def _assemble_label_data(
self, attribute_data: Data, domain: Domain
) -> RasaModelData:
"""Constructs data regarding labels to be fed to the model.
The resultant model data should contain the keys `label_intent`, `label`.
`label_intent` will contain the sequence, sentence and mask features
for all intent labels and `label` will contain the numerical label ids.
Args:
attribute_data: Feature data for all intent labels.
domain: Domain of the assistant.
Returns:
Features of labels ready to be fed to the model.
"""
label_data = RasaModelData()
label_data.add_data(attribute_data, key_prefix=f"{LABEL_KEY}_")
label_data.add_lengths(
f"{LABEL}_{INTENT}", SEQUENCE_LENGTH, f"{LABEL}_{INTENT}", SEQUENCE,
)
label_ids = np.arange(len(domain.intents))
label_data.add_features(
LABEL_KEY,
LABEL_SUB_KEY,
[FeatureArray(np.expand_dims(label_ids, -1), number_of_dimensions=2)],
)
return label_data
def _assemble_label_data(self, attribute_data: Data,
domain: Domain) -> RasaModelData:
"""Constructs data regarding labels to be fed to the model.
The resultant model data can possibly contain one or both of the
keys - [`label_action_name`, `label_action_text`] but will definitely
contain the `label` key.
`label_action_*` will contain the sequence, sentence and mask features
for corresponding labels and `label` will contain the numerical label ids.
Args:
attribute_data: Feature data for all labels.
domain: Domain of the assistant.
Returns:
Features of labels ready to be fed to the model.
"""
label_data = RasaModelData()
label_data.add_data(attribute_data, key_prefix=f"{LABEL_KEY}_")
label_data.add_lengths(
f"{LABEL}_{ACTION_TEXT}",
SEQUENCE_LENGTH,
f"{LABEL}_{ACTION_TEXT}",
SEQUENCE,
)
label_ids = np.arange(domain.num_actions)
label_data.add_features(
LABEL_KEY,
LABEL_SUB_KEY,
[
FeatureArray(np.expand_dims(label_ids, -1),
number_of_dimensions=2)
],
)
return label_data
def _create_label_data(
self, domain: Domain, interpreter: NaturalLanguageInterpreter
) -> Tuple[RasaModelData, List[Dict[Text, List["Features"]]]]:
# encode all label_ids with policies' featurizer
state_featurizer = self.featurizer.state_featurizer
encoded_all_labels = state_featurizer.encode_all_actions(domain, interpreter)
attribute_data, _ = convert_to_data_format(encoded_all_labels)
label_data = RasaModelData()
label_data.add_data(attribute_data, key_prefix=f"{LABEL_KEY}_")
label_ids = np.arange(domain.num_actions)
label_data.add_features(
LABEL_KEY, LABEL_SUB_KEY, [np.expand_dims(label_ids, -1)]
)
return label_data, encoded_all_labels
def _create_model_data(
self,
tracker_state_features: List[List[Dict[Text, List["Features"]]]],
label_ids: Optional[np.ndarray] = None,
encoded_all_labels: Optional[List[Dict[Text, List["Features"]]]] = None,
) -> RasaModelData:
"""Combine all model related data into RasaModelData.
Args:
tracker_state_features: a dictionary of attributes (INTENT, TEXT, ACTION_NAME, ACTION_TEXT,
ENTITIES, SLOTS, ACTIVE_LOOP) to a list of features for all dialogue
turns in all training trackers
label_ids: the label ids (e.g. action ids) for every dialogue turn in all
training trackers
encoded_all_labels: a list of dictionaries containing attribute features for labels ids
Returns:
RasaModelData
"""
model_data = RasaModelData(label_key=LABEL_KEY, label_sub_key=LABEL_SUB_KEY)
if label_ids is not None and encoded_all_labels is not None:
label_ids = np.array(
[np.expand_dims(seq_label_ids, -1) for seq_label_ids in label_ids]
)
model_data.add_features(LABEL_KEY, LABEL_SUB_KEY, [label_ids])
attribute_data, self.zero_state_features = convert_to_data_format(
tracker_state_features
)
else:
# method is called during prediction
attribute_data, _ = convert_to_data_format(
tracker_state_features, self.zero_state_features
)
model_data.add_data(attribute_data)
model_data.add_lengths(
DIALOGUE, LENGTH, next(iter(list(attribute_data.keys()))), MASK
)
return model_data
def _create_model_data(
self,
tracker_state_features: List[List[Dict[Text, List["Features"]]]],
label_ids: Optional[np.ndarray] = None,
entity_tags: Optional[List[List[Dict[Text, List["Features"]]]]] = None,
encoded_all_labels: Optional[List[Dict[Text,
List["Features"]]]] = None,
) -> RasaModelData:
"""Combine all model related data into RasaModelData.
Args:
tracker_state_features: a dictionary of attributes
(INTENT, TEXT, ACTION_NAME, ACTION_TEXT, ENTITIES, SLOTS, ACTIVE_LOOP)
to a list of features for all dialogue turns in all training trackers
label_ids: the label ids (e.g. action ids) for every dialogue turn in all
training trackers
entity_tags: a dictionary of entity type (ENTITY_TAGS) to a list of features
containing entity tag ids for text user inputs otherwise empty dict
for all dialogue turns in all training trackers
encoded_all_labels: a list of dictionaries containing attribute features
for label ids
Returns:
RasaModelData
"""
model_data = RasaModelData(label_key=LABEL_KEY,
label_sub_key=LABEL_SUB_KEY)
if label_ids is not None and encoded_all_labels is not None:
label_ids = np.array([
np.expand_dims(seq_label_ids, -1)
for seq_label_ids in label_ids
])
model_data.add_features(
LABEL_KEY,
LABEL_SUB_KEY,
[FeatureArray(label_ids, number_of_dimensions=3)],
)
attribute_data, self.fake_features = convert_to_data_format(
tracker_state_features, featurizers=self.config[FEATURIZERS])
entity_tags_data = self._create_data_for_entities(entity_tags)
if entity_tags_data is not None:
model_data.add_data(entity_tags_data)
else:
# method is called during prediction
attribute_data, _ = convert_to_data_format(
tracker_state_features,
self.fake_features,
featurizers=self.config[FEATURIZERS],
)
model_data.add_data(attribute_data)
model_data.add_lengths(TEXT, SEQUENCE_LENGTH, TEXT, SEQUENCE)
model_data.add_lengths(ACTION_TEXT, SEQUENCE_LENGTH, ACTION_TEXT,
SEQUENCE)
# add the dialogue lengths
attribute_present = next(iter(list(attribute_data.keys())))
dialogue_lengths = np.array([
np.size(np.squeeze(f, -1))
for f in model_data.data[attribute_present][MASK][0]
])
model_data.data[DIALOGUE][LENGTH] = [
FeatureArray(dialogue_lengths, number_of_dimensions=1)
]
# make sure all keys are in the same order during training and prediction
model_data.sort()
return model_data
