Add scikit-learn 1.0 and 1.1 values for test (openml#1168)

PGijsbers · PGijsbers · commit 2c0b9834da1e · 2023-02-23T15:32:04.000+01:00
* Add scikit-learn 1.0 and 1.1 values for test

DecisionTree and RandomForestRegressor have one less default
hyperparameter: `min_impurity_split`

* Remove min_impurity_split requirements for &gt;=1.0

* Update KMeans checks for scikit-learn 1.0 and 1.1
diff --git a/tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py b/tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py
@@ -168,7 +168,7 @@ def test_serialize_model(self):
                     ("splitter", '"best"'),
                 )
             )
-        else:
+        elif LooseVersion(sklearn.__version__) < "1.0":
             fixture_parameters = OrderedDict(
                 (
                     ("class_weight", "null"),
@@ -186,6 +186,24 @@ def test_serialize_model(self):
                     ("splitter", '"best"'),
                 )
             )
+        else:
+            fixture_parameters = OrderedDict(
+                (
+                    ("class_weight", "null"),
+                    ("criterion", '"entropy"'),
+                    ("max_depth", "null"),
+                    ("max_features", '"auto"'),
+                    ("max_leaf_nodes", "2000"),
+                    ("min_impurity_decrease", "0.0"),
+                    ("min_samples_leaf", "1"),
+                    ("min_samples_split", "2"),
+                    ("min_weight_fraction_leaf", "0.0"),
+                    ("presort", presort_val),
+                    ("random_state", "null"),
+                    ("splitter", '"best"'),
+                )
+            )
+
         if LooseVersion(sklearn.__version__) >= "0.22":
             fixture_parameters.update({"ccp_alpha": "0.0"})
             fixture_parameters.move_to_end("ccp_alpha", last=False)
@@ -249,7 +267,7 @@ def test_serialize_model_clustering(self):
                     ("verbose", "0"),
                 )
             )
-        else:
+        elif LooseVersion(sklearn.__version__) < "1.0":
             fixture_parameters = OrderedDict(
                 (
                     ("algorithm", '"auto"'),
@@ -265,6 +283,34 @@ def test_serialize_model_clustering(self):
                     ("verbose", "0"),
                 )
             )
+        elif LooseVersion(sklearn.__version__) < "1.1":
+            fixture_parameters = OrderedDict(
+                (
+                    ("algorithm", '"auto"'),
+                    ("copy_x", "true"),
+                    ("init", '"k-means++"'),
+                    ("max_iter", "300"),
+                    ("n_clusters", "8"),
+                    ("n_init", "10"),
+                    ("random_state", "null"),
+                    ("tol", "0.0001"),
+                    ("verbose", "0"),
+                )
+            )
+        else:
+            fixture_parameters = OrderedDict(
+                (
+                    ("algorithm", '"lloyd"'),
+                    ("copy_x", "true"),
+                    ("init", '"k-means++"'),
+                    ("max_iter", "300"),
+                    ("n_clusters", "8"),
+                    ("n_init", "10"),
+                    ("random_state", "null"),
+                    ("tol", "0.0001"),
+                    ("verbose", "0"),
+                )
+            )
         fixture_structure = {"sklearn.cluster.{}.KMeans".format(cluster_name): []}
 
         serialization, _ = self._serialization_test_helper(
@@ -1335,12 +1381,19 @@ def test__get_fn_arguments_with_defaults(self):
                 (sklearn.tree.DecisionTreeClassifier.__init__, 14),
                 (sklearn.pipeline.Pipeline.__init__, 2),
             ]
-        else:
+        elif sklearn_version < "1.0":
             fns = [
                 (sklearn.ensemble.RandomForestRegressor.__init__, 18),
                 (sklearn.tree.DecisionTreeClassifier.__init__, 13),
                 (sklearn.pipeline.Pipeline.__init__, 2),
             ]
+        else:
+            # Tested with 1.0 and 1.1
+            fns = [
+                (sklearn.ensemble.RandomForestRegressor.__init__, 17),
+                (sklearn.tree.DecisionTreeClassifier.__init__, 12),
+                (sklearn.pipeline.Pipeline.__init__, 2),
+            ]
 
         for fn, num_params_with_defaults in fns:
             defaults, defaultless = self.extension._get_fn_arguments_with_defaults(fn)
