Adding workflow to test against main

Signed-off-by: Adam Li <[email protected]>

.github/workflows/main.yml

@@ -84,6 +84,11 @@ jobs:
           pip install -r build_requirements.txt
           pip install -r test_requirements.txt
 
+      - name: Install nightly wheels for scikit-learn (only for ubuntu 3.12)
+        if: ${{ matrix.python-version == '3.12' }} && ${{ matrix.os == 'ubuntu-latest' }}
+        run: |
+          pip install --pre --extra-index https://pypi.anaconda.org/scientific-python-nightly-wheels/simple scikit-learn --force
+
       - name: Prepare compiler cache
         id: prep-ccache
         shell: bash

treeple/_lib/meson.build

@@ -8,6 +8,9 @@ tree_extension_metadata = {
   '_tree':
     {'sources': ['./sklearn/tree/' + '_tree.pyx'],
      'override_options': ['cython_language=cpp', 'optimization=3']},
+  '_partitioner':
+    {'sources': ['./sklearn/tree/' + '_partitioner.pyx'],
+     'override_options': ['cython_language=cpp', 'optimization=3']},
   '_splitter':
     {'sources': ['./sklearn/tree/' + '_splitter.pyx'],
      'override_options': ['cython_language=cpp', 'optimization=3']},

treeple/tree/_honest_prune.pxd

@@ -1,11 +1,6 @@
-# from .._lib.sklearn.tree._tree import _build_pruned_tree
-
 from .._lib.sklearn.tree._criterion cimport Criterion
-from .._lib.sklearn.tree._splitter cimport (
-    SplitRecord,
-    Splitter,
-    shift_missing_values_to_left_if_required,
-)
+from .._lib.sklearn.tree._partitioner cimport shift_missing_values_to_left_if_required
+from .._lib.sklearn.tree._splitter cimport SplitRecord, Splitter
 from .._lib.sklearn.tree._tree cimport Node, ParentInfo, Tree
 from .._lib.sklearn.utils._typedefs cimport float32_t, float64_t, int8_t, intp_t, uint8_t, uint32_t
 

treeple/tree/_honest_tree.py

@@ -689,8 +689,6 @@ def _fit_leaves(self, X, y, sample_weight):
         y = y_encoded
         self.n_classes_ = np.array(self.n_classes_, dtype=np.intp)
 
-        # XXX: implement honest pruning
-        print(self.honest_method)
         if self.honest_method == "apply":
             # Fit leaves using other subsample
             honest_leaves = self.tree_.apply(X[self.honest_indices_])
@@ -744,7 +742,6 @@ def _fit_leaves(self, X, y, sample_weight):
                 pruned_tree, self.tree_, pruner, X, y, sample_weight, missing_values_in_feature_mask
             )
             self.tree_ = pruned_tree
-            # raise NotImplementedError("Pruning is not yet implemented.")
 
         if self.n_outputs_ == 1:
             self.n_classes_ = self.n_classes_[0]