Numpy v2.0.0 has deprecated np.NINF

[cesar-perceiv]

• ebm2onnx version: 3.1.3
• Python version: 3.12
• Operating System: Debian 12 (bookworm)

Description

Serialization of an EBM model fails with numpy==v2.0.0 due to np.NINF being deprecated.

What I Did

onnx_model = ebm2onnx.to_onnx(model=model, dtype=ebm2onnx.get_dtype_from_pandas(features))

File [/usr/local/lib/python3.12/site-packages/ebm2onnx/convert.py:113](http://localhost:8888/usr/local/lib/python3.12/site-packages/ebm2onnx/convert.py#line=112), in to_onnx(model, dtype, name, predict_proba, explain, target_opset, prediction_name, probabilities_name, explain_name)
    110 feature_group=model.term_features_[feature_index]
    112 if feature_type == 'continuous':
--> 113     bins = [np.NINF, np.NINF] + list(model.bins_[feature_group[0]][0])
    114     additive_terms = model.term_scores_[feature_index]
    116     feature_dtype = infer_features_dtype(dtype, feature_name)

File [/usr/local/lib/python3.12/site-packages/numpy/__init__.py:397](http://localhost:8888/usr/local/lib/python3.12/site-packages/numpy/__init__.py#line=396), in __getattr__(attr)
    394     raise AttributeError(__former_attrs__[attr])
    396 if attr in __expired_attributes__:
--> 397     raise AttributeError(
    398         f"`np.{attr}` was removed in the NumPy 2.0 release. "
    399         f"{__expired_attributes__[attr]}"
    400     )
    402 if attr == "chararray":
    403     warnings.warn(
    404         "`np.chararray` is deprecated and will be removed from "
    405         "the main namespace in the future. Use an array with a string "
    406         "or bytes dtype instead.", DeprecationWarning, stacklevel=2)

AttributeError: `np.NINF` was removed in the NumPy 2.0 release. Use `-np.inf` instead.

I will make a PR for this easy fix.

[MainRo]

Thanks!