TypeError: object of type 'NoneType' has no len() during python -m chebai fit when using chebi50_graph_properties.yml

[aditya0by0]

Description:
When running the fit command for training on ChEBI50 with graph properties, the process fails during data loading due to recent commit ChEB-AI/python-chebai@5870948 in python-chebai .
The traceback points to a NoneType object where a feature vector was expected.

Command executed:

python -m chebai fit \
  --trainer=configs/training/default_trainer.yml \
  --trainer.callbacks=configs/training/default_callbacks.yml \
  --model=../python-chebai-graph/configs/model/gnn_res_gated.yml \
  --model.train_metrics=configs/metrics/micro-macro-f1.yml \
  --model.val_metrics=configs/metrics/micro-macro-f1.yml \
  --model.test_metrics=configs/metrics/micro-macro-f1.yml \
  --data=../python-chebai-graph/configs/data/chebi50_graph_properties.yml \
  --model.criterion=configs/loss/bce.yml \
  --data.init_args.batch_size=40 \
  --data.init_args.num_workers=12 \
  --data.init_args.chebi_version=231 \
  --trainer.logger.init_args.name=chebi50_bce_unweighted_resgatedgraph \
  --trainer.min_epochs=1 \
  --trainer.max_epochs=1 \
  --model.pass_loss_kwargs=false

---

Error Traceback:

.Traceback (most recent call last):
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_link_arguments.py", line 267, in call_compute_fn
    return self.compute_fn(*args)
  File "G:\github-aditya0by0\python-chebai\chebai\cli.py", line 46, in call_data_methods
    data.setup()
  File "G:\anaconda3\envs\gnn3\lib\site-packages\chebai_graph\preprocessing\datasets\chebi.py", line 138, in setup
    super().setup(keep_reader=True, **kwargs)
  File "G:\github-aditya0by0\python-chebai\chebai\preprocessing\datasets\base.py", line 440, in setup
    self.setup_processed()
  File "G:\github-aditya0by0\python-chebai\chebai\preprocessing\datasets\chebi.py", line 321, in setup_processed
    super().setup_processed()
  File "G:\github-aditya0by0\python-chebai\chebai\preprocessing\datasets\base.py", line 874, in setup_processed
    self._load_data_from_file(
  File "G:\github-aditya0by0\python-chebai\chebai\preprocessing\datasets\base.py", line 334, in _load_data_from_file
    data = [
  File "G:\github-aditya0by0\python-chebai\chebai\preprocessing\datasets\base.py", line 339, in <listcomp>
    or len(val["features"]) <= self.n_token_limit
TypeError: object of type 'NoneType' has no len()

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "G:\anaconda3\envs\gnn3\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "G:\anaconda3\envs\gnn3\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "G:\github-aditya0by0\python-chebai\chebai\__main__.py", line 10, in <module>
    cli()
  File "G:\github-aditya0by0\python-chebai\chebai\cli.py", line 94, in cli
    r = ChebaiCLI(
  File "G:\github-aditya0by0\python-chebai\chebai\cli.py", line 32, in __init__
    super().__init__(trainer_class=CustomTrainer, *args, **kwargs)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\lightning\pytorch\cli.py", line 394, in __init__
    self.instantiate_classes()
  File "G:\anaconda3\envs\gnn3\lib\site-packages\lightning\pytorch\cli.py", line 561, in instantiate_classes
    self.config_init = self.parser.instantiate_classes(self.config)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_deprecated.py", line 140, in patched_instantiate_classes
    cfg = self._unpatched_instantiate_classes(cfg, **kwargs)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_core.py", line 1254, in instantiate_classes
    cfg[subcommand] = subparser.instantiate_classes(cfg[subcommand], instantiate_groups=instantiate_groups)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_deprecated.py", line 140, in patched_instantiate_classes
    cfg = self._unpatched_instantiate_classes(cfg, **kwargs)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_core.py", line 1232, in instantiate_classes
    ActionLink.apply_instantiation_links(self, cfg, target=component.dest)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_link_arguments.py", line 364, in apply_instantiation_links
    value = action.call_compute_fn(source_objects)
  File "G:\anaconda3\envs\gnn3\lib\site-packages\jsonargparse\_link_arguments.py", line 271, in call_compute_fn
    raise ValueError(f"Call to compute_fn of link '{link}' with args ({args}) failed: {ex}") from ex
ValueError: Call to compute_fn of link 'call_data_methods(data) --> model.init_args.out_dim' with args ({Train dataloader: None}
{Validation dataloader: None}
{Test dataloader: None}
{Predict dataloader: None}) failed: object of type 'NoneType' has no len()

[aditya0by0]

closed by ChEB-AI/python-chebai#85