added package data

- added pytest for get_plz_mapping

.github/workflows/publish-to-test-pypi.yml

@@ -30,7 +30,7 @@ jobs:
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
         password: ${{ secrets.TEST_PYPI_API_TOKEN }}
-        repository_url: https://test.pypi.org/legacy/
+        repository-url: https://test.pypi.org/legacy/
     - name: Publish distribution 📦 to PyPI
       if: startsWith(github.ref, 'refs/tags')
       uses: pypa/gh-action-pypi-publish@release/v1

setup.py

@@ -7,16 +7,25 @@
 
 setup(
     name="sam_ml-py",
-    version="0.11.0rc1",
+    version="0.11.0rc2",
     description="a library for ML programing created by Samuel Brinkmann",
     long_description=long_description,
     long_description_content_type="text/markdown",
     python_requires=">=3.10",
     packages=find_packages(),
-    package_data={},
+    package_data={
+        "sam_ml": [
+            "data/regio/*.csv",
+            "data/regio/*.dbf",
+            "data/regio/*.prj",
+            "data/regio/*.shp",
+            "data/regio/*.shx",
+            "models/microwave_finish_sound.mp3",
+        ]
+    },
     scripts=[],
     install_requires=[
-        "scikit-learn<1.3", # version 1.3 has some issues currently (04/07/2023)
+        "scikit-learn<1.3",  # version 1.3 has some issues currently (04/07/2023)
         "pandas",
         "matplotlib",
         "numpy",
@@ -27,11 +36,13 @@
         "statsmodels",
         "sentence-transformers",
         "xgboost",
-        "ConfigSpace", # for hyperparameter tuning spaces
-        "geopandas", # for regio data (e.g. germany map plot)
+        "ConfigSpace",  # for hyperparameter tuning spaces
+        "geopandas",  # for regio data (e.g. germany map plot)
     ],
-    extras_require={"test": ["pytest", "pylint", "isort", "refurb", "black"],
-                    "with_swig": ["smac"]},
+    extras_require={
+        "test": ["pytest", "pylint", "isort", "refurb", "black"],
+        "with_swig": ["smac"],
+    },
     author="Samuel Brinkmann",
     license="MIT",
     tests_require=["pytest"],

test/test_regio.py

@@ -0,0 +1,6 @@
+from sam_ml.data.regio import get_plz_mapping
+
+
+def test_get_plz_mapping():
+    df = get_plz_mapping()
+    assert df.columns == ["ort", "plz", "landkreis", "bundesland"], "columns ['ort', 'plz', 'landkreis', 'bundesland'] should be included"