MNT convert unsigned char to uint8_t (scikit-learn#29510)

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

Author: adam2392

sklearn/tree/_splitter.pxd

@@ -5,7 +5,7 @@
 from ._criterion cimport Criterion
 from ._tree cimport ParentInfo
 
-from ..utils._typedefs cimport float32_t, float64_t, intp_t, int8_t, int32_t, uint32_t
+from ..utils._typedefs cimport float32_t, float64_t, intp_t, int8_t, int32_t, uint8_t, uint32_t
 
 
 cdef struct SplitRecord:
@@ -20,7 +20,7 @@ cdef struct SplitRecord:
     float64_t impurity_right  # Impurity of the right split.
     float64_t lower_bound     # Lower bound on value of both children for monotonicity
     float64_t upper_bound     # Upper bound on value of both children for monotonicity
-    unsigned char missing_go_to_left  # Controls if missing values go to the left node.
+    uint8_t missing_go_to_left  # Controls if missing values go to the left node.
     intp_t n_missing            # Number of missing values for the feature being split on
 
 cdef class Splitter:
@@ -81,7 +81,7 @@ cdef class Splitter:
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ) except -1
 
     cdef int node_reset(

sklearn/tree/_splitter.pyx

@@ -113,7 +113,7 @@ cdef class Splitter:
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ) except -1:
         """Initialize the splitter.
 
@@ -932,14 +932,14 @@ cdef class DensePartitioner:
         cdef intp_t start
         cdef intp_t end
         cdef intp_t n_missing
-        cdef const unsigned char[::1] missing_values_in_feature_mask
+        cdef const uint8_t[::1] missing_values_in_feature_mask
 
     def __init__(
         self,
         const float32_t[:, :] X,
         intp_t[::1] samples,
         float32_t[::1] feature_values,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ):
         self.X = X
         self.samples = samples
@@ -967,7 +967,7 @@ cdef class DensePartitioner:
             const float32_t[:, :] X = self.X
             intp_t[::1] samples = self.samples
             intp_t n_missing = 0
-            const unsigned char[::1] missing_values_in_feature_mask = self.missing_values_in_feature_mask
+            const uint8_t[::1] missing_values_in_feature_mask = self.missing_values_in_feature_mask
 
         # Sort samples along that feature; by
         # copying the values into an array and
@@ -1022,7 +1022,7 @@ cdef class DensePartitioner:
             float32_t max_feature_value = -INFINITY_32t
             float32_t[::1] feature_values = self.feature_values
             intp_t n_missing = 0
-            const unsigned char[::1] missing_values_in_feature_mask = self.missing_values_in_feature_mask
+            const uint8_t[::1] missing_values_in_feature_mask = self.missing_values_in_feature_mask
 
         # We are copying the values into an array and
         # finding min/max of the array in a manner which utilizes the cache more
@@ -1184,7 +1184,7 @@ cdef class SparsePartitioner:
     cdef intp_t start
     cdef intp_t end
     cdef intp_t n_missing
-    cdef const unsigned char[::1] missing_values_in_feature_mask
+    cdef const uint8_t[::1] missing_values_in_feature_mask
 
     cdef const float32_t[::1] X_data
     cdef const int32_t[::1] X_indices
@@ -1205,7 +1205,7 @@ cdef class SparsePartitioner:
         intp_t[::1] samples,
         intp_t n_samples,
         float32_t[::1] feature_values,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ):
         if not (issparse(X) and X.format == "csc"):
             raise ValueError("X should be in csc format")
@@ -1607,7 +1607,7 @@ cdef class BestSplitter(Splitter):
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ) except -1:
         Splitter.init(self, X, y, sample_weight, missing_values_in_feature_mask)
         self.partitioner = DensePartitioner(
@@ -1635,7 +1635,7 @@ cdef class BestSparseSplitter(Splitter):
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ) except -1:
         Splitter.init(self, X, y, sample_weight, missing_values_in_feature_mask)
         self.partitioner = SparsePartitioner(
@@ -1663,7 +1663,7 @@ cdef class RandomSplitter(Splitter):
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ) except -1:
         Splitter.init(self, X, y, sample_weight, missing_values_in_feature_mask)
         self.partitioner = DensePartitioner(
@@ -1691,7 +1691,7 @@ cdef class RandomSparseSplitter(Splitter):
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight,
-        const unsigned char[::1] missing_values_in_feature_mask,
+        const uint8_t[::1] missing_values_in_feature_mask,
     ) except -1:
         Splitter.init(self, X, y, sample_weight, missing_values_in_feature_mask)
         self.partitioner = SparsePartitioner(

sklearn/tree/_tree.pxd

@@ -6,7 +6,7 @@
 import numpy as np
 cimport numpy as cnp
 
-from ..utils._typedefs cimport float32_t, float64_t, intp_t, int32_t, uint32_t
+from ..utils._typedefs cimport float32_t, float64_t, intp_t, int32_t, uint8_t, uint32_t
 
 from ._splitter cimport Splitter
 from ._splitter cimport SplitRecord
@@ -21,7 +21,7 @@ cdef struct Node:
     float64_t impurity                   # Impurity of the node (i.e., the value of the criterion)
     intp_t n_node_samples                # Number of samples at the node
     float64_t weighted_n_node_samples    # Weighted number of samples at the node
-    unsigned char missing_go_to_left     # Whether features have missing values
+    uint8_t missing_go_to_left     # Whether features have missing values
 
 
 cdef struct ParentInfo:
@@ -58,7 +58,7 @@ cdef class Tree:
                           intp_t feature, float64_t threshold, float64_t impurity,
                           intp_t n_node_samples,
                           float64_t weighted_n_node_samples,
-                          unsigned char missing_go_to_left) except -1 nogil
+                          uint8_t missing_go_to_left) except -1 nogil
     cdef int _resize(self, intp_t capacity) except -1 nogil
     cdef int _resize_c(self, intp_t capacity=*) except -1 nogil
 
@@ -105,7 +105,7 @@ cdef class TreeBuilder:
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight=*,
-        const unsigned char[::1] missing_values_in_feature_mask=*,
+        const uint8_t[::1] missing_values_in_feature_mask=*,
     )
 
     cdef _check_input(

sklearn/tree/_tree.pyx

@@ -80,7 +80,7 @@ cdef class TreeBuilder:
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight=None,
-        const unsigned char[::1] missing_values_in_feature_mask=None,
+        const uint8_t[::1] missing_values_in_feature_mask=None,
     ):
         """Build a decision tree from the training set (X, y)."""
         pass
@@ -156,7 +156,7 @@ cdef class DepthFirstTreeBuilder(TreeBuilder):
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight=None,
-        const unsigned char[::1] missing_values_in_feature_mask=None,
+        const uint8_t[::1] missing_values_in_feature_mask=None,
     ):
         """Build a decision tree from the training set (X, y)."""
 
@@ -411,7 +411,7 @@ cdef class BestFirstTreeBuilder(TreeBuilder):
         object X,
         const float64_t[:, ::1] y,
         const float64_t[:] sample_weight=None,
-        const unsigned char[::1] missing_values_in_feature_mask=None,
+        const uint8_t[::1] missing_values_in_feature_mask=None,
     ):
         """Build a decision tree from the training set (X, y)."""
 
@@ -910,7 +910,7 @@ cdef class Tree:
                           intp_t feature, float64_t threshold, float64_t impurity,
                           intp_t n_node_samples,
                           float64_t weighted_n_node_samples,
-                          unsigned char missing_go_to_left) except -1 nogil:
+                          uint8_t missing_go_to_left) except -1 nogil:
         """Add a node to the tree.
 
         The new node registers itself as the child of its parent.
@@ -1578,7 +1578,7 @@ cdef class _CCPPruneController:
         """Save metrics when pruning"""
         pass
 
-    cdef void after_pruning(self, unsigned char[:] in_subtree) noexcept nogil:
+    cdef void after_pruning(self, uint8_t[:] in_subtree) noexcept nogil:
         """Called after pruning"""
         pass
 
@@ -1597,7 +1597,7 @@ cdef class _AlphaPruner(_CCPPruneController):
         # less than or equal to self.ccp_alpha
         return self.ccp_alpha < effective_alpha
 
-    cdef void after_pruning(self, unsigned char[:] in_subtree) noexcept nogil:
+    cdef void after_pruning(self, uint8_t[:] in_subtree) noexcept nogil:
         """Updates the number of leaves in subtree"""
         for i in range(in_subtree.shape[0]):
             if in_subtree[i]:
@@ -1627,7 +1627,7 @@ cdef struct CostComplexityPruningRecord:
     intp_t node_idx
     intp_t parent
 
-cdef _cost_complexity_prune(unsigned char[:] leaves_in_subtree,  # OUT
+cdef _cost_complexity_prune(uint8_t[:] leaves_in_subtree,  # OUT
                             Tree orig_tree,
                             _CCPPruneController controller):
     """Perform cost complexity pruning.
@@ -1640,7 +1640,7 @@ cdef _cost_complexity_prune(unsigned char[:] leaves_in_subtree,  # OUT
 
     Parameters
     ----------
-    leaves_in_subtree : unsigned char[:]
+    leaves_in_subtree : uint8_t[:]
         Output for leaves of subtree
     orig_tree : Tree
         Original tree
@@ -1674,10 +1674,9 @@ cdef _cost_complexity_prune(unsigned char[:] leaves_in_subtree,  # OUT
         intp_t parent_idx
 
         # candidate nodes that can be pruned
-        unsigned char[:] candidate_nodes = np.zeros(shape=n_nodes,
-                                                    dtype=np.uint8)
+        uint8_t[:] candidate_nodes = np.zeros(shape=n_nodes, dtype=np.uint8)
         # nodes in subtree
-        unsigned char[:] in_subtree = np.ones(shape=n_nodes, dtype=np.uint8)
+        uint8_t[:] in_subtree = np.ones(shape=n_nodes, dtype=np.uint8)
         intp_t pruned_branch_node_idx
         float64_t subtree_alpha
         float64_t effective_alpha
@@ -1811,7 +1810,7 @@ def _build_pruned_tree_ccp(
 
     cdef:
         intp_t n_nodes = orig_tree.node_count
-        unsigned char[:] leaves_in_subtree = np.zeros(
+        uint8_t[:] leaves_in_subtree = np.zeros(
             shape=n_nodes, dtype=np.uint8)
 
     pruning_controller = _AlphaPruner(ccp_alpha=ccp_alpha)
@@ -1843,7 +1842,7 @@ def ccp_pruning_path(Tree orig_tree):
             corresponding alpha value in ``ccp_alphas``.
     """
     cdef:
-        unsigned char[:] leaves_in_subtree = np.zeros(
+        uint8_t[:] leaves_in_subtree = np.zeros(
             shape=orig_tree.node_count, dtype=np.uint8)
 
     path_finder = _PathFinder(orig_tree.node_count)
@@ -1876,7 +1875,7 @@ cdef struct BuildPrunedRecord:
 cdef _build_pruned_tree(
     Tree tree,  # OUT
     Tree orig_tree,
-    const unsigned char[:] leaves_in_subtree,
+    const uint8_t[:] leaves_in_subtree,
     intp_t capacity
 ):
     """Build a pruned tree.
@@ -1890,7 +1889,7 @@ cdef _build_pruned_tree(
         Location to place the pruned tree
     orig_tree : Tree
         Original tree
-    leaves_in_subtree : unsigned char memoryview, shape=(node_count, )
+    leaves_in_subtree : uint8_t memoryview, shape=(node_count, )
         Boolean mask for leaves to include in subtree
     capacity : intp_t
         Number of nodes to initially allocate in pruned tree

sklearn/tree/_utils.pxd

@@ -6,7 +6,7 @@
 cimport numpy as cnp
 from ._tree cimport Node
 from ..neighbors._quad_tree cimport Cell
-from ..utils._typedefs cimport float32_t, float64_t, intp_t, int32_t, uint32_t
+from ..utils._typedefs cimport float32_t, float64_t, intp_t, uint8_t, int32_t, uint32_t
 
 cdef enum:
     # Max value for our rand_r replacement (near the bottom).
@@ -26,7 +26,7 @@ ctypedef fused realloc_ptr:
     # Add pointer types here as needed.
     (float32_t*)
     (intp_t*)
-    (unsigned char*)
+    (uint8_t*)
     (WeightedPQueueRecord*)
     (float64_t*)
     (float64_t**)

sklearn/tree/_utils.pyx

@@ -447,7 +447,7 @@ def _any_isnan_axis0(const float32_t[:, :] X):
         intp_t i, j
         intp_t n_samples = X.shape[0]
         intp_t n_features = X.shape[1]
-        unsigned char[::1] isnan_out = np.zeros(X.shape[1], dtype=np.bool_)
+        uint8_t[::1] isnan_out = np.zeros(X.shape[1], dtype=np.bool_)
 
     with nogil:
         for i in range(n_samples):