rasa.core.featurizers.single_state_featurizer
SingleStateFeaturizer Objects
Base class to transform the dialogue state into an ML format.
Subclasses of SingleStateFeaturizer will decide how a bot will
transform the dialogue state into a dictionary mapping an attribute
to its features. Possible attributes are: INTENT
, TEXT
, ACTION_NAME
,
ACTION_TEXT
, ENTITIES
, SLOTS
and ACTIVE_LOOP
. Each attribute will be
featurized into a list of rasa.utils.features.Features
.
__init__
Initialize the single state featurizer.
prepare_for_training
Gets necessary information for featurization from domain.
Arguments:
domain
- An instance of :class:rasa.shared.core.domain.Domain
.bilou_tagging
- indicates whether BILOU tagging should be used or not
encode_state
Encode the given state.
Arguments:
state
- The state to encodeprecomputations
- Contains precomputed features and attributes.
Returns:
A dictionary of state_type to list of features.
encode_entities
Encode the given entity data.
Produce numeric entity tags for tokens.
Arguments:
entity_data
- The dict containing the text and entity labels and locationsprecomputations
- Contains precomputed features and attributes.bilou_tagging
- indicates whether BILOU tagging should be used or not
Returns:
A dictionary of entity type to list of features.
encode_all_labels
Encode all action from the domain.
Arguments:
domain
- The domain that contains the actions.precomputations
- Contains precomputed features and attributes.
Returns:
A list of encoded actions.
IntentTokenizerSingleStateFeaturizer Objects
A SingleStateFeaturizer for use with policies that predict intent labels.
encode_all_labels
Encodes all relevant labels from the domain using the given precomputations.
Arguments:
domain
- The domain that contains the labels.precomputations
- Contains precomputed features and attributes.
Returns:
A list of encoded labels.