[LCDB 2.0] ValueError on DenseNNWorkflow

[Deathn0t]

The command to reproduce is:

lcdb test -id 6 -w lcdb.workflow.keras.DenseNNWorkflow -m -vs 42 -ts 42 -ws 42 --parameters '{"activation": "tanh", "activity_regularizer": "none", "batch_norm": false, "batch_size": 74, "bias_regularizer": "L1", "dropout_rate": 0.5235265140514189, "kernel_initializer": "random_uniform", "kernel_regularizer": "none", "learning_rate": 0.0010642794778408, "num_layers": 13, "num_units": 4, "optimizer": "Nadam", "regularizer_factor": 0.7423546250656852, "shuffle_each_epoch": false, "skip_co": true, "transform_cat": "onehot", "transform_real": "none"}'

The example trace is:

2023-12-22 22:56:01,852 - ERROR - controller.py:fit_workflow_on_current_anchor - Error while fitting the workflow:
Traceback (most recent call last):
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/lcdb/controller.py", line 208, in fit_workflow_on_current_anchor
    self.workflow.fit(
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/lcdb/utils.py", line 67, in terminate_on_timeout
    return results.get(timeout)
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/build/dhenv/lib/python3.10/multiprocessing/pool.py", line 774, in get
    raise self._value
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/build/dhenv/lib/python3.10/multiprocessing/pool.py", line 125, in worker
    result = (True, func(*args, **kwds))
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/lcdb/workflow/_base_workflow.py", line 31, in fit
    self._fit(X=X, y=y, metadata=metadata, *args, **kwargs)
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/lcdb/workflow/keras/_dense.py", line 299, in _fit
    y_valid_ = self._transformer_label.transform(y_valid)
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/build/dhenv/lib/python3.10/site-packages/sklearn/preprocessing/_label.py", line 137, in transform
    return _encode(y, uniques=self.classes_)
  File "/lus/grand/projects/datascience/regele/polaris/lcdb/publications/2023-neurips/build/dhenv/lib/python3.10/site-packages/sklearn/utils/_encode.py", line 232, in _encode
    raise ValueError(f"y contains previously unseen labels: {str(diff)}")
ValueError: y contains previously unseen labels: [1, 3, 4, 6, 7, 9, 11, 13, 14, 16, 18, 19, 24]