WIP correct CI errors relating to partial_fit

sklearn/ensemble/_forest.py

@@ -1332,7 +1332,6 @@ def partial_fit(self, X, y, sample_weight=None, classes=None):
         Parallel(
             n_jobs=self.n_jobs,
             verbose=self.verbose,
-            prefer="threads",
         )(
             delayed(_parallel_update_trees)(
                 t,

sklearn/tree/_tree.pyx

@@ -178,7 +178,7 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
         SIZE_t max_depth,
         double min_impurity_decrease,
         unsigned char store_leaf_values=False,
-        cnp.ndarray initial_roots=None,
+        object initial_roots=None,
     ):
         self.splitter = splitter
         self.min_samples_split = min_samples_split
@@ -220,19 +220,24 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
         X_copy = {}
         y_copy = {}
         for i in range(X.shape[0]):
+            # collect depths from the node paths
             depth_i = paths[i].indices.shape[0] - 1
             PARENT = depth_i - 1
             CHILD = depth_i
 
+            # find leaf node's & their parent node's IDs
             if PARENT < 0:
                 parent_i = 0
             else:
                 parent_i = paths[i].indices[PARENT]
             child_i = paths[i].indices[CHILD]
             left = 0
             if tree.children_left[parent_i] == child_i:
-                left = 1
+                left = 1  # leaf node is left child
 
+            # organize samples by the leaf they fall into (false root)
+            # leaf nodes are marked by parent node and
+            # their relative position (left or right child)
             if (parent_i, left) in false_roots:
                 false_roots[(parent_i, left)][0] += 1
                 X_copy[(parent_i, left)].append(X[i])
@@ -244,12 +249,15 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
 
         X_list = []
         y_list = []
+
+        # reorder the samples according to parent node IDs
         for key, value in reversed(sorted(X_copy.items())):
             X_list = X_list + value
             y_list = y_list + y_copy[key]
         cdef object X_new = np.array(X_list)
         cdef cnp.ndarray y_new = np.array(y_list)
 
+        # initialize the splitter using sorted samples
         cdef Splitter splitter = self.splitter
         splitter.init(X_new, y_new, sample_weight, missing_values_in_feature_mask)
 
@@ -275,11 +283,13 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
         cdef double min_weight_leaf = self.min_weight_leaf
         cdef SIZE_t min_samples_split = self.min_samples_split
         cdef double min_impurity_decrease = self.min_impurity_decrease
+        cdef unsigned char store_leaf_values = self.store_leaf_values
+        initial_roots = self.initial_roots
 
         # Initial capacity
         cdef int init_capacity
         cdef bint first = 0
-        if self.initial_roots is None:
+        if initial_roots is None:
             # Recursive partition (without actual recursion)
             splitter.init(X, y, sample_weight, missing_values_in_feature_mask)
 
@@ -318,7 +328,7 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
 
         if not first:
             # push reached leaf nodes onto stack
-            for key, value in reversed(sorted(self.initial_roots.items())):
+            for key, value in reversed(sorted(initial_roots.items())):
                 end += value[0]
                 update_stack.push({
                     "start": start,
@@ -471,7 +481,7 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
                         "lower_bound": left_child_min,
                         "upper_bound": left_child_max,
                     })
-                elif self.store_leaf_values and is_leaf:
+                elif store_leaf_values and is_leaf:
                     # copy leaf values to leaf_values array
                     splitter.node_samples(tree.value_samples[node_id])
 
@@ -599,7 +609,7 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
                         "lower_bound": left_child_min,
                         "upper_bound": left_child_max,
                     })
-                elif self.store_leaf_values and is_leaf:
+                elif store_leaf_values and is_leaf:
                     # copy leaf values to leaf_values array
                     splitter.node_samples(tree.value_samples[node_id])
 
@@ -672,7 +682,7 @@ cdef class BestFirstTreeBuilder(TreeBuilder):
         SIZE_t max_leaf_nodes,
         double min_impurity_decrease,
         unsigned char store_leaf_values=False,
-        cnp.ndarray initial_roots=None,
+        object initial_roots=None,
     ):
         self.splitter = splitter
         self.min_samples_split = min_samples_split
@@ -712,6 +722,7 @@ cdef class BestFirstTreeBuilder(TreeBuilder):
         # Parameters
         cdef Splitter splitter = self.splitter
         cdef SIZE_t max_leaf_nodes = self.max_leaf_nodes
+        cdef unsigned char store_leaf_values = self.store_leaf_values
 
         # Recursive partition (without actual recursion)
         splitter.init(X, y, sample_weight, missing_values_in_feature_mask)
@@ -770,7 +781,7 @@ cdef class BestFirstTreeBuilder(TreeBuilder):
                     node.feature = _TREE_UNDEFINED
                     node.threshold = _TREE_UNDEFINED
 
-                    if self.store_leaf_values:
+                    if store_leaf_values:
                         # copy leaf values to leaf_values array
                         splitter.node_samples(tree.value_samples[record.node_id])
                 else: