Step 4: M2, multiple-instance model in PyTorch (shared sensor MLP, attention per family, averaged seeds); the time-split report shared with M1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
975ebc7c1a
commit
fef30b5ef4
4 files changed
+153
-16
No files matched your search
+22
@@ -75,6 +75,28 @@ def show(title, base, new):
|
||||
print(f" {f:<22}{cell(b, 0):>21}{cell(n, 0):>21}{cell(b, 1):>21}{cell(n, 1):>21}")
|
||||
|
||||
|
||||
CUT = 0.7 # the criterion: trained on the first 70 % of every station, tested on the last 30 %
|
||||
|
||||
|
||||
def report_time_split(cache, data, proba, families, threshold=0.5):
|
||||
"""The criterion: {station: proba [last 30 %, pilot family]} against the rules on the same instants -> the
|
||||
regressions station by station and the total, printed; returns (rules, model) counts per station."""
|
||||
base, new = {}, {}
|
||||
for s, d in data.items():
|
||||
cut = int(CUT * len(d["y"]))
|
||||
rules_yhat = np.load(Path(cache) / "rules" / f"{s}.npz")["yhat"][cut:]
|
||||
yhat = rules_yhat.copy()
|
||||
for j, f in enumerate(families):
|
||||
yhat[:, FAMILIES.index(f)] = proba[s][:, j] >= threshold
|
||||
keep = lambda c: {f: v for f, v in c.items() if f in families} # noqa: E731
|
||||
base[s], new[s] = keep(counts(d["y"][cut:], rules_yhat)), keep(counts(d["y"][cut:], yhat))
|
||||
for f, name, pb, pn in regressions(base[s], new[s]):
|
||||
print(f" regression: {s}, {f}, {name} {pb:.0f} % -> {pn:.0f} %"
|
||||
f" (rules {base[s][f]}, model {new[s].get(f)}: labelled, flagged, both)")
|
||||
show(f"Last {round(100 * (1 - CUT))} % of every station", total(base), total(new))
|
||||
return base, new
|
||||
|
||||
|
||||
def rules(a):
|
||||
sys.path[:0] = [str(Path(a.detectors) / "scripts"), str(Path(a.detectors) / "bench")]
|
||||
import score # noqa: E402
|
||||
|
||||
Reference in new issue
Block a user