Fixes for sklearn 1.7 pre-release support (#2451) (#2527)

* Fixes for sklearn 1.7 pre-release support

* Fix ensemble probabilities interval

* Change scaling method to `clip`

---------


(cherry picked from commit 95c73bd)

Co-authored-by: Alexander Andreev <alexander.andreev@intel.com>
Co-authored-by: icfaust <icfaust@gmail.com>

Author: 3 people

daal4py/sklearn/ensemble/_forest.py

@@ -679,8 +679,8 @@ def _daal_predict_proba(self, X):
         dfc_predictionResult = dfc_algorithm.compute(X, self.daal_model_)
 
         pred = dfc_predictionResult.probabilities
-
-        return pred
+        # TODO: fix probabilities out of [0, 1] interval on oneDAL side
+        return pred.clip(0.0, 1.0)
 
     def _daal_fit_classifier(self, X, y, sample_weight=None):
         y = check_array(y, ensure_2d=False, dtype=None)

daal4py/sklearn/manifold/_t_sne.py

@@ -66,7 +66,13 @@ def _daal_tsne(self, P, n_samples, X_embedded):
             [n_samples],
             [P.nnz],
             [self.n_iter_without_progress],
-            [self._max_iter if sklearn_check_version("1.5") else self.n_iter],
+            [
+                (
+                    self.max_iter
+                    if sklearn_check_version("1.7")
+                    else (self._max_iter if sklearn_check_version("1.5") else self.n_iter)
+                )
+            ],
         ]
 
         # Pass params to daal4py backend

daal4py/sklearn/metrics/_pairwise.py

@@ -18,6 +18,7 @@
 from functools import partial
 
 import numpy as np
+from joblib import effective_n_jobs
 from sklearn.exceptions import DataConversionWarning
 from sklearn.metrics import pairwise_distances as pairwise_distances_original
 from sklearn.metrics.pairwise import (
@@ -28,7 +29,6 @@
     _parallel_pairwise,
     check_pairwise_arrays,
 )
-from sklearn.utils._joblib import effective_n_jobs
 from sklearn.utils.validation import check_non_negative
 
 try:

onedal/ensemble/forest.py

@@ -424,7 +424,9 @@ def _predict_proba(self, X, hparams=None):
         else:
             result = self.infer(params, model, X)
 
-        return from_table(result.probabilities)
+        # TODO: fix probabilities out of [0, 1] interval on oneDAL side
+        pred = from_table(result.probabilities)
+        return pred.clip(0.0, 1.0)
 
 
 class RandomForestClassifier(ClassifierMixin, BaseForest, metaclass=ABCMeta):

onedal/utils/_array_api.py

@@ -68,7 +68,12 @@ def _asarray(data, xp, *args, **kwargs):
 
 def _is_numpy_namespace(xp):
     """Return True if xp is backed by NumPy."""
-    return xp.__name__ in {"numpy", "array_api_compat.numpy", "numpy.array_api"}
+    return xp.__name__ in {
+        "numpy",
+        "array_api_compat.numpy",
+        "numpy.array_api",
+        "sklearn.externals.array_api_compat.numpy",
+    }
 
 
 def _get_sycl_namespace(*arrays):