- Every station's auto labels reviewed by an analyst (/review-auto-labels), then a cross-review per family across all stations (new skill /cross-review-labels), a finishing pass, and descriptions rewritten in words (no numeric values). - The three never-labeled ranges (WILDSTRUBEL 07/09-01/10, NORDEND 16/08-01/10) labeled and reviewed: 991 auto labels on 11 stations, labeling/controle.py at 0 errors. - Labeling knowledge gathered in labeling/: regles-d-etiquetage.md (new), familles.md (settled boundaries), connaissances/ (notes moved from docs/, links updated), the label map rebuilt from reviewed labels, events and cases; events tied to their stations (PS_DES_COUDRES is JUNGFRAU). The labeler and reviewers read only labeling/. - labels-map reads auto labels and events; decision D-130; living plan points 73-75. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
41 lines
1.8 KiB
Python
41 lines
1.8 KiB
Python
"""Par heure UTC sur un lot : pas médian de la pose de la caméra d'une mesure à la suivante (pan, tilt, rotation,
|
|
scale), écart médian de l'error_value des cibles à leur niveau du lot, et température médiane du boîtier.
|
|
Dit si le bruit de jour vient d'une pose agitée (commune) ou des taches elles-mêmes (error_value).
|
|
|
|
Usage (depuis la racine) : python3 pose_ev.py STATION DEBUT FIN
|
|
"""
|
|
import sys, statistics as st
|
|
sys.path.insert(0, "agent-tools")
|
|
import donnees as d
|
|
|
|
nom, t1, t2 = sys.argv[1], d.instant(sys.argv[2]), d.instant(sys.argv[3])
|
|
dos = f"data/{nom}"
|
|
cam = [p for p in d.charger_camera(dos) if t1 <= p["t"] <= t2]
|
|
par = d.charger(dos)
|
|
cib = {s: d.filtrer(ms, t1, t2) for s, ms in par.items() if not d.est_reference(ms)}
|
|
tmp = [(t, v) for t, v in d.charger_temperature(dos) if t1 <= t <= t2]
|
|
pas = {}
|
|
for a, b in zip(cam, cam[1:]):
|
|
if (b["t"] - a["t"]).total_seconds() < 7200:
|
|
for q in ("pan", "tilt", "rotation", "scale"):
|
|
if a[q] is not None and b[q] is not None:
|
|
pas.setdefault((b["t"].hour, q), []).append(abs(b[q] - a[q]))
|
|
ev = {}
|
|
for s, ms in cib.items():
|
|
v = [m["error_value"] for m in ms if m["error_value"] is not None]
|
|
if not v:
|
|
continue
|
|
n = st.median(v)
|
|
for m in ms:
|
|
if m["error_value"] is not None:
|
|
ev.setdefault(m["t"].hour, []).append(m["error_value"] - n)
|
|
th = {}
|
|
for t, v in tmp:
|
|
th.setdefault(t.hour, []).append(v)
|
|
print(f"{nom} heure pan tilt rotation scale ev-niveau temp")
|
|
for h in range(24):
|
|
c = [st.median(pas[(h, q)]) if (h, q) in pas else float("nan") for q in ("pan", "tilt", "rotation", "scale")]
|
|
e = st.median(ev[h]) if h in ev else float("nan")
|
|
tt = st.median(th[h]) if h in th else float("nan")
|
|
print(f" {h:02d} {c[0]:.5f} {c[1]:.5f} {c[2]:.5f} {c[3]:.7f} {e:+.4f} {tt:.1f}")
|