Skip to main content
Elman proposed this classic recurrent neural network (RNN) in 1990, where each layer uses the following recurrent transformation: htl=Activation([yt,xt(h),x(s)]Wih⊺+bih+ht−1lWhh⊺+bhh)\mathbf{h}^{l}_{t} = \mathrm{Activation}([\mathbf{y}_{t},\mathbf{x}^{(h)}_{t},\mathbf{x}^{(s)}] W^{\intercal}_{ih} + b_{ih} + \mathbf{h}^{l}_{t-1} W^{\intercal}_{hh} + b_{hh}) where htl\mathbf{h}^{l}_{t}, is the hidden state of RNN layer ll for time tt, yt\mathbf{y}_{t} is the input at time tt and ht−1\mathbf{h}_{t-1} is the hidden state of the previous layer at t−1t-1, x(s)\mathbf{x}^{(s)} are static exogenous inputs, xt(h)\mathbf{x}^{(h)}_{t} historic exogenous, x[:t+H](f)\mathbf{x}^{(f)}_{[:t+H]} are future exogenous available at the time of the prediction. The available activations are tanh, and relu. The predictions are obtained by transforming the hidden states into contexts c[t+1:t+H]\mathbf{c}_{[t+1:t+H]}, that are decoded and adapted into y^[t+1:t+H],[q]\mathbf{\hat{y}}_{[t+1:t+H],[q]} through MLPs. References Figure 1. Single Layer Elman RNN with MLP decoder. Figure 1. Single Layer Elman RNN with MLP decoder.

​
RNN

​
RNN

RNN(
    h,
    input_size=-1,
    inference_input_size=None,
    h_train=1,
    encoder_n_layers=2,
    encoder_hidden_size=128,
    encoder_activation="tanh",
    encoder_bias=True,
    encoder_dropout=0.0,
    context_size=None,
    decoder_hidden_size=128,
    decoder_layers=2,
    futr_exog_list=None,
    hist_exog_list=None,
    stat_exog_list=None,
    exclude_insample_y=False,
    recurrent=False,
    loss=MAE(),
    valid_loss=None,
    max_steps=1000,
    learning_rate=0.001,
    num_lr_decays=-1,
    early_stop_patience_steps=-1,
    val_check_steps=100,
    batch_size=32,
    valid_batch_size=None,
    windows_batch_size=128,
    inference_windows_batch_size=1024,
    start_padding_enabled=False,
    training_data_availability_threshold=0.0,
    step_size=1,
    scaler_type="robust",
    random_seed=1,
    drop_last_loader=False,
    alias=None,
    optimizer=None,
    optimizer_kwargs=None,
    lr_scheduler=None,
    lr_scheduler_kwargs=None,
    dataloader_kwargs=None,
    **trainer_kwargs
)
Bases: BaseModel RNN Multi Layer Elman RNN (RNN), with MLP decoder. The network has tanh or relu non-linearities, it is trained using ADAM stochastic gradient descent. The network accepts static, historic and future exogenous data. Parameters:
NameTypeDescriptionDefault
hintforecast horizon.required
input_sizeintmaximum sequence length for truncated train backpropagation. Default -1 uses 3 * horizon.-1
inference_input_sizeintmaximum sequence length for truncated inference. Default None uses input_size history.None
h_trainintmaximum sequence length for truncated train backpropagation. Default 1.1
encoder_n_layersintnumber of layers for the RNN.2
encoder_hidden_sizeintunits for the RNN’s hidden state size.128
encoder_activationstrtype of RNN activation from tanh or relu.‘tanh’
encoder_biasboolwhether or not to use biases b_ih, b_hh within RNN units.True
encoder_dropoutfloatdropout regularization applied to RNN outputs.0.0
decoder_hidden_sizeintsize of hidden layer for the MLP decoder.128
decoder_layersintnumber of layers for the MLP decoder.2
futr_exog_liststr listfuture exogenous columns.None
hist_exog_liststr listhistoric exogenous columns.None
stat_exog_liststr liststatic exogenous columns.None
exclude_insample_yboolwhether to exclude the target variable from the historic exogenous data.False
recurrentboolwhether to produce forecasts recursively (True) or direct (False).False
lossPyTorch moduleinstantiated train loss class from losses collection.MAE()
valid_lossPyTorch moduleinstantiated valid loss class from losses collection.None
max_stepsintmaximum number of training steps.1000
learning_ratefloatLearning rate between (0, 1).0.001
num_lr_decaysintNumber of learning rate decays, evenly distributed across max_steps.-1
early_stop_patience_stepsintNumber of validation iterations before early stopping.-1
val_check_stepsintNumber of training steps between every validation loss check.100
batch_sizeintnumber of differentseries in each batch.32
valid_batch_sizeintnumber of different series in each validation and test batch.None
windows_batch_sizeintnumber of windows to sample in each training batch, default uses all.128
inference_windows_batch_sizeintnumber of windows to sample in each inference batch, -1 uses all.1024
start_padding_enabledboolif True, the model will pad the time series with zeros at the beginning, by input size.False
training_data_availability_thresholdUnion[float, List[float]]minimum fraction of valid data points required for training windows. Single float applies to both insample and outsample; list of two floats specifies [insample_fraction, outsample_fraction]. Default 0.0 allows windows with only 1 valid data point (current behavior).0.0
step_sizeintstep size between each window of temporal data.1
scaler_typestrtype of scaler for temporal inputs normalization see temporal scalers.‘robust’
random_seedintrandom_seed for pytorch initializer and numpy generators.1
drop_last_loaderboolif True TimeSeriesDataLoader drops last non-full batch.False
aliasstroptional, Custom name of the model.None
optimizerSubclass of ‘torch.optim.Optimizer’optional, user specified optimizer instead of the default choice (Adam).None
optimizer_kwargsdictoptional, list of parameters used by the user specified optimizer.None
lr_schedulerSubclass of ‘torch.optim.lr_scheduler.LRScheduler’optional, user specified lr_scheduler instead of the default choice (StepLR).None
lr_scheduler_kwargsdictoptional, list of parameters used by the user specified lr_scheduler.None
dataloader_kwargsdictoptional, list of parameters passed into the PyTorch Lightning dataloader by the TimeSeriesDataLoader.None
**trainer_kwargsintkeyword trainer arguments inherited from PyTorch Lighning’s trainer.

​
RNN.fit

fit(
    dataset, val_size=0, test_size=0, random_seed=None, distributed_config=None
)
Fit. The fit method, optimizes the neural network’s weights using the initialization parameters (learning_rate, windows_batch_size, …) and the loss function as defined during the initialization. Within fit we use a PyTorch Lightning Trainer that inherits the initialization’s self.trainer_kwargs, to customize its inputs, see PL’s trainer arguments. The method is designed to be compatible with SKLearn-like classes and in particular to be compatible with the StatsForecast library. By default the model is not saving training checkpoints to protect disk memory, to get them change enable_checkpointing=True in __init__. Parameters:
NameTypeDescriptionDefault
datasetTimeSeriesDatasetNeuralForecast’s TimeSeriesDataset, see documentation.required
val_sizeintValidation size for temporal cross-validation.0
random_seedintRandom seed for pytorch initializer and numpy generators, overwrites model.init’s.None
test_sizeintTest size for temporal cross-validation.0
Returns:
TypeDescription
None

​
RNN.predict

predict(
    dataset,
    test_size=None,
    step_size=1,
    random_seed=None,
    quantiles=None,
    h=None,
    explainer_config=None,
    **data_module_kwargs
)
Predict. Neural network prediction with PL’s Trainer execution of predict_step. Parameters:
NameTypeDescriptionDefault
datasetTimeSeriesDatasetNeuralForecast’s TimeSeriesDataset, see documentation.required
test_sizeintTest size for temporal cross-validation.None
step_sizeintStep size between each window.1
random_seedintRandom seed for pytorch initializer and numpy generators, overwrites model.init’s.None
quantileslistTarget quantiles to predict.None
hintPrediction horizon, if None, uses the model’s fitted horizon. Defaults to None.None
explainer_configdictconfiguration for explanations.None
**data_module_kwargsdictPL’s TimeSeriesDataModule args, see documentation.
Returns:
TypeDescription
None

​
Usage Example

import pandas as pd
import matplotlib.pyplot as plt

from neuralforecast import NeuralForecast
from neuralforecast.models import RNN
from neuralforecast.losses.pytorch import MQLoss
from neuralforecast.utils import AirPassengersPanel, AirPassengersStatic
Y_train_df = AirPassengersPanel[AirPassengersPanel.ds<AirPassengersPanel['ds'].values[-12]] # 132 train
Y_test_df = AirPassengersPanel[AirPassengersPanel.ds>=AirPassengersPanel['ds'].values[-12]].reset_index(drop=True) # 12 test

fcst = NeuralForecast(
    models=[RNN(h=12,
                input_size=24,
                inference_input_size=24,
                loss=MQLoss(level=[80, 90]),
                valid_loss=MQLoss(level=[80, 90]),
                scaler_type='standard',
                encoder_n_layers=2,
                encoder_hidden_size=128,
                decoder_hidden_size=128,
                decoder_layers=2,
                max_steps=200,
                futr_exog_list=['y_[lag12]'],
                stat_exog_list=['airline1'],
                )
    ],
    freq='ME'
)
fcst.fit(df=Y_train_df, static_df=AirPassengersStatic, val_size=12)
forecasts = fcst.predict(futr_df=Y_test_df)

Y_hat_df = forecasts.reset_index(drop=False).drop(columns=['unique_id','ds'])
plot_df = pd.concat([Y_test_df, Y_hat_df], axis=1)
plot_df = pd.concat([Y_train_df, plot_df])

plot_df = plot_df[plot_df.unique_id=='Airline1'].drop('unique_id', axis=1)
plt.plot(plot_df['ds'], plot_df['y'], c='black', label='True')
plt.plot(plot_df['ds'], plot_df['RNN-median'], c='blue', label='median')
plt.fill_between(x=plot_df['ds'][-12:], 
                 y1=plot_df['RNN-lo-90'][-12:].values, 
                 y2=plot_df['RNN-hi-90'][-12:].values,
                 alpha=0.4, label='level 90')
plt.legend()
plt.grid()
plt.plot()