MAINT Parameters validation for MultiTaskElasticNet and MultiTaskLasso (scikit-learn#24295)

Co-authored-by: jeremie du boisberranger <[email protected]>

Author: OmarManzoor

sklearn/linear_model/_coordinate_descent.py

@@ -2410,6 +2410,12 @@ class MultiTaskElasticNet(Lasso):
     [0.0872422 0.0872422]
     """
 
+    _parameter_constraints: dict = {
+        **ElasticNet._parameter_constraints,
+    }
+    for param in ("precompute", "positive"):
+        _parameter_constraints.pop(param)
+
     def __init__(
         self,
         alpha=1.0,
@@ -2459,6 +2465,8 @@ def fit(self, X, y):
         To avoid memory re-allocation it is advised to allocate the
         initial data in memory directly using that format.
         """
+        self._validate_params()
+
         _normalize = _deprecate_normalize(
             self.normalize, default=False, estimator_name=self.__class__.__name__
         )
@@ -2501,8 +2509,6 @@ def fit(self, X, y):
 
         self.coef_ = np.asfortranarray(self.coef_)  # coef contiguous in memory
 
-        if self.selection not in ["random", "cyclic"]:
-            raise ValueError("selection should be either random or cyclic.")
         random = self.selection == "random"
 
         (
@@ -2660,6 +2666,11 @@ class MultiTaskLasso(MultiTaskElasticNet):
     [-0.41888636 -0.87382323]
     """
 
+    _parameter_constraints: dict = {
+        **MultiTaskElasticNet._parameter_constraints,
+    }
+    _parameter_constraints.pop("l1_ratio")
+
     def __init__(
         self,
         alpha=1.0,

sklearn/linear_model/tests/test_coordinate_descent.py

@@ -1385,10 +1385,6 @@ def test_convergence_warnings():
     X = random_state.standard_normal((1000, 500))
     y = random_state.standard_normal((1000, 3))
 
-    # check that the model fails to converge (a negative dual gap cannot occur)
-    with pytest.warns(ConvergenceWarning):
-        MultiTaskElasticNet(max_iter=1, tol=-1).fit(X, y)
-
     # check that the model converges w/o convergence warnings
     with warnings.catch_warnings():
         warnings.simplefilter("error", ConvergenceWarning)

sklearn/tests/test_common.py

@@ -466,8 +466,6 @@ def test_estimators_do_not_raise_errors_in_init_or_set_params(Estimator):
 PARAM_VALIDATION_ESTIMATORS_TO_IGNORE = [
     "DictionaryLearning",
     "MiniBatchDictionaryLearning",
-    "MultiTaskElasticNet",
-    "MultiTaskLasso",
     "Nystroem",
     "OAS",
     "OPTICS",