v1.4.2

STree 1.4.2

Highlights

• scikit-learn 1.8 compatibility: Migrated to the new sklearn API (validate_data, __sklearn_tags__) and bumped the minimum required version to
  scikit-learn>=1.8.0.
• mufs 1.0 support: Now depends on mufs>=1.0.0, which fixes the CFS merit denominator (k + 2*rff instead of the previous k + (k**2 - k)*rff).
  Test expectations have been updated to match the new feature selection order.
• Explicit numpy dependency: numpy is now declared directly in pyproject.toml instead of relying on scikit-learn's transitive pull.

Build & CI

• Dropped requirements.txt; dependencies are installed via pip install .[dev].
• Extended the Python matrix to 3.11, 3.12, 3.13 and 3.14.
• Bumped CodeQL action to v3 and enabled pip cache.
• Removed Windows from the CI matrix to streamline the workflow.
• Updated Read the Docs configuration.

Fixes & Cleanup

• Removed an unused parameter from the Stree constructor.
• Cleaned up import formatting in Strees.py.
• Added an init_depth reference and an "Ask the Wiki" link in the README.
• Fixed the CI badge link in the README.

Installation

pip install STree==1.4.2

Full Changelog: v1.4.0...v1.4.2

v1.4.0: Upgrade requirements

• Change python minor version to 3.11
• Change build tool to hatch
• Update build source from setup.py to pyproject.toml
• Update github action versions
• Remove black from github actions linting as it wouldn't read from pyproject.toml
• Add call method to Stree to support sklearn ensembles requirements for base estimators
• Update tests
• Update readthedocs configuration

v1.3.2: Fixing minor issues

• Reformat test with new black version
• Add separate methods to return nodes/leaves/depth
• Black format issue
• Update benchmark.ipynb

Working nicely with scikit-learn v 1.4.2 and python 3.11.5

v1.3.1: update to sklearn 1.2

Update to sklearn 1.2

v1.3.0: predict_proba

Update doc and version 1.30 (#55)

* Add complete classes counts to node and tests

* Implement optimized predict and new predict_proba

* Add predict_proba test

* Add python 3.10 to CI

* Update version number and documentation

v1.2.4: Graphviz (#52)

* Add graphviz representation of the tree

* Complete graphviz test
Add comments to some tests

* Add optional title to tree graph

* Add fontcolor keyword to nodes of the tree

* Add color keyword to arrows of graph

* Update version file to 1.2.4

v1.2.3

Fix random seed not used in fs_mutual (mutual_info_classif from sklearn.feature_selection) that produced flaky tests in odte

v1.2.2

• Add iwss and true random (only one combination generated) feature selection

• Update docs and source comments

• Remove obsolete binder links

v1.2.1

Add feature selection to node splits: f-value, mutual information, cfs and fcbf

1.2: Update version info (#42)

* Update version info and update docs (#41)