phlower.settings.RolloutSetting¶

class phlower.settings.RolloutSetting(*, variables, n_steps=None)[source]¶

Bases: BaseModel

Predict a time series by applying the model step by step.

At every step, the increment predicted by the model is added to the state in the unit of the data before scaling, and the new state is the input of the next step. The model sees one time step of the inputs at a time, so it must be a one-step model.

Methods

check_variables()

Attributes

`model_computed_fields`
`model_config`	Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
`model_extra`	Get extra fields set during validation.
`model_fields`
`model_fields_set`	Returns the set of fields that have been explicitly set on this model instance.
`variables`	Pairs of state and increment, all updated at every step.
`n_steps`	Number of steps.

Parameters:

variables (Annotated[list[RolloutVariableSetting], MinLen(min_length=1)])
n_steps (Annotated[int | None, Gt(gt=0)])

model_config = {'extra': 'forbid', 'frozen': True}¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

n_steps: int | None¶: Number of steps. Defaults to None, which means the time length of the states.

variables: list[RolloutVariableSetting]¶: Pairs of state and increment, all updated at every step.