Consolidate optional dependencies; test nuke; parallelize tests

* Move previous dev, test, and datasette optional dependencies into
  the required dependencies to simplify application installation.
* Test make nuke; parallelize --live-dbs tests
* Move prettier into conda-only dependencies
* Update conda-lock.yml and rendered conda environment files.
* Remove action test file hashlog
* Remove merge markers.
* Remove transitive astroid dependency that's now correctly included in solve.
* Use the real immature library version of dagster-postgres (0.21.6)
  rather than the accidentally packaged 1.5.6 version found in conda.
  We'll need to keep an eye out for when dagster-postgres graduates
  to the stable versioning and update it. This is a bit of a mess
  because of some broken automation in the conda packaging for dagster
  which has now been fixed.
* Update "make pudl" to remove the old PUDL DB and reinitialize with
  alembic, rather than writing to the DB that already exists.
* Fixed some groupby.agg() deprecation warnings.
* Fix dagster-postgres version (again).
* Update username in path to settings file
* Avoid bugs in ferc_to_sqlite --clobber; don't use cache_dir for pip install.
* Make FERC extraction output removal more specific.
* Bump numpy and numba minimum versions.
* Bump black version in pre-commit
* Bump ruff pre-commit hook version

.github/workflows/build-deploy-pudl.yml

@@ -117,8 +117,8 @@ jobs:
             --container-env DAGSTER_PG_PASSWORD="$DAGSTER_PG_PASSWORD" \
             --container-env DAGSTER_PG_HOST="104.154.182.24" \
             --container-env DAGSTER_PG_DB="dagster-storage" \
-            --container-env PUDL_SETTINGS_YML="/home/catalyst/src/pudl/package_data/settings/etl_full.yml" \
             --container-env FLY_ACCESS_TOKEN=${{ secrets.FLY_ACCESS_TOKEN }} \
+            --container-env PUDL_SETTINGS_YML="/home/mambauser/src/pudl/package_data/settings/etl_full.yml" \
 
       # Start the VM
       - name: Start the deploy-pudl-vm

.github/workflows/tox-pytest.yml

@@ -34,7 +34,6 @@ jobs:
           environment-file: environments/conda-lock.yml
           environment-name: pudl-dev
           cache-environment: true
-          create-args: --category main dev docs test datasette
 
       - name: Log environment details
         run: |
@@ -74,7 +73,6 @@ jobs:
           environment-file: environments/conda-lock.yml
           environment-name: pudl-dev
           cache-environment: true
-          create-args: --category main dev docs test datasette
 
       - name: Log environment details
         run: |
@@ -125,7 +123,6 @@ jobs:
           environment-file: environments/conda-lock.yml
           environment-name: pudl-dev
           cache-environment: true
-          create-args: --category main dev docs test datasette
 
       - name: Log environment details
         run: |

.readthedocs.yaml

@@ -10,7 +10,7 @@ version: 2
 build:
   os: ubuntu-22.04
   tools:
-    python: mambaforge-4.10
+    python: mambaforge-22.9
 
 # Define the python environment using conda / mamba
 conda:

Makefile

@@ -5,7 +5,6 @@ coverage_report := coverage report --sort=cover
 pytest_args := --durations 20 ${pytest_covargs} ${gcs_cache_path}
 etl_fast_yml := src/pudl/package_data/settings/etl_fast.yml
 etl_full_yml := src/pudl/package_data/settings/etl_full.yml
-pip_install_pudl := pip install --no-deps --editable ./
 
 # We use mamba locally, but micromamba in CI, so choose the right binary:
 ifdef GITHUB_ACTION
@@ -47,25 +46,17 @@ conda-lock.yml: pyproject.toml
 	cd environments && conda-lock render \
 		--kind env \
 		--dev-dependencies \
-		--extras docs \
-		--extras datasette \
 		conda-lock.yml
 	prettier --write environments/*.yml
 
 # Create the pudl-dev conda environment based on the universal lockfile
 .PHONY: pudl-dev
 pudl-dev: conda-lock.yml
-	conda-lock install \
-		--name pudl-dev \
-		--${mamba} \
-		--dev \
-		--extras docs \
-		--extras datasette \
-		environments/conda-lock.yml
+	conda-lock install --name pudl-dev --${mamba} --dev environments/conda-lock.yml
 
 .PHONY: install-pudl
 install-pudl: pudl-dev
-	${mamba} run --name pudl-dev pip install --no-deps --editable .
+	${mamba} run --name pudl-dev pip install --no-cache-dir --no-deps --editable .
 
 ########################################################################################
 # Build documentation for local use or testing
@@ -92,19 +83,24 @@ docs-build: docs-clean
 ########################################################################################
 
 # Extract all FERC DBF and XBRL data to SQLite.
-ferc1.sqlite ferc1_xbrl.sqlite:
+.PHONY: ferc
+ferc:
+	rm -f ${PUDL_OUTPUT}/ferc*.sqlite
+	rm -f ${PUDL_OUTPUT}/ferc*_xbrl_datapackage.json
+	rm -f ${PUDL_OUTPUT}/ferc*_xbrl_taxonomy_metadata.json
 	coverage run ${covargs} -- \
 		src/pudl/ferc_to_sqlite/cli.py \
-		--clobber \
 		${gcs_cache_path} \
 		${etl_full_yml}
 
-# Run the full PUDL ETL
-pudl.sqlite:
-	coverage run ${covargs} -- \
-		src/pudl/cli/etl.py \
-		${gcs_cache_path} \
-		${etl_full_yml}
+# Remove the existing PUDL DB if it exists.
+# Create a new empty DB using alembic.
+# Run the full PUDL ETL.
+.PHONY: pudl
+pudl:
+	rm -f ${PUDL_OUTPUT}/pudl.sqlite
+	alembic upgrade head
+	coverage run ${covargs} -- src/pudl/cli/etl.py ${gcs_cache_path} ${etl_full_yml}
 
 ########################################################################################
 # pytest
@@ -140,11 +136,10 @@ pytest-validate:
 # Backgrounding the data validation and integration tests and using wait allows them to
 # run in parallel.
 .PHONY: nuke
-nuke: coverage-erase docs-build pytest-unit ferc1.sqlite ferc1_xbrl.sqlite pudl.sqlite
+nuke: coverage-erase docs-build pytest-unit ferc pudl
 	pudl_check_fks
-	pytest ${pytest_args} --live-dbs --etl-settings ${etl_full_yml} test/integration & \
-	pytest ${pytest_args} --live-dbs test/validate & \
-	wait
+	pytest ${pytest_args} -n auto --live-dbs --etl-settings ${etl_full_yml} test/integration
+	pytest ${pytest_args} -n auto --live-dbs test/validate
 	${coverage_report}
 
 # Check that designated Jupyter notebooks can be run against the current DB

docker/Dockerfile

@@ -46,7 +46,7 @@ COPY docker/dagster.yaml ${DAGSTER_HOME}/dagster.yaml
 
 # Create a conda environment based on the specification in the repo
 COPY environments/conda-lock.yml environments/conda-lock.yml
-RUN micromamba create --prefix ${CONDA_PREFIX} --yes --category main dev docs test datasette --file environments/conda-lock.yml && \
+RUN micromamba create --prefix ${CONDA_PREFIX} --yes --file environments/conda-lock.yml && \
     micromamba clean -afy
 # Copy the cloned pudl repository into the user's home directory
 COPY --chown=${MAMBA_USER}:${MAMBA_USER} . ${CONTAINER_HOME}

docker/gcp_pudl_etl.sh

@@ -24,21 +24,23 @@ function run_pudl_etl() {
     alembic upgrade head && \
     pudl_setup && \
     ferc_to_sqlite \
-        --loglevel=DEBUG \
-        --gcs-cache-path=gs://internal-zenodo-cache.catalyst.coop \
-        --workers=8 \
+        --loglevel DEBUG \
+        --gcs-cache-path gs://internal-zenodo-cache.catalyst.coop \
+        --workers 8 \
         $PUDL_SETTINGS_YML && \
     pudl_etl \
         --loglevel DEBUG \
         --gcs-cache-path gs://internal-zenodo-cache.catalyst.coop \
         $PUDL_SETTINGS_YML && \
     pytest \
-        --gcs-cache-path=gs://internal-zenodo-cache.catalyst.coop \
-        --etl-settings=$PUDL_SETTINGS_YML \
+        -n auto \
+        --gcs-cache-path gs://internal-zenodo-cache.catalyst.coop \
+        --etl-settings $PUDL_SETTINGS_YML \
         --live-dbs test/integration test/unit && \
     pytest \
-        --gcs-cache-path=gs://internal-zenodo-cache.catalyst.coop \
-        --etl-settings=$PUDL_SETTINGS_YML \
+        -n auto \
+        --gcs-cache-path gs://internal-zenodo-cache.catalyst.coop \
+        --etl-settings $PUDL_SETTINGS_YML \
         --live-dbs test/validate
 }