TimeLLMForecaster

TimeLLMForecaster

class TimeLLMForecaster(task_name='long_term_forecast', pred_len=24, seq_len=96, llm_model='GPT2', llm_layers=3, llm_dim=768, patch_len=16, stride=8, d_model=128, d_ff=128, n_heads=4, dropout=0.1, device: str | None = None, prompt_domain=False)[source]

Interface to the Time-LLM.

Time-LLM is a reprogramming framework to repurpose LLMs for general time series forecasting with the backbone language models kept intact. This method has been proposed in [2] and official code is given at [1].

Parameters:

task_namestr, default=’long_term_forecast’

Task to perform - can be one of [‘long_term_forecast’, ‘short_term_forecast’].

pred_lenint, default=24

Forecast horizon - number of time steps to predict.

seq_lenint, default=96

Length of input sequence.

llm_modelstr, default=’GPT2’

LLM model to use - can be one of [‘GPT2’, ‘LLAMA’, ‘BERT’].

llm_layersint, default=3

Number of transformer layers to use from LLM.

patch_lenint, default=16

Length of patches for patch embedding.

strideint, default=8

Stride between patches.

d_modelint, default=128

Model dimension.

d_ffint, default=128

Feed-forward dimension.

n_headsint, default=4

Number of attention heads.

dropoutfloat, default=0.1

Dropout rate.

devicestr, default=’cuda’ if available else ‘cpu’

Device to run model on.

Attributes:

cutoff

Cut-off = “present time” state of forecaster.

fh

Forecasting horizon that was passed.

is_fitted

Whether fit has been called.

state

State of the estimator.

References

[1]

https://github.com/KimMeen/Time-LLM

[2]

Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y. Zhang,

Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, Qingsong Wen. Time-LLM: Time Series Forecasting by Reprogramming Large Language Models. https://arxiv.org/abs/2310.01728.

Examples

>>> from sktime.forecasting.time_llm import TimeLLMForecaster
>>> from sktime.datasets import load_airline
>>> y = load_airline()
>>> forecaster = TimeLLMForecaster(
...     pred_len=36,
...     seq_len=96,
...     llm_model='GPT2'
... )
>>> forecaster.fit(y, fh=[1])
TimeLLMForecaster(pred_len=36)
>>> y_pred = forecaster.predict(fh=[1])

Methods

check_is_fitted([method_name])	Check if the estimator has been fitted.
clone()	Obtain a clone of the object with same hyper-parameters and config.
clone_tags(estimator[, tag_names])	Clone tags from another object as dynamic override.
create_test_instance([parameter_set])	Construct an instance of the class, using first test parameter set.
create_test_instances_and_names([parameter_set])	Create list of all test instances and a list of names for them.
fit(y[, X, fh])	Fit forecaster to training data.
fit_predict(y[, X, fh, X_pred])	Fit and forecast time series at future horizon.
get_class_tag(tag_name[, tag_value_default])	Get class tag value from class, with tag level inheritance from parents.
get_class_tags()	Get class tags from class, with tag level inheritance from parent classes.
get_config()	Get config flags for self.
get_fitted_params([deep])	Get fitted parameters.
get_param_defaults()	Get object's parameter defaults.
get_param_names([sort])	Get object's parameter names.
get_params([deep])	Get a dict of parameters values for this object.
get_pretrained_params([deep])	Get pretrained parameters of this estimator.
get_tag(tag_name[, tag_value_default, ...])	Get tag value from instance, with tag level inheritance and overrides.
get_tags()	Get tags from instance, with tag level inheritance and overrides.
get_test_params([parameter_set])	Return testing parameter settings for the estimator.
is_composite()	Check if the object is composed of other BaseObjects.
load_from_path(serial)	Load object from file location.
load_from_serial(serial)	Load object from serialized memory container.
predict([fh, X])	Forecast time series at future horizon.
predict_interval([fh, X, coverage])	Compute/return prediction interval forecasts.
predict_proba([fh, X, marginal])	Compute/return fully probabilistic forecasts.
predict_quantiles([fh, X, alpha])	Compute/return quantile forecasts.
predict_residuals([y, X])	Return residuals of time series forecasts.
predict_var([fh, X, cov])	Compute/return variance forecasts.
pretrain(y[, X, fh])	Pre-train forecaster on panel (global) data.
reset()	Reset the object to a clean post-init state.
save([path, serialization_format])	Save serialized self to bytes-like object or to (.zip) file.
score(y[, X, fh])	Scores forecast against ground truth, using MAPE (non-symmetric).
set_config(**config_dict)	Set config flags to given values.
set_params(**params)	Set the parameters of this object.
set_random_state([random_state, deep, ...])	Set random_state pseudo-random seed parameters for self.
set_tags(**tag_dict)	Set instance level tag overrides to given values.
update(y[, X, update_params])	Update cutoff value and, optionally, fitted parameters.
update_predict(y[, cv, X, update_params, ...])	Make predictions and update model iteratively over the test set.
update_predict_single([y, fh, X, update_params])	Update model with new data and make forecasts.