.chain(*crf_features)
if not has_pattern_feature:
rasa.shared.utils.io.raise_warning(
"You have defined training data consisting of lookup tables, but "
"your NLU pipeline's 'CRFEntityExtractor' does not include the "
"'pattern' feature. To featurize lookup tables, add the 'pattern' "
"feature to the 'CRFEntityExtractor' in your pipeline."
)
if data.entity_synonyms and not any_components_in_pipeline(
["EntitySynonymMapper"], pipeline
):
rasa.shared.utils.io.raise_warning(
"You have defined synonyms in your training data, but "
"your NLU pipeline does not include an 'EntitySynonymMapper'. "
"To map synonyms, add an 'EntitySynonymMapper' to your pipeline."
)
def _warn_if_some_training_data_is_unused(
self, training_data: TrainingData) -> None:
"""Validates that all training data will be consumed by some component.
For example, if you specify response examples in your training data, but there
is no `ResponseSelector` component in your configuration, then this method
issues a warning.
Args:
training_data: The training data for the NLU components.
"""
if (training_data.response_examples
and ResponseSelector not in self._component_types):
rasa.shared.utils.io.raise_warning(
f"You have defined training data with examples for training a response "
f"selector, but your NLU configuration does not include a response "
f"selector component. "
f"To train a model on your response selector data, add a "
f"'{ResponseSelector.__name__}' to your configuration.",
docs=DOCS_URL_COMPONENTS,
)
if training_data.entity_examples and self._component_types.isdisjoint(
TRAINABLE_EXTRACTORS):
rasa.shared.utils.io.raise_warning(
f"You have defined training data consisting of entity examples, but "
f"your NLU configuration does not include an entity extractor "
f"trained on your training data. "
f"To extract non-pretrained entities, add one of "
f"{_types_to_str(TRAINABLE_EXTRACTORS)} to your configuration.",
docs=DOCS_URL_COMPONENTS,
)
if training_data.entity_examples and self._component_types.isdisjoint(
{DIETClassifier, CRFEntityExtractor}):
if training_data.entity_roles_groups_used():
rasa.shared.utils.io.raise_warning(
f"You have defined training data with entities that "
f"have roles/groups, but your NLU configuration does not "
f"include a '{DIETClassifier.__name__}' "
f"or a '{CRFEntityExtractor.__name__}'. "
f"To train entities that have roles/groups, "
f"add either '{DIETClassifier.__name__}' "
f"or '{CRFEntityExtractor.__name__}' to your "
f"configuration.",
docs=DOCS_URL_COMPONENTS,
)
if training_data.regex_features and self._component_types.isdisjoint(
[RegexFeaturizer, RegexEntityExtractor]):
rasa.shared.utils.io.raise_warning(
f"You have defined training data with regexes, but "
f"your NLU configuration does not include a 'RegexFeaturizer' "
f" or a "
f"'RegexEntityExtractor'. To use regexes, include either a "
f"'{RegexFeaturizer.__name__}' or a "
f"'{RegexEntityExtractor.__name__}' "
f"in your configuration.",
docs=DOCS_URL_COMPONENTS,
)
if training_data.lookup_tables and self._component_types.isdisjoint(
[RegexFeaturizer, RegexEntityExtractor]):
rasa.shared.utils.io.raise_warning(
f"You have defined training data consisting of lookup tables, but "
f"your NLU configuration does not include a featurizer "
f"or an entity extractor using the lookup table."
f"To use the lookup tables, include either a "
f"'{RegexFeaturizer.__name__}' "
f"or a '{RegexEntityExtractor.__name__}' "
f"in your configuration.",
docs=DOCS_URL_COMPONENTS,
)
if training_data.lookup_tables:
if self._component_types.isdisjoint(
[CRFEntityExtractor, DIETClassifier]):
rasa.shared.utils.io.raise_warning(
f"You have defined training data consisting of lookup tables, but "
f"your NLU configuration does not include any components "
f"that uses the features created from the lookup table. "
f"To make use of the features that are created with the "
f"help of the lookup tables, "
f"add a '{DIETClassifier.__name__}' or a "
f"'{CRFEntityExtractor.__name__}' "
f"with the 'pattern' feature "
f"to your configuration.",
docs=DOCS_URL_COMPONENTS,
)
elif CRFEntityExtractor in self._component_types:
crf_schema_nodes = [
schema_node
for schema_node in self._graph_schema.nodes.values()
if schema_node.uses == CRFEntityExtractor
]
has_pattern_feature = any(
CRFEntityExtractorOptions.PATTERN in feature_list
for crf in crf_schema_nodes
for feature_list in crf.config.get("features", []))
if not has_pattern_feature:
rasa.shared.utils.io.raise_warning(
f"You have defined training data consisting of "
f"lookup tables, but your NLU configuration's "
f"'{CRFEntityExtractor.__name__}' "
f"does not include the "
f"'pattern' feature. To featurize lookup tables, "
f"add the 'pattern' feature to the "
f"'{CRFEntityExtractor.__name__}' "
"in your configuration.",
docs=DOCS_URL_COMPONENTS,
)
if (training_data.entity_synonyms
and EntitySynonymMapper not in self._component_types):
rasa.shared.utils.io.raise_warning(
f"You have defined synonyms in your training data, but "
f"your NLU configuration does not include an "
f"'{EntitySynonymMapper.__name__}'. "
f"To map synonyms, add an "
f"'{EntitySynonymMapper.__name__}' to your "
f"configuration.",
docs=DOCS_URL_COMPONENTS,
)
