wf-improve scripts take their paths as arguments (--labels, --data)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
80e00a4898
commit
cff2b0ad1e
3 files changed
+40
-42
No files matched your search
@@ -1,15 +1,14 @@
|
||||
"""Benchmark of the wf-improve workflow (D-116): the detectors against all the labeller's labels (labeling/auto/).
|
||||
"""Benchmark of the detectors against a reference truth: every labelled station.
|
||||
|
||||
For each station of labeling/auto/ that has its folder in data/, the score per family and per instant of score.py
|
||||
(D-112), over the range of its labels: from the day of the first to the midnight after the last. Then the total, family
|
||||
by family, which says whether the detectors do better overall from one session to the next. The block of the session's
|
||||
station is its score; the other blocks, the non-regression: a family that goes back on a station is a regression, even
|
||||
if the total rises.
|
||||
Usage: python3 detectors/skills/wf-improve/scripts/regression.py [--stations A,B]
|
||||
For each <STATION>.jsonl of --labels that has its folder <STATION>/ in --data, the score per family and per instant of
|
||||
score.py, over the range of its labels: from the day of the first to the midnight after the last. Then the total,
|
||||
family by family, which says whether the detectors do better overall. The block of a station is its score; the
|
||||
others, the non-regression: a family that goes back on a station is a regression, even if the total rises.
|
||||
Usage: python3 regression.py --labels <folder of <STATION>.jsonl> --data <folder of <STATION>/> [--stations A,B]
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
from datetime import timedelta
|
||||
from pathlib import Path
|
||||
|
||||
import score # next to it
|
||||
|
||||
@@ -17,31 +16,32 @@ from data import iso, parse_time # on the path through score
|
||||
|
||||
|
||||
def label_range(path):
|
||||
"""labeling/auto/<STATION>.jsonl -> (start, end) iso, in whole UTC days, end excluded."""
|
||||
with open(path, encoding="utf-8") as f:
|
||||
labels = [json.loads(l) for l in f if l.strip()]
|
||||
"""Labels JSONL -> (start, end) iso, in whole UTC days, end excluded."""
|
||||
labels = score.read_labels(path)
|
||||
start = min(e["debut"] for e in labels)[:10]
|
||||
# ponytail: the end of the batch is not written; midnight closest to the last bound (a label bound overflows by one
|
||||
# measurement after midnight); the real end of the batch in labeling/auto/ if the gap matters
|
||||
# ponytail: the end of the labelled batch is not written; midnight closest to the last bound (a label bound
|
||||
# overflows by one measurement after midnight)
|
||||
end = iso(parse_time(max(e["fin"] for e in labels)) + timedelta(hours=12))[:10]
|
||||
return iso(parse_time(start)), iso(parse_time(end))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
p = argparse.ArgumentParser(usage=__doc__)
|
||||
p.add_argument("--labels", required=True, help="folder of the labels, one <STATION>.jsonl per station")
|
||||
p.add_argument("--data", required=True, help="folder of the station folders, <STATION>/")
|
||||
p.add_argument("--stations", help="A,B: these stations only (a shorter run)")
|
||||
a = p.parse_args()
|
||||
total = {}
|
||||
for path in sorted((score.WORK / "labeling" / "auto").glob("*.jsonl")):
|
||||
for path in sorted(Path(a.labels).glob("*.jsonl")):
|
||||
station = path.stem
|
||||
if a.stations and station not in a.stations.split(","):
|
||||
continue
|
||||
folder = score.WORK / "data" / station
|
||||
folder = Path(a.data) / station
|
||||
if not folder.is_dir():
|
||||
print(f"{station}: no data/{station}/, skipped\n")
|
||||
print(f"{station}: no {folder}/, skipped\n")
|
||||
continue
|
||||
start, end = label_range(path)
|
||||
n, labels = score.family_scores(str(folder), start, end)
|
||||
n, labels = score.family_scores(str(folder), str(path), start, end)
|
||||
score.show(f"{station}: {start} → {end}, {len(labels)} labels", n)
|
||||
print()
|
||||
for k, v in n.items():
|
||||
|
||||
Reference in new issue
Block a user