lars
3faa272562
miniCaloSim's detector is a stack of planar layer slabs along one axis, so material/layer_id are a pure function of depth. The new "slab" method exploits this with an exact O(log #segments) binary search over depth-axis segment boundaries, instead of a nearest-neighbour search over hundreds of thousands of reference points — much cheaper per call, which matters since the oracle is queried on every autoregressive rollout step. "knn"/"svm" remain as fallbacks for non-slab geometries. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
75 lines
2.4 KiB
Python
75 lines
2.4 KiB
Python
"""Build a position -> (material, layer_id) geometry oracle from steps parquet.
|
|
|
|
Backs the `dwarf build-geometry-oracle` subcommand. The oracle is consumed by
|
|
`giant rollout` to supply the material/layer conditioning at each step, since the
|
|
surrogate does not predict them.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
from giant.data.loader import find_parquet_files
|
|
from giant.geometry import build_geometry_oracle
|
|
|
|
|
|
def run_build_geometry_oracle(
|
|
data: Path,
|
|
out: Path,
|
|
method: str = "slab",
|
|
k: int = 1,
|
|
subsample: int = 500_000,
|
|
escape_factor: float = 5.0,
|
|
seed: int = 0,
|
|
depth_axis: int = 2,
|
|
n_bins: int = 2000,
|
|
) -> None:
|
|
files = find_parquet_files(data)
|
|
print(f"found {len(files)} parquet file(s); sampling up to {subsample:,} points")
|
|
|
|
oracle = build_geometry_oracle(
|
|
files,
|
|
method=method,
|
|
k=k,
|
|
subsample=subsample,
|
|
escape_factor=escape_factor,
|
|
seed=seed,
|
|
depth_axis=depth_axis,
|
|
n_bins=n_bins,
|
|
)
|
|
|
|
print(
|
|
f"method: {method} reference points: {oracle.metadata['n_reference_points']:,}"
|
|
)
|
|
print("classes (material, layer_id):")
|
|
for material, layer_id in oracle.classes:
|
|
print(f" {material:<12} layer_id={layer_id}")
|
|
|
|
if method == "slab":
|
|
z_lo, z_hi = oracle.metadata["z_range"]
|
|
print(
|
|
f"depth axis: {'xyz'[depth_axis]} segments: {oracle.metadata['n_segments']} "
|
|
f"z range: [{z_lo:.3f}, {z_hi:.3f}] radius_max: {oracle.metadata['radius_max']:.3f}"
|
|
)
|
|
print(
|
|
f"median depth spacing: {oracle.metadata['median_z_spacing']:.3f} "
|
|
f"escape_threshold: {oracle.escape_threshold:.3f} (= {escape_factor}x spacing)"
|
|
)
|
|
else:
|
|
print(
|
|
f"median NN spacing: {oracle.metadata['median_nn_dist']:.3f} "
|
|
f"escape_threshold: {oracle.escape_threshold:.3f} "
|
|
f"(= {escape_factor}x spacing)"
|
|
)
|
|
if oracle.escape_threshold <= 0.0:
|
|
print(
|
|
"warning: escape_threshold is 0 (reference points are coincident) — "
|
|
"every rollout query would be flagged as escaped. Pass "
|
|
"`giant rollout --escape-threshold <mm>` to override, or use data "
|
|
"with distinct step positions."
|
|
)
|
|
|
|
out.parent.mkdir(parents=True, exist_ok=True)
|
|
oracle.save(out)
|
|
print(f"wrote oracle -> {out}")
|