Files
aimsight-labeling/auto/analyses/LENZSPITZE_2026-10-16T0235_2026-10-23T2355/scripts/thermal.py
T
maximeandClaude Opus 5.5 ddb17c2189 auto: labels requalified under the 5-noise rules (only what stands out from the noise): 32 analyses refined, the 6 paused periods verified, the long labels requalified with the fixes the period analysts found; 1153 -> 961 labels
- 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>
2026-11-17 23:58:00 +01:00

68 lines
3.1 KiB
Python

"""Thermal labels: does the corrected curve keep the cycle beyond 5 noises of the night level?
For each Thermal displacement label: night level = median of corr over the night before
(20:00-03:00 UTC of the previous evening; on the first day, the measurements before the label),
own noise = median |difference between two measurements| over that night (as ranges.py);
then the hourly median of corr within the label minus the night level, in noises (the hourly
median removes the agitation of the visibility labels that overlap the thermal days).
Prints the targets whose hourly deviation exceeds 5 noises, largest first, in px and mm.
Usage: .venv/bin/python thermal.py <input.jsonl>
"""
import json, sys, statistics
from datetime import datetime, timedelta, timezone
sys.path.insert(0, "tools/scripts")
import data
REFS = {"8002", "8004", "8011", "8012", "8013", "8014", "8017", "8019", "92H"}
def T(s):
return datetime.strptime(s, "%Y-%m-%dT%H:%MZ").replace(tzinfo=timezone.utc)
def main():
labs = [json.loads(l) for l in open(sys.argv[1]) if l.strip()]
labs = [l for l in labs if l["family"] == "Thermal displacement"]
d = data.load("data/LENZSPITZE")
for lab in labs:
s, e = T(lab["start"]), T(lab["end"])
day = s.replace(hour=0, minute=0)
n0, n1 = day - timedelta(hours=4), day + timedelta(hours=3)
if s.day == 16:
n0, n1 = day, s
out = []
for name, ms in d.items():
if name in REFS:
continue
for c in ("corr_x", "corr_y"):
night = [m[c] for m in ms if n0 <= m["t"] < n1 and m[c] is not None]
if len(night) < 6:
continue
lvl = statistics.median(night)
noise = statistics.median(abs(a - b) for a, b in zip(night[1:], night[:-1]))
if noise <= 0:
continue
hours = {}
for m in ms:
if s < m["t"] < e and m[c] is not None:
hours.setdefault(m["t"].replace(minute=0), []).append(m[c])
best = None
for h, v in hours.items():
if len(v) < 6:
continue
dev = statistics.median(v) - lvl
if best is None or abs(dev) > abs(best[0]):
best = (dev, h)
if best and abs(best[0]) / noise > 5:
k = (ms[0].get("corr_x_mm") or 0) / ms[0]["corr_x"] if ms[0].get("corr_x_mm") and ms[0]["corr_x"] else None
mm = f" ({best[0]*k:+.2f} mm)" if k else ""
out.append((abs(best[0]) / noise, f"{name} {c} {best[0]:+.3f} px{mm} = {best[0]/noise:+.1f} noises, hour {best[1]:%H}"))
out.sort(reverse=True)
print(f"{lab['id']} {lab['start']} -> {lab['end']}: {len(out)} target-columns > 5 noises (hourly median vs night {n0:%d %H}-{n1:%d %H})")
for _, txt in [o for o in out if (len(sys.argv) < 3 or o[1].split()[0] == sys.argv[2])][:8]:
print(" ", txt)
if __name__ == "__main__":
main()