Lots of ruff fixes

create_trace_mapping.py

@@ -1,3 +1,7 @@
+"""Create trace mapping."""
+
+from pathlib import Path
+
 import yaml
 from nemosis import static_table
 
@@ -20,14 +24,14 @@
 solar_generator_mapping = draft_solar_generator_to_trace_mapping(
     solar_gens, solar_traces
 )
-with open("draft_solar_generator_mapping.yaml", "w") as file:
+with Path.open("draft_solar_generator_mapping.yaml", "w") as file:
     yaml.dump(solar_generator_mapping, file, default_flow_style=False)
 
 
 solar_traces = "/media/nick/Samsung_T5/isp_2024_data/trace_data/solar/solar_2023"
 rezs = gets_rezs(workbook)
 solar_rez_mapping = draft_solar_rez_mapping(rezs, solar_traces)
-with open("solar_area_mapping.yaml", "w") as file:
+with Path.open("solar_area_mapping.yaml", "w") as file:
     yaml.dump(solar_rez_mapping, file, default_flow_style=False)
 
 duids_and_station_names = static_table(
@@ -48,12 +52,12 @@
 wind_generator_mapping = draft_wind_generator_to_trace_mapping(
     wind_gens, wind_duids_and_station_names, wind_traces
 )
-with open("draft_wind_generator_mapping.yaml", "w") as file:
+with Path.open("draft_wind_generator_mapping.yaml", "w") as file:
     yaml.dump(wind_generator_mapping, file, default_flow_style=False, sort_keys=False)
 
 
 wind_traces = "D:/isp_2024_data/trace_data/wind/wind_2023"
 rezs = gets_rezs(workbook)
 wind_rez_mapping = draft_wind_rez_mapping(rezs, wind_traces)
-with open("draft_wind_rez_mapping.yaml", "w") as file:
+with Path.open("draft_wind_rez_mapping.yaml", "w") as file:
     yaml.dump(wind_rez_mapping, file, default_flow_style=False)

generator_to_trace_draft_mapper.py

@@ -22,25 +22,23 @@ def get_all_generators(workbook_filepath):
     additional_gens["Status"] = "additional"
 
     existing_gens = existing_gens.rename(
-        columns={existing_gens.columns.values[0]: "Generator"}
+        columns={existing_gens.columns.to_numpy[0]: "Generator"}
     )
     committed_gens = committed_gens.rename(
-        columns={committed_gens.columns.values[0]: "Generator"}
+        columns={committed_gens.columns.to_numpy[0]: "Generator"}
     )
     anticipated_gens = anticipated_gens.rename(
-        columns={anticipated_gens.columns.values[0]: "Generator"}
+        columns={anticipated_gens.columns.to_numpy[0]: "Generator"}
     )
     additional_gens = additional_gens.rename(
-        columns={additional_gens.columns.values[0]: "Generator"}
+        columns={additional_gens.columns.to_numpy[0]: "Generator"}
     )
 
     all_gens = pd.concat(
         [existing_gens, committed_gens, anticipated_gens, additional_gens]
     )
 
-    all_gens = all_gens.loc[:, ["Generator", "Technology type"]]
-
-    return all_gens
+    return all_gens.loc[:, ["Generator", "Technology type"]]
 
 
 def gets_rezs(workbook_filepath):
@@ -53,15 +51,12 @@ def gets_rezs(workbook_filepath):
     )
     workbook = Parser(workbook_filepath)
     rezs = workbook.get_table_from_config(table_config)
-    rezs = rezs.loc[:, ["Name"]]
-    return rezs
+    return rezs.loc[:, ["Name"]]
 
 
 def find_best_match(plant_name, csv_files):
     best_match = process.extractOne(plant_name, csv_files, scorer=fuzz.token_set_ratio)
-    best_match = best_match[0] if best_match else None
-    best_match = best_match
-    return best_match
+    return best_match[0] if best_match else None
 
 
 def find_best_match_two_columns(row, csv_files):
@@ -91,17 +86,15 @@ def draft_solar_generator_to_trace_mapping(solar_generators, solar_trace_directo
     solar_generators["CSVFile"] = solar_generators["Generator"].apply(
         lambda x: find_best_match(x, csv_project_names)
     )
-    solar_generators = solar_generators.set_index("Generator")["CSVFile"].to_dict()
-    return solar_generators
+    return solar_generators.set_index("Generator")["CSVFile"].to_dict()
 
 
 def draft_solar_rez_mapping(rezs, rezs_trace_directory):
     csv_file_names = [f for f in os.listdir(rezs_trace_directory) if f.endswith(".csv")]
     csv_file_metadata = [extract_solar_trace_metadata(f) for f in csv_file_names]
     csv_rez_names = [f["name"] for f in csv_file_metadata if f["file_type"] == "area"]
     rezs["CSVFile"] = rezs["Name"].apply(lambda x: find_best_match(x, csv_rez_names))
-    rezs = rezs.set_index("Name")["CSVFile"].to_dict()
-    return rezs
+    return rezs.set_index("Name")["CSVFile"].to_dict()
 
 
 def draft_wind_generator_to_trace_mapping(
@@ -118,8 +111,8 @@ def draft_wind_generator_to_trace_mapping(
     wind_generators["Station Name"] = wind_generators["Generator"].apply(
         lambda x: find_best_match(x, wind_station_names)
     )
-    wind_generators = pd.merge(
-        wind_generators, wind_duids_and_station_names, how="left", on="Station Name"
+    wind_generators = wind_generators.merge(
+        wind_duids_and_station_names, how="left", on="Station Name"
     )
     wind_generators = wind_generators.drop_duplicates(["Generator"])
 
@@ -131,14 +124,12 @@ def draft_wind_generator_to_trace_mapping(
         :, ["Generator", "Station Name", "DUID", "CSVFile"]
     ]
 
-    wind_generators = wind_generators.set_index("Generator").to_dict(orient="index")
-    return wind_generators
+    return wind_generators.set_index("Generator").to_dict(orient="index")
 
 
 def draft_wind_rez_mapping(rezs, rezs_trace_directory):
     csv_file_names = [f for f in os.listdir(rezs_trace_directory) if f.endswith(".csv")]
     csv_file_metadata = [extract_wind_trace_metadata(f) for f in csv_file_names]
     csv_rez_names = [f["name"] for f in csv_file_metadata if f["file_type"] == "area"]
     rezs["CSVFile"] = rezs["Name"].apply(lambda x: find_best_match(x, csv_rez_names))
-    rezs = rezs.set_index("Name")["CSVFile"].to_dict()
-    return rezs
+    return rezs.set_index("Name")["CSVFile"].to_dict()

noxfile.py

@@ -1,3 +1,5 @@
+"""Nox configuration file."""
+
 import nox
 
 nox.options.default_venv_backend = "uv"

src/isp_trace_parser/construct_reference_year_mapping.py

@@ -35,4 +35,4 @@ def construct_reference_year_mapping(
         reference_years = (
             reference_years * full_reference_year_cycles
         ) + reference_years[:partial_cycle_length]
-    return dict(zip(years, reference_years))
+    return dict(zip(years, reference_years, strict=True))

src/isp_trace_parser/demand_traces.py

@@ -1,7 +1,7 @@
 import functools
 import os
 from pathlib import Path
-from typing import Literal, Optional
+from typing import Literal
 
 import polars as pl
 from joblib import Parallel, delayed
@@ -46,15 +46,16 @@ class DemandMetadataFilter(BaseModel):
         reference_year: list of ints specifying reference_years
     """
 
-    subregion: Optional[list[str]] = None
-    scenario: Optional[
+    subregion: list[str] | None = None
+    scenario: (
         list[Literal["Step Change", "Progressive Change", "Green Energy Exports"]]
-    ] = None
-    poe: Optional[list[Literal["POE50", "POE10"]]] = None
-    demand_type: Optional[
-        list[Literal["OPSO_MODELLING", "OPSO_MODELLING_PVLITE", "PV_TOT"]]
-    ] = None
-    reference_year: Optional[list[int]] = None
+        | None
+    ) = None
+    poe: list[Literal["POE50", "POE10"]] | None = None
+    demand_type: (
+        list[Literal["OPSO_MODELLING", "OPSO_MODELLING_PVLITE", "PV_TOT"]] | None
+    ) = None
+    reference_year: list[int] | None = None
 
 
 @validate_call
@@ -270,4 +271,4 @@ def extract_metadata_for_all_demand_files(
         A dictionary with filepaths as keys and metadata dicts as values.
     """
     file_metadata = [extract_demand_trace_metadata(str(f.name)) for f in filenames]
-    return dict(zip(filenames, file_metadata))
+    return dict(zip(filenames, file_metadata, strict=True))

src/isp_trace_parser/get_data.py

@@ -1,6 +1,6 @@
 import datetime
 from pathlib import Path
-from typing import List, Literal
+from typing import Literal
 
 import pandas as pd
 import polars as pl
@@ -37,19 +37,20 @@ def _year_range_to_dt_range(
             end_year, 7, 1
         )
 
-    elif year_type == "calendar":
+    if year_type == "calendar":
         return datetime.datetime(start_year, 1, 1), datetime.datetime(
             end_year + 1, 1, 1
         )
+    raise ValueError(year_type)
 
 
 def _query_parquet_single_reference_year(
     start_year: int,
     end_year: int,
     reference_year: int,
     directory: str | Path,
-    filters: dict[str, any] = None,
-    select_columns: list[str] = None,
+    filters: dict[str, any] | None = None,
+    select_columns: list[str] | None = None,
     year_type: Literal["fy", "calendar"] = "fy",
 ) -> pd.DataFrame:
     """
@@ -103,14 +104,14 @@ def _query_parquet_single_reference_year(
         # Otherwise select all columns
         columns_to_select = df_lazy.columns
 
-    df = (
+    dframe = (
         df_lazy.filter(filter_expr)
         .select(*columns_to_select)
         .sort("datetime")
         .collect()
     )
 
-    return df.to_pandas()
+    return dframe.to_pandas()
 
 
 def _query_parquet_multiple_reference_years(
@@ -136,19 +137,18 @@ def _query_parquet_multiple_reference_years(
                 start_year=year, end_year=year, reference_year=reference_year, **kwargs
             )
         )
-    data = pd.concat(data).reset_index(drop=True)
-    return data
+    return pd.concat(data).reset_index(drop=True)
 
 
 @validate_call
 def get_project_single_reference_year(
     start_year: int,
     end_year: int,
     reference_year: int,
-    project: str | List,
+    project: str | list,
     directory: str | Path,
     year_type: Literal["fy", "calendar"] = "fy",
-    select_columns: list[str] = None,
+    select_columns: list[str] | None = None,
 ):
     """
     Query project trace data for a single reference year.
@@ -237,11 +237,11 @@ def get_zone_single_reference_year(
     start_year: int,
     end_year: int,
     reference_year: int,
-    zone: str | List,
-    resource_type: str | List,
+    zone: str | list,
+    resource_type: str | list,
     directory: str | Path,
     year_type: Literal["fy", "calendar"] = "fy",
-    select_columns: list[str] = None,
+    select_columns: list[str] | None = None,
 ):
     """
     Query zone trace data for a single reference year.
@@ -333,13 +333,13 @@ def get_demand_single_reference_year(
     start_year: int,
     end_year: int,
     reference_year: int,
-    scenario: str | List,
-    subregion: str | List,
-    demand_type: str | List,
-    poe: str | List,
+    scenario: str | list,
+    subregion: str | list,
+    demand_type: str | list,
+    poe: str | list,
     directory: str | Path,
     year_type: Literal["fy", "calendar"] = "fy",
-    select_columns: list[str] = None,
+    select_columns: list[str] | None = None,
 ):
     """
     Query demand trace data for a single reference year.
@@ -441,10 +441,10 @@ def get_demand_single_reference_year(
 @validate_call
 def get_project_multiple_reference_years(
     reference_year_mapping: dict[int, int],
-    project: str | List,
+    project: str | list,
     directory: str | Path,
     year_type: Literal["fy", "calendar"] = "fy",
-    select_columns: list[str] = None,
+    select_columns: list[str] | None = None,
 ):
     """
     Query project trace data across multiple reference years.
@@ -530,11 +530,11 @@ def get_project_multiple_reference_years(
 @validate_call
 def get_zone_multiple_reference_years(
     reference_year_mapping: dict[int, int],
-    zone: str | List,
-    resource_type: str | List,
+    zone: str | list,
+    resource_type: str | list,
     directory: str | Path,
     year_type: Literal["fy", "calendar"] = "fy",
-    select_columns: list[str] = None,
+    select_columns: list[str] | None = None,
 ):
     """
     Query zone trace data across multiple reference years.
@@ -623,13 +623,13 @@ def get_zone_multiple_reference_years(
 @validate_call
 def get_demand_multiple_reference_years(
     reference_year_mapping: dict[int, int],
-    scenario: str | List,
-    subregion: str | List,
-    demand_type: str | List,
-    poe: str | List,
+    scenario: str | list,
+    subregion: str | list,
+    demand_type: str | list,
+    poe: str | list,
     directory: str | Path,
     year_type: Literal["fy", "calendar"] = "fy",
-    select_columns: list[str] = None,
+    select_columns: list[str] | None = None,
 ):
     """
     Query demand trace data across multiple reference years.

src/isp_trace_parser/input_validation.py

@@ -4,7 +4,8 @@
 def input_directory(path: Path | str) -> Path:
     path = is_valid_path(path)
     if not path.is_dir():
-        raise ValueError(f"Directory {path} does not exist")
+        msg = f"Directory {path} does not exist"
+        raise ValueError(msg)
     return path
 
 
@@ -16,9 +17,11 @@ def is_valid_path(path: str | Path) -> Path:
     try:
         return Path(path)
     except (TypeError, ValueError):
-        raise ValueError(f"Invalid parsed directory path: {path}")
+        msg = f"Invalid parsed directory path: {path}"
+        raise ValueError(msg) from None
 
 
-def start_year_before_end_year(start_year, end_year):
+def start_year_before_end_year(start_year, end_year) -> None:
     if end_year < start_year:
-        raise ValueError(f"Start year {end_year} < end year {start_year}")
+        msg = f"Start year {end_year} < end year {start_year}"
+        raise ValueError(msg)

src/isp_trace_parser/metadata_extractors.py

@@ -28,7 +28,8 @@ def extract_solar_trace_metadata(filename):
         match_data["reference_year"] = int(match_data["reference_year"])
         return match_data
 
-    raise ValueError(f"Filename '{filename}' does not match the expected pattern")
+    msg = f"Filename '{filename}' does not match the expected pattern"
+    raise ValueError(msg)
 
 
 def extract_wind_trace_metadata(filename):
@@ -57,7 +58,8 @@ def extract_wind_trace_metadata(filename):
         match_data["reference_year"] = int(match_data["reference_year"])
         return match_data
 
-    raise ValueError(f"Filename '{filename}' does not match the expected pattern")
+    msg = f"Filename '{filename}' does not match the expected pattern"
+    raise ValueError(msg)
 
 
 def extract_demand_trace_metadata(filename):
@@ -75,6 +77,7 @@ def extract_demand_trace_metadata(filename):
         match_data = match.groupdict()
         match_data["reference_year"] = int(match_data["reference_year"])
         return match_data
-    else:
-        # If the pattern does not match, raise an error or return None
-        raise ValueError(f"Filename '{filename}' does not match the expected pattern")
+
+    # If the pattern does not match, raise an error or return None
+    msg = f"Filename '{filename}' does not match the expected pattern"
+    raise ValueError(msg)