refactor(setup): update scikit-learn to scikit-lexicographical-trees …

…[cd build]

.github/workflows/wheels.yml

@@ -112,7 +112,7 @@ jobs:
           # Non-macos arm64 envrionments already have conda installed
           echo "CONDA_HOME=/usr/local/miniconda" >> $GITHUB_ENV
 
-      - name: Build and test wheels
+      - name: 👀Build and test wheels
         env:
           CIBW_PRERELEASE_PYTHONS: ${{ matrix.prerelease }}
           CIBW_ENVIRONMENT: SKLEARN_SKIP_NETWORK_TESTS=1
@@ -133,7 +133,7 @@ jobs:
 
   # Build the source distribution under Linux
   build_sdist:
-    name: Source distribution
+    name: ⚙️ Source distribution
     runs-on: ubuntu-latest
     needs: check_build_trigger
     if: needs.check_build_trigger.outputs.build

README.rst

@@ -1,3 +1,32 @@
+Scikit-lexicographical-trees
+=============================
+
+**Scikit-lexicographical-trees** is an adaptation of the Scikit-Learn trees module to support lexicographical approaches
+for longitudinal data. Refer to the following document for further information:
+`Lexico Decision Tree Classifier <https://simonprovost.github.io/scikit-longitudinal/API/estimators/trees/lexico_decision_tree_classifier/>`_.
+
+Classifiers and regressors supporting lexicographical approaches:
+
+🌲 Decision Tree Classifier
+🌲 Random Forest Classifier
+🌲 Decision Tree Regressor
+
+For more information, refer to the Scikit-Longitudinal
+– main library utilizing the current fork – : `Scikit-Longitudinal <https://simonprovost.github.io/scikit-longitudinal>`_.
+
+Acknowledgements
+----------------
+
+This fork is from NeuroData, an endeavor that paved the path for improving trees/forests in Scikit-Learn.
+Nonetheless, while our compliments go to the NeuroData team, we also like to thank the original Scikit-Learn
+team for their excellent effort over the years in providing a robust and versatile library for machine learning.
+
+Do not forget to cite them!
+
+💬💬💬💬💬💬💬💬💬💬
+
+🔄🔄🔄 Original Scikit-Learn README 🔄🔄🔄
+
 .. -*- mode: rst -*-
 
 |Azure| |CirrusCI| |Codecov| |CircleCI| |Nightly wheels| |Black| |PythonVersion| |PyPi| |DOI| |Benchmark|

pyproject.toml

@@ -1,10 +1,10 @@
 [project]
-name = "scikit-learn"
-version = "1.6.dev0"
+name = "scikit-lexicographical-trees"
+version = "0.0.4"
 description = "A set of python modules for machine learning and data mining"
 readme = "README.rst"
 maintainers = [
-    {name = "scikit-learn developers", email="[email protected]"},
+    {name = "scikit-longitudinal-developpers", email="[email protected]"},
 ]
 dependencies = [
   "numpy>=1.19.5",
@@ -36,11 +36,11 @@ classifiers=[
 ]
 
 [project.urls]
-homepage = "https://scikit-learn.org"
-source = "https://github.com/scikit-learn/scikit-learn"
-download = "https://pypi.org/project/scikit-learn/#files"
-tracker = "https://github.com/scikit-learn/scikit-learn/issues"
-"release notes" = "https://scikit-learn.org/stable/whats_new"
+homepage = "https://simonprovost.github.io/scikit-longitudinal/"
+source = "https://github.com/simonprovost/scikit-lexicographical-trees"
+download = "https://pypi.org/project/scikit-lexicographical-trees/#files"
+tracker = "https://github.com/simonprovost/scikit-lexicographical-trees/issues"
+"release notes" = "https://github.com/simonprovost/scikit-longitudinal/releases"
 
 [project.optional-dependencies]
 build = ["numpy>=1.19.5", "scipy>=1.6.0", "cython>=3.0.10", "meson-python>=0.16.0"]

setup.py

@@ -28,21 +28,22 @@
 builtins.__SKLEARN_SETUP__ = True
 
 
-DISTNAME = "scikit-lexicographical_trees"
+DISTNAME = "scikit-lexicographical-trees"
 DESCRIPTION = "A set of python modules for machine learning and data mining"
 with open("README.rst") as f:
     LONG_DESCRIPTION = f.read()
-MAINTAINER = "scikit-learn developers"
-MAINTAINER_EMAIL = "[email protected]"
-URL = "https://scikit-learn.org"
-DOWNLOAD_URL = "https://pypi.org/project/scikit-learn/#files"
+MAINTAINER = "Simon Provost"
+MAINTAINER_EMAIL = "[email protected]"
+URL = "https://simonprovost.github.io/scikit-longitudinal/"
+DOWNLOAD_URL = "https://pypi.org/project/scikit-lexicographical-trees/#files"
 LICENSE = "new BSD"
 PROJECT_URLS = {
-    "Bug Tracker": "https://github.com/scikit-learn/scikit-learn/issues",
-    "Documentation": "https://scikit-learn.org/stable/documentation.html",
-    "Source Code": "https://github.com/scikit-learn/scikit-learn",
+    "Bug Tracker": "https://github.com/simonprovost/scikit-lexicographical-trees/issues",
+    "Documentation": "https://simonprovost.github.io/scikit-longitudinal/",
+    "Source Code": "https://github.com/simonprovost/scikit-lexicographical-trees",
 }
 
+
 # We can actually import a restricted version of sklearn that
 # does not need the compiled code
 import sklearn  # noqa
@@ -51,7 +52,8 @@
 from sklearn.externals._packaging.version import parse as parse_version  # noqa
 
 
-VERSION = sklearn.__version__
+# VERSION = sklearn.__version__
+VERSION = "0.0.4"
 
 # Custom clean command to remove build artifacts
 

sklearn/ensemble/_gb.py

@@ -394,6 +394,9 @@ def __init__(
         validation_fraction=0.1,
         n_iter_no_change=None,
         tol=1e-4,
+        splitter="best",
+        features_group=None,
+        threshold_gain=0.0015,
     ):
         self.n_estimators = n_estimators
         self.learning_rate = learning_rate
@@ -416,6 +419,9 @@ def __init__(
         self.validation_fraction = validation_fraction
         self.n_iter_no_change = n_iter_no_change
         self.tol = tol
+        self.splitter = splitter
+        self.features_group = features_group
+        self.threshold_gain = threshold_gain
 
     @abstractmethod
     def _encode_y(self, y=None, sample_weight=None):
@@ -470,7 +476,7 @@ def _fit_stage(
             # induce regression tree on the negative gradient
             tree = DecisionTreeRegressor(
                 criterion=self.criterion,
-                splitter="best",
+                splitter=self.splitter,
                 max_depth=self.max_depth,
                 min_samples_split=self.min_samples_split,
                 min_samples_leaf=self.min_samples_leaf,
@@ -480,6 +486,8 @@ def _fit_stage(
                 max_leaf_nodes=self.max_leaf_nodes,
                 random_state=random_state,
                 ccp_alpha=self.ccp_alpha,
+                threshold_gain=self.threshold_gain,
+                features_group=self.features_group,
             )
 
             if self.subsample < 1.0:
@@ -1470,6 +1478,9 @@ def __init__(
         n_iter_no_change=None,
         tol=1e-4,
         ccp_alpha=0.0,
+        splitter="best",
+        features_group=None,
+        threshold_gain=0.0015,
     ):
         super().__init__(
             loss=loss,
@@ -1492,6 +1503,9 @@ def __init__(
             n_iter_no_change=n_iter_no_change,
             tol=tol,
             ccp_alpha=ccp_alpha,
+            splitter=splitter,
+            features_group=features_group,
+            threshold_gain=threshold_gain,
         )
 
     def _encode_y(self, y, sample_weight):