From 47997eeac8579de53b54a5c862a94e15b27402f2 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 15 Dec 2021 15:33:46 -0500
Subject: [PATCH 01/41] max_depth: add tests

---
 sklearn/tree/tests/test_tree.py | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index cd6b245bee60e..a17b9b9977e21 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -602,8 +602,8 @@ def test_error():
             TreeEstimator(min_samples_split=1.1).fit(X, y)
         with pytest.raises(ValueError):
             TreeEstimator(min_samples_split=2.5).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(max_depth=-1).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(max_depth=-1).fit(X, y)
         with pytest.raises(ValueError):
             TreeEstimator(max_features=42).fit(X, y)
         with pytest.raises(ValueError):
@@ -662,6 +662,31 @@ def test_error():
         est.fit([[0, 1, 2]], [5, -0.1, 2])
 
 
+@pytest.mark.parametrize("name, Tree", ALL_TREES.items())
+@pytest.mark.parametrize(
+    "params, err_type, err_msg",
+    [
+        ({"max_depth": -1}, ValueError, "max_depth == -1, must be > 0"),
+        (
+            {"max_depth": 1.1},
+            TypeError,
+            "max_depth must be an instance of <class 'numbers.Integral'>, not",
+        ),
+    ],
+)
+def test_tree_params_validation(name, Tree, params, err_type, err_msg):
+    """Check parameter validation in DecisionTreeClassifier, DecisionTreeRegressor,
+    ExtraTreeClassifier, and ExtraTreeRegressor.
+    """
+    if "Classifier" in name:
+        X, y = iris.data, iris.target
+    else:
+        X, y = diabetes.data, diabetes.target
+    est = Tree(**params)
+    with pytest.raises(err_type, match=err_msg):
+        est.fit(X, y)
+
+
 def test_min_samples_split():
     """Test min_samples_split parameter"""
     X = np.asfortranarray(iris.data, dtype=tree._tree.DTYPE)

From 02fc4aff4c5c48f01339b9cfb260d2cd42ffb5cd Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 15 Dec 2021 15:34:05 -0500
Subject: [PATCH 02/41] max_depth: add validation

---
 sklearn/tree/_classes.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 3cd0e000bd4dd..b6e44d77eda00 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -32,6 +32,7 @@
 from ..base import MultiOutputMixin
 from ..utils import Bunch
 from ..utils import check_random_state
+from ..utils import check_scalar
 from ..utils.deprecation import deprecated
 from ..utils.validation import _check_sample_weight
 from ..utils import compute_sample_weight
@@ -225,6 +226,14 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             y = np.ascontiguousarray(y, dtype=DOUBLE)
 
         # Check parameters
+        if self.max_depth is not None:
+            check_scalar(
+                self.max_depth,
+                "max_depth",
+                target_type=numbers.Integral,
+                min_val=0,
+                include_boundaries="neither",
+            )
         max_depth = np.iinfo(np.int32).max if self.max_depth is None else self.max_depth
         max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
 
@@ -300,8 +309,8 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             )
         if not 0 <= self.min_weight_fraction_leaf <= 0.5:
             raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
-        if max_depth <= 0:
-            raise ValueError("max_depth must be greater than zero. ")
+        # if max_depth <= 0:
+        #     raise ValueError("max_depth must be greater than zero. ")
         if not (0 < max_features <= self.n_features_in_):
             raise ValueError("max_features must be in (0, n_features]")
         if not isinstance(max_leaf_nodes, numbers.Integral):

From 0ab553512bc05c3b8bff44c06ea21ae1b054ce77 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 15 Dec 2021 16:49:18 -0500
Subject: [PATCH 03/41] min_sample_split: add tests and validation

---
 sklearn/tree/_classes.py        | 45 ++++++++++++++++++++++-----------
 sklearn/tree/tests/test_tree.py | 39 ++++++++++++++++++++++------
 2 files changed, 61 insertions(+), 23 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index b6e44d77eda00..a0775f3fe8285 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -253,22 +253,37 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             min_samples_leaf = int(ceil(self.min_samples_leaf * n_samples))
 
         if isinstance(self.min_samples_split, numbers.Integral):
-            if not 2 <= self.min_samples_split:
-                raise ValueError(
-                    "min_samples_split must be an integer "
-                    "greater than 1 or a float in (0.0, 1.0]; "
-                    "got the integer %s"
-                    % self.min_samples_split
-                )
+            # if not 2 <= self.min_samples_split:
+            #     raise ValueError(
+            #         "min_samples_split must be an integer "
+            #         "greater than 1 or a float in (0.0, 1.0]; "
+            #         "got the integer %s"
+            #         % self.min_samples_split
+            #     )
+            check_scalar(
+                self.min_samples_split,
+                "min_samples_split",
+                target_type=numbers.Integral,
+                min_val=1,
+                include_boundaries="neither",
+            )
             min_samples_split = self.min_samples_split
-        else:  # float
-            if not 0.0 < self.min_samples_split <= 1.0:
-                raise ValueError(
-                    "min_samples_split must be an integer "
-                    "greater than 1 or a float in (0.0, 1.0]; "
-                    "got the float %s"
-                    % self.min_samples_split
-                )
+        else:  # float, string, other
+            # if not 0.0 < self.min_samples_split <= 1.0:
+            #     raise ValueError(
+            #         "min_samples_split must be an integer "
+            #         "greater than 1 or a float in (0.0, 1.0]; "
+            #         "got the float %s"
+            #         % self.min_samples_split
+            #     )
+            check_scalar(
+                self.min_samples_split,
+                "min_samples_split",
+                target_type=numbers.Real,
+                min_val=0.0,
+                max_val=1.0,
+                include_boundaries="right",
+            )
             min_samples_split = int(ceil(self.min_samples_split * n_samples))
             min_samples_split = max(2, min_samples_split)
 
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a17b9b9977e21..7db4980830340 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -594,14 +594,14 @@ def test_error():
             TreeEstimator(min_weight_fraction_leaf=-1).fit(X, y)
         with pytest.raises(ValueError):
             TreeEstimator(min_weight_fraction_leaf=0.51).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_split=-1).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_split=0.0).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_split=1.1).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_split=2.5).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_samples_split=-1).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_samples_split=0.0).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_samples_split=1.1).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_samples_split=2.5).fit(X, y)
         # with pytest.raises(ValueError):
         #     TreeEstimator(max_depth=-1).fit(X, y)
         with pytest.raises(ValueError):
@@ -672,6 +672,29 @@ def test_error():
             TypeError,
             "max_depth must be an instance of <class 'numbers.Integral'>, not",
         ),
+        ({"min_samples_split": -1}, ValueError, "min_samples_split == -1, must be > 1"),
+        ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be > 1"),
+        (
+            {"min_samples_split": 0.0},
+            ValueError,
+            "min_samples_split == 0.0, must be > 0.0",
+        ),
+        (
+            {"min_samples_split": 1.1},
+            ValueError,
+            "min_samples_split == 1.1, must be <= 1.0",
+        ),
+        (
+            {"min_samples_split": 2.5},
+            ValueError,
+            "min_samples_split == 2.5, must be <= 1.0",
+        ),
+        (
+            {"min_samples_split": "foo"},
+            TypeError,
+            "min_samples_split must be an instance of <class 'numbers.Real'>, not"
+            " <class 'str'>.",
+        ),
     ],
 )
 def test_tree_params_validation(name, Tree, params, err_type, err_msg):

From 88b13d64c0bd7929c7cb70bcf3e66a38a1c25f12 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 15 Dec 2021 17:15:10 -0500
Subject: [PATCH 04/41] min_impurity_decrease: add tests and valiation

---
 sklearn/tree/_classes.py        | 12 +++++++++---
 sklearn/tree/tests/test_tree.py | 14 ++++++++++++--
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index a0775f3fe8285..d78e2e156594a 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -354,9 +354,15 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         else:
             min_weight_leaf = self.min_weight_fraction_leaf * np.sum(sample_weight)
 
-        if self.min_impurity_decrease < 0.0:
-            raise ValueError("min_impurity_decrease must be greater than or equal to 0")
-
+        # if self.min_impurity_decrease < 0.0:
+        #     raise ValueError("min_impurity_decrease must be greater than or equal to 0")
+        check_scalar(
+            self.min_impurity_decrease,
+            "min_impurity_decrease",
+            target_type=numbers.Real,
+            min_val=0,
+            include_boundaries="left",
+        )
         # Build tree
         criterion = self.criterion
         if not isinstance(criterion, Criterion):
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 7db4980830340..8080ba5ffceb2 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -606,8 +606,8 @@ def test_error():
         #     TreeEstimator(max_depth=-1).fit(X, y)
         with pytest.raises(ValueError):
             TreeEstimator(max_features=42).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_impurity_decrease=-1.0).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_impurity_decrease=-1.0).fit(X, y)
 
         # Wrong dimensions
         est = TreeEstimator()
@@ -695,6 +695,16 @@ def test_error():
             "min_samples_split must be an instance of <class 'numbers.Real'>, not"
             " <class 'str'>.",
         ),
+        (
+            {"min_impurity_decrease": -1.0},
+            ValueError,
+            "min_impurity_decrease == -1.0, must be >= 0",
+        ),
+        (
+            {"min_impurity_decrease": "foo"},
+            TypeError,
+            "min_impurity_decrease must be an instance of <class 'numbers.Real'>",
+        ),
     ],
 )
 def test_tree_params_validation(name, Tree, params, err_type, err_msg):

From 645fc2291a4c7cdf341dfc9243bd68f77d4149a1 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 15 Dec 2021 18:01:49 -0500
Subject: [PATCH 05/41] fix lint issue

---
 sklearn/tree/_classes.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index d78e2e156594a..1bc5d1300a63d 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -355,7 +355,9 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             min_weight_leaf = self.min_weight_fraction_leaf * np.sum(sample_weight)
 
         # if self.min_impurity_decrease < 0.0:
-        #     raise ValueError("min_impurity_decrease must be greater than or equal to 0")
+        #     raise ValueError(
+        #         "min_impurity_decrease must be greater than or equal to 0"
+        #     )
         check_scalar(
             self.min_impurity_decrease,
             "min_impurity_decrease",

From 69c43472cfb76ee225a86822b1c9966a2bb62ae8 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 15 Dec 2021 23:24:54 -0500
Subject: [PATCH 06/41] max_leaf_nodes: add tests and validation

---
 sklearn/tree/_classes.py        | 19 +++++++++----------
 sklearn/tree/tests/test_tree.py |  6 ++++++
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 1bc5d1300a63d..a64698767b445 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -235,6 +235,15 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 include_boundaries="neither",
             )
         max_depth = np.iinfo(np.int32).max if self.max_depth is None else self.max_depth
+
+        if self.max_leaf_nodes is not None:
+            check_scalar(
+                self.max_leaf_nodes,
+                "max_leaf_nodes",
+                target_type=numbers.Integral,
+                min_val=2,
+                include_boundaries="left",
+            )
         max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
 
         if isinstance(self.min_samples_leaf, numbers.Integral):
@@ -328,16 +337,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         #     raise ValueError("max_depth must be greater than zero. ")
         if not (0 < max_features <= self.n_features_in_):
             raise ValueError("max_features must be in (0, n_features]")
-        if not isinstance(max_leaf_nodes, numbers.Integral):
-            raise ValueError(
-                "max_leaf_nodes must be integral number but was %r" % max_leaf_nodes
-            )
-        if -1 < max_leaf_nodes < 2:
-            raise ValueError(
-                ("max_leaf_nodes {0} must be either None or larger than 1").format(
-                    max_leaf_nodes
-                )
-            )
 
         if sample_weight is not None:
             sample_weight = _check_sample_weight(sample_weight, X, DOUBLE)
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 8080ba5ffceb2..7efab0bbec04f 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -695,6 +695,12 @@ def test_error():
             "min_samples_split must be an instance of <class 'numbers.Real'>, not"
             " <class 'str'>.",
         ),
+        ({"max_leaf_nodes": 0}, ValueError, "max_leaf_nodes == 0, must be >= 2"),
+        (
+            {"max_leaf_nodes": 1.5},
+            TypeError,
+            "max_leaf_nodes must be an instance of <class 'numbers.Integral'>",
+        ),
         (
             {"min_impurity_decrease": -1.0},
             ValueError,

From a2c8c4b9a9fa2b5d830098e3dd87e43e6ae21aeb Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Thu, 16 Dec 2021 20:27:46 -0500
Subject: [PATCH 07/41] min_weight_fraction_leaf: add tests and validation

---
 sklearn/tree/_classes.py        | 12 ++++++++++--
 sklearn/tree/tests/test_tree.py | 11 +++++++----
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index a64698767b445..0642c26347bea 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -331,8 +331,16 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 "Number of labels=%d does not match number of samples=%d"
                 % (len(y), n_samples)
             )
-        if not 0 <= self.min_weight_fraction_leaf <= 0.5:
-            raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
+        # if not 0 <= self.min_weight_fraction_leaf <= 0.5:
+        #     raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
+        check_scalar(
+            self.min_weight_fraction_leaf,
+            "min_weight_fraction_leaf",
+            target_type=numbers.Real,
+            min_val=0,
+            max_val=1,
+            include_boundaries="left"
+        )
         # if max_depth <= 0:
         #     raise ValueError("max_depth must be greater than zero. ")
         if not (0 < max_features <= self.n_features_in_):
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 7efab0bbec04f..5cfe1bd586ba6 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -590,10 +590,10 @@ def test_error():
             TreeEstimator(min_samples_leaf=0.0).fit(X, y)
         with pytest.raises(ValueError):
             TreeEstimator(min_samples_leaf=3.0).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_weight_fraction_leaf=-1).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_weight_fraction_leaf=0.51).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_weight_fraction_leaf=-1).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(min_weight_fraction_leaf=0.51).fit(X, y)
         # with pytest.raises(ValueError):
         #     TreeEstimator(min_samples_split=-1).fit(X, y)
         # with pytest.raises(ValueError):
@@ -695,6 +695,9 @@ def test_error():
             "min_samples_split must be an instance of <class 'numbers.Real'>, not"
             " <class 'str'>.",
         ),
+        ({"min_weight_fraction_leaf": -1}, ValueError, "min_weight_fraction_leaf == -1, must be >= 0"),
+        ({"min_weight_fraction_leaf": 1.1}, ValueError, "min_weight_fraction_leaf == 1.1, must be < 1"),
+        ({"min_weight_fraction_leaf": "foo"}, TypeError, "min_weight_fraction_leaf must be an instance of <class 'numbers.Real'>"),
         ({"max_leaf_nodes": 0}, ValueError, "max_leaf_nodes == 0, must be >= 2"),
         (
             {"max_leaf_nodes": 1.5},

From 4100bbd8b5b00aec830e18ac648df7f7a6cacc6e Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Thu, 16 Dec 2021 20:29:29 -0500
Subject: [PATCH 08/41] format files w/ black

---
 sklearn/tree/_classes.py        |  2 +-
 sklearn/tree/tests/test_tree.py | 18 +++++++++++++++---
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 0642c26347bea..d056adbf76ba5 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -339,7 +339,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             target_type=numbers.Real,
             min_val=0,
             max_val=1,
-            include_boundaries="left"
+            include_boundaries="left",
         )
         # if max_depth <= 0:
         #     raise ValueError("max_depth must be greater than zero. ")
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 5cfe1bd586ba6..7ad1928fa6447 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -695,9 +695,21 @@ def test_error():
             "min_samples_split must be an instance of <class 'numbers.Real'>, not"
             " <class 'str'>.",
         ),
-        ({"min_weight_fraction_leaf": -1}, ValueError, "min_weight_fraction_leaf == -1, must be >= 0"),
-        ({"min_weight_fraction_leaf": 1.1}, ValueError, "min_weight_fraction_leaf == 1.1, must be < 1"),
-        ({"min_weight_fraction_leaf": "foo"}, TypeError, "min_weight_fraction_leaf must be an instance of <class 'numbers.Real'>"),
+        (
+            {"min_weight_fraction_leaf": -1},
+            ValueError,
+            "min_weight_fraction_leaf == -1, must be >= 0",
+        ),
+        (
+            {"min_weight_fraction_leaf": 1.1},
+            ValueError,
+            "min_weight_fraction_leaf == 1.1, must be < 1",
+        ),
+        (
+            {"min_weight_fraction_leaf": "foo"},
+            TypeError,
+            "min_weight_fraction_leaf must be an instance of <class 'numbers.Real'>",
+        ),
         ({"max_leaf_nodes": 0}, ValueError, "max_leaf_nodes == 0, must be >= 2"),
         (
             {"max_leaf_nodes": 1.5},

From ec647de9ee3cbadcf5144d5a44bdd7e1d167a482 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Fri, 17 Dec 2021 13:09:34 -0500
Subject: [PATCH 09/41] remove comments

---
 sklearn/tree/_classes.py | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index d056adbf76ba5..70061f0605449 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -262,13 +262,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             min_samples_leaf = int(ceil(self.min_samples_leaf * n_samples))
 
         if isinstance(self.min_samples_split, numbers.Integral):
-            # if not 2 <= self.min_samples_split:
-            #     raise ValueError(
-            #         "min_samples_split must be an integer "
-            #         "greater than 1 or a float in (0.0, 1.0]; "
-            #         "got the integer %s"
-            #         % self.min_samples_split
-            #     )
             check_scalar(
                 self.min_samples_split,
                 "min_samples_split",
@@ -278,13 +271,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             )
             min_samples_split = self.min_samples_split
         else:  # float, string, other
-            # if not 0.0 < self.min_samples_split <= 1.0:
-            #     raise ValueError(
-            #         "min_samples_split must be an integer "
-            #         "greater than 1 or a float in (0.0, 1.0]; "
-            #         "got the float %s"
-            #         % self.min_samples_split
-            #     )
             check_scalar(
                 self.min_samples_split,
                 "min_samples_split",
@@ -331,18 +317,15 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 "Number of labels=%d does not match number of samples=%d"
                 % (len(y), n_samples)
             )
-        # if not 0 <= self.min_weight_fraction_leaf <= 0.5:
-        #     raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
+
         check_scalar(
             self.min_weight_fraction_leaf,
             "min_weight_fraction_leaf",
             target_type=numbers.Real,
-            min_val=0,
-            max_val=1,
+            min_val=0.0,
+            max_val=1.0,
             include_boundaries="left",
         )
-        # if max_depth <= 0:
-        #     raise ValueError("max_depth must be greater than zero. ")
         if not (0 < max_features <= self.n_features_in_):
             raise ValueError("max_features must be in (0, n_features]")
 
@@ -361,15 +344,11 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         else:
             min_weight_leaf = self.min_weight_fraction_leaf * np.sum(sample_weight)
 
-        # if self.min_impurity_decrease < 0.0:
-        #     raise ValueError(
-        #         "min_impurity_decrease must be greater than or equal to 0"
-        #     )
         check_scalar(
             self.min_impurity_decrease,
             "min_impurity_decrease",
             target_type=numbers.Real,
-            min_val=0,
+            min_val=0.0,
             include_boundaries="left",
         )
         # Build tree

From 9bc65821fcea2e542b96d33b17106f24effb8d6e Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 04:56:01 -0500
Subject: [PATCH 10/41] min_samples_leaf: add tests and validation

---
 sklearn/tree/_classes.py        | 25 +++++++++++++++----------
 sklearn/tree/tests/test_tree.py | 13 +++++++++++++
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 70061f0605449..9a1fe58c31155 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -247,18 +247,23 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
 
         if isinstance(self.min_samples_leaf, numbers.Integral):
-            if not 1 <= self.min_samples_leaf:
-                raise ValueError(
-                    "min_samples_leaf must be at least 1 or in (0, 0.5], got %s"
-                    % self.min_samples_leaf
-                )
+            check_scalar(
+                self.min_samples_leaf,
+                "min_samples_leaf",
+                target_type=numbers.Integral,
+                min_val=1,
+                max_val=n_samples,
+            )
             min_samples_leaf = self.min_samples_leaf
         else:  # float
-            if not 0.0 < self.min_samples_leaf <= 0.5:
-                raise ValueError(
-                    "min_samples_leaf must be at least 1 or in (0, 0.5], got %s"
-                    % self.min_samples_leaf
-                )
+            check_scalar(
+                self.min_samples_leaf,
+                "min_samples_leaf",
+                target_type=numbers.Real,
+                min_val=0.0,
+                max_val=0.5,
+                include_boundaries="right",
+            )
             min_samples_leaf = int(ceil(self.min_samples_leaf * n_samples))
 
         if isinstance(self.min_samples_split, numbers.Integral):
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 7ad1928fa6447..993289dcdaf76 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -695,6 +695,19 @@ def test_error():
             "min_samples_split must be an instance of <class 'numbers.Real'>, not"
             " <class 'str'>.",
         ),
+        ({"min_samples_leaf": 0}, ValueError, "min_samples_leaf == 0, must be >= 1"),
+        ({"min_samples_leaf": 900}, ValueError, "min_samples_leaf == 900, must be <="),
+        ({"min_samples_leaf": 0.0}, ValueError, "min_samples_leaf == 0.0, must be > 0"),
+        (
+            {"min_samples_leaf": 0.6},
+            ValueError,
+            "min_samples_leaf == 0.6, must be <= 0.5",
+        ),
+        (
+            {"min_samples_leaf": "foo"},
+            TypeError,
+            "min_samples_leaf must be an instance of <class 'numbers.Real'>",
+        ),
         (
             {"min_weight_fraction_leaf": -1},
             ValueError,

From c850f6cc6a9c31225b8c388fa53c29d1d97f0a43 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 05:00:19 -0500
Subject: [PATCH 11/41] max_features: add tests and validation

---
 sklearn/tree/_classes.py        | 20 +++++++++++++++++---
 sklearn/tree/tests/test_tree.py | 30 +++++++-----------------------
 2 files changed, 24 insertions(+), 26 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 9a1fe58c31155..acb508159e734 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -14,6 +14,7 @@
 #
 # License: BSD 3 clause
 
+from io import IncrementalNewlineDecoder
 import numbers
 import warnings
 import copy
@@ -308,8 +309,24 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         elif self.max_features is None:
             max_features = self.n_features_in_
         elif isinstance(self.max_features, numbers.Integral):
+            check_scalar(
+                self.max_features,
+                "max_features",
+                target_type=numbers.Integral,
+                min_val=0,
+                max_val=self.n_features_in_,
+                include_boundaries="right",
+            )
             max_features = self.max_features
         else:  # float
+            check_scalar(
+                self.max_features,
+                "max_features",
+                target_type=numbers.Real,
+                min_val=0.0,
+                max_val=1.0,
+                include_boundaries="right",
+            )
             if self.max_features > 0.0:
                 max_features = max(1, int(self.max_features * self.n_features_in_))
             else:
@@ -331,9 +348,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             max_val=1.0,
             include_boundaries="left",
         )
-        if not (0 < max_features <= self.n_features_in_):
-            raise ValueError("max_features must be in (0, n_features]")
-
         if sample_weight is not None:
             sample_weight = _check_sample_weight(sample_weight, X, DOUBLE)
 
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 993289dcdaf76..d8271f79af488 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -546,27 +546,6 @@ def test_max_features():
         est.fit(iris.data, iris.target)
         assert est.max_features_ == iris.data.shape[1]
 
-        # use values of max_features that are invalid
-        est = TreeEstimator(max_features=10)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
-        est = TreeEstimator(max_features=-1)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
-        est = TreeEstimator(max_features=0.0)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
-        est = TreeEstimator(max_features=1.5)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
-        est = TreeEstimator(max_features="foobar")
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
 
 def test_error():
     # Test that it gives proper exception on deficient input.
@@ -604,8 +583,8 @@ def test_error():
         #     TreeEstimator(min_samples_split=2.5).fit(X, y)
         # with pytest.raises(ValueError):
         #     TreeEstimator(max_depth=-1).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(max_features=42).fit(X, y)
+        # with pytest.raises(ValueError):
+        #     TreeEstimator(max_features=42).fit(X, y)
         # with pytest.raises(ValueError):
         #     TreeEstimator(min_impurity_decrease=-1.0).fit(X, y)
 
@@ -723,6 +702,11 @@ def test_error():
             TypeError,
             "min_weight_fraction_leaf must be an instance of <class 'numbers.Real'>",
         ),
+        ({"max_features": 0}, ValueError, "max_features == 0, must be > 0"),
+        ({"max_features": 1_000}, ValueError, "max_features == 1000, must be <="),
+        ({"max_features": 0.0}, ValueError, "max_features == 0.0, must be > 0.0"),
+        ({"max_features": 1.1}, ValueError, "max_features == 1.1, must be <= 1.0"),
+        ({"max_features": "foobar"}, ValueError, "Invalid value for max_features."),
         ({"max_leaf_nodes": 0}, ValueError, "max_leaf_nodes == 0, must be >= 2"),
         (
             {"max_leaf_nodes": 1.5},

From 4fe47d0c451a61bf78e9490ddf6006d0eb7ffed6 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 05:08:28 -0500
Subject: [PATCH 12/41] min_samples_split: update

---
 sklearn/tree/_classes.py        |  2 +-
 sklearn/tree/tests/test_tree.py | 13 +++----------
 2 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index acb508159e734..4446f6d695adc 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -282,7 +282,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 "min_samples_split",
                 target_type=numbers.Real,
                 min_val=0.0,
-                max_val=1.0,
+                max_val=0.5,
                 include_boundaries="right",
             )
             min_samples_split = int(ceil(self.min_samples_split * n_samples))
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index d8271f79af488..a541557903406 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -651,7 +651,6 @@ def test_error():
             TypeError,
             "max_depth must be an instance of <class 'numbers.Integral'>, not",
         ),
-        ({"min_samples_split": -1}, ValueError, "min_samples_split == -1, must be > 1"),
         ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be > 1"),
         (
             {"min_samples_split": 0.0},
@@ -659,20 +658,14 @@ def test_error():
             "min_samples_split == 0.0, must be > 0.0",
         ),
         (
-            {"min_samples_split": 1.1},
+            {"min_samples_split": 0.6},
             ValueError,
-            "min_samples_split == 1.1, must be <= 1.0",
-        ),
-        (
-            {"min_samples_split": 2.5},
-            ValueError,
-            "min_samples_split == 2.5, must be <= 1.0",
+            "min_samples_split == 0.6, must be <= 0.5",
         ),
         (
             {"min_samples_split": "foo"},
             TypeError,
-            "min_samples_split must be an instance of <class 'numbers.Real'>, not"
-            " <class 'str'>.",
+            "min_samples_split must be an instance of <class 'numbers.Real'>",
         ),
         ({"min_samples_leaf": 0}, ValueError, "min_samples_leaf == 0, must be >= 1"),
         ({"min_samples_leaf": 900}, ValueError, "min_samples_leaf == 900, must be <="),

From 44c5afc38e5cb91eafb15bae9fc94adbd244dd91 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 05:13:38 -0500
Subject: [PATCH 13/41] max_leaf_nodes: remove redundant tests

---
 sklearn/tree/tests/test_tree.py | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a541557903406..b97cce2698e1b 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -1329,17 +1329,6 @@ def test_max_leaf_nodes():
         est = TreeEstimator(max_depth=None, max_leaf_nodes=k + 1).fit(X, y)
         assert est.get_n_leaves() == k + 1
 
-        # max_leaf_nodes in (0, 1) should raise ValueError
-        est = TreeEstimator(max_depth=None, max_leaf_nodes=0)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-        est = TreeEstimator(max_depth=None, max_leaf_nodes=1)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-        est = TreeEstimator(max_depth=None, max_leaf_nodes=0.1)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
 
 def test_max_leaf_nodes_max_depth():
     # Test precedence of max_leaf_nodes over max_depth.

From 12eb88acddc9efe3adfd2e7754f32ab38226f087 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 05:13:38 -0500
Subject: [PATCH 14/41] remove redundant tests

---
 sklearn/tree/tests/test_tree.py | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a541557903406..b97cce2698e1b 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -1329,17 +1329,6 @@ def test_max_leaf_nodes():
         est = TreeEstimator(max_depth=None, max_leaf_nodes=k + 1).fit(X, y)
         assert est.get_n_leaves() == k + 1
 
-        # max_leaf_nodes in (0, 1) should raise ValueError
-        est = TreeEstimator(max_depth=None, max_leaf_nodes=0)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-        est = TreeEstimator(max_depth=None, max_leaf_nodes=1)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-        est = TreeEstimator(max_depth=None, max_leaf_nodes=0.1)
-        with pytest.raises(ValueError):
-            est.fit(X, y)
-
 
 def test_max_leaf_nodes_max_depth():
     # Test precedence of max_leaf_nodes over max_depth.

From 60a215f76f72163bfb916f7b0ec0a095c8ea8e7a Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 05:30:01 -0500
Subject: [PATCH 15/41] Fix lint issue

---
 sklearn/tree/_classes.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 4446f6d695adc..abce2789823c9 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -14,7 +14,6 @@
 #
 # License: BSD 3 clause
 
-from io import IncrementalNewlineDecoder
 import numbers
 import warnings
 import copy

From e845597267a6aab5223731a4f942f688406623ed Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 28 Dec 2021 05:58:10 -0500
Subject: [PATCH 16/41] update range for min_weight_fraction_leaf

---
 sklearn/tree/_classes.py        | 3 +--
 sklearn/tree/tests/test_tree.py | 4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index abce2789823c9..46065b92863d4 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -344,8 +344,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             "min_weight_fraction_leaf",
             target_type=numbers.Real,
             min_val=0.0,
-            max_val=1.0,
-            include_boundaries="left",
+            max_val=0.5,
         )
         if sample_weight is not None:
             sample_weight = _check_sample_weight(sample_weight, X, DOUBLE)
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index b97cce2698e1b..67a15b2531045 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -686,9 +686,9 @@ def test_error():
             "min_weight_fraction_leaf == -1, must be >= 0",
         ),
         (
-            {"min_weight_fraction_leaf": 1.1},
+            {"min_weight_fraction_leaf": 0.6},
             ValueError,
-            "min_weight_fraction_leaf == 1.1, must be < 1",
+            "min_weight_fraction_leaf == 0.6, must be <= 0.5",
         ),
         (
             {"min_weight_fraction_leaf": "foo"},

From 6eb026c43e5a625eaaa1466d310fec95f2f9150b Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 19:09:18 -0500
Subject: [PATCH 17/41] remove redundant tests

---
 sklearn/tree/tests/test_tree.py | 30 +-----------------------------
 1 file changed, 1 insertion(+), 29 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 67a15b2531045..dd22c4976f72d 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -560,34 +560,6 @@ def test_error():
         with pytest.raises(ValueError):
             est.predict_proba(X2)
 
-    for name, TreeEstimator in ALL_TREES.items():
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_leaf=-1).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_leaf=0.6).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_leaf=0.0).fit(X, y)
-        with pytest.raises(ValueError):
-            TreeEstimator(min_samples_leaf=3.0).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_weight_fraction_leaf=-1).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_weight_fraction_leaf=0.51).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_samples_split=-1).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_samples_split=0.0).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_samples_split=1.1).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_samples_split=2.5).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(max_depth=-1).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(max_features=42).fit(X, y)
-        # with pytest.raises(ValueError):
-        #     TreeEstimator(min_impurity_decrease=-1.0).fit(X, y)
-
         # Wrong dimensions
         est = TreeEstimator()
         y2 = y[:-1]
@@ -649,7 +621,7 @@ def test_error():
         (
             {"max_depth": 1.1},
             TypeError,
-            "max_depth must be an instance of <class 'numbers.Integral'>, not",
+            "max_depth must be an instance of <class 'numbers.Integral'>",
         ),
         ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be > 1"),
         (

From b9a5091766bec1bd358799d7e9f128f276101387 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 19:29:30 -0500
Subject: [PATCH 18/41] min_samples_split: update to include upper bound

---
 sklearn/tree/_classes.py        | 4 ++--
 sklearn/tree/tests/test_tree.py | 7 ++++++-
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 46065b92863d4..e332e2a73255e 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -271,8 +271,8 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 self.min_samples_split,
                 "min_samples_split",
                 target_type=numbers.Integral,
-                min_val=1,
-                include_boundaries="neither",
+                min_val=2,
+                max_val=n_samples,
             )
             min_samples_split = self.min_samples_split
         else:  # float, string, other
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index dd22c4976f72d..57a84692a3615 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -623,7 +623,12 @@ def test_error():
             TypeError,
             "max_depth must be an instance of <class 'numbers.Integral'>",
         ),
-        ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be > 1"),
+        ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be >= 2"),
+        (
+            {"min_samples_split": 900},
+            ValueError,
+            "min_samples_split == 900, must be <=",
+        ),
         (
             {"min_samples_split": 0.0},
             ValueError,

From eb8bacb453559900b7458a0b268db5beec6fd729 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 19:34:27 -0500
Subject: [PATCH 19/41] slight style edit to tests

---
 sklearn/tree/tests/test_tree.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 57a84692a3615..a9d7e11e4566b 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -660,7 +660,7 @@ def test_error():
         (
             {"min_weight_fraction_leaf": -1},
             ValueError,
-            "min_weight_fraction_leaf == -1, must be >= 0",
+            "min_weight_fraction_leaf == -1, must be >= 0.0",
         ),
         (
             {"min_weight_fraction_leaf": 0.6},
@@ -673,7 +673,7 @@ def test_error():
             "min_weight_fraction_leaf must be an instance of <class 'numbers.Real'>",
         ),
         ({"max_features": 0}, ValueError, "max_features == 0, must be > 0"),
-        ({"max_features": 1_000}, ValueError, "max_features == 1000, must be <="),
+        ({"max_features": 1000}, ValueError, "max_features == 1000, must be <="),
         ({"max_features": 0.0}, ValueError, "max_features == 0.0, must be > 0.0"),
         ({"max_features": 1.1}, ValueError, "max_features == 1.1, must be <= 1.0"),
         ({"max_features": "foobar"}, ValueError, "Invalid value for max_features."),
@@ -684,9 +684,9 @@ def test_error():
             "max_leaf_nodes must be an instance of <class 'numbers.Integral'>",
         ),
         (
-            {"min_impurity_decrease": -1.0},
+            {"min_impurity_decrease": -1},
             ValueError,
-            "min_impurity_decrease == -1.0, must be >= 0",
+            "min_impurity_decrease == -1, must be >= 0.0",
         ),
         (
             {"min_impurity_decrease": "foo"},

From 1060fd74f862612fc246ec065f95b4dfbeaf8532 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 20:40:09 -0500
Subject: [PATCH 20/41] update boundary inclusivity for max_features

---
 sklearn/tree/_classes.py        | 3 +--
 sklearn/tree/tests/test_tree.py | 2 +-
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index e332e2a73255e..a7c1d822c916f 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -312,9 +312,8 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 self.max_features,
                 "max_features",
                 target_type=numbers.Integral,
-                min_val=0,
+                min_val=1,
                 max_val=self.n_features_in_,
-                include_boundaries="right",
             )
             max_features = self.max_features
         else:  # float
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a9d7e11e4566b..af76d23557c56 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -672,7 +672,7 @@ def test_error():
             TypeError,
             "min_weight_fraction_leaf must be an instance of <class 'numbers.Real'>",
         ),
-        ({"max_features": 0}, ValueError, "max_features == 0, must be > 0"),
+        ({"max_features": 0}, ValueError, "max_features == 0, must be >= 1"),
         ({"max_features": 1000}, ValueError, "max_features == 1000, must be <="),
         ({"max_features": 0.0}, ValueError, "max_features == 0.0, must be > 0.0"),
         ({"max_features": 1.1}, ValueError, "max_features == 1.1, must be <= 1.0"),

From f5973f842810f3b560b22490a4498511154c82f2 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 20:50:18 -0500
Subject: [PATCH 21/41] update order of tests

---
 sklearn/tree/tests/test_tree.py | 118 ++++++++++++++++----------------
 1 file changed, 59 insertions(+), 59 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index af76d23557c56..5e466cd06381d 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -501,52 +501,6 @@ def test_importances_gini_equal_squared_error():
     assert_array_equal(clf.tree_.n_node_samples, reg.tree_.n_node_samples)
 
 
-def test_max_features():
-    # Check max_features.
-    for name, TreeRegressor in REG_TREES.items():
-        reg = TreeRegressor(max_features="auto")
-        reg.fit(diabetes.data, diabetes.target)
-        assert reg.max_features_ == diabetes.data.shape[1]
-
-    for name, TreeClassifier in CLF_TREES.items():
-        clf = TreeClassifier(max_features="auto")
-        clf.fit(iris.data, iris.target)
-        assert clf.max_features_ == 2
-
-    for name, TreeEstimator in ALL_TREES.items():
-        est = TreeEstimator(max_features="sqrt")
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == int(np.sqrt(iris.data.shape[1]))
-
-        est = TreeEstimator(max_features="log2")
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == int(np.log2(iris.data.shape[1]))
-
-        est = TreeEstimator(max_features=1)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == 1
-
-        est = TreeEstimator(max_features=3)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == 3
-
-        est = TreeEstimator(max_features=0.01)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == 1
-
-        est = TreeEstimator(max_features=0.5)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == int(0.5 * iris.data.shape[1])
-
-        est = TreeEstimator(max_features=1.0)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == iris.data.shape[1]
-
-        est = TreeEstimator(max_features=None)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == iris.data.shape[1]
-
-
 def test_error():
     # Test that it gives proper exception on deficient input.
     for name, TreeEstimator in CLF_TREES.items():
@@ -623,6 +577,19 @@ def test_error():
             TypeError,
             "max_depth must be an instance of <class 'numbers.Integral'>",
         ),
+        ({"min_samples_leaf": 0}, ValueError, "min_samples_leaf == 0, must be >= 1"),
+        ({"min_samples_leaf": 900}, ValueError, "min_samples_leaf == 900, must be <="),
+        ({"min_samples_leaf": 0.0}, ValueError, "min_samples_leaf == 0.0, must be > 0"),
+        (
+            {"min_samples_leaf": 0.6},
+            ValueError,
+            "min_samples_leaf == 0.6, must be <= 0.5",
+        ),
+        (
+            {"min_samples_leaf": "foo"},
+            TypeError,
+            "min_samples_leaf must be an instance of <class 'numbers.Real'>",
+        ),
         ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be >= 2"),
         (
             {"min_samples_split": 900},
@@ -644,19 +611,6 @@ def test_error():
             TypeError,
             "min_samples_split must be an instance of <class 'numbers.Real'>",
         ),
-        ({"min_samples_leaf": 0}, ValueError, "min_samples_leaf == 0, must be >= 1"),
-        ({"min_samples_leaf": 900}, ValueError, "min_samples_leaf == 900, must be <="),
-        ({"min_samples_leaf": 0.0}, ValueError, "min_samples_leaf == 0.0, must be > 0"),
-        (
-            {"min_samples_leaf": 0.6},
-            ValueError,
-            "min_samples_leaf == 0.6, must be <= 0.5",
-        ),
-        (
-            {"min_samples_leaf": "foo"},
-            TypeError,
-            "min_samples_leaf must be an instance of <class 'numbers.Real'>",
-        ),
         (
             {"min_weight_fraction_leaf": -1},
             ValueError,
@@ -708,6 +662,52 @@ def test_tree_params_validation(name, Tree, params, err_type, err_msg):
         est.fit(X, y)
 
 
+def test_max_features():
+    # Check max_features.
+    for name, TreeRegressor in REG_TREES.items():
+        reg = TreeRegressor(max_features="auto")
+        reg.fit(diabetes.data, diabetes.target)
+        assert reg.max_features_ == diabetes.data.shape[1]
+
+    for name, TreeClassifier in CLF_TREES.items():
+        clf = TreeClassifier(max_features="auto")
+        clf.fit(iris.data, iris.target)
+        assert clf.max_features_ == 2
+
+    for name, TreeEstimator in ALL_TREES.items():
+        est = TreeEstimator(max_features="sqrt")
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == int(np.sqrt(iris.data.shape[1]))
+
+        est = TreeEstimator(max_features="log2")
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == int(np.log2(iris.data.shape[1]))
+
+        est = TreeEstimator(max_features=1)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == 1
+
+        est = TreeEstimator(max_features=3)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == 3
+
+        est = TreeEstimator(max_features=0.01)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == 1
+
+        est = TreeEstimator(max_features=0.5)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == int(0.5 * iris.data.shape[1])
+
+        est = TreeEstimator(max_features=1.0)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == iris.data.shape[1]
+
+        est = TreeEstimator(max_features=None)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == iris.data.shape[1]
+
+
 def test_min_samples_split():
     """Test min_samples_split parameter"""
     X = np.asfortranarray(iris.data, dtype=tree._tree.DTYPE)

From 5c5769bf0badf38a06fb7bcc65c852d16a153670 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 21:09:42 -0500
Subject: [PATCH 22/41] update order of validations to match signature more
 closely

---
 sklearn/tree/_classes.py | 50 +++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 24 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index a7c1d822c916f..a96967a302e7b 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -236,16 +236,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             )
         max_depth = np.iinfo(np.int32).max if self.max_depth is None else self.max_depth
 
-        if self.max_leaf_nodes is not None:
-            check_scalar(
-                self.max_leaf_nodes,
-                "max_leaf_nodes",
-                target_type=numbers.Integral,
-                min_val=2,
-                include_boundaries="left",
-            )
-        max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
-
         if isinstance(self.min_samples_leaf, numbers.Integral):
             check_scalar(
                 self.min_samples_leaf,
@@ -289,6 +279,14 @@ def fit(self, X, y, sample_weight=None, check_input=True):
 
         min_samples_split = max(min_samples_split, 2 * min_samples_leaf)
 
+        check_scalar(
+            self.min_weight_fraction_leaf,
+            "min_weight_fraction_leaf",
+            target_type=numbers.Real,
+            min_val=0.0,
+            max_val=0.5,
+        )
+
         if isinstance(self.max_features, str):
             if self.max_features == "auto":
                 if is_classification:
@@ -332,19 +330,30 @@ def fit(self, X, y, sample_weight=None, check_input=True):
 
         self.max_features_ = max_features
 
-        if len(y) != n_samples:
-            raise ValueError(
-                "Number of labels=%d does not match number of samples=%d"
-                % (len(y), n_samples)
+        if self.max_leaf_nodes is not None:
+            check_scalar(
+                self.max_leaf_nodes,
+                "max_leaf_nodes",
+                target_type=numbers.Integral,
+                min_val=2,
+                include_boundaries="left",
             )
+        max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
 
         check_scalar(
-            self.min_weight_fraction_leaf,
-            "min_weight_fraction_leaf",
+            self.min_impurity_decrease,
+            "min_impurity_decrease",
             target_type=numbers.Real,
             min_val=0.0,
-            max_val=0.5,
+            include_boundaries="left",
         )
+
+        if len(y) != n_samples:
+            raise ValueError(
+                "Number of labels=%d does not match number of samples=%d"
+                % (len(y), n_samples)
+            )
+
         if sample_weight is not None:
             sample_weight = _check_sample_weight(sample_weight, X, DOUBLE)
 
@@ -360,13 +369,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         else:
             min_weight_leaf = self.min_weight_fraction_leaf * np.sum(sample_weight)
 
-        check_scalar(
-            self.min_impurity_decrease,
-            "min_impurity_decrease",
-            target_type=numbers.Real,
-            min_val=0.0,
-            include_boundaries="left",
-        )
         # Build tree
         criterion = self.criterion
         if not isinstance(criterion, Criterion):

From 2e4528d96141bb7de0189f7d5e867c585eb29e0a Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 29 Dec 2021 22:45:02 -0500
Subject: [PATCH 23/41] remove some boundary args to rely on defaults more and
 reduce lines

---
 sklearn/tree/_classes.py        | 5 +----
 sklearn/tree/tests/test_tree.py | 2 +-
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index a96967a302e7b..03a9cea4c64ef 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -231,8 +231,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 self.max_depth,
                 "max_depth",
                 target_type=numbers.Integral,
-                min_val=0,
-                include_boundaries="neither",
+                min_val=1,
             )
         max_depth = np.iinfo(np.int32).max if self.max_depth is None else self.max_depth
 
@@ -336,7 +335,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 "max_leaf_nodes",
                 target_type=numbers.Integral,
                 min_val=2,
-                include_boundaries="left",
             )
         max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
 
@@ -345,7 +343,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
             "min_impurity_decrease",
             target_type=numbers.Real,
             min_val=0.0,
-            include_boundaries="left",
         )
 
         if len(y) != n_samples:
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 5e466cd06381d..a83f33a7063e0 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -571,7 +571,7 @@ def test_error():
 @pytest.mark.parametrize(
     "params, err_type, err_msg",
     [
-        ({"max_depth": -1}, ValueError, "max_depth == -1, must be > 0"),
+        ({"max_depth": -1}, ValueError, "max_depth == -1, must be >= 1"),
         (
             {"max_depth": 1.1},
             TypeError,

From dfb4b87a8ce5876cae72994c1649cfdc0943fe2b Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Mon, 3 Jan 2022 23:31:13 -0500
Subject: [PATCH 24/41] ccp_alpha: add tests and validation

---
 sklearn/tree/_classes.py        | 10 +++++++---
 sklearn/tree/tests/test_tree.py |  8 +++++++-
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 03a9cea4c64ef..950f7abdf277b 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -152,8 +152,12 @@ def fit(self, X, y, sample_weight=None, check_input=True):
 
         random_state = check_random_state(self.random_state)
 
-        if self.ccp_alpha < 0.0:
-            raise ValueError("ccp_alpha must be greater than or equal to 0")
+        check_scalar(
+            self.ccp_alpha,
+            "ccp_alpha",
+            target_type=numbers.Real,
+            min_val=0.0,
+        )
 
         if check_input:
             # Need to validate separately here.
@@ -570,7 +574,7 @@ def _prune_tree(self):
         check_is_fitted(self)
 
         if self.ccp_alpha < 0.0:
-            raise ValueError("ccp_alpha must be greater than or equal to 0")
+            raise ValueError("must be >= 0.0.")
 
         if self.ccp_alpha == 0.0:
             return
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a83f33a7063e0..ed7cdfb4dfa78 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -647,6 +647,12 @@ def test_error():
             TypeError,
             "min_impurity_decrease must be an instance of <class 'numbers.Real'>",
         ),
+        ({"ccp_alpha": -1.0}, ValueError, "ccp_alpha == -1.0, must be >= 0.0"),
+        (
+            {"ccp_alpha": "foo"},
+            TypeError,
+            "ccp_alpha must be an instance of <class 'numbers.Real'>",
+        ),
     ],
 )
 def test_tree_params_validation(name, Tree, params, err_type, err_msg):
@@ -2019,7 +2025,7 @@ def assert_is_subtree(tree, subtree):
 
 def test_prune_tree_raises_negative_ccp_alpha():
     clf = DecisionTreeClassifier()
-    msg = "ccp_alpha must be greater than or equal to 0"
+    msg = "must be >= 0.0."
 
     with pytest.raises(ValueError, match=msg):
         clf.set_params(ccp_alpha=-1.0)

From fa7a486b7c34abfdf6c8d37388636eca084d0c41 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Mon, 3 Jan 2022 23:45:01 -0500
Subject: [PATCH 25/41] edit comment

---
 sklearn/tree/_classes.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 950f7abdf277b..ade6e8ec78ffe 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -268,7 +268,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 max_val=n_samples,
             )
             min_samples_split = self.min_samples_split
-        else:  # float, string, other
+        else:  # float
             check_scalar(
                 self.min_samples_split,
                 "min_samples_split",

From 42676787bcdaba12c7a96fa3456d8234b695d589 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 4 Jan 2022 10:22:56 -0500
Subject: [PATCH 26/41] Update sklearn/tree/_classes.py

Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
---
 sklearn/tree/_classes.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index ade6e8ec78ffe..2885cd2f56bb5 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -274,7 +274,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 "min_samples_split",
                 target_type=numbers.Real,
                 min_val=0.0,
-                max_val=0.5,
+                max_val=1.0,
                 include_boundaries="right",
             )
             min_samples_split = int(ceil(self.min_samples_split * n_samples))

From 9d1bed6f795c08599f479d24580f9444392e6ba7 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 4 Jan 2022 12:14:02 -0500
Subject: [PATCH 27/41] min_samples_split: update tests

---
 sklearn/tree/tests/test_tree.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index ed7cdfb4dfa78..6ebd806ff01e1 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -602,9 +602,9 @@ def test_error():
             "min_samples_split == 0.0, must be > 0.0",
         ),
         (
-            {"min_samples_split": 0.6},
+            {"min_samples_split": 1.1},
             ValueError,
-            "min_samples_split == 0.6, must be <= 0.5",
+            "min_samples_split == 1.1, must be <= 1.0",
         ),
         (
             {"min_samples_split": "foo"},

From 63a5a937bee290b4aaef9603aa30adf91080f126 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 4 Jan 2022 12:30:58 -0500
Subject: [PATCH 28/41] ccp_alpha: remove redundant tests

---
 sklearn/tree/_classes.py        |  3 ---
 sklearn/tree/tests/test_tree.py | 16 ----------------
 2 files changed, 19 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 2885cd2f56bb5..f3304dcc804e5 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -573,9 +573,6 @@ def _prune_tree(self):
         """Prune tree using Minimal Cost-Complexity Pruning."""
         check_is_fitted(self)
 
-        if self.ccp_alpha < 0.0:
-            raise ValueError("must be >= 0.0.")
-
         if self.ccp_alpha == 0.0:
             return
 
diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 6ebd806ff01e1..e43dc65ce8a8b 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -2023,22 +2023,6 @@ def assert_is_subtree(tree, subtree):
             )
 
 
-def test_prune_tree_raises_negative_ccp_alpha():
-    clf = DecisionTreeClassifier()
-    msg = "must be >= 0.0."
-
-    with pytest.raises(ValueError, match=msg):
-        clf.set_params(ccp_alpha=-1.0)
-        clf.fit(X, y)
-
-    clf.set_params(ccp_alpha=0.0)
-    clf.fit(X, y)
-
-    with pytest.raises(ValueError, match=msg):
-        clf.set_params(ccp_alpha=-1.0)
-        clf._prune_tree()
-
-
 def check_apply_path_readonly(name):
     X_readonly = create_memmap_backed_data(X_small.astype(tree._tree.DTYPE, copy=False))
     y_readonly = create_memmap_backed_data(np.array(y_small, dtype=tree._tree.DTYPE))

From 5cf4fa3736cba6b9e502a60a694598ee69670cd9 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Fri, 7 Jan 2022 21:20:16 -0500
Subject: [PATCH 29/41] update check scalar calls to explicitly reference
 "name" param

---
 sklearn/tree/_classes.py | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index f3304dcc804e5..08a427394080e 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -154,7 +154,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
 
         check_scalar(
             self.ccp_alpha,
-            "ccp_alpha",
+            name="ccp_alpha",
             target_type=numbers.Real,
             min_val=0.0,
         )
@@ -233,7 +233,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         if self.max_depth is not None:
             check_scalar(
                 self.max_depth,
-                "max_depth",
+                name="max_depth",
                 target_type=numbers.Integral,
                 min_val=1,
             )
@@ -242,7 +242,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         if isinstance(self.min_samples_leaf, numbers.Integral):
             check_scalar(
                 self.min_samples_leaf,
-                "min_samples_leaf",
+                name="min_samples_leaf",
                 target_type=numbers.Integral,
                 min_val=1,
                 max_val=n_samples,
@@ -251,7 +251,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         else:  # float
             check_scalar(
                 self.min_samples_leaf,
-                "min_samples_leaf",
+                name="min_samples_leaf",
                 target_type=numbers.Real,
                 min_val=0.0,
                 max_val=0.5,
@@ -262,7 +262,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         if isinstance(self.min_samples_split, numbers.Integral):
             check_scalar(
                 self.min_samples_split,
-                "min_samples_split",
+                name="min_samples_split",
                 target_type=numbers.Integral,
                 min_val=2,
                 max_val=n_samples,
@@ -271,7 +271,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         else:  # float
             check_scalar(
                 self.min_samples_split,
-                "min_samples_split",
+                name="min_samples_split",
                 target_type=numbers.Real,
                 min_val=0.0,
                 max_val=1.0,
@@ -284,7 +284,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
 
         check_scalar(
             self.min_weight_fraction_leaf,
-            "min_weight_fraction_leaf",
+            name="min_weight_fraction_leaf",
             target_type=numbers.Real,
             min_val=0.0,
             max_val=0.5,
@@ -311,7 +311,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         elif isinstance(self.max_features, numbers.Integral):
             check_scalar(
                 self.max_features,
-                "max_features",
+                name="max_features",
                 target_type=numbers.Integral,
                 min_val=1,
                 max_val=self.n_features_in_,
@@ -320,7 +320,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         else:  # float
             check_scalar(
                 self.max_features,
-                "max_features",
+                name="max_features",
                 target_type=numbers.Real,
                 min_val=0.0,
                 max_val=1.0,
@@ -336,7 +336,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
         if self.max_leaf_nodes is not None:
             check_scalar(
                 self.max_leaf_nodes,
-                "max_leaf_nodes",
+                name="max_leaf_nodes",
                 target_type=numbers.Integral,
                 min_val=2,
             )
@@ -344,7 +344,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
 
         check_scalar(
             self.min_impurity_decrease,
-            "min_impurity_decrease",
+            name="min_impurity_decrease",
             target_type=numbers.Real,
             min_val=0.0,
         )

From 0b895876a834860d30c34206cdc447c71a704579 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Mon, 10 Jan 2022 23:32:01 -0500
Subject: [PATCH 30/41] Update sklearn/tree/_classes.py

Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
---
 sklearn/tree/_classes.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 08a427394080e..d39d42272d554 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -264,8 +264,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 self.min_samples_split,
                 name="min_samples_split",
                 target_type=numbers.Integral,
-                min_val=2,
-                max_val=n_samples,
+                min_val=1,
             )
             min_samples_split = self.min_samples_split
         else:  # float

From a61e73c7d70bff77c1af477f8a6e594462247ddc Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 11 Jan 2022 18:24:28 -0500
Subject: [PATCH 31/41] update tests for min_samples_split

---
 sklearn/tree/tests/test_tree.py | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index e43dc65ce8a8b..a443e249a249d 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -590,12 +590,7 @@ def test_error():
             TypeError,
             "min_samples_leaf must be an instance of <class 'numbers.Real'>",
         ),
-        ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be >= 2"),
-        (
-            {"min_samples_split": 900},
-            ValueError,
-            "min_samples_split == 900, must be <=",
-        ),
+        ({"min_samples_split": 0}, ValueError, "min_samples_split == 0, must be >= 1"),
         (
             {"min_samples_split": 0.0},
             ValueError,

From 51e098040871e33626d60dd2f2fbdcb40cae8bf7 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Tue, 11 Jan 2022 22:50:01 -0500
Subject: [PATCH 32/41] update messages in test_gbdt_parameter_checks to pass
 CI

---
 .../ensemble/tests/test_gradient_boosting.py  | 84 +++++++++++++------
 1 file changed, 58 insertions(+), 26 deletions(-)

diff --git a/sklearn/ensemble/tests/test_gradient_boosting.py b/sklearn/ensemble/tests/test_gradient_boosting.py
index c2045aa35d652..df1dddf942f12 100644
--- a/sklearn/ensemble/tests/test_gradient_boosting.py
+++ b/sklearn/ensemble/tests/test_gradient_boosting.py
@@ -79,31 +79,63 @@ def test_classification_toy(loss):
 
 
 @pytest.mark.parametrize(
-    "params, err_msg",
+    "params, err_type, err_msg",
     [
-        ({"n_estimators": 0}, "n_estimators must be greater than 0"),
-        ({"n_estimators": -1}, "n_estimators must be greater than 0"),
-        ({"learning_rate": 0}, "learning_rate must be greater than 0"),
-        ({"learning_rate": -1.0}, "learning_rate must be greater than 0"),
-        ({"loss": "foobar"}, "Loss 'foobar' not supported"),
-        ({"min_samples_split": 0.0}, "min_samples_split must be an integer"),
-        ({"min_samples_split": -1.0}, "min_samples_split must be an integer"),
-        ({"min_samples_split": 1.1}, "min_samples_split must be an integer"),
-        ({"min_samples_leaf": 0}, "min_samples_leaf must be at least 1 or"),
-        ({"min_samples_leaf": -1.0}, "min_samples_leaf must be at least 1 or"),
-        ({"min_weight_fraction_leaf": -1.0}, "min_weight_fraction_leaf must in"),
-        ({"min_weight_fraction_leaf": 0.6}, "min_weight_fraction_leaf must in"),
-        ({"subsample": 0.0}, r"subsample must be in \(0,1\]"),
-        ({"subsample": 1.1}, r"subsample must be in \(0,1\]"),
-        ({"subsample": -0.1}, r"subsample must be in \(0,1\]"),
-        ({"max_depth": -0.1}, "max_depth must be greater than zero"),
-        ({"max_depth": 0}, "max_depth must be greater than zero"),
-        ({"init": {}}, "The init parameter must be an estimator or 'zero'"),
-        ({"max_features": "invalid"}, "Invalid value for max_features:"),
-        ({"max_features": 0}, r"max_features must be in \(0, n_features\]"),
-        ({"max_features": 100}, r"max_features must be in \(0, n_features\]"),
-        ({"max_features": -0.1}, r"max_features must be in \(0, n_features\]"),
-        ({"n_iter_no_change": "invalid"}, "n_iter_no_change should either be"),
+        ({"n_estimators": 0}, ValueError, "n_estimators must be greater than 0"),
+        ({"n_estimators": -1}, ValueError, "n_estimators must be greater than 0"),
+        ({"learning_rate": 0}, ValueError, "learning_rate must be greater than 0"),
+        ({"learning_rate": -1.0}, ValueError, "learning_rate must be greater than 0"),
+        ({"loss": "foobar"}, ValueError, "Loss 'foobar' not supported"),
+        (
+            {"min_samples_split": 0.0},
+            ValueError,
+            "min_samples_split == 0.0, must be > 0.0",
+        ),
+        (
+            {"min_samples_split": -1.0},
+            ValueError,
+            "min_samples_split == -1.0, must be > 0.0",
+        ),
+        (
+            {"min_samples_split": 1.1},
+            ValueError,
+            "min_samples_split == 1.1, must be <= 1.0.",
+        ),
+        ({"min_samples_leaf": 0}, ValueError, "min_samples_leaf == 0, must be >= 1"),
+        (
+            {"min_samples_leaf": -1.0},
+            ValueError,
+            "min_samples_leaf == -1.0, must be > 0.0.",
+        ),
+        (
+            {"min_weight_fraction_leaf": -1.0},
+            ValueError,
+            "min_weight_fraction_leaf == -1.0, must be >= 0",
+        ),
+        (
+            {"min_weight_fraction_leaf": 0.6},
+            ValueError,
+            "min_weight_fraction_leaf == 0.6, must be <= 0.5.",
+        ),
+        ({"subsample": 0.0}, ValueError, r"subsample must be in \(0,1\]"),
+        ({"subsample": 1.1}, ValueError, r"subsample must be in \(0,1\]"),
+        ({"subsample": -0.1}, ValueError, r"subsample must be in \(0,1\]"),
+        ({"max_depth": -0.1}, TypeError, "max_depth must be an instance of"),
+        ({"max_depth": 0}, ValueError, "max_depth == 0, must be >= 1."),
+        ({"init": {}}, ValueError, "The init parameter must be an estimator or 'zero'"),
+        ({"max_features": "invalid"}, ValueError, "Invalid value for max_features:"),
+        ({"max_features": 0}, ValueError, "max_features == 0, must be >= 1"),
+        ({"max_features": 100}, ValueError, "max_features == 100, must be <="),
+        (
+            {"max_features": -0.1},
+            ValueError,
+            r"max_features must be in \(0, n_features\]",
+        ),
+        (
+            {"n_iter_no_change": "invalid"},
+            ValueError,
+            "n_iter_no_change should either be",
+        ),
     ],
     # Avoid long error messages in test names:
     # https://github.com/scikit-learn/scikit-learn/issues/21362
@@ -116,9 +148,9 @@ def test_classification_toy(loss):
         (GradientBoostingClassifier, iris.data, iris.target),
     ],
 )
-def test_gbdt_parameter_checks(GradientBoosting, X, y, params, err_msg):
+def test_gbdt_parameter_checks(GradientBoosting, X, y, params, err_type, err_msg):
     # Check input parameter validation for GradientBoosting
-    with pytest.raises(ValueError, match=err_msg):
+    with pytest.raises(err_type, match=err_msg):
         GradientBoosting(**params).fit(X, y)
 
 

From 5eda80ac09774370b7649ae907fb0e4038be7285 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 12 Jan 2022 09:46:30 -0500
Subject: [PATCH 33/41] Update sklearn/ensemble/tests/test_gradient_boosting.py

Co-authored-by: Julien Jerphanion <git@jjerphan.xyz>
---
 sklearn/ensemble/tests/test_gradient_boosting.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sklearn/ensemble/tests/test_gradient_boosting.py b/sklearn/ensemble/tests/test_gradient_boosting.py
index df1dddf942f12..66d1010eda30c 100644
--- a/sklearn/ensemble/tests/test_gradient_boosting.py
+++ b/sklearn/ensemble/tests/test_gradient_boosting.py
@@ -150,8 +150,9 @@ def test_classification_toy(loss):
 )
 def test_gbdt_parameter_checks(GradientBoosting, X, y, params, err_type, err_msg):
     # Check input parameter validation for GradientBoosting
+    est = GradientBoosting(**params)
     with pytest.raises(err_type, match=err_msg):
-        GradientBoosting(**params).fit(X, y)
+        est.fit(X, y)
 
 
 @pytest.mark.parametrize(

From a65e9bf2959f5309d50f5a9bcbbaebe05ee041a1 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 12 Jan 2022 14:49:52 -0500
Subject: [PATCH 34/41] Put test_max_features back on line 504

---
 sklearn/tree/tests/test_tree.py | 46 +++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a443e249a249d..0f98911094c90 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -501,6 +501,52 @@ def test_importances_gini_equal_squared_error():
     assert_array_equal(clf.tree_.n_node_samples, reg.tree_.n_node_samples)
 
 
+def test_max_features():
+    # Check max_features.
+    for name, TreeRegressor in REG_TREES.items():
+        reg = TreeRegressor(max_features="auto")
+        reg.fit(diabetes.data, diabetes.target)
+        assert reg.max_features_ == diabetes.data.shape[1]
+
+    for name, TreeClassifier in CLF_TREES.items():
+        clf = TreeClassifier(max_features="auto")
+        clf.fit(iris.data, iris.target)
+        assert clf.max_features_ == 2
+
+    for name, TreeEstimator in ALL_TREES.items():
+        est = TreeEstimator(max_features="sqrt")
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == int(np.sqrt(iris.data.shape[1]))
+
+        est = TreeEstimator(max_features="log2")
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == int(np.log2(iris.data.shape[1]))
+
+        est = TreeEstimator(max_features=1)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == 1
+
+        est = TreeEstimator(max_features=3)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == 3
+
+        est = TreeEstimator(max_features=0.01)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == 1
+
+        est = TreeEstimator(max_features=0.5)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == int(0.5 * iris.data.shape[1])
+
+        est = TreeEstimator(max_features=1.0)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == iris.data.shape[1]
+
+        est = TreeEstimator(max_features=None)
+        est.fit(iris.data, iris.target)
+        assert est.max_features_ == iris.data.shape[1]
+
+
 def test_error():
     # Test that it gives proper exception on deficient input.
     for name, TreeEstimator in CLF_TREES.items():

From 5e5b3818dd9536401b1741407eefd8b41e12458e Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 12 Jan 2022 15:03:58 -0500
Subject: [PATCH 35/41] fix lint issue

---
 sklearn/tree/tests/test_tree.py | 46 ---------------------------------
 1 file changed, 46 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 0f98911094c90..a6834106a8331 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -709,52 +709,6 @@ def test_tree_params_validation(name, Tree, params, err_type, err_msg):
         est.fit(X, y)
 
 
-def test_max_features():
-    # Check max_features.
-    for name, TreeRegressor in REG_TREES.items():
-        reg = TreeRegressor(max_features="auto")
-        reg.fit(diabetes.data, diabetes.target)
-        assert reg.max_features_ == diabetes.data.shape[1]
-
-    for name, TreeClassifier in CLF_TREES.items():
-        clf = TreeClassifier(max_features="auto")
-        clf.fit(iris.data, iris.target)
-        assert clf.max_features_ == 2
-
-    for name, TreeEstimator in ALL_TREES.items():
-        est = TreeEstimator(max_features="sqrt")
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == int(np.sqrt(iris.data.shape[1]))
-
-        est = TreeEstimator(max_features="log2")
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == int(np.log2(iris.data.shape[1]))
-
-        est = TreeEstimator(max_features=1)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == 1
-
-        est = TreeEstimator(max_features=3)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == 3
-
-        est = TreeEstimator(max_features=0.01)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == 1
-
-        est = TreeEstimator(max_features=0.5)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == int(0.5 * iris.data.shape[1])
-
-        est = TreeEstimator(max_features=1.0)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == iris.data.shape[1]
-
-        est = TreeEstimator(max_features=None)
-        est.fit(iris.data, iris.target)
-        assert est.max_features_ == iris.data.shape[1]
-
-
 def test_min_samples_split():
     """Test min_samples_split parameter"""
     X = np.asfortranarray(iris.data, dtype=tree._tree.DTYPE)

From 3a424c241ad3b05f1a281c2faa6989ea0747f674 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 12 Jan 2022 19:01:39 -0500
Subject: [PATCH 36/41] Update sklearn/tree/_classes.py

Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
---
 sklearn/tree/_classes.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index d39d42272d554..9490ff52a1e94 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -264,7 +264,7 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 self.min_samples_split,
                 name="min_samples_split",
                 target_type=numbers.Integral,
-                min_val=1,
+                min_val=2,
             )
             min_samples_split = self.min_samples_split
         else:  # float

From 521a35c5a03af5b67f70215a3957c671c8383564 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 12 Jan 2022 19:15:11 -0500
Subject: [PATCH 37/41] Revert "update tests for min_samples_split"

---
 sklearn/tree/tests/test_tree.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index a6834106a8331..4570deee7ef0e 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -636,7 +636,12 @@ def test_error():
             TypeError,
             "min_samples_leaf must be an instance of <class 'numbers.Real'>",
         ),
-        ({"min_samples_split": 0}, ValueError, "min_samples_split == 0, must be >= 1"),
+        ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be >= 2"),
+        (
+            {"min_samples_split": 900},
+            ValueError,
+            "min_samples_split == 900, must be <=",
+        ),
         (
             {"min_samples_split": 0.0},
             ValueError,

From ce3f22ddae134ce725a2c59d01e54f46dd01666e Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Wed, 12 Jan 2022 19:23:48 -0500
Subject: [PATCH 38/41] update min_val for min_samples_split

---
 sklearn/tree/tests/test_tree.py | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 4570deee7ef0e..1bff7f1965890 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -637,11 +637,6 @@ def test_error():
             "min_samples_leaf must be an instance of <class 'numbers.Real'>",
         ),
         ({"min_samples_split": 1}, ValueError, "min_samples_split == 1, must be >= 2"),
-        (
-            {"min_samples_split": 900},
-            ValueError,
-            "min_samples_split == 900, must be <=",
-        ),
         (
             {"min_samples_split": 0.0},
             ValueError,

From 9357c879fbe737717a2efe91a1db0b5fb05df332 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Mon, 24 Jan 2022 13:10:45 -0500
Subject: [PATCH 39/41] Update sklearn/tree/_classes.py

Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
---
 sklearn/tree/_classes.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index 9490ff52a1e94..f3bbcc9a3dc63 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -245,7 +245,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 name="min_samples_leaf",
                 target_type=numbers.Integral,
                 min_val=1,
-                max_val=n_samples,
             )
             min_samples_leaf = self.min_samples_leaf
         else:  # float

From 733a3c801999f256116f4762b5e6c7fe325c1852 Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Mon, 24 Jan 2022 13:37:06 -0500
Subject: [PATCH 40/41] Update sklearn/tree/_classes.py

Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
---
 sklearn/tree/_classes.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sklearn/tree/_classes.py b/sklearn/tree/_classes.py
index f3bbcc9a3dc63..b8eae3975e09d 100644
--- a/sklearn/tree/_classes.py
+++ b/sklearn/tree/_classes.py
@@ -253,7 +253,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
                 name="min_samples_leaf",
                 target_type=numbers.Real,
                 min_val=0.0,
-                max_val=0.5,
                 include_boundaries="right",
             )
             min_samples_leaf = int(ceil(self.min_samples_leaf * n_samples))

From 9167c472b730c18d2520d74c8e9337af3f391b2e Mon Sep 17 00:00:00 2001
From: genvalen <genvalen@protonmail.com>
Date: Mon, 24 Jan 2022 13:40:37 -0500
Subject: [PATCH 41/41] update tests

---
 sklearn/tree/tests/test_tree.py | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
index 1bff7f1965890..9bba3ee861a65 100644
--- a/sklearn/tree/tests/test_tree.py
+++ b/sklearn/tree/tests/test_tree.py
@@ -624,13 +624,7 @@ def test_error():
             "max_depth must be an instance of <class 'numbers.Integral'>",
         ),
         ({"min_samples_leaf": 0}, ValueError, "min_samples_leaf == 0, must be >= 1"),
-        ({"min_samples_leaf": 900}, ValueError, "min_samples_leaf == 900, must be <="),
         ({"min_samples_leaf": 0.0}, ValueError, "min_samples_leaf == 0.0, must be > 0"),
-        (
-            {"min_samples_leaf": 0.6},
-            ValueError,
-            "min_samples_leaf == 0.6, must be <= 0.5",
-        ),
         (
             {"min_samples_leaf": "foo"},
             TypeError,