Merge branch 'dev' into entity_matching

.pre-commit-config.yaml

@@ -80,7 +80,7 @@ repos:
         verbose: false
         pass_filenames: false
         always_run: true
-        entry: pytest --doctest-modules src/pudl test/unit
+        entry: pytest --doctest-modules src/pudl test/unit -m "not slow"
 
 # Configuration for pre-commit.ci
 ci:

docs/release_notes.rst

@@ -3,7 +3,23 @@ PUDL Release Notes
 =======================================================================================
 
 ---------------------------------------------------------------------------------------
-v2023.XX.XX
+v2023.12.XX
+---------------------------------------------------------------------------------------
+* The ``epacems_to_parquet`` and ``state_demand`` scripts have been retired in favor of
+  using the Dagster UI. See :issue:`3107` and :pr:`3086`. Visualizations of hourly
+  state-level electricity demand have been moved into our example notebooks which can
+  be found both `on Kaggle <https://www.kaggle.com/code/catalystcooperative/02-state-hourly-electricity-demand>`__
+  and `on GitHub <https://github.com/catalyst-cooperative/pudl-examples/>`__
+* The ``pudl_setup`` script has been retired. All input/output locations are now set
+  using the ``$PUDL_INPUT`` and ``$PUDL_OUTPUT`` environment variables.  See
+  :issue:`3107` and :pr:`3086`.
+* The :func:`pudl.analysis.service_territory.pudl_service_territories` script has been
+  fixed, and can be used to generate `GeoParquet <https://geoparquet.org/>`__
+  outputs describing historical utility and balancing authority service territories. See
+  :issue:`1174` and :pr:`3086`.
+
+---------------------------------------------------------------------------------------
+v2023.12.01
 ---------------------------------------------------------------------------------------
 
 Dagster Adoption
@@ -207,7 +223,6 @@ Data Coverage
     centralized service companies. `FERC Form 60 will also be available on Datasette
     <https://data.catalyst.coop/ferc6>`__.
 
-
 Data Cleaning
 ^^^^^^^^^^^^^
 
@@ -274,10 +289,6 @@ Analysis
   :ref:`compiled_geometry_utility_eia861`), and the estimated total hourly electricity
   demand for each US state in :ref:`predicted_state_hourly_demand`. See :issue:`1973`
   and :pr:`2550`.
-* The :func:`pudl.analysis.service_territory.pudl_service_territories` script has been
-  fixed, and can be used to generate `GeoParquet <https://geoparquet.org/>`__
-  outputs describing historical utility and balancing authority service territories. See
-  :issue:`1174` and :pr:`3086`.
 
 Deprecations
 ^^^^^^^^^^^^
@@ -316,14 +327,6 @@ Deprecations
   :mod:`pudl.settings` no longer have table attributes because the ETL no longer
   supports loading specific tables via settings. Use dagster to select subsets of
   tables to process.
-* The ``epacems_to_parquet`` and ``state_demand`` scripts have been retired in favor of
-  using the Dagster UI. See :issue:`3107` and :pr:`3086`. Visualizations of hourly
-  state-level electricity demand have been moved into our example notebooks which can
-  be found both `on Kaggle <https://www.kaggle.com/code/catalystcooperative/02-state-hourly-electricity-demand>`__
-  and `on GitHub <https://github.com/catalyst-cooperative/pudl-examples/>`__
-* The ``pudl_setup`` script has been retired. All input/output locations are now set
-  using the ``$PUDL_INPUT`` and ``$PUDL_OUTPUT`` environment variables.  See
-  :issue:`3107` and :pr:`3086`.
 
 Miscellaneous
 ^^^^^^^^^^^^^

pyproject.toml

@@ -263,6 +263,9 @@ filterwarnings = [
     "once:The behavior of DataFrame concatenation with empty or all-NA entries is deprecated.:FutureWarning",
 ]
 
+markers = [
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
+]
 # Oddly, despite the use of --cov-config=pyproject.toml here, pytest does not seem to
 # pick up the source directories specified in the [tool.coverage.run] section below.
 # (though it *does* pick up the omit parameters!). This means we need to specify the

test/unit/io_managers_test.py

@@ -242,6 +242,7 @@ def test_pudl_sqlite_io_manager_delete_stmt(fake_pudl_sqlite_io_manager_fixture)
     assert len(returned_df) == 1
 
 
+@pytest.mark.slow
 def test_migrations_match_metadata(tmp_path, monkeypatch):
     """If you create a `PudlSQLiteIOManager` that points at a non-existing
     `pudl.sqlite` - it will initialize the DB based on the `package`.
@@ -422,7 +423,10 @@ def test_ferc_xbrl_sqlite_io_manager_dedupes(mocker, tmp_path):
 )
 
 
-@hypothesis.settings(print_blob=True, deadline=400)
+# ridiculous deadline - dataframe generation is always slow and sometimes
+# *very* slow
+@pytest.mark.slow
+@hypothesis.settings(print_blob=True, deadline=2_000)
 @hypothesis.given(example_schema.strategy(size=3))
 def test_filter_for_freshest_data(df):
     # XBRL context is the identifying metadata for reported values

test/unit/settings_test.py

@@ -281,6 +281,7 @@ def test_partitions_with_json_normalize(pudl_etl_settings):
         )
 
 
+@pytest.mark.slow
 def test_partitions_for_datasource_table(pudl_etl_settings):
     """Test whether or not we can make the datasource table."""
     ds = Datastore(local_cache_path=PudlPaths().data_dir)