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+ht1lWhh+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 ht1\mathbf{h}_{t-1} is the hidden state of the previous layer at t1t-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.

-Jeffrey L. Elman (1990). “Finding Structure in Time”.
-Cho, K., van Merrienboer, B., Gülcehre, C., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation.



 RNN (h:int, input_size:int=-1, inference_input_size:int=-1,
      encoder_n_layers:int=2, encoder_hidden_size:int=200,
      encoder_activation:str='tanh', encoder_bias:bool=True,
      encoder_dropout:float=0.0, context_size:int=10,
      decoder_hidden_size:int=200, decoder_layers:int=2,
      futr_exog_list=None, hist_exog_list=None, stat_exog_list=None,
      loss=MAE(), 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:Optional[int]=None,
      scaler_type:str='robust', random_seed=1, num_workers_loader=0,
      drop_last_loader=False, optimizer=None, optimizer_kwargs=None,


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.

h: int, forecast horizon.
input_size: int, maximum sequence length for truncated train backpropagation. Default -1 uses all history.
inference_input_size: int, maximum sequence length for truncated inference. Default -1 uses all history.
encoder_n_layers: int=2, number of layers for the RNN.
encoder_hidden_size: int=200, units for the RNN’s hidden state size.
encoder_activation: str=tanh, type of RNN activation from tanh or relu.
encoder_bias: bool=True, whether or not to use biases b_ih, b_hh within RNN units.
encoder_dropout: float=0., dropout regularization applied to RNN outputs.
context_size: int=10, size of context vector for each timestamp on the forecasting window.
decoder_hidden_size: int=200, size of hidden layer for the MLP decoder.
decoder_layers: int=2, number of layers for the MLP decoder.
futr_exog_list: str list, future exogenous columns.
hist_exog_list: str list, historic exogenous columns.
stat_exog_list: str list, static exogenous columns.
loss: PyTorch module, instantiated train loss class from losses collection.
valid_loss: PyTorch module=loss, instantiated valid loss class from losses collection.
max_steps: int=1000, maximum number of training steps.
learning_rate: float=1e-3, Learning rate between (0, 1).
num_lr_decays: int=-1, Number of learning rate decays, evenly distributed across max_steps.
early_stop_patience_steps: int=-1, Number of validation iterations before early stopping.
val_check_steps: int=100, Number of training steps between every validation loss check.
batch_size: int=32, number of differentseries in each batch.
valid_batch_size: int=None, number of different series in each validation and test batch.
scaler_type: str=‘robust’, type of scaler for temporal inputs normalization see temporal scalers.
random_seed: int=1, random_seed for pytorch initializer and numpy generators.
num_workers_loader: int=os.cpu_count(), workers to be used by TimeSeriesDataLoader.
drop_last_loader: bool=False, if True TimeSeriesDataLoader drops last non-full batch.
optimizer: Subclass of ‘torch.optim.Optimizer’, optional, user specified optimizer instead of the default choice (Adam).
optimizer_kwargs: dict, optional, list of parameters used by the user specified optimizer.
alias: str, optional, Custom name of the model.

**trainer_kwargs: int, keyword trainer arguments inherited from PyTorch Lighning’s trainer.


 RNN.fit (dataset, val_size=0, test_size=0, random_seed=None,


The fit method, optimizes the neural network’s weights using the initialization parameters (learning_rate, 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__.

dataset: NeuralForecast’s TimeSeriesDataset, see documentation.
val_size: int, validation size for temporal cross-validation.
test_size: int, test size for temporal cross-validation.
random_seed: int=None, random_seed for pytorch initializer and numpy generators, overwrites model.__init__’s.


 RNN.predict (dataset, step_size=1, random_seed=None,


Neural network prediction with PL’s Trainer execution of predict_step.

dataset: NeuralForecast’s TimeSeriesDataset, see documentation.
step_size: int=1, Step size between each window.
random_seed: int=None, random_seed for pytorch initializer and numpy generators, overwrites model.__init__’s.
**data_module_kwargs: PL’s TimeSeriesDataModule args, see documentation.

Usage Example

import numpy as np
import pandas as pd
import pytorch_lightning as pl
import matplotlib.pyplot as plt

from neuralforecast import NeuralForecast
from neuralforecast.models import RNN
from neuralforecast.losses.pytorch import MQLoss, DistributionLoss
from neuralforecast.utils import AirPassengersPanel, AirPassengersStatic
from neuralforecast.tsdataset import TimeSeriesDataset, TimeSeriesLoader

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(
                loss=MQLoss(level=[80, 90]),
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')
                 alpha=0.4, label='level 90')