Files
seismo-relay/analysis_idf/corpus_accuracy.py
T

66 lines
1.9 KiB
Python

"""Run read_idf_file across the corpus and report per-channel accuracy vs sidecars."""
from __future__ import annotations
import sys
from pathlib import Path
REPO = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(REPO))
from micromate.idf_file import read_idf_file
from analysis_idf.recon import load_sidecar_samples
def sidecar_path(idfw: Path) -> Path:
return idfw.parent / "TXT" / f"{idfw.name}.txt"
def main():
root = REPO / "tests/fixtures/THORDATA_example"
files = [f for f in root.rglob("*.IDFW") if not str(f).endswith(".CDB")]
files.sort()
GEO_LSB = 0.0003
n_ok = n_skip = 0
overall = {"Tran": [], "Vert": [], "Long": []}
for f in files:
try:
res = read_idf_file(f)
except Exception:
n_skip += 1
continue
sc_path = sidecar_path(f)
if not sc_path.exists():
n_skip += 1
continue
try:
sc = load_sidecar_samples(sc_path)
except Exception:
n_skip += 1
continue
per_file = {}
for ch in ("Tran", "Vert", "Long"):
sc_counts = [int(round(v / GEO_LSB)) for v in sc[ch]]
dec = res.samples.get(ch, [])
n = min(len(sc_counts), len(dec))
if n == 0:
per_file[ch] = 0.0
continue
exact = sum(1 for i in range(n) if sc_counts[i] == dec[i])
pct = 100.0 * exact / n
per_file[ch] = pct
overall[ch].append(pct)
n_ok += 1
print(f"Processed {n_ok} files (skipped {n_skip})")
print("Per-channel exact-match % (mean / min / max):")
for ch, vals in overall.items():
if vals:
avg = sum(vals) / len(vals)
print(f" {ch}: mean={avg:.2f}% min={min(vals):.2f}% max={max(vals):.2f}% n={len(vals)}")
if __name__ == "__main__":
main()