Complete merge

Signed-off-by: Adam Li <adam2392@gmail.com>

Author: adam2392

sklearn/ensemble/_forest.py

@@ -2316,6 +2316,25 @@ class ExtraTreesClassifier(ForestClassifier):
 
         .. versionadded:: 1.4
 
+    monotonic_cst : array-like of int of shape (n_features), default=None
+        Indicates the monotonicity constraint to enforce on each feature.
+          - 1: monotonically increasing
+          - 0: no constraint
+          - -1: monotonically decreasing
+
+        If monotonic_cst is None, no constraints are applied.
+
+        Monotonicity constraints are not supported for:
+          - multiclass classifications (i.e. when `n_classes > 2`),
+          - multioutput classifications (i.e. when `n_outputs_ > 1`),
+          - classifications trained on data with missing values.
+
+        The constraints hold over the probability of the positive class.
+
+        Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
+
+        .. versionadded:: 1.4
+
     Attributes
     ----------
     estimator_ : :class:`~sklearn.tree.ExtraTreesClassifier`

sklearn/tree/_splitter.pxd

@@ -71,7 +71,6 @@ cdef class BaseSplitter:
     #   +1: monotonic increase
     cdef const cnp.int8_t[:] monotonic_cst
     cdef bint with_monotonic_cst
-
     cdef const DOUBLE_t[:] sample_weight
 
     # The samples vector `samples` is maintained by the Splitter object such

sklearn/tree/_splitter.pyx

@@ -300,7 +300,7 @@ cdef class Splitter(BaseSplitter):
         """Copy the value of node samples[start:end] into dest."""
 
         self.criterion.node_value(dest)
-    
+
     cdef inline void clip_node_value(self, double* dest, double lower_bound, double upper_bound) noexcept nogil:
         """Clip the value in dest between lower_bound and upper_bound for monotonic constraints."""
 
@@ -310,6 +310,11 @@ cdef class Splitter(BaseSplitter):
         """Copy the samples[start:end] into dest."""
         self.criterion.node_samples(dest)
 
+    cdef inline void clip_node_value(self, double* dest, double lower_bound, double upper_bound) noexcept nogil:
+        """Clip the value in dest between lower_bound and upper_bound for monotonic constraints."""
+
+        self.criterion.clip_node_value(dest, lower_bound, upper_bound)
+
     cdef double node_impurity(self) noexcept nogil:
         """Return the impurity of the current node."""
 
@@ -564,6 +569,18 @@ cdef inline int node_split_best(
 
                 criterion.update(current_split.pos)
 
+                # Reject if monotonicity constraints are not satisfied
+                if (
+                    with_monotonic_cst and
+                    monotonic_cst[current_split.feature] != 0 and
+                    not criterion.check_monotonicity(
+                        monotonic_cst[current_split.feature],
+                        lower_bound,
+                        upper_bound,
+                    )
+                ):
+                    continue
+
                 # Reject if min_weight_leaf is not satisfied
                 if splitter.check_postsplit_conditions() == 1:
                     continue
@@ -915,6 +932,18 @@ cdef inline int node_split_random(
         ):
             continue
 
+        # Reject if monotonicity constraints are not satisfied
+        if (
+                with_monotonic_cst and
+                monotonic_cst[current_split.feature] != 0 and
+                not criterion.check_monotonicity(
+                    monotonic_cst[current_split.feature],
+                    lower_bound,
+                    upper_bound,
+                )
+        ):
+            continue
+
         current_proxy_improvement = criterion.proxy_impurity_improvement()
 
         if current_proxy_improvement > best_proxy_improvement:

sklearn/tree/_tree.pyx

@@ -364,7 +364,6 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
                         "is_left": 1,
                         "impurity": split.impurity_left,
                         "n_constant_features": n_constant_features,
-                        "n_constant_features": n_constant_features,
                         "lower_bound": left_child_min,
                         "upper_bound": left_child_max,
                     })