DeepGBM bug during data preprocessing

[duncanmcelfresh]

this error with alg DeepGBM was encountered with dataset openml__credit-approval__29. this occurs when running with both GPU and CPU.

Preprocess data for CatNN...
caught exception during cross-validation...
Traceback (most recent call last):
  File "/home/shared/tabzilla/TabSurvey/tabzilla_experiment.py", line 137, in __call__
    result = cross_validation(model, self.dataset, self.time_limit)
  File "/home/shared/tabzilla/TabSurvey/tabzilla_utils.py", line 246, in cross_validation
    loss_history, val_loss_history = curr_model.fit(
  File "/home/shared/tabzilla/TabSurvey/models/deepgbm.py", line 55, in fit
    train_x_cat, feature_sizes = self.ce.fit_transform(X.copy())
  File "/home/shared/tabzilla/TabSurvey/models/deepgbm_lib/preprocess/preprocessing_cat.py", line 35, in fit_transform
    out, bins = pd.qcut(X[:, idx], config.config['bins'], labels=False, retbins=True, duplicates='drop')
  File "/opt/conda/envs/torch/lib/python3.10/site-packages/pandas/core/reshape/tile.py", line 375, in qcut
    x_np = x_np[~np.isnan(x_np)]
TypeError: ufunc 'isnan' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''