lars/giant
1
0
Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Fix ruff, ty, and pytest failures; apply ruff format

Browse Source 
Removes unused imports and an ambiguous variable name, narrows
Optional types before use so ty's flow analysis is satisfied, swaps
sum() over polars expressions for pl.sum_horizontal to avoid the
Literal[0] fallback type, and converts numpy bin edges to plain lists
before passing to matplotlib's hist (whose stub only accepts
Sequence[float]). Also applies ruff format across the repo, which had
drifted out of sync with the formatter.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Lars Bogner
2026-07-02 16:59:22 +02:00
parent e5bf7c51cb
commit 25718f175e
18 changed files with 469 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/bump_dataset_version.py
+57 -16
View File
@@ -92,7 +92,11 @@ def _git_user_name() -> str | None:
def plan_bump_gen(
root: Path, kind: str, reason: str, by: str | None, date: str,
root: Path,
kind: str,
reason: str,
by: str | None,
date: str,
target: str | None = None,
) -> tuple[list[Path], str]:
"""New gen tag is one past the highest seen under raw/ or processed/ for *kind*,
@@ -120,7 +124,12 @@ def plan_bump_gen(
def plan_bump_schema(
root: Path, kind: str, gen_tag: str, reason: str, by: str | None, date: str,
root: Path,
kind: str,
gen_tag: str,
reason: str,
by: str | None,
date: str,
target: str | None = None,
) -> tuple[list[Path], str]:
if not GEN_RE.match(gen_tag):
@@ -140,7 +149,9 @@ def plan_bump_schema(
schema_tag = f"schema{next_schema}"
new_dirs = [processed_gen_dir / schema_tag]
by_suffix = f" ({by})" if by else ""
log_line = f"- `{gen_tag}`/`{schema_tag}` (kind={kind}) — {date} — {reason}{by_suffix}"
log_line = (
f"- `{gen_tag}`/`{schema_tag}` (kind={kind}) — {date} — {reason}{by_suffix}"
)
return new_dirs, log_line
@@ -196,7 +207,9 @@ def _manifest_referenced_files(pools_root: Path) -> set[Path]:
return referenced
def _referenced_root_count(raw_gen_dir: Path, processed_gen_dir: Path) -> tuple[int, int]:
def _referenced_root_count(
raw_gen_dir: Path, processed_gen_dir: Path
) -> tuple[int, int]:
"""(total .root files, count with a same-named .parquet under any schema) for one gen."""
if not raw_gen_dir.is_dir():
return 0, 0
@@ -349,13 +362,17 @@ def print_status(root: Path) -> None:
)
schema_sizes = {s: _du(schema_dir / f"schema{s}") for s in schemas}
schema_counts = {
s: _referenced_parquet_count(schema_dir / f"schema{s}", manifest_referenced)
s: _referenced_parquet_count(
schema_dir / f"schema{s}", manifest_referenced
)
for s in schemas
}
processed_size = sum(schema_sizes.values())
processed_files = sum(c[0] for c in schema_counts.values())
processed_referenced = sum(c[1] for c in schema_counts.values())
raw_files, raw_referenced = _referenced_root_count(raw_gen_dir, processed_gen_dir)
raw_files, raw_referenced = _referenced_root_count(
raw_gen_dir, processed_gen_dir
)
gen_total = raw_size + processed_size
gen_files = raw_files + processed_files
kind_total += gen_total
@@ -367,14 +384,22 @@ def print_status(root: Path) -> None:
print(_reason_line(gen_reason, indent=2))
print(
_row(
"raw", raw_size, indent=2, level="bucket",
count=raw_files, referenced=raw_referenced,
"raw",
raw_size,
indent=2,
level="bucket",
count=raw_files,
referenced=raw_referenced,
)
)
print(
_row(
"processed", processed_size, indent=2, level="bucket",
count=processed_files, referenced=processed_referenced,
"processed",
processed_size,
indent=2,
level="bucket",
count=processed_files,
referenced=processed_referenced,
)
)
if schemas:
@@ -382,8 +407,12 @@ def print_status(root: Path) -> None:
s_total, s_referenced = schema_counts[s]
print(
_row(
f"schema{s}", schema_sizes[s], indent=3, level="schema",
count=s_total, referenced=s_referenced,
f"schema{s}",
schema_sizes[s],
indent=3,
level="schema",
count=s_total,
referenced=s_referenced,
)
)
schema_reason = schema_reasons.get((kind, gen_tag, f"schema{s}"))
@@ -391,7 +420,9 @@ def print_status(root: Path) -> None:
print(_reason_line(schema_reason, indent=4))
else:
print(_colorize(" (none)", "schema"))
print(_row(f"{kind} total", kind_total, indent=1, level="gen", count=kind_files))
print(
_row(f"{kind} total", kind_total, indent=1, level="gen", count=kind_files)
)
print()
grand_total += kind_total
grand_files += kind_files
@@ -414,6 +445,7 @@ def print_status(root: Path) -> None:
# update-manifest
# ---------------------------------------------------------------------------
def plan_update_manifest(
manifest_path: Path,
target_schema: str | None,
@@ -489,8 +521,13 @@ def plan_update_manifest(
return result, missing
def apply_update_manifest(manifest_path: Path, lines: list[tuple[str, str | None]]) -> None:
out = [replacement if replacement is not None else original for original, replacement in lines]
def apply_update_manifest(
manifest_path: Path, lines: list[tuple[str, str | None]]
) -> None:
out = [
replacement if replacement is not None else original
for original, replacement in lines
]
manifest_path.write_text("\n".join(out) + "\n")
@@ -498,6 +535,7 @@ def apply_update_manifest(manifest_path: Path, lines: list[tuple[str, str | None
# create-manifest
# ---------------------------------------------------------------------------
def _resolve_manifest_files(manifest_path: Path) -> list[Path]:
"""Read a manifest and return its entries as resolved absolute paths."""
files = []
@@ -571,6 +609,7 @@ def apply_create_manifest(output_path: Path, lines: list[str]) -> None:
# CLI entry points (called from scripts/dwarf.py)
# ---------------------------------------------------------------------------
def run_status(root: str) -> None:
root_path = Path(root)
if not root_path.is_dir():
@@ -597,7 +636,9 @@ def _run_bump(
if gen is None:
new_dirs, log_line = plan_bump_gen(root_path, kind, reason, by, date, to)
else:
new_dirs, log_line = plan_bump_schema(root_path, kind, gen, reason, by, date, to)
new_dirs, log_line = plan_bump_schema(
root_path, kind, gen, reason, by, date, to
)
print(f"=== {'EXECUTING' if execute else 'DRY RUN'} ===")
print("new directories:")