auto: the analysts verified the labels of 32 periods (11 stations, up to 14 days each): 710 labels -> 835, 587 unchanged; one analysis folder per period with its report (section Verification)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
maximeandClaude Opus 5.5 committed 2026-11-17 15:13:44 +01:00
1 parent df979301b5
commit 2a5d87659b
279 files changed
+10758 -710

No files matched your search

@@ -0,0 +1,43 @@
"""Every 3 h over the range: median of BJ_D corr_x - BJ_G corr_x, median error_value of BJ_C/BJ_D/BJ_G and of BL_D/PBL_D/PBJ_C;
then per day the correlation, measurement by measurement, of the spread with the BJ error_value."""
import sys, statistics as st
from collections import defaultdict
sys.path.insert(0, "tools/scripts")
import data
m = data.load("data/JUNGFRAU")
a, b = data.parse_time("2026-10-10T16:15Z"), data.parse_time("2026-10-21T10:30Z")
by = defaultdict(dict)
for s, ms in m.items():
for x in data.filter_window(ms, a, b):
by[x["t"].replace(second=0, microsecond=0)][s] = x
bins = defaultdict(lambda: defaultdict(list))
days = defaultdict(list)
for t, d in sorted(by.items()):
k = t.replace(hour=t.hour // 3 * 3, minute=0)
ev = st.mean(d[s]["error_value"] for s in ("BJ_C", "BJ_D", "BJ_G"))
if d["BJ_D"]["corr_x"] is not None and d["BJ_G"]["corr_x"] is not None:
sp = d["BJ_D"]["corr_x"] - d["BJ_G"]["corr_x"]
bins[k]["spread"].append(sp)
days[t.date()].append((ev, sp))
bins[k]["evBJ"].append(ev)
bins[k]["evO"].append(st.mean(d[s]["error_value"] for s in ("BL_D", "PBL_D", "PBJ_C")))
for k in sorted(bins):
v = bins[k]
print(data.iso(k), "spread %.2f" % st.median(v["spread"]) if v["spread"] else "spread -",
"evBJ %.3f" % st.median(v["evBJ"]), "evOther %.3f" % st.median(v["evO"]))
for d, p in sorted(days.items()):
if len(p) > 10:
print(d, "n", len(p), "r(evBJ, spread) %.2f" % st.correlation([x for x, _ in p], [y for _, y in p]))
# step to step: does the spread jump with the BJ error_value from one measurement to the next?
ts = sorted(by)
dev, dsp = [], []
for t0, t1 in zip(ts, ts[1:]):
if (t1 - t0).seconds != 900:
continue
p = [by[t][s] for t in (t0, t1) for s in ("BJ_D", "BJ_G")]
if any(x["corr_x"] is None for x in p):
continue
e = [st.mean(by[t][s]["error_value"] for s in ("BJ_C", "BJ_D", "BJ_G")) for t in (t0, t1)]
dev.append(e[1] - e[0])
dsp.append((p[2]["corr_x"] - p[3]["corr_x"]) - (p[0]["corr_x"] - p[1]["corr_x"]))
print("steps", len(dev), "r(d evBJ, d spread) %.2f" % st.correlation(dev, dsp), "slope %.1f" % st.linear_regression(dev, dsp).slope)