Merge pull request #33 from ccao-data/jeancochrane/make-python-packag…

…e-spark-compatible

Make the the Python package compatible with Athena PySpark

.github/workflows/docs.yaml

@@ -33,16 +33,12 @@ jobs:
           needs: website
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v3
-        with:
-          enable-cache: true
-          cache-dependency-glob: python/pyproject.toml
-          cache-suffix: docs
+        uses: astral-sh/setup-uv@v4
 
       - name: Setup Python
-        uses: actions/setup-python@v5
-        with:
-          python-version-file: python/pyproject.toml
+        shell: bash
+        working-directory: python
+        run: uv venv
 
       - name: Install Python dependencies
         working-directory: python
@@ -54,7 +50,7 @@ jobs:
         shell: Rscript {0}
 
       - name: Build Python docs
-        run: sphinx-build python/docs/source docs/python
+        run: uv run sphinx-build python/docs/source docs/python
 
       - name: Configure pages
         uses: actions/configure-pages@v5

.github/workflows/python-build-and-test.yaml

@@ -0,0 +1,44 @@
+on:
+  pull_request:
+  push:
+    branches: [main, master]
+
+name: python-build-and-test
+
+env:
+  PYTHONUNBUFFERED: "1"
+
+jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v4
+      with:
+        enable-cache: true
+        cache-dependency-glob: python/pyproject.toml
+        cache-suffix: ${{ matrix.python-version }}-test
+
+    - name: Install Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install tox
+      shell: bash
+      run: |
+        uv tool install tox --with tox-uv,tox-gh-actions
+        tox --version
+
+    - name: Build and test with tox
+      shell: bash
+      working-directory: python
+      run: tox r

python/ccao/vars_funs.py

@@ -1,5 +1,6 @@
 # Functions for translating variables between different data sources
 import importlib.resources
+import typing
 
 import pandas as pd
 
@@ -14,12 +15,12 @@
 
 
 def vars_rename(
-    data: list[str] | pd.DataFrame,
+    data: typing.Union[typing.List[str], pd.DataFrame],
     names_from: str,
     names_to: str,
     output_type: str = "inplace",
-    dictionary: pd.DataFrame | None = None,
-) -> list[str] | pd.DataFrame:
+    dictionary: typing.Optional[pd.DataFrame] = None,
+) -> typing.Union[typing.List[str], pd.DataFrame]:
     """
     Rename variables from one naming convention to another.
 
@@ -130,10 +131,10 @@ def vars_rename(
 
 def vars_recode(
     data: pd.DataFrame,
-    cols: list[str] | None = None,
+    cols: typing.Optional[typing.List[str]] = None,
     code_type: str = "long",
     as_factor: bool = True,
-    dictionary: pd.DataFrame | None = None,
+    dictionary: typing.Optional[pd.DataFrame] = None,
 ) -> pd.DataFrame:
     """
     Replace numerically coded variables with human-readable values.
@@ -259,7 +260,7 @@ def vars_recode(
     # vars dict
     def transform_column(
         col: pd.Series, var_name: str, values_to: str, as_factor: bool
-    ) -> pd.Series | pd.Categorical:
+    ) -> typing.Union[pd.Series, pd.Categorical]:
         if var_name in dict_long["var_name"].values:
             var_rows = dict_long[dict_long["var_name"] == var_name]
             # Get a dictionary mapping the possible codes to their values.

python/pyproject.toml

@@ -3,26 +3,28 @@ name = "ccao"
 version = "1.3.0"
 description = "Convenience Functions and Datasets for the Cook County Assessor's Office"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.9"
 authors = [
     {name = "Jean Cochrane", email="jean.cochrane@cookcountyil.gov"},
     {name = "Dan Snow", email="daniel.snow@cookcountyil.gov"},
 ]
 dependencies = [
-    "pandas>=2.2.3",
+    "pandas>=1.4.3",
+    "numpy>=1.23.1"
 ]
 
 [project.optional-dependencies]
 dev = [
-    "mypy>=1.13.0",
-    "pytest>=8.3.3",
-    "ruff>=0.7.4",
+    "mypy>=1.0.0",
+    "pytest>=7.0.0",
+    "ruff>=0.8.0",
 ]
 docs = [
-    "Sphinx>=8.1.3",
-    "myst-parser>=4.0.0",
+    "Sphinx>=7.0",
+    "myst-parser>=1.0.0",
     "pydata-sphinx-theme>=0.16.0",
-    "sphinx-pyproject>=0.3.0"
+    "sphinx-pyproject>=0.3.0",
+    "sphinx-autobuild>=2024.10.3"
 ]
 
 [tool.setuptools]
@@ -55,3 +57,38 @@ highlight_language = "none"
 html_theme = "pydata_sphinx_theme"
 html_logo = "../images/logo.png"
 html_show_copyright = false
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+addopts = "-v --cache-clear -rf --doctest-modules"
+console_output_style = "count"
+
+[tool.tox]
+legacy_tox_ini = """
+[tox]
+min_version = 4.0
+envlist =
+    py{39, 310, 311}-lowest
+    py{39, 310, 311, 312, 313}
+
+[gh-actions]
+python =
+    3.9: py39
+    3.10: py310
+    3.11: py311
+    3.12: py312
+    3.13: py313
+
+[testenv]
+extras = dev,docs
+commands = pytest
+passenv =
+    UV_CACHE_DIR
+    PYTHONUNBUFFERED
+
+[testenv:py{39, 310, 311}-lowest]
+uv_resolution = lowest-direct
+
+[testenv:py{39, 310, 311, 312, 313}]
+uv_resolution = highest
+"""