etna.models.nn.ChronosModel#

class ChronosModel(path_or_url: str, encoder_length: int = 512, device: str = 'cpu', dtype: str | dtype | None = None, num_samples: int = 1, temperature: float = 1.0, top_k: int = 50, top_p: float = 1.0, limit_prediction_length: bool = False, batch_size: int = 128, cache_dir: str = '/home/runner/.etna/chronos-models/chronos')[source]#

Bases: ChronosBaseModel

Class for pretrained chronos models.

This model is only for zero-shot forecasting: it doesn’t support training on data during fit.

Official implementation: amazon-science/chronos-forecasting

Note

This model requires chronos extension to be installed. Read more about this at installation page.

Init Chronos model.

Parameters:

path_or_url (str) –
Path to the model. It can be huggingface repository, local path or external url.
- If huggingface repository, the available models are:
  - ’amazon/chronos-t5-tiny’
  - ’amazon/chronos-t5-mini’
  - ’amazon/chronos-t5-small’
  - ’amazon/chronos-t5-base’
  - ’amazon/chronos-t5-large’.
  During the first initialization model is downloaded from huggingface and saved to local cache_dir. All following initializations model will be loaded from cache_dir. See pretrained_model_name_or_path parameter of transformers.PreTrainedModel.from_pretrained().
- If local path, model will not be saved to local cache_dir.
- If external url, it must be zip archive with the same name as model directory inside. Model will be downloaded to cache_dir.
device (str) – Device type. See device_map parameter of transformers.PreTrainedModel.from_pretrained().
dtype (str | dtype | None) – Torch dtype of computation. See torch_dtype parameter of transformers.PreTrainedModel.from_pretrained(). By default “float32” is set.
encoder_length (int) – Number of last timestamps to use as a context.
num_samples (int) – Number of samples generated for one timestamp.
temperature (float) – Temperature of generation. Higher temperature will make outputs more random and diverse.
top_k (int) – Number of most likely tokens to sample from at each step of generation. Higher top_k will make outputs more random and diverse.
top_p (float) – The cumulative probability cutoff for token selection at each step of generation. Lower top_p will make outputs more random and diverse.
limit_prediction_length (bool) – Whether to cancel prediction if prediction_length is greater that built-in prediction length from the model.
batch_size (int) – Batch size. It can be useful when inference is done on gpu.
cache_dir (str) – Local path to save model from huggingface during first model initialization. All following class initializations appropriate model version will be downloaded from this path. See cache_dir parameter of transformers.PreTrainedModel.from_pretrained().

Methods

`fit`(ts)	Fit model.
`forecast`(ts, prediction_size[, ...])	Make autoregressive forecasts.
`get_model`()	Get model.
`list_models`()	Return a list of available pretrained chronos models.
`load`(path)	Load the model.
`params_to_tune`()	Get default grid for tuning hyperparameters.
`predict`(ts, prediction_size[, ...])	Make predictions using true values as autoregression context (teacher forcing).
`save`(path)	Save the model.
`set_params`(**params)	Return new object instance with modified parameters.
`to_dict`()	Collect all information about etna object in dict.

Attributes

This class stores its __init__ parameters as attributes.

context_size

Context size for model.

fit(ts: TSDataset)[source]#

Fit model.

For this model, fit does nothing.

Parameters:: ts (TSDataset) – Dataset with features.
Returns:: Model after fit

forecast(ts: TSDataset, prediction_size: int, prediction_interval: bool = False, quantiles: Sequence[float] = (0.025, 0.975), return_components: bool = False) → TSDataset[source]#

Make autoregressive forecasts.

Parameters:

ts (TSDataset) – Dataset with features.
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context.
prediction_interval (bool) – If True returns prediction interval for forecast.
quantiles (Sequence[float]) – Levels of prediction distribution. By default 2.5% and 97.5% are taken to form a 95% prediction interval.
return_components (bool) – If True additionally returns forecast components.

Returns:

Dataset with predictions.

Return type:

TSDataset

get_model() → ChronosModelForForecasting | ChronosBoltModelForForecasting[source]#

Get model.

Return type:: ChronosModelForForecasting | ChronosBoltModelForForecasting

static list_models() → List[str][source]#

Return a list of available pretrained chronos models.

Returns:: List of available pretrained chronos models.
Return type:: List[str]

classmethod load(path: Path)[source]#

Load the model.

Parameters:: path (Path) – Path to load object from.

params_to_tune() → Dict[str, BaseDistribution][source]#

Get default grid for tuning hyperparameters.

This grid is empty.

Returns:: Grid to tune.
Return type:: Dict[str, BaseDistribution]

predict(ts: TSDataset, prediction_size: int, prediction_interval: bool = False, quantiles: Sequence[float] = (0.025, 0.975), return_components: bool = False) → TSDataset[source]#

Make predictions using true values as autoregression context (teacher forcing).

Parameters:

ts (TSDataset) – Dataset with features.
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context.
prediction_interval (bool) – If True returns prediction interval for forecast.
quantiles (Sequence[float]) – Levels of prediction distribution. By default 2.5% and 97.5% are taken to form a 95% prediction interval.
return_components (bool) – If True additionally returns forecast components.

Returns:

Dataset with predictions.

Return type:

TSDataset

save(path: Path)[source]#

Save the model. This method doesn’t save model’s weights.

During load weights are loaded from the path where they were saved during init

Parameters:: path (Path) – Path to save object to.

set_params(**params: dict) → Self[source]#

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters:: **params (dict) – Estimator parameters
Returns:: New instance with changed parameters
Return type:: Self

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()[source]#: Collect all information about etna object in dict.

property context_size: int[source]#: Context size for model.