autointent.configs.DataConfig

class autointent.configs.DataConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the data used in the optimization process.

Parameters:

data (Any)

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

scheme: autointent.custom_types.ValidationScheme = None

Hold-out or cross-validation.

n_folds: pydantic.PositiveInt = None

Number of folds in cross-validation.

validation_size: autointent.custom_types.FloatFromZeroToOne = None

Fraction of train samples to allocate for validation (if input dataset doesn’t contain validation split).

separation_ratio: autointent.custom_types.FloatFromZeroToOne | None = None

Set to float to prevent data leak between scoring and decision nodes.

is_few_shot_train: bool = None

Whether to use few-shot training.

examples_per_intent: pydantic.PositiveInt = None

Number of examples per intent for few-shot validation. If None, all examples will be used.