Very minor but widespread formatting changes from ruff 0.3.0

.pre-commit-config.yaml

@@ -29,7 +29,7 @@ repos:
   # Formatters: hooks that re-write Python & documentation files
   ####################################################################################
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.2.2
+    rev: v0.3.0
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

devtools/print_requirements.py

@@ -1,5 +1,6 @@
 #!/usr/bin/python3
 """Print out install requirements from setup.py for use with pip install."""
+
 import distutils.core
 
 setup = distutils.core.run_setup("setup.py")

devtools/sqlite_to_duckdb.py

@@ -1,5 +1,6 @@
 #! /usr/bin/env python
 """A naive script for converting SQLite to DuckDB."""
+
 import logging
 from pathlib import Path
 

devtools/zenodo/zenodo_data_release.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 """Script to sync a directory up to Zenodo."""
+
 import datetime
 import logging
 import os

src/pudl/analysis/__init__.py

@@ -5,6 +5,7 @@
 rich library of tools that show how the data can be put to use. We may also generate
 post-ETL derived database tables for distribution at some point.
 """
+
 from . import (
     allocate_gen_fuel,
     epacamd_eia,

src/pudl/analysis/mcoe.py

@@ -1,4 +1,5 @@
 """A module with functions to aid generating MCOE."""
+
 from typing import Literal
 
 import pandas as pd

src/pudl/analysis/ml_tools/__init__.py

@@ -1,4 +1,5 @@
 """Implements shared tooling for machine learning models in PUDL."""
+
 from . import models
 
 

src/pudl/analysis/ml_tools/experiment_tracking.py

@@ -8,6 +8,7 @@
 to a file named 'experiments.sqlite' in the base directory of your PUDL repo, but
 this is a configurable value, which can be found in the dagster UI.
 """
+
 from collections.abc import Callable
 from pathlib import Path
 

src/pudl/analysis/ml_tools/models.py

@@ -17,6 +17,7 @@
 values can be edited here. This configuration will override both default values and
 yaml configuration, but will only be used for a single run.
 """
+
 import importlib
 
 import yaml

src/pudl/analysis/plant_parts_eia.py

@@ -176,6 +176,7 @@
     parts_compiler = MakePlantParts(pudl_out)
     plant_parts_eia = parts_compiler.execute(gens_mega=gens_mega)
 """
+
 from collections import OrderedDict
 from copy import deepcopy
 from importlib import resources

src/pudl/analysis/record_linkage/__init__.py

@@ -1,4 +1,5 @@
 """This module implements models for various forms of record linkage."""
+
 from . import (
     classify_plants_ferc1,
     eia_ferc1_model_config,

src/pudl/analysis/record_linkage/eia_ferc1_record_linkage.py

@@ -202,9 +202,9 @@ def get_training_data_df(inputs):
     )
     train_df.loc[:, "source_dataset_r"] = "ferc_df"
     train_df.loc[:, "source_dataset_l"] = "eia_df"
-    train_df.loc[
-        :, "clerical_match_score"
-    ] = 1  # this column shows that all these labels are positive labels
+    train_df.loc[:, "clerical_match_score"] = (
+        1  # this column shows that all these labels are positive labels
+    )
     return train_df
 
 
@@ -616,9 +616,9 @@ def override_bad_predictions(
     override_df.loc[:, "match_type"] = "prediction; not in training data"
     override_df.loc[override_rows, "match_type"] = "incorrect prediction; overwritten"
     override_df.loc[correct_rows, "match_type"] = "correct match"
-    override_df.loc[
-        incorrect_rows, "match_type"
-    ] = "incorrect prediction; no predicted match"
+    override_df.loc[incorrect_rows, "match_type"] = (
+        "incorrect prediction; no predicted match"
+    )
     # print out stats
     percent_correct = len(override_df[override_df.match_type == "correct match"]) / len(
         train_df

src/pudl/analysis/record_linkage/eia_ferc1_train.py

@@ -116,9 +116,9 @@ def _pct_diff(df, col) -> pd.DataFrame:
     # Fed in the _pct_diff column so make sure it is neutral for this analysis
     col = col.replace("_pct_diff", "")
     # Fill in the _pct_diff column with the actual percent difference value
-    df.loc[
-        (df[f"{col}_eia"] > 0) & (df[f"{col}_ferc1"] > 0), f"{col}_pct_diff"
-    ] = round(((df[f"{col}_ferc1"] - df[f"{col}_eia"]) / df[f"{col}_ferc1"] * 100), 2)
+    df.loc[(df[f"{col}_eia"] > 0) & (df[f"{col}_ferc1"] > 0), f"{col}_pct_diff"] = (
+        round(((df[f"{col}_ferc1"] - df[f"{col}_eia"]) / df[f"{col}_ferc1"] * 100), 2)
+    )
 
     return df
 

src/pudl/analysis/record_linkage/link_cross_year.py

@@ -1,4 +1,5 @@
 """Define a record linkage model interface and implement common functionality."""
+
 from pathlib import Path
 from tempfile import TemporaryDirectory
 
@@ -61,9 +62,9 @@ def __init__(
         year_inds = original_df.groupby("report_year").indices
         for inds in year_inds.values():
             matching_year_inds = np.array(np.meshgrid(inds, inds)).T.reshape(-1, 2)
-            self.distance_matrix[
-                matching_year_inds[:, 0], matching_year_inds[:, 1]
-            ] = config.distance_penalty
+            self.distance_matrix[matching_year_inds[:, 0], matching_year_inds[:, 1]] = (
+                config.distance_penalty
+            )
 
         np.fill_diagonal(self.distance_matrix, 0)
         self.distance_matrix.flush()

src/pudl/analysis/service_territory.py

@@ -5,6 +5,7 @@
 the historical spatial extent of utility and balancing area territories. Output the
 resulting geometries for use in other applications.
 """
+
 import math
 import pathlib
 import sys

src/pudl/analysis/spatial.py

@@ -1,4 +1,5 @@
 """Spatial operations for demand allocation."""
+
 import itertools
 import warnings
 from collections.abc import Callable, Iterable

src/pudl/analysis/state_demand.py

@@ -16,6 +16,7 @@
 Additional predictive spatial variables will be required to obtain more granular
 electricity demand estimates (e.g. at the county level).
 """
+
 import datetime
 from collections.abc import Iterable
 from typing import Any
@@ -280,9 +281,9 @@ def load_hourly_demand_matrix_ferc714(
         of each `respondent_id_ferc714` and reporting `year` (int).
     """
     # Convert UTC to local time (ignoring daylight savings)
-    out_ferc714__hourly_planning_area_demand[
-        "utc_offset"
-    ] = out_ferc714__hourly_planning_area_demand["timezone"].map(STANDARD_UTC_OFFSETS)
+    out_ferc714__hourly_planning_area_demand["utc_offset"] = (
+        out_ferc714__hourly_planning_area_demand["timezone"].map(STANDARD_UTC_OFFSETS)
+    )
     out_ferc714__hourly_planning_area_demand["datetime"] = utc_to_local(
         out_ferc714__hourly_planning_area_demand["utc_datetime"],
         out_ferc714__hourly_planning_area_demand["utc_offset"],
@@ -292,9 +293,9 @@ def load_hourly_demand_matrix_ferc714(
         index="datetime", columns="respondent_id_ferc714", values="demand_mwh"
     )
     # List timezone by year for each respondent
-    out_ferc714__hourly_planning_area_demand[
-        "year"
-    ] = out_ferc714__hourly_planning_area_demand["report_date"].dt.year
+    out_ferc714__hourly_planning_area_demand["year"] = (
+        out_ferc714__hourly_planning_area_demand["report_date"].dt.year
+    )
     utc_offset = out_ferc714__hourly_planning_area_demand.groupby(
         ["respondent_id_ferc714", "year"], as_index=False
     )["utc_offset"].first()

src/pudl/analysis/timeseries_cleaning.py

@@ -28,6 +28,7 @@
 * https://arxiv.org/abs/2008.03194
 * https://github.com/xinychen/tensor-learning
 """
+
 import functools
 import warnings
 from collections.abc import Iterable, Sequence

src/pudl/convert/__init__.py

@@ -4,6 +4,7 @@
 to another, both independent of and within the context of the ETL pipeline.
 This subpackage collects those tools together in one place.
 """
+
 from . import (
     censusdp1tract_to_sqlite,
     metadata_to_rst,

src/pudl/etl/__init__.py

@@ -1,4 +1,5 @@
 """Dagster definitions for the PUDL ETL and Output tables."""
+
 import importlib.resources
 import itertools
 import warnings

src/pudl/etl/check_foreign_keys.py

@@ -1,4 +1,5 @@
 """Check that foreign key constraints in the PUDL database are respected."""
+
 import pathlib
 import sys
 

src/pudl/etl/cli.py

@@ -1,4 +1,5 @@
 """A command line interface (CLI) to the main PUDL ETL functionality."""
+
 import pathlib
 import sys
 from collections.abc import Callable

src/pudl/etl/eia_bulk_elec_assets.py

@@ -1,4 +1,5 @@
 """EIA Bulk Electricty Aggregate assets."""
+
 from dagster import asset
 
 import pudl

src/pudl/etl/epacems_assets.py

@@ -8,6 +8,7 @@
 for processing each year of EPA CEMS data and execute these ops in parallel. For more information
 see: https://docs.dagster.io/concepts/ops-jobs-graphs/dynamic-graphs and https://docs.dagster.io/concepts/assets/graph-backed-assets.
 """
+
 from collections import namedtuple
 from pathlib import Path
 

src/pudl/etl/glue_assets.py

@@ -1,4 +1,5 @@
 """FERC and EIA and EPA CAMD glue assets."""
+
 import networkx as nx
 import pandas as pd
 from dagster import AssetOut, Output, asset, multi_asset

src/pudl/etl/static_assets.py

@@ -1,4 +1,5 @@
 """Dagster assets of static data tables."""
+
 from typing import Literal
 
 import pandas as pd
@@ -51,9 +52,9 @@ def static_pudl_tables(context):
     dataset_settings = context.resources.dataset_settings
 
     static_pudl_tables_dict = {"core_pudl__codes_subdivisions": POLITICAL_SUBDIVISIONS}
-    static_pudl_tables_dict[
-        "core_pudl__codes_datasources"
-    ] = dataset_settings.make_datasources_table(ds)
+    static_pudl_tables_dict["core_pudl__codes_datasources"] = (
+        dataset_settings.make_datasources_table(ds)
+    )
     return (
         Output(output_name=table_name, value=df)
         for table_name, df in static_pudl_tables_dict.items()

src/pudl/extract/__init__.py

@@ -7,6 +7,7 @@
 are ready for normalization and data cleaning by the data source specific modules in the
 :mod:`pudl.transform` subpackage.
 """
+
 from . import (
     eia176,
     eia860,

src/pudl/extract/csv.py

@@ -1,4 +1,5 @@
 """Extractor for CSV data."""
+
 from csv import DictReader
 from importlib import resources
 from zipfile import ZipFile

src/pudl/extract/dbf.py

@@ -1,4 +1,5 @@
 """Generalized DBF extractor for FERC data."""
+
 import contextlib
 import csv
 import importlib.resources

src/pudl/extract/eia860.py

@@ -4,6 +4,7 @@
 
 This code is for use analyzing EIA Form 860 data.
 """
+
 import pandas as pd
 from dagster import AssetOut, Output, multi_asset
 

src/pudl/extract/eia861.py

@@ -4,6 +4,7 @@
 
 This code is for use analyzing EIA Form 861 data.
 """
+
 import warnings
 
 import pandas as pd

src/pudl/extract/eia923.py

@@ -5,6 +5,7 @@
 This code is for use analyzing EIA Form 923 data. Currenly only years 2009-2016 work, as
 they share nearly identical file formatting.
 """
+
 import pandas as pd
 from dagster import AssetOut, Output, multi_asset
 

src/pudl/extract/eia_bulk_elec.py

@@ -11,6 +11,7 @@
 tables: one of metadata and one of timeseries. That is the format delivered by this
 module.
 """
+
 import warnings
 from io import BytesIO
 from pathlib import Path

src/pudl/extract/epacems.py

@@ -19,6 +19,7 @@
 Hence, we've called it `plant_id_epa` until it gets transformed into `plant_id_eia`
 during the transform process with help from the crosswalk.
 """
+
 from pathlib import Path
 from typing import Annotated
 
@@ -173,9 +174,12 @@ def __init__(self, datastore: Datastore):
 
     def get_data_frame(self, partition: EpaCemsPartition) -> pd.DataFrame:
         """Constructs dataframe from a zipfile for a given (year_quarter) partition."""
-        with self.datastore.get_zipfile_resource(
-            "epacems", **partition.get_filters()
-        ) as zf, zf.open(str(partition.get_quarterly_file()), "r") as csv_file:
+        with (
+            self.datastore.get_zipfile_resource(
+                "epacems", **partition.get_filters()
+            ) as zf,
+            zf.open(str(partition.get_quarterly_file()), "r") as csv_file,
+        ):
             df = self._csv_to_dataframe(
                 csv_file,
                 ignore_cols=API_IGNORE_COLS,

src/pudl/extract/excel.py

@@ -1,4 +1,5 @@
 """Load excel metadata CSV files form a python data package."""
+
 import importlib.resources
 import pathlib
 import re

src/pudl/extract/ferc.py

@@ -1,6 +1,5 @@
 """Hooks to integrate ferc to sqlite functionality into dagster graph."""
 
-
 import pudl
 from pudl.extract.ferc1 import Ferc1DbfExtractor
 from pudl.extract.ferc2 import Ferc2DbfExtractor

src/pudl/extract/ferc1.py

@@ -66,6 +66,7 @@
 
 https://data.catalyst.coop/ferc1
 """
+
 import json
 from itertools import chain
 from pathlib import Path

src/pudl/extract/ferc714.py

@@ -1,4 +1,5 @@
 """Routines used for extracting the raw FERC 714 data."""
+
 from collections import OrderedDict
 
 import pandas as pd
@@ -84,9 +85,10 @@ def _extract_raw_ferc714(context):
         logger.info(
             f"Extracting {table_name} from CSV into pandas DataFrame (years: {years})."
         )
-        with ds.get_zipfile_resource("ferc714", name="ferc714.zip") as zf, zf.open(
-            FERC714_FILES[table_name]["name"]
-        ) as csv_file:
+        with (
+            ds.get_zipfile_resource("ferc714", name="ferc714.zip") as zf,
+            zf.open(FERC714_FILES[table_name]["name"]) as csv_file,
+        ):
             df = pd.read_csv(
                 csv_file,
                 encoding=FERC714_FILES[table_name]["encoding"],

src/pudl/extract/phmsagas.py

@@ -3,7 +3,6 @@
 This modules pulls data from PHMSA's published Excel spreadsheets.
 """
 
-
 import pandas as pd
 from dagster import AssetOut, Output, multi_asset
 

src/pudl/extract/xbrl.py

@@ -1,4 +1,5 @@
 """Generic extractor for all FERC XBRL data."""
+
 import io
 from collections.abc import Callable
 from datetime import date

src/pudl/ferc_to_sqlite/__init__.py

@@ -1,4 +1,5 @@
 """Dagster definitions for the FERC to SQLite process."""
+
 import importlib.resources
 
 from dagster import Definitions, graph