def from_config(
cls,
config: Config,
feature_config: ModelInputConfig,
target_config: TargetConfig,
**kwargs,
):
"""Factory method to construct an instance of
ContextualIntentSlotModelDataHandler object from the module's config,
model input config and target config.
Args:
config (Config): Configuration object specifying all the
parameters of ContextualIntentSlotModelDataHandler.
feature_config (ModelInputConfig): Configuration object specifying
model input.
target_config (TargetConfig): Configuration object specifying target.
Returns:
type: An instance of ContextualIntentSlotModelDataHandler.
"""
features: Dict[str, Field] = create_fields(
feature_config,
{
ModelInput.TEXT: TextFeatureField,
ModelInput.DICT: DictFeatureField,
ModelInput.CHAR: CharFeatureField,
ModelInput.CONTEXTUAL_TOKEN_EMBEDDING:
ContextualTokenEmbeddingField,
ModelInput.SEQ: SeqFeatureField,
ModelInput.DENSE: FloatVectorField,
},
)
# Label fields.
labels: Dict[str, Field] = create_label_fields(
target_config,
{
DocLabelConfig._name: DocLabelField,
WordLabelConfig._name: WordLabelField,
},
)
extra_fields: Dict[str, Field] = {
ExtraField.DOC_WEIGHT: FloatField(),
ExtraField.WORD_WEIGHT: FloatField(),
ExtraField.RAW_WORD_LABEL: RawField(),
ExtraField.TOKEN_RANGE: RawField(),
ExtraField.UTTERANCE: RawField(),
}
kwargs.update(config.items())
return cls(
raw_columns=config.columns_to_read,
labels=labels,
features=features,
extra_fields=extra_fields,
**kwargs,
)
def from_config(
cls,
config: Config,
feature_config: ModelInputConfig,
target_config: TargetConfig,
**kwargs,
):
features: Dict[str, Field] = create_fields(
feature_config,
{
ModelInput.TEXT1: TextFeatureField,
ModelInput.TEXT2: TextFeatureField
},
)
assert len(features) == 2
# share the processing field
features[ModelInput.TEXT2] = features[ModelInput.TEXT1]
labels: Dict[str, Field] = create_label_fields(
target_config, {DocLabelConfig._name: DocLabelField})
extra_fields: Dict[str, Field] = {
ExtraField.UTTERANCE_PAIR: RawField()
}
kwargs.update(config.items())
return cls(
raw_columns=config.columns_to_read,
labels=labels,
features=features,
extra_fields=extra_fields,
**kwargs,
)
def from_config(
cls,
config: Config,
model_input_config: ModelInputConfig,
target_config: TargetConfig,
**kwargs,
):
"""
Factory method to construct an instance of `DocClassificationDataHandler`
from the module's config object and feature config object.
Args:
config (DocClassificationDataHandler.Config): Configuration object
specifying all the parameters of `DocClassificationDataHandler`.
model_input_config (ModelInputConfig): Configuration object
specifying all the parameters of the model config.
target_config (TargetConfig): Configuration object specifying all
the parameters of the target.
Returns:
type: An instance of `KDDocClassificationDataHandler`.
"""
model_input_fields: Dict[str, Field] = create_fields(
model_input_config,
{
ModelInput.WORD_FEAT:
TextFeatureField,
ModelInput.DICT_FEAT:
DictFeatureField,
ModelInput.CHAR_FEAT:
CharFeatureField,
ModelInput.PRETRAINED_MODEL_EMBEDDING:
PretrainedModelEmbeddingField,
},
)
target_fields: Dict[str, Field] = create_label_fields(
target_config, {DocLabelConfig._name: DocLabelField})
extra_fields: Dict[str, Field] = {ExtraField.RAW_TEXT: RawField()}
if target_config.target_prob:
target_fields[Target.TARGET_PROB_FIELD] = RawField()
target_fields[Target.TARGET_LOGITS_FIELD] = RawField()
if target_config.target_prob:
extra_fields[Target.TARGET_LABEL_FIELD] = RawField()
kwargs.update(config.items())
return cls(
raw_columns=config.columns_to_read,
labels=target_fields,
features=model_input_fields,
extra_fields=extra_fields,
**kwargs,
)
def from_config(
cls,
config: Config,
feature_config: FeatureConfig,
label_configs: Union[DocLabelConfig, WordLabelConfig,
List[TargetConfigBase]],
**kwargs,
):
features: Dict[str, Field] = create_fields(
feature_config,
{
DatasetFieldName.TEXT_FIELD:
TextFeatureField,
DatasetFieldName.DICT_FIELD:
DictFeatureField,
DatasetFieldName.CHAR_FIELD:
CharFeatureField,
DatasetFieldName.DENSE_FIELD:
FloatVectorField,
DatasetFieldName.PRETRAINED_MODEL_EMBEDDING:
PretrainedModelEmbeddingField,
},
)
# Label fields.
labels: Dict[str, Field] = create_label_fields(
label_configs,
{
DocLabelConfig._name: DocLabelField,
WordLabelConfig._name: WordLabelField,
},
)
has_word_label = WordLabelConfig._name in labels
extra_fields: Dict[str, Field] = {
DatasetFieldName.DOC_WEIGHT_FIELD: FloatField(),
DatasetFieldName.WORD_WEIGHT_FIELD: FloatField(),
DatasetFieldName.TOKEN_RANGE: RawField(),
DatasetFieldName.UTTERANCE_FIELD: RawField(),
}
if has_word_label:
extra_fields[DatasetFieldName.RAW_WORD_LABEL] = RawField()
kwargs.update(config.items())
return cls(
raw_columns=config.columns_to_read,
labels=labels,
features=features,
extra_fields=extra_fields,
**kwargs,
)