English: label map, families, labeling rules, knowledge/, validate.py (ex controle.py), ids.py, precedents.py; the labels of auto/ translated, keys start/end/family/review/analysis (manual/: keys only); analysis folders renamed; the 2026-11-16 trial analysis (NORDEND-243)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
maximeandClaude Opus 5.5 committed 2026-11-16 12:40:03 +01:00
1 parent 4d926ecddc
commit 68a0eefd8b
79 files changed
+2789 -2652

No files matched your search

@@ -0,0 +1,22 @@
"""Vérifie les bornes : instants de mesure, debut < fin, et à chaque borne les
capteurs rejetés (CTR01 exclu, rejeté d'habitude) et CTR03.
Usage : python3 bornes.py data/NORDEND etiquettes.jsonl
"""
import csv, glob, json, sys
dossier, fichier = sys.argv[1], sys.argv[2]
rows = {}
for f in sorted(glob.glob(f'{dossier}/displacement/*_advanced_202611*.csv')):
for r in csv.DictReader(open(f)):
t = r['time_utc'][:16].replace(' ', 'T') + 'Z'
t = t[:14] + f"{int(t[14:16]) - int(t[14:16]) % 15:02d}" + 'Z'
rows.setdefault(t, {})[r['sensor_name']] = r
for n, l in enumerate(open(fichier), 1):
d = json.loads(l)
ok = d['debut'] < d['fin'] and d['debut'] in rows and d['fin'] in rows
info = []
for b in ('debut', 'fin'):
rj = [c for c, r in rows.get(d[b], {}).items()
if c != 'CTR01' and float(r['error_value']) > float(r['error_threshold'])]
if rj: info.append(f"{b} rejetés : {','.join(rj)}")
print(f"{n:2} {'OK ' if ok else 'ERR'} {d['debut']} → {d['fin']} {d['categorie']:<20} {'; '.join(info)}")
@@ -0,0 +1,30 @@
"""Par jour et par cible : corr de la journée (médiane 10:00-16:00) moins la nuit
d'avant (médiane 02:00-05:00), en bruits, sans les instants où CTR03 est rejetée.
Usage : python3 cycle_jour.py data/NORDEND AAAA-MM-JJ[,AAAA-MM-JJ...]
"""
import csv, glob, sys, statistics as st
dossier, jours = sys.argv[1], sys.argv[2].split(',')
rows = {}
for f in sorted(glob.glob(f'{dossier}/displacement/*_advanced_*.csv')):
for r in csv.DictReader(open(f)):
if r['time_utc'][:10] in jours:
rows.setdefault(r['time_utc'][:16], {})[r['sensor_name']] = r
rej = lambda r: float(r['error_value']) > float(r['error_threshold'])
bad = {t for t, d in rows.items() if 'CTR03' in d and rej(d['CTR03'])}
cibles = sorted({n for d in rows.values() for n in d if n.startswith('PR')})
for j in jours:
print(f'== {j} : jour 10-16 moins nuit 02-05 (bruits), triés')
for c in ('corr_x', 'corr_y'):
out = []
for n in cibles:
def serie(h0, h1):
return [float(d[n][c]) for t, d in sorted(rows.items()) if t[:10] == j and h0 <= t[11:13] < h1
and t not in bad and n in d and not rej(d[n]) and d[n][c]]
nuit, jour = serie('02', '05'), serie('10', '16')
tout = serie('00', '24')
if len(nuit) < 3 or len(jour) < 3: continue
b = st.median(abs(a - b) for a, b in zip(tout, tout[1:])) or 1e-9
out.append(((st.median(jour) - st.median(nuit)) / b, n))
out.sort()
print(f' {c}: ' + ' '.join(f'{n}:{v:+.0f}' for v, n in out))
@@ -0,0 +1,17 @@
"""Par jour : error_value médiane et nombre de rejets de capteurs choisis.
Usage : python3 par_jour.py data/NORDEND AAAAMMJJ AAAAMMJJ CAPT1,CAPT2
"""
import csv, glob, sys, statistics as st
dossier, d0, d1, capteurs = sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4].split(',')
print('jour ' + ''.join(f'{c:>22}' for c in capteurs))
for f in sorted(glob.glob(f'{dossier}/displacement/*_advanced_*.csv')):
jour = f[-12:-4]
if not d0 <= jour <= d1: continue
ev = {c: [] for c in capteurs}; rj = {c: 0 for c in capteurs}
for r in csv.DictReader(open(f)):
c = r['sensor_name']
if c in ev:
v = float(r['error_value']); ev[c].append(v)
rj[c] += v > float(r['error_threshold'])
print(jour + ' ' + ''.join(f"{(st.median(ev[c]) if ev[c] else 0):>8.3f} {rj[c]:>4}/{len(ev[c]):<4} " for c in capteurs))
@@ -0,0 +1,64 @@
"""Pics des corr des cibles face aux rejets de CTR03, instant par instant.
Niveau local de chaque cible : médiane de ses corr dans ±2 h, sans les instants
où CTR03 est rejetée. Imprime, par instant : error_value de CTR03 (r si rejetée),
CTR02, CTR04, sigma0, médiane des résidus corr_x / corr_y des cibles acceptées,
nombre de cibles à plus de K bruits (bruit = médiane des |écarts| d'un pas).
Usage : python3 pics_ctr03.py data/NORDEND DEBUT FIN [K]
"""
import csv, glob, sys, statistics as st
from datetime import datetime, timedelta
dossier, debut, fin = sys.argv[1], sys.argv[2], sys.argv[3]
K = float(sys.argv[4]) if len(sys.argv) > 4 else 4
t0 = datetime.fromisoformat(debut.replace('Z', '+00:00'))
t1 = datetime.fromisoformat(fin.replace('Z', '+00:00'))
REFS = ('CTR02', 'CTR03', 'CTR04')
rows = {} # t -> name -> dict
for f in sorted(glob.glob(f'{dossier}/displacement/*_advanced_*.csv')):
jour = f[-12:-4]
if not (t0 - timedelta(days=1)).strftime('%Y%m%d') <= jour <= (t1 + timedelta(days=1)).strftime('%Y%m%d'):
continue
for r in csv.DictReader(open(f)):
t = datetime.fromisoformat(r['time_utc']).replace(second=0, microsecond=0)
t = t.replace(minute=t.minute - t.minute % 15)
if t0 - timedelta(hours=3) <= t <= t1 + timedelta(hours=3):
rows.setdefault(t, {})[r['sensor_name']] = r
T = sorted(rows)
def rej(r): return float(r['error_value']) > float(r['error_threshold'])
bad = {t for t in T if 'CTR03' in rows[t] and rej(rows[t]['CTR03'])}
cibles = sorted({n for t in T for n in rows[t] if n not in REFS and n != 'CTR01'})
def val(t, n, c):
r = rows[t].get(n)
if r is None or rej(r) or r[c] == '': return None
return float(r[c])
res = {} # (t, n, c) -> residu en bruits
for c in ('corr_x', 'corr_y'):
for n in cibles:
serie = [(t, val(t, n, c)) for t in T]
ok = [v for t, v in serie if v is not None and t not in bad]
bruit = st.median(abs(a - b) for a, b in zip(ok, ok[1:])) or 1e-9
for i, (t, v) in enumerate(serie):
if v is None: continue
voisins = [w for (u, w) in serie[max(0, i - 8):i + 9] if w is not None and u not in bad and u != t]
if voisins:
res[(t, n, c)] = ((v - st.median(voisins)), bruit)
print('instant CTR03 CTR02 CTR04 sigma0 med_dcx med_dcy n>K(cx) n>K(cy) top')
for t in T:
if not t0 <= t <= t1: continue
ev = {n: rows[t][n] for n in REFS if n in rows[t]}
s = lambda n: ('r' if rej(ev[n]) else '') + f"{float(ev[n]['error_value']):.3f}" if n in ev else '-'
sig = next((rows[t][n]['sigma0'] for n in rows[t] if rows[t][n]['sigma0']), '')
line = []
for c in ('corr_x', 'corr_y'):
d = [res[(t, n, c)] for n in cibles if (t, n, c) in res]
line.append((st.median(x for x, _ in d) if d else 0, sum(abs(x) > K * b for x, b in d), d))
top = sorted(((abs(res[(t, n, 'corr_y')][0]) / res[(t, n, 'corr_y')][1], n) for n in cibles if (t, n, 'corr_y') in res), reverse=True)[:3]
print(f"{t:%Y-%m-%dT%H:%MZ} {s('CTR03'):>6} {s('CTR02'):>6} {s('CTR04'):>6} {sig[:7]:>7} "
f"{line[0][0]:+.4f} {line[1][0]:+.4f} {line[0][1]:>4} {line[1][1]:>4} "
+ ' '.join(f'{n}:{v:.0f}' for v, n in top))