NeuralForecastLSTM

NeuralForecast LSTM model.

Quickstart

from sktime.forecasting.neuralforecast import NeuralForecastLSTM

estimator = NeuralForecastLSTM(freq: str | int='auto', local_scaler_type: Literal ['standard', 'robust', 'robust-iqr', 'minmax', 'boxcox' ] | None=None, futr_exog_list: list [str ] | None=None, verbose_fit: bool=False, verbose_predict: bool=False, input_size: int=-1, inference_input_size: int=-1, encoder_n_layers: int=2, encoder_hidden_size: int=200, encoder_bias: bool=True, encoder_dropout: float=0.0, context_size: int=10, decoder_hidden_size: int=200, decoder_layers: int=2, loss=None, valid_loss=None, max_steps: int=1000, learning_rate: float=0.001, num_lr_decays: int=-1, early_stop_patience_steps: int=-1, val_check_steps: int=100, batch_size=32, valid_batch_size: int | None=None, scaler_type: str='robust', random_seed=1, num_workers_loader=0, drop_last_loader=False, trainer_kwargs: dict | None=None, optimizer=None, optimizer_kwargs: dict | None=None, broadcasting: bool=False, lr_scheduler=None, lr_scheduler_kwargs: dict | None=None)

Parameters(33)

freqUnion[str, int] (default=”auto”)

frequency of the data, see available frequencies [4] from pandas use int freq when using RangeIndex in y

default (“auto”) interprets freq from ForecastingHorizon in fit

local_scaler_typestr (default=None)

scaler to apply per-series to all features before fitting, which is inverted after predicting

can be one of the following:

• ‘standard’

• ‘robust’

• ‘robust-iqr’

• ‘minmax’

• ‘boxcox’

futr_exog_liststr list, (default=None)

future exogenous variables

verbose_fitbool (default=False)

print processing steps during fit

verbose_predictbool (default=False)

print processing steps during predict

input_sizeint (default=-1)

maximum sequence length for truncated train backpropagation

default (-1) uses all history

inference_input_sizeint (default=-1)

maximum sequence length for truncated inference

default (-1) uses all history

encoder_n_layersint (default=2)

number of layers for the LSTM

encoder_hidden_sizeint (default=200)

units for the LSTM hidden state size

encoder_biasbool (default=True)

whether or not to use biases b_ih, b_hh within LSTM units

encoder_dropoutfloat (default=0.0)

dropout regularization applied to LSTM outputs

context_sizeint (default=10)

size of context vector for each timestamp on the forecasting window

decoder_hidden_sizeint (default=200)

size of hidden layer for the MLP decoder

decoder_layersint (default=2)

number of layers for the MLP decoder

losspytorch module (default=None)

instantiated train loss class from losses collection [5]

valid_losspytorch module (default=None)

instantiated validation loss class from losses collection [5]

max_stepsint (default=1000)

maximum number of training steps

learning_ratefloat (default=1e-3)

learning rate between (0, 1)

num_lr_decaysint (default=-1)

number of learning rate decays, evenly distributed across max_steps

early_stop_patience_stepsint (default=-1)

number of validation iterations before early stopping

val_check_stepsint (default=100)

number of training steps between every validation loss check

batch_sizeint (default=32)

number of different series in each batch

valid_batch_sizeOptional[int] (default=None)

number of different series in each validation and test batch

scaler_typestr (default=”robust”)

type of scaler for temporal inputs normalization

random_seedint (default=1)

random_seed for pytorch initializer and numpy generators

num_workers_loaderint (default=0)

workers to be used by TimeSeriesDataLoader

drop_last_loaderbool (default=False)

whether TimeSeriesDataLoader drops last non-full batch

trainer_kwargsdict (default=None)

keyword trainer arguments inherited from PyTorch Lighning’s trainer [6]

optimizerpytorch optimizer (default=None) [7]

optimizer to use for training, if passed with None defaults to Adam

optimizer_kwargsdict (default=None) [8]

dict of parameters to pass to the user defined optimizer

broadcastingbool (default=False)

if True, a model will be fit per time series. Panels, e.g., multiindex data input, will be broadcasted to single series, and for each single series, one copy of this forecaster will be applied.

lr_schedulerpytorch learning rate scheduler (default=None) [9]

user specified lr_scheduler instead of the default choice StepLR [10]

lr_scheduler_kwargsdict (default=None)

list of parameters used by the user specified lr_scheduler

Examples

>>> 
>>> # importing necessary libraries
>>> from sktime.datasets import load_longley
>>> from sktime.forecasting.neuralforecast import NeuralForecastLSTM
>>> from sktime.split import temporal_train_test_split
>>> 
>>> # loading the Longley dataset and splitting it into train and test subsets
>>> y, X = load_longley ()
>>> y_train, y_test, X_train, X_test = temporal_train_test_split (y, X, test_size = 4)
>>> 
>>> # creating model instance configuring the hyperparameters
>>> model = NeuralForecastLSTM (
... "A-DEC", futr_exog_list = ["ARMED", "POP" ], max_steps = 5
... )
>>> 
>>> # fitting the model
>>> model. fit (y_train, X = X_train, fh = [1, 2, 3, 4 ]) Seed set to 1 Epoch 4: 100%|█| 1/1 [00:00<00:00, 42.85it/s, v_num=870, train_loss_step=0.589, train_loss_epoc NeuralForecastLSTM(freq='A-DEC', futr_exog_list=['ARMED', 'POP'], max_steps=5)
>>> 
>>> # getting point predictions
>>> model. predict (X = X_test) Predicting DataLoader 0: 100%|██████████████████████████████████| 1/1 [00:00<00:00, 198.64it/s] 1959 64083.226562 1960 64426.304688 1961 64754.886719 1962 64889.496094 Freq: A-DEC, Name: TOTEMP, dtype: float64
>>>

References

1. [1 ] https://nixtlaverse.nixtla.io/neuralforecast/models.lstm.html#lstm [2 ] https://nixtlaverse.nixtla.io/neuralforecast/core.html#neuralforecast [3 ] https://github.com/Nixtla/neuralforecast/ [4 ] https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases [5 ] (1, 2) https://nixtlaverse.nixtla.io/neuralforecast/losses.pytorch.html [6 ] https://lightning.ai/docs/pytorch/stable/api/pytorch_lightning.trainer.trainer.Trainer.html#lightning.pytorch.trainer.trainer.Trainer [7 ] https://pytorch.org/docs/stable/optim.html [8 ] https://pytorch.org/docs/stable/optim.html#algorithms [9 ] https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.LRScheduler.html [10 ] https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.StepLR.html