def preprocess_train_data(self, training_data: TrainingData) -> RasaModelData:
"""Prepares data for training.
Performs sanity checks on training data, extracts encodings for labels.
"""
if self.retrieval_intent:
training_data = training_data.filter_by_intent(self.retrieval_intent)
label_id_index_mapping = self._label_id_index_mapping(
training_data, attribute=RESPONSE
)
if not label_id_index_mapping:
# no labels are present to train
return RasaModelData()
self.index_label_id_mapping = self._invert_mapping(label_id_index_mapping)
self._label_data = self._create_label_data(
training_data, label_id_index_mapping, attribute=RESPONSE
)
model_data = self._create_model_data(
training_data.intent_examples,
label_id_index_mapping,
label_attribute=RESPONSE,
)
self._check_input_dimension_consistency(model_data)
return model_data
def preprocess_train_data(self,
training_data: TrainingData) -> RasaModelData:
"""Prepares data for training.
Performs sanity checks on training data, extracts encodings for labels.
"""
if self.retrieval_intent:
training_data = training_data.filter_by_intent(
self.retrieval_intent)
else:
# retrieval intent was left to its default value
logger.info(
"Retrieval intent parameter was left to its default value. This "
"response selector will be trained on training examples combining "
"all retrieval intents.")
label_id_index_mapping = self._label_id_index_mapping(
training_data, attribute=RESPONSE)
self.retrieval_intent_mapping = self._create_retrieval_intent_mapping(
training_data)
if not label_id_index_mapping:
# no labels are present to train
return RasaModelData()
self.index_label_id_mapping = self._invert_mapping(
label_id_index_mapping)
self._label_data = self._create_label_data(training_data,
label_id_index_mapping,
attribute=RESPONSE)
model_data = self._create_model_data(
training_data.intent_examples,
label_id_index_mapping,
label_attribute=RESPONSE,
)
self._check_input_dimension_consistency(model_data)
return model_data
