[FIX] Update submodule (#93)

* Update submodule commit

---------

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

README.md

@@ -9,16 +9,18 @@ scikit-tree
 
 scikit-tree is a scikit-learn compatible API for building state-of-the-art decision trees. These include unsupervised trees, oblique trees, uncertainty trees, quantile trees and causal trees.
 
+Tree-models have withstood the test of time, and are consistently used for modern-day data science and machine learning applications. They especially perform well when there are limited samples for a problem and are flexible learners that can be applied to a wide variety of different settings, such as tabular, images, time-series, genomics, EEG data and more.
+
 We welcome contributions for modern tree-based algorithms. We use Cython to achieve fast C/C++ speeds, while abiding by a scikit-learn compatible (tested) API. Moreover, our Cython internals are easily extensible because they follow the internal Cython API of scikit-learn as well.
 
-**Dependency on a fork of scikit-learn**
+**Submodule dependency on a fork of scikit-learn**
 Due to the current state of scikit-learn's internal Cython code for trees, we have to instead leverage a maintained fork of scikit-learn at https://github.com/neurodata/scikit-learn, where specifically, the `fork` branch is used to build and install this repo. We keep that fork well-maintained and up-to-date with respect to the main sklearn repo. The only difference is the refactoring of the `tree/` submodule. This fork is used internally under the namespace ``sktree._lib.sklearn``. It is necessary to use this fork for anything related to:
 
 - `RandomForest*`
 - `ExtraTrees*`
 - or any importable items from the `tree/` submodule, whether it is a Cython or Python object
 
-If you are developing for scikit-tree, we will always depend on the most up-to-date commit of `https://github.com/neurodata/scikit-learn/submodule` as a submodule within scikit-tee. This branch is consistently maintained for changes upstream that occur in the scikit-learn tree submodule. This ensures that our fork maintains consistency and robustness due to bug fixes and improvements upstream.
+If you are developing for scikit-tree, we will always depend on the most up-to-date commit of `https://github.com/neurodata/scikit-learn/submodulev2` as a submodule within scikit-tee. This branch is consistently maintained for changes upstream that occur in the scikit-learn tree submodule. This ensures that our fork maintains consistency and robustness due to bug fixes and improvements upstream.
 
 Documentation
 =============
@@ -43,7 +45,7 @@ We minimally require:
     * Python (>=3.8)
     * numpy
     * scipy
-    * scikit-learn
+    * scikit-learn >= 1.3
 
 Building locally with Meson (RECOMMENDED)
 -----------------------------------------
@@ -55,9 +57,6 @@ Make sure you have the necessary packages installed
     # you may need these optional dependencies to build scikit-learn locally
     conda install -c conda-forge joblib threadpoolctl pytest compilers llvm-openmp
 
-    # (caution only if you know what you're doing) or if you're a developer and need some latest changes on the fork:
-    pip install scikit-learn-tree@git+https://git@github.com/neurodata/scikit-learn.git@fork
-
 We use the ``spin`` CLI to abstract away build details:
 
     # run the build using Meson/Ninja

build_requirements.txt

@@ -3,7 +3,7 @@ meson-python
 cython
 ninja
 numpy
-scikit-learn@git+https://git@github.com/scikit-learn/scikit-learn
+scikit-learn>=1.3
 click
 rich-click
 doit

doc_requirements.txt

@@ -11,4 +11,5 @@ ipython
 nbsphinx
 memory_profiler
 pandas
-seaborn
+seaborn
+joblib

docs/conf.py

@@ -168,6 +168,7 @@
     "pipeline.Pipeline": "sklearn.pipeline.Pipeline",
     # "sklearn_fork.inspection.permutation_importance": "sklearn.inspection.permutation_importance",
 }
+
 numpydoc_xref_ignore = {
     "of",
     "or",
@@ -218,6 +219,7 @@
     "n_features_z",
     "n_neighbors",
     "one",
+    "joblib.parallel_backend",
 }
 
 # validation
@@ -254,7 +256,7 @@
 
 # -- intersphinx -------------------------------------------------------------
 intersphinx_mapping = {
-    "python": ("https://docs.python.org/3", None),
+    "python": ("https://docs.python.org/{.major}".format(sys.version_info), None),
     "numpy": ("https://numpy.org/devdocs", None),
     "scipy": ("https://scipy.github.io/devdocs", None),
     "sklearn": ("https://scikit-learn.org/dev", None),

pyproject.toml

@@ -17,6 +17,7 @@ classifiers = [
     'Programming Language :: Python :: 3.8',
     'Programming Language :: Python :: 3.9',
     'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
 ]
 keywords = ['tree', 'oblique trees', 'manifold-learning', 'scikit-learn']
 include = [
@@ -35,7 +36,7 @@ requires = [
     "setuptools<=65.5",
     "packaging",
     "Cython>=0.29.24",
-    "scikit-learn",
+    "scikit-learn>=1.3",
     "lazy_loader>=0.1",
 
     # We follow scipy for much of these pinnings
@@ -68,11 +69,11 @@ vcs = "git"
 files = ["sktree/__init__.py"]
 
 [tool.poetry.dependencies]
-python = ">=3.8,<3.11"
+python = ">=3.8,<3.12"
 numpy = "^1.23.0"
 scipy = "^1.9.0"
 scikit-learn = "^1.2.2"
-importlib-resources = { version = "*", python = "<3.9" }
+importlib-resources = { version = "*", python = "<3.10" }
 
 [tool.poetry.group.test]
 optional = true

requirements.txt

@@ -1,3 +1,3 @@
 numpy
 scipy
-scikit-learn@git+https://git@github.com/scikit-learn/scikit-learn
+scikit-learn>=1.3

sktree/ensemble/_honest_forest.py

@@ -113,7 +113,7 @@ class HonestForestClassifier(ForestClassifier):
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
         :meth:`decision_path` and :meth:`apply` are all parallelized over the
-        trees. ``None`` means 1 unless in a :obj:`joblib.parallel_backend`
+        trees. ``None`` means 1 unless in a `joblib.parallel_backend`
         context. ``-1`` means using all processors. See :term:`Glossary
         <n_jobs>` for more details.
 

sktree/ensemble/_supervised_forest.py

@@ -114,7 +114,7 @@ class ObliqueRandomForestClassifier(SimMatrixMixin, ForestClassifier):
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
         :meth:`decision_path` and :meth:`apply` are all parallelized over the
-        trees. ``None`` means 1 unless in a :obj:`joblib.parallel_backend`
+        trees. ``None`` means 1 unless in a `joblib.parallel_backend`
         context. ``-1`` means using all processors. See :term:`Glossary
         <n_jobs>` for more details.
 
@@ -454,7 +454,7 @@ class ObliqueRandomForestRegressor(SimMatrixMixin, ForestRegressor):
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
         :meth:`decision_path` and :meth:`apply` are all parallelized over the
-        trees. ``None`` means 1 unless in a :obj:`joblib.parallel_backend`
+        trees. ``None`` means 1 unless in a `joblib.parallel_backend`
         context. ``-1`` means using all processors. See :term:`Glossary
         <n_jobs>` for more details.
 
@@ -743,7 +743,7 @@ class PatchObliqueRandomForestClassifier(SimMatrixMixin, ForestClassifier):
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
         :meth:`decision_path` and :meth:`apply` are all parallelized over the
-        trees. ``None`` means 1 unless in a :obj:`joblib.parallel_backend`
+        trees. ``None`` means 1 unless in a `joblib.parallel_backend`
         context. ``-1`` means using all processors. See :term:`Glossary
         <n_jobs>` for more details.
 
@@ -1095,7 +1095,7 @@ class PatchObliqueRandomForestRegressor(SimMatrixMixin, ForestRegressor):
     n_jobs : int, default=None
         The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`,
         :meth:`decision_path` and :meth:`apply` are all parallelized over the
-        trees. ``None`` means 1 unless in a :obj:`joblib.parallel_backend`
+        trees. ``None`` means 1 unless in a `joblib.parallel_backend`
         context. ``-1`` means using all processors. See :term:`Glossary
         <n_jobs>` for more details.
 

sktree/tree/_marginalize.py

@@ -165,7 +165,7 @@ def _apply_marginal_tree(
 
 
 def compute_marginal(self: BaseForest, X, S, n_repeats=10):
-    """Compute marginal distribution of P(S = s) for each s in X.
+    r"""Compute marginal distribution of P(S = s) for each s in X.
 
     Parameters
     ----------
@@ -194,7 +194,7 @@ def compute_marginal(self: BaseForest, X, S, n_repeats=10):
 
 
 def compute_conditional(self, X, S, y=None, n_repeats=10):
-    """Compute conditional P(Y | X, Z = z) for each X and Z.
+    r"""Compute conditional P(Y | X, Z = z) for each X and Z.
 
     Parameters
     ----------