MAINT: Don't make inapplicable conditions block oneDAL usage in LogisticRegression (#2513)

* remove unnecessary conditions

* update support table

* Update sklearnex/linear_model/logistic_regression.py

Co-authored-by: Ian Faust <[email protected]>

---------

Co-authored-by: Ian Faust <[email protected]>

Author: david-cortes-intel

doc/sources/algorithms.rst

@@ -313,9 +313,8 @@ Classification
        - ``penalty`` != `'l2'`
        - ``dual`` = `True`
        - ``intercept_scaling`` != `1`
-       - ``multi_class`` != `'multinomial'`
        - ``warm_start`` = `True`
-       - ``l1_ratio`` != `None`
+       - ``l1_ratio`` != 0 and ``l1_ratio`` != ``None``
        - Only binary classification is supported
      - No limitations
 

sklearnex/linear_model/logistic_regression.py

@@ -208,12 +208,11 @@ def _onedal_gpu_fit_supported(self, method_name, *data):
                     ),
                     (self.class_weight is None, "Class weight is not supported"),
                     (self.solver == "newton-cg", "Only newton-cg solver is supported."),
+                    (self.warm_start == False, "Warm start is not supported."),
                     (
-                        self.multi_class != "multinomial",
-                        "multi_class parameter is not supported.",
+                        not self.l1_ratio,
+                        "l1 ratio is not supported.",
                     ),
-                    (self.warm_start == False, "Warm start is not supported."),
-                    (self.l1_ratio is None, "l1 ratio is not supported."),
                     (sample_weight is None, "Sample weight is not supported."),
                     (
                         target_type == "binary",