formatting

csiro-energy-systems · Feb 20, 2024 · dc07fae · dc07fae
1 parent e12dfe6
commit dc07fae
Show file tree

Hide file tree

Showing 6 changed files with 63 additions and 215 deletions.
diff --git a/utils/dd_to_csv.py b/utils/dd_to_csv.py
@@ -47,9 +47,7 @@ def parse_parameter_values_from_file(
             while data[index].strip() == "":
                 index += 1
 
-            param_name = data[index].replace(
-                " ' '/", ""
-            )  # param_name is followed by this pattern
+            param_name = data[index].replace(" ' '/", "")  # param_name is followed by this pattern
 
             index += 1
             param_data = []
@@ -64,9 +62,7 @@ def parse_parameter_values_from_file(
                     attributes = words[0].split(".")
                     attributes = [a if " " in a else a.strip("'") for a in attributes]
                 else:
-                    raise ValueError(
-                        f"Unexpected number of spaces in parameter value setting: {data[index]}"
-                    )
+                    raise ValueError(f"Unexpected number of spaces in parameter value setting: {data[index]}")
 
                 value = words[-1]
                 param_data.append([*attributes, value])
@@ -106,9 +102,7 @@ def parse_parameter_values_from_file(
                     text = words[1]
                     set_data.add(tuple([*attributes, text]))
                 else:
-                    raise ValueError(
-                        f"Unexpected number of spaces in set value setting: {data[index]}"
-                    )
+                    raise ValueError(f"Unexpected number of spaces in set value setting: {data[index]}")
 
                 index += 1
 
@@ -140,17 +134,11 @@ def save_data_with_headers(
         try:
             columns = headers_data[param_name]
         except KeyError:
-            raise ValueError(
-                f"Could not find mapping for {param_name} in mapping file."
-            )
+            raise ValueError(f"Could not find mapping for {param_name} in mapping file.")
         for row in param_data:
             if len(row) != len(columns):
-                raise ValueError(
-                    f"Mismatched number of columns for param {param_name} between data ({len(row)}) and mapping ({len(columns)})"
-                )
-        df = pd.DataFrame(
-            data=np.asarray(param_data)[:, 0 : len(columns)], columns=columns
-        )
+                raise ValueError(f"Mismatched number of columns for param {param_name} between data ({len(row)}) and mapping ({len(columns)})")
+        df = pd.DataFrame(data=np.asarray(param_data)[:, 0 : len(columns)], columns=columns)
         df.to_csv(os.path.join(save_dir, param_name + ".csv"), index=False)
 
     return
@@ -171,9 +159,7 @@ def generate_headers_by_attr() -> Dict[str, List[str]]:
     return headers_by_attr
 
 
-def convert_dd_to_tabular(
-    basedir: str, output_dir: str, headers_by_attr: Dict[str, List[str]]
-) -> None:
+def convert_dd_to_tabular(basedir: str, output_dir: str, headers_by_attr: Dict[str, List[str]]) -> None:
     dd_files = [p for p in Path(basedir).rglob("*.dd")]
 
     all_sets = defaultdict(list)
@@ -219,12 +205,8 @@ def convert_dd_to_tabular(
 
 def main(arg_list: None | list[str] = None):
     args_parser = argparse.ArgumentParser()
-    args_parser.add_argument(
-        "input_dir", type=str, help="Input directory containing .dd files."
-    )
-    args_parser.add_argument(
-        "output_dir", type=str, help="Output directory to save the .csv files in."
-    )
+    args_parser.add_argument("input_dir", type=str, help="Input directory containing .dd files.")
+    args_parser.add_argument("output_dir", type=str, help="Output directory to save the .csv files in.")
     args = args_parser.parse_args(arg_list)
     convert_dd_to_tabular(args.input_dir, args.output_dir, generate_headers_by_attr())
 

diff --git a/utils/run_benchmarks.py b/utils/run_benchmarks.py
@@ -90,9 +90,7 @@ def run_gams_gdxdiff(
         return "Error: dd_files not in benchmark"
 
     # Copy GAMS scaffolding
-    scaffolding_folder = path.join(
-        path.dirname(path.realpath(__file__)), "..", "xl2times", "gams_scaffold"
-    )
+    scaffolding_folder = path.join(path.dirname(path.realpath(__file__)), "..", "xl2times", "gams_scaffold")
     shutil.copytree(scaffolding_folder, out_folder, dirs_exist_ok=True)
     # Create link to TIMES source
     if not path.exists(path.join(out_folder, "source")):
@@ -307,9 +305,7 @@ def run_all_benchmarks(
     # The rest of this script checks regressions against main
     # so skip it if we're already on main
     repo = git.Repo(".")  # pyright: ignore
-    origin = (
-        repo.remotes.origin if "origin" in repo.remotes else repo.remotes[0]
-    )  # don't assume remote is called 'origin'
+    origin = repo.remotes.origin if "origin" in repo.remotes else repo.remotes[0]  # don't assume remote is called 'origin'
     origin.fetch("main")
     if "main" not in repo.heads:
         repo.create_head("main", origin.refs.main).set_tracking_branch(origin.refs.main)
@@ -332,9 +328,7 @@ def run_all_benchmarks(
                 result = parse_result(f.readlines()[-1])
             # Use a fake runtime and GAMS result
             results_main.append((benchmark["name"], 999, "--", *result))
-        print(
-            f"Skipped running on main. Using results from {path.join(benchmarks_folder, 'out-main')}"
-        )
+        print(f"Skipped running on main. Using results from {path.join(benchmarks_folder, 'out-main')}")
 
     else:
         if repo.is_dirty():
@@ -396,23 +390,17 @@ def run_all_benchmarks(
     runtime_change = our_time - main_time
 
     print(f"Total runtime: {our_time:.2f}s (main: {main_time:.2f}s)")
-    print(
-        f"Change in runtime (negative == faster): {runtime_change:+.2f}s ({100 * runtime_change / main_time:+.1f}%)"
-    )
+    print(f"Change in runtime (negative == faster): {runtime_change:+.2f}s ({100 * runtime_change / main_time:+.1f}%)")
 
     our_correct = df["Correct"].sum()
     main_correct = df["M Correct"].sum()
     correct_change = our_correct - main_correct
-    print(
-        f"Change in correct rows (higher == better): {correct_change:+d} ({100 * correct_change / main_correct:+.1f}%)"
-    )
+    print(f"Change in correct rows (higher == better): {correct_change:+d} ({100 * correct_change / main_correct:+.1f}%)")
 
     our_additional_rows = df["Additional"].sum()
     main_additional_rows = df["M Additional"].sum()
     additional_change = our_additional_rows - main_additional_rows
-    print(
-        f"Change in additional rows: {additional_change:+d} ({100 * additional_change / main_additional_rows:+.1f}%)"
-    )
+    print(f"Change in additional rows: {additional_change:+d} ({100 * additional_change / main_additional_rows:+.1f}%)")
 
     if len(accu_regressions) + len(addi_regressions) + len(time_regressions) > 0:
         print()
@@ -511,10 +499,7 @@ def run_all_benchmarks(
             verbose=args.verbose,
             debug=args.debug,
         )
-        print(
-            f"Ran {args.run} in {runtime:.2f}s. {acc}% ({cor} correct, {add} additional).\n"
-            f"GAMS: {gms}"
-        )
+        print(f"Ran {args.run} in {runtime:.2f}s. {acc}% ({cor} correct, {add} additional).\n" f"GAMS: {gms}")
     else:
         run_all_benchmarks(
             benchmarks_folder,