Dev

.github/workflows/test.yml

@@ -9,14 +9,14 @@ on:
     paths:
       - "powershap/**"
       - "tests/**"
-      - "poetry.lock"
+      - "uv.lock"
       - ".github/workflows/test.yml"
   pull_request:
     branches: [ main ]
     paths:
       - "powershap/**"
       - "tests/**"
-      - "poetry.lock"
+      - "uv.lock"
       - ".github/workflows/test.yml"
 
 jobs:
@@ -26,54 +26,48 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: ['ubuntu-latest']  # TODO - do we add other OSes?
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        os: ['ubuntu-latest', 'windows-latest']  # TODO - do we add other OSes?
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
     defaults:
       run:
         shell: bash
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v6
+      with:
+        enable-cache: true
+
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
+
+    - name: Install llvm on Ubuntu
+      if: runner.os == 'Linux'
+      run: sudo apt-get install llvm # Because https://github.com/slundberg/shap/issues/1854
+
+    - name: Install MSVC build tools on Windows
+      if: runner.os == 'Windows'
+      uses: microsoft/setup-msbuild@v1
 
-    - name: Install Poetry
-      uses: snok/install-poetry@v1
-      with:
-        version: 1.5.1
-    - name: Cache poetry
-      id: cached-poetry-dependencies
-      uses: actions/cache@v3
-      with:
-        path: ~/.cache/pypoetry/virtualenvs
-        key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}-python-${{ matrix.python-version }}
-    - run: poetry --version
 
-    - run: sudo apt-get install llvm  # Because https://github.com/slundberg/shap/issues/1854
     - name: Install dependencies
-      run: poetry install --all-extras
-      # Do not use caching (anymore)
-#      if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+      run: uv sync --locked --all-extras --dev
 
-#     - name: Lint with flake8
-#       run: |
-#         # stop the build if there are Python syntax errors or undefined names
-#         flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-#         # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-#         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with pytest
-
       run: |
-        poetry run pytest --cov=powershap --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov-report=xml tests
+        uv run pytest --cov=powershap --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov-report=xml tests
+
     - name: Upload pytest test results
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
-        name: pytest-results-${{ matrix.python-version }}
-        path: junit/test-results-${{ matrix.python-version }}.xml
+        name: pytest-results-${{ matrix.python-version }}-${{matrix.os}}
+        path: junit/test-results-${{ matrix.python-version }}-${{matrix.os}}.xml
         # Use always() to always run this step to publish test results when there are test failures
       if: ${{ always() }}
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v3
+      uses: codecov/codecov-action@v5

powershap/powershap.py

@@ -8,7 +8,9 @@
 from sklearn.base import BaseEstimator
 from sklearn.feature_selection import SelectorMixin
 from sklearn.model_selection import BaseCrossValidator
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_is_fitted,validate_data
+
+
 
 from .shap_wrappers import ShapExplainerFactory
 from .utils import powerSHAP_statistical_analysis
@@ -365,19 +367,21 @@ def fit(self, X, y, stratify=None, groups=None, **kwargs):
         # Perform the necessary sklearn checks -> X and y are both ndarray.
         # Logs the feature names as well (in self.feature_names_in_ in sklearn 1.x).
         #
-        # These two operations (_validate_data and pd.DataFrame) will also copy
+        # These two operations (validate_data and pd.DataFrame) will also copy
         # the data into a new place in memory, avoiding data mutation. How this
         # happens may not be obvious at first glance:
         #
-        # 1. _validate_data ensures that the data is a numpy array, copying it
+        # 1. validate_data ensures that the data is a numpy array, copying it
         # upon conversion if necessary.
         #
         # 2. pd.DataFrame then copies X, which is now an numpy array, into a
         # new pandas dataframe.
         #
         # If this is changed in some way which would allow explain() to mutate
         # the original data, it should cause the data mutation tests to fail.
-        X, y = self._explainer._validate_data(self._validate_data, X, y, multi_output=True)
+
+        # X, y = validate_data(self, X, y, multi_output=True)
+        X, y = self._explainer.validate_data(self, X, y, multi_output=True)
         X = pd.DataFrame(data=X, columns=list(range(X.shape[1])))
 
         self._print("Starting powershap")
@@ -530,5 +534,8 @@ def transform(self, X):
             )
         return super().transform(X)
 
-    def _more_tags(self):
+    # Since sklearn 1.6, the tag system changed so this function is necessary to make it compatible
+    # https://scikit-learn.org/stable/auto_examples/release_highlights/plot_release_highlights_1_6_0.html#improvements-to-the-developer-api-for-third-party-libraries
+    def __sklearn_tags__(self):
         return self._explainer._get_more_tags()
+