STG - input contains NaN error

[duncanmcelfresh]

occurs with datasets:

• openml__veteran__4828
• openml__mv__4774

traceback:

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 264, in cross_validation
    scorers["train"].eval(
  File "/home/shared/tabzilla/TabSurvey/utils/scorer.py", line 49, in eval
    mse = mean_squared_error(y_true, y_prediction)
  File "/opt/conda/envs/torch/lib/python3.10/site-packages/sklearn/metrics/_regression.py", line 442, in mean_squared_error
    y_type, y_true, y_pred, multioutput = _check_reg_targets(
  File "/opt/conda/envs/torch/lib/python3.10/site-packages/sklearn/metrics/_regression.py", line 102, in _check_reg_targets
    y_pred = check_array(y_pred, ensure_2d=False, dtype=dtype)
  File "/opt/conda/envs/torch/lib/python3.10/site-packages/sklearn/utils/validation.py", line 899, in check_array
    _assert_all_finite(
  File "/opt/conda/envs/torch/lib/python3.10/site-packages/sklearn/utils/validation.py", line 146, in _assert_all_finite
    raise ValueError(msg_err)
ValueError: Input contains NaN.