chore: update gitignore

[fede-bello]

We were getting an error when preprocessing 1 dimensional labels vectors.
I tried fixing this directly but then I started having issues with the MTAD_GAT training, since it expects the same shape in the data and in the labels

For now, I tackled this broadcasting the labels to meet the shape of the data. Eventually we can think of something more intelligent, but we will need to update MTAD_GAT so I believe that we are good for now

[gonzachiar]

Which error are you getting? I don't like this fix because it will affect the model's performance, I prefer to fix the model.

[fede-bello]

This is the error:

(gragod-py3.10)  ✘  ~/personal/GraGOD   feat/mtad-gat-for-swat ±  python models/mtad_gat/train.py
Seed set to 42
Data cleaned!
Data cleaned!
Data cleaned!
/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/utilities/parsing.py:208: Attribute 'forecast_criterion' is an instance of `nn.Module` and is already saved during checkpointing. It is recommended to ignore them using `self.save_hyperparameters(ignore=['forecast_criterion'])`.
/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/utilities/parsing.py:208: Attribute 'recon_criterion' is an instance of `nn.Module` and is already saved during checkpointing. It is recommended to ignore them using `self.save_hyperparameters(ignore=['recon_criterion'])`.
GPU available: True (mps), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/callbacks/model_checkpoint.py:654: Checkpoint directory /Users/fbello/personal/GraGOD/output exists and is not empty.

  | Name               | Type     | Params | Mode
--------------------------------------------------------
0 | model              | MTAD_GAT | 1.3 M  | train
1 | forecast_criterion | MSELoss  | 0      | train
2 | recon_criterion    | MSELoss  | 0      | train
--------------------------------------------------------
1.3 M     Trainable params
0         Non-trainable params
1.3 M     Total params
5.138     Total estimated model params size (MB)
29        Modules in train mode
0         Modules in eval mode
Sanity Checking: |                                                                                                                                                                              | 0/? [00:00<?, ?it/s]/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:424: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=10` in the `DataLoader` to improve performance.
Sanity Checking DataLoader 0:   0%|                                                                                                                                                             | 0/2 [00:00<?, ?it/s]Traceback (most recent call last):
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/train.py", line 114, in <module>
    main(
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/train.py", line 102, in main
    trainer.fit(train_loader, val_loader, args_summary=args_summary)
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/trainer_pl.py", line 261, in fit
    trainer.fit(self.lightning_module, train_loader, val_loader)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 538, in fit
    call._call_and_handle_interrupt(
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 47, in _call_and_handle_interrupt
    return trainer_fn(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 574, in _fit_impl
    self._run(model, ckpt_path=ckpt_path)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 981, in _run
    results = self._run_stage()
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1023, in _run_stage
    self._run_sanity_check()
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1052, in _run_sanity_check
    val_loop.run()
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/loops/utilities.py", line 178, in _decorator
    return loop_run(self, *args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/loops/evaluation_loop.py", line 135, in run
    self._evaluation_step(batch, batch_idx, dataloader_idx, dataloader_iter)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/loops/evaluation_loop.py", line 396, in _evaluation_step
    output = call._call_strategy_hook(trainer, hook_name, *step_args)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/trainer/call.py", line 319, in _call_strategy_hook
    output = fn(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/pytorch_lightning/strategies/strategy.py", line 411, in validation_step
    return self.lightning_module.validation_step(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/trainer_pl.py", line 138, in validation_step
    loss, recon_loss, forecast_loss = self.shared_step(batch, batch_idx)
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/trainer_pl.py", line 113, in shared_step
    preds, recons = self(x)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/trainer_pl.py", line 77, in forward
    return self.model(x)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/model.py", line 86, in forward
    x = self.conv(x)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/models/mtad_gat/modules.py", line 33, in forward
    x = self.relu(self.conv(x))
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 375, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/Users/fbello/personal/GraGOD/.venv/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 370, in _conv_forward
    return F.conv1d(
RuntimeError: Given groups=1, weight of size [51, 51, 7], expected input[264, 1, 10] to have 51 channels, but got 1 channels instead
(gragod-py3.10)  ✘  ~/personal/GraGOD   feat/mtad-gat-for-swat ± 

However, I don't think it will be that easy to change the model, right? Isn't it thought to have one label per column?

[gonzachiar]

Labels are not used during training. This happens because the load_swat_training_data is returning the arrays in the wrong order. I'll fix it in another branch.

[gonzachiar]

https://github.com/gonzachiar/GraGOD/pull/13