- 32 analyses: each label kept, rewritten or removed by its analyst (section Requalification of the report; mm magnitudes where the targets have them) - SNCF01 x3, WILDSTRUBEL 2026-09-01 -> 2026-10-06 x3: verified from their existing labels under the new rules - long labels (no analysis): auto/analyses/long-labels/<STATION>/; NORDEND-169 and -195 run to 07/11, so NORDEND-283 and -284 (their continuation) are removed - reading-rules.md, stations.md: the citations of removed or rewritten labels point to their successor, or to [expert] Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
43 lines
2.0 KiB
Python
43 lines
2.0 KiB
Python
"""Requalification of the thermal labels: per label and per sensor, the largest deviation of corr_x / corr_y from the
|
|
night level (median of the evening measurements 12, 16, 20 UTC of the day before the label's first morning), in the
|
|
sensor's own noise as printed by ranges.py (file given). Usage: requalify_thermal.py FOLDER RANGES_TXT LABELS_JSONL"""
|
|
import sys, json, re, statistics
|
|
from datetime import timedelta
|
|
sys.path.insert(0, "tools/scripts")
|
|
import data
|
|
|
|
folder, rtxt, lab = sys.argv[1:4]
|
|
noise, col = {}, None
|
|
for line in open(rtxt):
|
|
m = re.match(r"== (corr_[xy]): level", line)
|
|
if m: col = m.group(1); continue
|
|
if line.startswith("corr_"): col = None
|
|
p = line.split()
|
|
if col and len(p) >= 4 and p[0] != "sensor":
|
|
try: noise[(p[0], col)] = float(p[3])
|
|
except ValueError: pass
|
|
meas = data.load(folder)
|
|
ser = {s: {m["t"].replace(second=0, microsecond=0): m for m in v} for s, v in meas.items()}
|
|
for l in map(json.loads, open(lab)):
|
|
if l["family"] != "Thermal displacement": continue
|
|
a, b = data.parse_time(l["start"]), data.parse_time(l["end"])
|
|
morning = b.replace(hour=0, minute=0)
|
|
d0 = morning - timedelta(days=1)
|
|
ev = [d0 + timedelta(hours=h) for h in (12, 16, 20)]
|
|
print(f"\n{l.get('id','')} {l['start']} -> {l['end']} (night level: evening of {data.iso(d0)[:10]})")
|
|
rows = []
|
|
for s, sv in ser.items():
|
|
for c in ("corr_x", "corr_y"):
|
|
n = noise.get((s, c))
|
|
base = [sv[t][c] for t in ev if t in sv and sv[t][c] is not None]
|
|
if not n or not base: continue
|
|
lvl = statistics.median(base)
|
|
best = None
|
|
for t, m in sv.items():
|
|
if a < t < b and m[c] is not None:
|
|
d = (m[c] - lvl) / n
|
|
if best is None or abs(d) > abs(best[0]): best = (d, t, m[c] - lvl)
|
|
if best: rows.append((abs(best[0]), s, c, best))
|
|
for _, s, c, (d, t, v) in sorted(rows, reverse=True)[:6]:
|
|
print(f" {s:10} {c} {d:+5.1f} noises ({v:+.4f} px) at {data.iso(t)}")
|