lars/giant
1
0
Fork 0
Code Issues 1 Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Bump ruff line-length to 120 and reformat
CI / Lint (ruff check) (push) Successful in 31s
Details
CI / Format (ruff format) (push) Successful in 32s
Details
CI / Sync project version with tag (push) Has been skipped
Details
CI / Lint (ruff check) (pull_request) Successful in 26s
Details
CI / Type check (ty) (push) Successful in 29s
Details
CI / Format (ruff format) (pull_request) Successful in 33s
Details
CI / Sync project version with tag (pull_request) Has been skipped
Details
CI / Type check (ty) (pull_request) Successful in 35s
Details
CI / Tests (pull_request) Successful in 3m47s
Details
CI / Tests (push) Successful in 3m55s
Details

Browse Source 
Rejoins lines that only wrapped because they exceeded the old 88-char
limit; ruff check and the full test suite (725 passed) are unaffected.
This commit is contained in:
Lars Bogner
2026-08-12 13:33:09 +02:00
parent 9ce7b32324
commit 55332db67a
66 changed files with 757 additions and 2413 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/dwarf.py
+40 -116
View File
@@ -80,8 +80,7 @@ def convert(
typer.Option(
"--output",
"-o",
help="Output Parquet file (default: <input>.parquet). Only valid "
"with a single input file and --jobs 1.",
help="Output Parquet file (default: <input>.parquet). Only valid with a single input file and --jobs 1.",
),
] = None,
batch_size: Annotated[
@@ -91,9 +90,7 @@ def convert(
help="Uproot read batch size, e.g. '100 MB' or '500000' (rows)",
),
] = "100 MB",
tree: Annotated[
str, typer.Option("--tree", help="Tree name inside the ROOT file")
] = "Steps",
tree: Annotated[str, typer.Option("--tree", help="Tree name inside the ROOT file")] = "Steps",
compression: Annotated[
Compression, typer.Option("--compression", help="Parquet compression codec")
] = Compression.snappy,
@@ -129,15 +126,11 @@ def convert(
raise typer.Exit(1)
_warn_if_exceeds_shared_quota(jobs, "--jobs")
compression_value = (
"uncompressed" if compression is Compression.none else compression.value
)
compression_value = "uncompressed" if compression is Compression.none else compression.value
if jobs == 1:
if output is not None and len(root_files) > 1:
typer.echo(
"error: --output can only be used with a single input file", err=True
)
typer.echo("error: --output can only be used with a single input file", err=True)
raise typer.Exit(1)
total_orphaned = 0
for root_file in root_files:
@@ -150,10 +143,7 @@ def convert(
)
total_orphaned += n_orphaned
if total_orphaned:
typer.echo(
f"\n{total_orphaned} orphaned child track(s) dropped across "
f"{len(root_files)} file(s)."
)
typer.echo(f"\n{total_orphaned} orphaned child track(s) dropped across {len(root_files)} file(s).")
return
if output is not None:
@@ -176,9 +166,7 @@ def convert(
@app.command()
def migrate(
root: Annotated[
Path, typer.Argument(help="Dataset root to migrate in place")
] = _DATASET_ROOT_DEFAULT,
root: Annotated[Path, typer.Argument(help="Dataset root to migrate in place")] = _DATASET_ROOT_DEFAULT,
execute: Annotated[
bool,
typer.Option(
@@ -190,8 +178,7 @@ def migrate(
bool,
typer.Option(
"--copy",
help="Copy instead of move, leaving the originals in place "
"(e.g. if another process is still reading them)",
help="Copy instead of move, leaving the originals in place (e.g. if another process is still reading them)",
),
] = False,
) -> None:
@@ -202,12 +189,8 @@ def migrate(
@app.command("bump-gen")
def bump_gen(
reason: Annotated[str, typer.Option("--reason", help="Why this gen exists")],
kind: Annotated[
str, typer.Option("--kind", help="steps | hits | ... (default: steps)")
] = "steps",
by: Annotated[
Optional[str], typer.Option("--by", help="Attribution (default: git user.name)")
] = None,
kind: Annotated[str, typer.Option("--kind", help="steps | hits | ... (default: steps)")] = "steps",
by: Annotated[Optional[str], typer.Option("--by", help="Attribution (default: git user.name)")] = None,
date: Annotated[
Optional[str],
typer.Option("--date", help="Override date (default: today, ISO)"),
@@ -220,12 +203,8 @@ def bump_gen(
help="Target gen tag (default: one past the current highest)",
),
] = None,
execute: Annotated[
bool, typer.Option("--execute", help="Apply (default: dry run)")
] = False,
root: Annotated[
Path, typer.Option("--root", help="Dataset root")
] = _DATASET_ROOT_DEFAULT,
execute: Annotated[bool, typer.Option("--execute", help="Apply (default: dry run)")] = False,
root: Annotated[Path, typer.Option("--root", help="Dataset root")] = _DATASET_ROOT_DEFAULT,
) -> None:
"""Cut a new raw generation."""
run_bump_gen(
@@ -243,12 +222,8 @@ def bump_gen(
def bump_schema(
gen: Annotated[str, typer.Option("--gen", help="Existing gen tag, e.g. gen1")],
reason: Annotated[str, typer.Option("--reason", help="Why this schema exists")],
kind: Annotated[
str, typer.Option("--kind", help="steps | hits | ... (default: steps)")
] = "steps",
by: Annotated[
Optional[str], typer.Option("--by", help="Attribution (default: git user.name)")
] = None,
kind: Annotated[str, typer.Option("--kind", help="steps | hits | ... (default: steps)")] = "steps",
by: Annotated[Optional[str], typer.Option("--by", help="Attribution (default: git user.name)")] = None,
date: Annotated[
Optional[str],
typer.Option("--date", help="Override date (default: today, ISO)"),
@@ -261,12 +236,8 @@ def bump_schema(
help="Target schema tag (default: one past the current highest)",
),
] = None,
execute: Annotated[
bool, typer.Option("--execute", help="Apply (default: dry run)")
] = False,
root: Annotated[
Path, typer.Option("--root", help="Dataset root")
] = _DATASET_ROOT_DEFAULT,
execute: Annotated[bool, typer.Option("--execute", help="Apply (default: dry run)")] = False,
root: Annotated[Path, typer.Option("--root", help="Dataset root")] = _DATASET_ROOT_DEFAULT,
) -> None:
"""Cut a new schema within a gen."""
run_bump_schema(
@@ -283,9 +254,7 @@ def bump_schema(
@app.command()
def status(
root: Annotated[
Path, typer.Option("--root", help="Dataset root")
] = _DATASET_ROOT_DEFAULT,
root: Annotated[Path, typer.Option("--root", help="Dataset root")] = _DATASET_ROOT_DEFAULT,
) -> None:
"""List existing gens/schemas per kind."""
run_status(str(root))
@@ -293,9 +262,7 @@ def status(
@app.command("update-manifest")
def update_manifest(
manifests: Annotated[
list[Path], typer.Argument(help="One or more .manifest files to update")
],
manifests: Annotated[list[Path], typer.Argument(help="One or more .manifest files to update")],
schema: Annotated[
Optional[str],
typer.Option(
@@ -306,9 +273,7 @@ def update_manifest(
] = None,
gen: Annotated[
Optional[str],
typer.Option(
"--gen", metavar="genN", help="Target gen tag (default: keep existing gen)"
),
typer.Option("--gen", metavar="genN", help="Target gen tag (default: keep existing gen)"),
] = None,
execute: Annotated[
bool,
@@ -316,9 +281,7 @@ def update_manifest(
] = False,
) -> None:
"""Repoint manifest(s) to a new gen and/or schema, verifying all target files exist."""
run_update_manifest(
[str(m) for m in manifests], schema=schema, execute=execute, gen=gen
)
run_update_manifest([str(m) for m in manifests], schema=schema, execute=execute, gen=gen)
@app.command("create-manifest")
@@ -333,22 +296,15 @@ def create_manifest(
typer.Option(
"--pool",
metavar="DETECTOR",
help="Detector name; combined with --type and --root to form "
"<root>/pools/<detector>/<type>.manifest",
help="Detector name; combined with --type and --root to form <root>/pools/<detector>/<type>.manifest",
),
] = None,
type_: Annotated[
Optional[PoolType],
typer.Option(
"--type", help="Pool type — full, holdout, or dev (required with --pool)"
),
typer.Option("--type", help="Pool type — full, holdout, or dev (required with --pool)"),
] = None,
root: Annotated[
Path, typer.Option("--root", help="Dataset root (used with --pool)")
] = _DATASET_ROOT_DEFAULT,
execute: Annotated[
bool, typer.Option("--execute", help="Write the manifest (default: dry run)")
] = False,
root: Annotated[Path, typer.Option("--root", help="Dataset root (used with --pool)")] = _DATASET_ROOT_DEFAULT,
execute: Annotated[bool, typer.Option("--execute", help="Write the manifest (default: dry run)")] = False,
force: Annotated[
bool,
typer.Option("--force", help="Overwrite the manifest if it already exists"),
@@ -368,9 +324,7 @@ def create_manifest(
@app.command("make-root")
def make_root(
executable: Annotated[
Path, typer.Option("--executable", help="Built minicalosim run_* executable")
],
executable: Annotated[Path, typer.Option("--executable", help="Built minicalosim run_* executable")],
detector: Annotated[
list[str],
typer.Option(
@@ -382,15 +336,9 @@ def make_root(
"Repeatable.",
),
],
num_files: Annotated[
int, typer.Option("--num-files", help="New shards to create per detector")
],
events_per_file: Annotated[
int, typer.Option("--events-per-file", help="nEvents passed to the executable")
],
gen: Annotated[
str, typer.Option("--gen", help="Existing gen tag under raw/<kind>/, e.g. gen1")
],
num_files: Annotated[int, typer.Option("--num-files", help="New shards to create per detector")],
events_per_file: Annotated[int, typer.Option("--events-per-file", help="nEvents passed to the executable")],
gen: Annotated[str, typer.Option("--gen", help="Existing gen tag under raw/<kind>/, e.g. gen1")],
energy_gev: Annotated[
float | None,
typer.Option(
@@ -401,20 +349,12 @@ def make_root(
"to name the dataset accordingly.",
),
] = None,
kind: Annotated[
str, typer.Option("--kind", help="steps | hits | ... (default: steps)")
] = "steps",
dataset_root: Annotated[
Path, typer.Option("--dataset-root", help="Dataset root")
] = _DATASET_ROOT_DEFAULT,
jobs: Annotated[
int, typer.Option("--jobs", "-j", help="Parallel simulation runs (default: 4)")
] = 4,
kind: Annotated[str, typer.Option("--kind", help="steps | hits | ... (default: steps)")] = "steps",
dataset_root: Annotated[Path, typer.Option("--dataset-root", help="Dataset root")] = _DATASET_ROOT_DEFAULT,
jobs: Annotated[int, typer.Option("--jobs", "-j", help="Parallel simulation runs (default: 4)")] = 4,
execute: Annotated[
bool,
typer.Option(
"--execute", help="Actually run jobs (default: dry run / print plan)"
),
typer.Option("--execute", help="Actually run jobs (default: dry run / print plan)"),
] = False,
) -> None:
"""Generate new ROOT shards via a minicalosim executable."""
@@ -441,9 +381,7 @@ class OracleMethod(str, Enum):
@app.command("build-geometry-oracle")
def build_geometry_oracle(
data: Annotated[
Path, typer.Argument(help="Steps parquet file or directory of steps files")
],
data: Annotated[Path, typer.Argument(help="Steps parquet file or directory of steps files")],
out: Annotated[Path, typer.Option("--out", "-o", help="Output oracle .pkl path")],
method: Annotated[
OracleMethod,
@@ -456,9 +394,7 @@ def build_geometry_oracle(
),
),
] = OracleMethod.slab,
k: Annotated[
int, typer.Option("--k", help="Neighbours for the knn classifier")
] = 1,
k: Annotated[int, typer.Option("--k", help="Neighbours for the knn classifier")] = 1,
subsample: Annotated[
int,
typer.Option("--subsample", help="Max reference points sampled from the data"),
@@ -504,9 +440,7 @@ def build_geometry_oracle(
def warm_cache(
data: Annotated[
Path,
typer.Argument(
help="Parquet file, directory, or .manifest — same as `giant train`'s"
),
typer.Argument(help="Parquet file, directory, or .manifest — same as `giant train`'s"),
],
val_fraction: Annotated[
float,
@@ -518,16 +452,13 @@ def warm_cache(
] = 0.1,
seed: Annotated[
int,
typer.Option(
"--seed", "-s", help="Must match the `giant train` run(s) to warm for"
),
typer.Option("--seed", "-s", help="Must match the `giant train` run(s) to warm for"),
] = 0,
particle_conditioning: Annotated[
Conditioning,
typer.Option(
"--particle-conditioning",
help="Must match the `giant train` run(s)' conditioning.particle.type "
"to warm for",
help="Must match the `giant train` run(s)' conditioning.particle.type to warm for",
),
] = Conditioning.physical,
material_conditioning: Annotated[
@@ -543,21 +474,14 @@ def warm_cache(
bool,
typer.Option(
"--router/--no-router",
help="Warm the process vocabulary too (only takes effect with "
"--router-type process)",
help="Warm the process vocabulary too (only takes effect with --router-type process)",
),
] = False,
router_type: Annotated[
str, typer.Option("--router-type", help="Router implementation name")
] = "energy",
n_experts: Annotated[
int, typer.Option("--n-experts", help="Number of routed experts")
] = 4,
router_type: Annotated[str, typer.Option("--router-type", help="Router implementation name")] = "energy",
n_experts: Annotated[int, typer.Option("--n-experts", help="Number of routed experts")] = 4,
rebuild: Annotated[
bool,
typer.Option(
"--rebuild", help="Ignore any existing sidecar and recompute every section"
),
typer.Option("--rebuild", help="Ignore any existing sidecar and recompute every section"),
] = False,
) -> None:
"""Precompute `giant train`'s setup-stage sidecar for `data` ahead of time.