fix: relax requests version from ==2.32.* to >=2.32.0

.github/workflows/publish-docs.yml

@@ -0,0 +1,47 @@
+# This workflow builds and publishes the latest docs to
+# the `gh-pages` branch.
+# For more details: https://github.com/marketplace/actions/deploy-to-github-pages
+name: Publish docs
+
+on:
+  release:
+    types: [created]
+  workflow_dispatch:
+
+jobs:
+  build-and-deploy:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pages: write
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        # fetch all tags so `versioneer` can properly determine current version
+        fetch-depth: 0
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.11'
+    - name: Install pandoc
+      uses: pandoc/actions/setup@v1
+    - name: Install dependencies
+      run: |
+        pip install -r requirements.txt
+        pip install -r requirements-ml.txt
+        pip install -r requirements-reports.txt
+        pip install -r requirements-docs.txt
+        pip install -e .
+
+    - name: Build
+      run: |
+        cd _docs/docs
+        python update_documentation.py
+    - name: Publish
+      uses: JamesIves/github-pages-deploy-action@v4
+      with:
+        branch: gh-pages
+        folder: _docs/docs/LATEST/html

.github/workflows/publish-package.yml

@@ -0,0 +1,52 @@
+# This workflow publishes the package to pypi.
+# For more details:
+# https://docs.github.com/en/actions/guides/building-and-testing-python#publishing-to-package-registries
+name: Publish to PyPi
+
+on:
+  release:
+    types: [created]
+  workflow_dispatch:
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+      # fetch all tags so `versioneer` can properly determine current version
+      with:
+        fetch-depth: 0
+    - name: Check if current commit is tagged
+      # fails and cancels release if the current commit is not tagged
+      run: |
+        git describe --exact-match --tags
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.11'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        if [ -f requirements-ml.txt ]; then pip install -r requirements-ml.txt; fi
+        if [ -f requirements-reports.txt ]; then pip install -r requirements-reports.txt; fi
+        pip install setuptools wheel twine
+    - name: Build
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_REPOSITORY: pypi
+      run: |
+        python setup.py sdist bdist_wheel
+    - name: Test build
+      # fails and cancels release if the built package fails to import
+      run: |
+        pip install dist/*.whl
+        python -c 'import dataprofiler; print(dataprofiler.__version__)'
+    - name: Publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_REPOSITORY: pypi
+      run: |
+        twine upload dist/*

.github/workflows/test-python-package.yml → .github/workflows/test-package.yml

@@ -7,21 +7,19 @@ on:
   pull_request:
     branches:
       - 'main'
-      - 'feature/**'
-      - 'dev'
 
 jobs:
   build:
 
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.8, 3.9, "3.10"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v4.3.1
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v5.6.0
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -38,4 +36,4 @@ jobs:
         pre-commit run --all-files
     - name: Test with pytest
       run: |
-        DATAPROFILER_SEED=0 pytest --forked --cov=dataprofiler --cov-fail-under=80
+        DATAPROFILER_SEED=0 pytest --cov=dataprofiler --cov-fail-under=80

.pre-commit-config.yaml

@@ -2,9 +2,10 @@ repos:
   # Black: format Python code
   # https://github.com/psf/black/blob/master/.pre-commit-hooks.yaml
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 24.3.0
     hooks:
       - id: black
+        exclude: (versioneer.py|dataprofiler/_version.py|_docs/)
         types: [file, python]
         language_version: python3
   # Isort: sort import statements
@@ -15,62 +16,67 @@ repos:
     rev: 5.12.0
     hooks:
       - id: isort
+        exclude: _docs/
         language_version: python3
   # Flake8: complexity and style checking
   # https://flake8.pycqa.org/en/latest/user/using-hooks.html
   - repo: https://github.com/pycqa/flake8
-    rev: 4.0.1
+    rev: 7.3.0
     hooks:
       - id: flake8
         additional_dependencies: [flake8-docstrings]
-        exclude: (^docs/|^dataprofiler/tests/|^.*/__init__.py)
+        exclude: (^docs/|^dataprofiler/tests/|^.*/__init__.py|_docs/)
         language_version: python3
   # General fixers: format files for white spaces and trailing new lines, warn on debug statements
   # https://github.com/pre-commit/pre-commit-hooks#hooks-available
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.0.1
     hooks:
       - id: trailing-whitespace
-        exclude: (^dataprofiler/tests/data/|^dataprofiler/tests/speed_tests/data/)
+        exclude: (^dataprofiler/tests/data/|^dataprofiler/tests/speed_tests/data/|_docs/)
       - id: debug-statements
       - id: end-of-file-fixer
-        exclude: (^dataprofiler/tests/data/)
+        exclude: (^dataprofiler/tests/data/|_docs/)
   # Mypy: Optional static type checking
   # https://github.com/pre-commit/mirrors-mypy
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.982
+    rev: v1.11.2
     hooks:
       - id: mypy
-        exclude: (^dataprofiler/tests/|^resources/|^examples|venv*/)
+        # Let mypy own target selection and exclusions via setup.cfg.
+        args: [--config-file=setup.cfg, dataprofiler]
+        pass_filenames: false
         language_version: python3
         additional_dependencies: # Keep up-to-date with the respective requirement files
           [
             # requirements.txt
             h5py>=2.10.0,
             wheel>=0.33.1,
-            numpy>=1.22.0,
-            pandas>=1.1.2,
+            'numpy>=1.22.0,<3.0.0',
+            'pandas>=1.1.2,<3.0.0',
             python-dateutil>=2.7.5,
             pytz>=2020.1,
-            pyarrow>=1.0.1,
-            chardet>=3.0.4,
-            fastavro>=1.0.0.post1,
-            python-snappy>=0.5.4,
+            'pyarrow>=1.0.1,<24.0.0',
+            'chardet>=3.0.4,<7.0.0',
+            fastavro>=1.1.0,
+            python-snappy>=0.7.1,
             charset-normalizer>=1.3.6,
             psutil>=4.0.0,
-            scipy>=1.4.1,
-            requests>=2.28.1,
+            scipy>=1.10.0,
+            requests>=2.32.4,
             networkx>=2.5.1,
             typing-extensions>=3.10.0.2,
             HLL>=2.0.3,
             datasketches>=4.1.0,
-            boto3>=1.28.61,
+            packaging>=23.0,
+            boto3>=1.37.15,
+            urllib3>=2.5.0,
 
             # requirements-dev.txt
-            check-manifest>=0.48,
-            black==22.3.0,
+            check-manifest>=0.50,
+            black>=24.3.0,
             isort==5.12.0,
-            pre-commit==2.19.0,
+            pre-commit==4.3.0,
             tox==3.25.1,
             types-setuptools==67.7.0.1,
             types-python-dateutil==2.8.19.12,
@@ -80,11 +86,9 @@ repos:
 
             # requirements-ml.txt
             scikit-learn>=0.23.2,
-            'keras>=2.4.3,<3.0.0',
+            'keras>3.4.0,<4.0.0',
             rapidfuzz>=2.6.1,
-            "tensorflow>=2.6.4,<2.15.0; sys.platform != 'darwin'",
-            "tensorflow>=2.6.4,<2.15.0; sys_platform == 'darwin' and platform_machine != 'arm64'",
-            "tensorflow-macos>=2.6.4,<2.15.0; sys_platform == 'darwin' and platform_machine == 'arm64'",
+            "tensorflow>=2.16.0",
             tqdm>=4.0.0,
 
             # requirements-reports.txt
@@ -93,36 +97,39 @@ repos:
 
             # requirements-test.txt
             coverage>=5.0.1,
-            dask>=2.29.0,
             fsspec>=0.3.3,
             pytest>=6.0.1,
             pytest-cov>=2.8.1,
             pytest-xdist>=2.1.0,
             pytest-forked>=1.3.0,
             toolz>=0.10.0,
-            'memray>=1.7.0,<1.12.0',
+            'memray>=1.18.0',
           ]
   # Check-manifest: ensures required non-Python files are included in MANIFEST.in
   # https://github.com/mgedmin/check-manifest/blob/master/.pre-commit-hooks.yaml
   - repo: https://github.com/mgedmin/check-manifest
-    rev: "0.48"
+    rev: "0.50"
     hooks:
       - id: check-manifest
-        additional_dependencies: ['h5py', 'wheel', 'future', 'numpy', 'pandas',
-        'python-dateutil', 'pytz', 'pyarrow', 'chardet', 'fastavro',
-        'python-snappy', 'charset-normalizer', 'psutil', 'scipy', 'requests',
-        'networkx','typing-extensions', 'HLL', 'datasketches', 'boto3']
+        additional_dependencies: ['h5py', 'wheel', 'future', 'numpy>=1.22.0,<3.0.0',
+        'pandas', 'python-dateutil', 'pytz', 'pyarrow<24.0.0', 'chardet',
+        'fastavro>=1.1.0', 'python-snappy', 'charset-normalizer', 'psutil',
+        'scipy>=1.10.0', 'requests>=2.32.4', 'networkx', 'typing-extensions',
+        'HLL', 'datasketches', 'packaging>=23.0', 'boto3>=1.37.15',
+        'urllib3>=2.5.0']
   # Pyupgrade - standardize and modernize Python syntax for newer versions of the language
   - repo: https://github.com/asottile/pyupgrade
     rev: v3.3.0
     hooks:
       - id: pyupgrade
         args: ["--py38-plus"]
+        exclude: (versioneer.py|dataprofiler/_version.py| _docs/)
   # Autoflake - cleanup unused variables and imports
   - repo: https://github.com/PyCQA/autoflake
     rev: v2.0.0
     hooks:
       - id: autoflake
+        exclude: _docs/
         args:
           - "--in-place"
           - "--ignore-pass-statements"

.whitesource

@@ -0,0 +1,3 @@
+{
+    "settingsInheritedFrom": "capitalone/whitesource-config"
+}

CHANGELOG.md

@@ -0,0 +1,46 @@
+# Changelog
+
+## 0.14.0 - 2026-09-08
+
+### Breaking Changes
+
+- Dropped support for Python 3.9. The minimum supported version is now Python
+  3.10 (`python_requires>=3.10`).
+- Raised the `keras` requirement to `>3.4.0,<4.0.0` (previously `<=3.4.0`) and
+  migrated the bundled labeler models from the TensorFlow SavedModel format to
+  the single-file `.keras` format. Environments pinned to `keras<=3.4.0` are no
+  longer supported, and previously saved models must be re-saved.
+- Moved the bundled labeler resources from the top-level `resources/` directory
+  into the package at `dataprofiler/resources/`. Code that referenced the old
+  top-level path must be updated; use
+  `dataprofiler.labelers.utils.find_resources_dir()` to resolve resource paths.
+
+### Added
+
+- Added compatibility support for NumPy 2.0 while constraining `numpy` to
+  `>=1.22.0,<3.0.0` to avoid future breakage from NumPy 3.
+- Added compatibility support for Keras versions newer than 3.4.0 while
+  constraining `keras` to `>3.4.0,<4.0.0` to avoid future breakage from Keras 4.
+- Added Python 3.12 and 3.13 to the test matrix.
+- Added `find_resources_dir()` for resolving packaged resources via
+  `importlib.resources`.
+
+### Changed
+
+- Replaced the deprecated `pkg_resources` usage with `importlib.resources`, and
+  switched packaging from `data_files` to `package_data`.
+- Constrained `chardet` to `<7.0.0` and `pandas` to `<3.0.0` to avoid breakage
+  from upcoming major releases.
+- Constrained `pyarrow` to `<24.0.0`.
+- Simplified the `tensorflow` requirement to `tensorflow>=2.16.0`, removing the
+  platform-specific `tensorflow-macos` marker.
+- Updated the pre-commit configuration to align hook versions and hook
+  dependencies with the current project requirements.
+- Enabled `mypy` checking across the `dataprofiler` package (excluding tests).
+- Removed `--forked` from the `tox` pytest invocation and raised `memray` to
+  `>=1.18.0`.
+
+### Security
+
+- Resolved reported vulnerabilities by raising `boto3>=1.37.15`,
+  `requests>=2.32.4`, and adding an explicit `urllib3>=2.5.0` floor.