TinyTimeMixerHyperparams

tiny_time_mixer_model.TinyTimeMixerHyperparams · inherits PydanticBaseModel

(No description provided)

TinyTimeMixerModel

tiny_time_mixer_model.TinyTimeMixerModel · inherits BaseModel

(No description provided)

__init__(self, params, settings)

Initialize TinyTimeMixer model.

Parameter	Type	Default	Description
params	Dict[str, Any]	-	Model parameters dictionary
settings	Dict[str, Any]	-	Settings dictionary containing device, python_version, etc.

train(self, y_context, y_target, timestamps_context, timestamps_target, **kwargs) -> TinyTimeMixerModel

Train/fine-tune the foundation model on given data.

Parameters:

Parameter	Type	Default	Description
y_context	np.ndarray	-	Past target values - training data during tuning time, training + validation data during testing time
y_target	np.ndarray	-	Future target values - validation data during tuning time, None during testing time (avoid data leakage)
timestamps_context	np.ndarray	-	Timestamps for y_context (optional)
timestamps_target	np.ndarray	-	Timestamps for y_target (optional)
**kwargs	-	-	Additional keyword arguments

Returns: Self (The fitted model instance).

predict(self, y_context, timestamps_context, timestamps_target, **kwargs)

(No description provided)

Parameters:

Parameter	Type	Default	Description
y_context	np.ndarray	-	(undocumented)
timestamps_context	np.ndarray	-	(undocumented)
timestamps_target	np.ndarray	-	(undocumented)
**kwargs	-	-	(undocumented)

Returns: np.ndarray (Returns the forecast array of shape (forecast_horizon, num_targets)).