DeepAR

class pytorch_forecasting.models.deepar.DeepAR(cell_type: str = 'LSTM', hidden_size: int = 10, rnn_layers: int = 2, dropout: float = 0.1, static_categoricals: List[str] = [], static_reals: List[str] = [], time_varying_categoricals_encoder: List[str] = [], time_varying_categoricals_decoder: List[str] = [], categorical_groups: Dict[str, List[str]] = {}, time_varying_reals_encoder: List[str] = [], time_varying_reals_decoder: List[str] = [], embedding_sizes: Dict[str, Tuple[int, int]] = {}, embedding_paddings: List[str] = [], embedding_labels: Dict[str, numpy.ndarray] = {}, x_reals: List[str] = [], x_categoricals: List[str] = [], n_validation_samples: Optional[int] = None, n_plotting_samples: Optional[int] = None, target: Optional[Union[str, List[str]]] = None, target_lags: Dict[str, List[int]] = {}, loss: Optional[pytorch_forecasting.metrics.DistributionLoss] = None, logging_metrics: Optional[torch.nn.modules.container.ModuleList] = None, **kwargs)[source]

Bases: pytorch_forecasting.models.base_model.AutoRegressiveBaseModelWithCovariates

DeepAR Network.

The code is based on the article DeepAR: Probabilistic forecasting with autoregressive recurrent networks.

Parameters

  • cell_type (str, optional) – Recurrent cell type [“LSTM”, “GRU”]. Defaults to “LSTM”.

  • hidden_size (int, optional) – hidden recurrent size - the most important hyperparameter along with rnn_layers. Defaults to 10.

  • rnn_layers (int, optional) – Number of RNN layers - important hyperparameter. Defaults to 2.

  • dropout (float, optional) – Dropout in RNN layers. Defaults to 0.1.

  • static_categoricals – integer of positions of static categorical variables

  • static_reals – integer of positions of static continuous variables

  • time_varying_categoricals_encoder – integer of positions of categorical variables for encoder

  • time_varying_categoricals_decoder – integer of positions of categorical variables for decoder

  • time_varying_reals_encoder – integer of positions of continuous variables for encoder

  • time_varying_reals_decoder – integer of positions of continuous variables for decoder

  • categorical_groups – dictionary where values are list of categorical variables that are forming together a new categorical variable which is the key in the dictionary

  • x_reals – order of continuous variables in tensor passed to forward function

  • x_categoricals – order of categorical variables in tensor passed to forward function

  • embedding_sizes – dictionary mapping (string) indices to tuple of number of categorical classes and embedding size

  • embedding_paddings – list of indices for embeddings which transform the zero’s embedding to a zero vector

  • embedding_labels – dictionary mapping (string) indices to list of categorical labels

  • n_validation_samples (int, optional) – Number of samples to use for calculating validation metrics. Defaults to None, i.e. no sampling at validation stage and using “mean” of distribution for logging metrics calculation.

  • n_plotting_samples (int, optional) – Number of samples to generate for plotting predictions during training. Defaults to n_validation_samples if not None or 100 otherwise.

  • target (str, optional) – Target variable or list of target variables. Defaults to None.

  • target_lags (Dict[str, Dict[str, int]]) – dictionary of target names mapped to list of time steps by which the variable should be lagged. Lags can be useful to indicate seasonality to the models. If you know the seasonalit(ies) of your data, add at least the target variables with the corresponding lags to improve performance. Defaults to no lags, i.e. an empty dictionary.

  • loss (DistributionLoss, optional) – Distribution loss function. Keep in mind that each distribution loss function might have specific requirements for target normalization. Defaults to NormalDistributionLoss.

  • logging_metrics (nn.ModuleList, optional) – Metrics to log during training. Defaults to nn.ModuleList([SMAPE(), MAE(), RMSE(), MAPE(), MASE()]).

Methods

construct_input_vector(x_cat, x_cont[, …])

Create input vector into RNN network

decode(input_vector, target_scale, …[, …])

Decode hidden state of RNN into prediction.

decode_all(x, hidden_state[, lengths])

encode(x)

Encode sequence into hidden state

forward(x[, n_samples])

Forward network

from_dataset(dataset[, …])

Create model from dataset.

log_metrics(x, y, out)

Log metrics every training/validation step.

log_prediction(x, out, batch_idx)

Log metrics every training/validation step.

plot_prediction(x, out, idx[, …])

Plot prediction of prediction vs actuals

predict(data[, mode, return_index, …])

predict dataloader

validation_step(batch, batch_idx)

Operates on a single batch of data from the validation set.
construct_input_vector(x_cat: torch.Tensor, x_cont: torch.Tensor, one_off_target: Optional[torch.Tensor] = None) → torch.Tensor[source]

Create input vector into RNN network

Parameters

one_off_target – tensor to insert into first position of target. If None (default), remove first time step.

decode(input_vector: torch.Tensor, target_scale: torch.Tensor, decoder_lengths: torch.Tensor, hidden_state: Union[Tuple[torch.Tensor, torch.Tensor], torch.Tensor], n_samples: Optional[int] = None) → Tuple[torch.Tensor, bool][source]

Decode hidden state of RNN into prediction. If n_smaples is given, decode not by using actual values but rather by sampling new targets from past predictions iteratively

encode(x: Dict[str, torch.Tensor]) → Union[Tuple[torch.Tensor, torch.Tensor], torch.Tensor][source]

Encode sequence into hidden state

forward(x: Dict[str, torch.Tensor], n_samples: Optional[int] = None) → Dict[str, torch.Tensor][source]

Forward network

classmethod from_dataset(dataset: pytorch_forecasting.data.timeseries.TimeSeriesDataSet, allowed_encoder_known_variable_names: Optional[List[str]] = None, **kwargs)[source]

Create model from dataset.

Parameters

  • dataset – timeseries dataset

  • allowed_encoder_known_variable_names – List of known variables that are allowed in encoder, defaults to all

  • **kwargs – additional arguments such as hyperparameters for model (see __init__())

Returns

DeepAR network

log_metrics(x: Dict[str, torch.Tensor], y: torch.Tensor, out: Dict[str, torch.Tensor])[source]

Log metrics every training/validation step.

Parameters

  • x (Dict[str, torch.Tensor]) – x as passed to the network by the dataloader

  • y (torch.Tensor) – y as passed to the loss function by the dataloader

  • out (Dict[str, torch.Tensor]) – output of the network

  • prediction_kwargs (Dict[str, Any]) – parameters for to_prediction() of the loss metric.

log_prediction(x, out, batch_idx) → None[source]

Log metrics every training/validation step.

Parameters

  • x (Dict[str, torch.Tensor]) – x as passed to the network by the dataloader

  • out (Dict[str, torch.Tensor]) – output of the network

  • batch_idx (int) – current batch index

  • **kwargs – paramters to pass to pot_prediction

plot_prediction(x: Dict[str, torch.Tensor], out: Dict[str, torch.Tensor], idx: int, add_loss_to_title: Union[pytorch_forecasting.metrics.Metric, torch.Tensor, bool] = False, show_future_observed: bool = True, ax=None, **kwargs) → matplotlib.figure.Figure[source]

Plot prediction of prediction vs actuals

Parameters

  • x – network input

  • out – network output

  • idx – index of prediction to plot

  • add_loss_to_title – if to add loss to title or loss function to calculate. Can be either metrics, bool indicating if to use loss metric or tensor which contains losses for all samples. Calcualted losses are determined without weights. Default to False.

  • show_future_observed – if to show actuals for future. Defaults to True.

  • ax – matplotlib axes to plot on

  • quantiles_kwargs (Dict[str, Any]) – parameters for to_quantiles() of the loss metric.

  • prediction_kwargs (Dict[str, Any]) – parameters for to_prediction() of the loss metric.

Returns

matplotlib figure

predict(data: Union[torch.utils.data.dataloader.DataLoader, pandas.core.frame.DataFrame, pytorch_forecasting.data.timeseries.TimeSeriesDataSet], mode: Union[str, Tuple[str, str]] = 'prediction', return_index: bool = False, return_decoder_lengths: bool = False, batch_size: int = 64, num_workers: int = 0, fast_dev_run: bool = False, show_progress_bar: bool = False, return_x: bool = False, n_samples: int = 100)[source]

predict dataloader

Parameters

  • dataloader – dataloader, dataframe or dataset

  • mode – one of “prediction”, “quantiles” or “raw”, or tuple ("raw", output_name) where output_name is a name in the dictionary returned by forward()

  • return_index – if to return the prediction index

  • return_decoder_lengths – if to return decoder_lengths

  • batch_size – batch size for dataloader - only used if data is not a dataloader is passed

  • num_workers – number of workers for dataloader - only used if data is not a dataloader is passed

  • fast_dev_run – if to only return results of first batch

  • show_progress_bar – if to show progress bar. Defaults to False.

  • return_x – if to return network inputs

  • n_samples – number of samples to draw. Defaults to 100.

Returns

some elements might not be present depending on what is configured

to be returned

Return type

output, x, index, decoder_lengths

validation_step(batch, batch_idx)[source]

Operates on a single batch of data from the validation set. In this step you’d might generate examples or calculate anything of interest like accuracy.

# the pseudocode for these calls
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    val_outs.append(out)
validation_epoch_end(val_outs)
Parameters

  • batch (Tensor | (Tensor, …) | [Tensor, …]) – The output of your DataLoader. A tensor, tuple or list.

  • batch_idx (int) – The index of this batch

  • dataloader_idx (int) – The index of the dataloader that produced this batch (only if multiple val dataloaders used)

Returns

Any of.

  • Any object or value

  • None - Validation will skip to the next batch

# pseudocode of order
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    if defined('validation_step_end'):
        out = validation_step_end(out)
    val_outs.append(out)
val_outs = validation_epoch_end(val_outs)

# if you have one val dataloader:
def validation_step(self, batch, batch_idx)

# if you have multiple val dataloaders:
def validation_step(self, batch, batch_idx, dataloader_idx)

Examples:

# CASE 1: A single validation dataset
def validation_step(self, batch, batch_idx):
    x, y = batch

    # implement your own
    out = self(x)
    loss = self.loss(out, y)

    # log 6 example images
    # or generated text... or whatever
    sample_imgs = x[:6]
    grid = torchvision.utils.make_grid(sample_imgs)
    self.logger.experiment.add_image('example_images', grid, 0)

    # calculate acc
    labels_hat = torch.argmax(out, dim=1)
    val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)

    # log the outputs!
    self.log_dict({'val_loss': loss, 'val_acc': val_acc})

If you pass in multiple val dataloaders, validation_step() will have an additional argument.

# CASE 2: multiple validation dataloaders
def validation_step(self, batch, batch_idx, dataloader_idx):
    # dataloader_idx tells you which dataset this is.

Note

If you don’t need to validate you don’t need to implement this method.

Note

When the validation_step() is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of validation, the model goes back to training mode and gradients are enabled.

Baseline DecoderMLP