Skip to content

[DOC] Add RecurrentNetwork usage example #2397

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
obaidsafi51 wants to merge 2 commits into
base: main
Choose a base branch
from
+52 −0
Open

[DOC] Add RecurrentNetwork usage example #2397

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
70e4873
[DOC]: Add RecurrentNetwork usage example
obaidsafi51 Aug 26, 2026
26279f8
Code Quality check fixed
obaidsafi51 Aug 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 52 additions & 0 deletions pytorch_forecasting/models/rnn/_rnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,58 @@ def __init__(
loss (MultiHorizonMetric, optional): loss: loss function taking prediction and targets.
logging_metrics (nn.ModuleList, optional): Metrics to log during training.
Defaults to nn.ModuleList([SMAPE(), MAE(), RMSE(), MAPE(), MASE()]).

Example:

@phoeenniixx phoeenniixx Aug 31, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

THis should be like this:

Example
-------------


>>> import lightning.pytorch as pl
>>> from pytorch_forecasting import RecurrentNetwork, TimeSeriesDataSet
>>> from pytorch_forecasting.data.examples import generate_ar_data
>>> data = generate_ar_data(n_series=10, timesteps=400, seed=42)
>>> max_encoder_length = 60
>>> max_prediction_length = 20
>>> training = TimeSeriesDataSet(
... data,
... time_idx="time_idx",
... target="value",
... group_ids=["series"],
... max_encoder_length=max_encoder_length,
... max_prediction_length=max_prediction_length,
... time_varying_unknown_reals=["value"],
... lags={"value": [12, 24]},
... add_relative_time_idx=True,
... add_target_scales=True,
... add_encoder_length=True,
... )
>>> validation = TimeSeriesDataSet.from_dataset(
... training, data, predict=True, stop_randomization=True
... )
>>> train_dataloader = training.to_dataloader(
... train=True, batch_size=32, num_workers=0
... )
>>> val_dataloader = validation.to_dataloader(
... train=False, batch_size=32, num_workers=0
... )
>>> rnn = RecurrentNetwork.from_dataset(
... training,
... cell_type="LSTM",
... hidden_size=32,
... rnn_layers=2,
... dropout=0.1,
... learning_rate=1e-3,
... log_interval=10,
... )
>>> trainer = pl.Trainer(
... max_epochs=1,
... accelerator="cpu",
... enable_checkpointing=False,
... logger=False,
... )
>>> trainer.fit(
... rnn,
... train_dataloaders=train_dataloader,
... val_dataloaders=val_dataloader,
... )
>>> predictions = rnn.predict(val_dataloader)
""" # noqa : E501
if static_categoricals is None:
static_categoricals = []
Expand Down
Loading