Maven/cmd/semantic-router-experiment/slice21_emit.py

#!/usr/bin/env python3
"""
Slice 21 emit: deterministic execution-frame guard — data files for the Go harness
==================================================================================

Slice 18 showed the sparse lexical gate owns the aggregate boundary (PR-AUC
0.838, strict operating point at threshold 0.715 with P>=0.95 | R=0.264) and
slice 19/20 showed learning heads collapse on capability-question LOFO. Slice 21
tests the deterministic alternative: a rule engine over existing parsers that
decides execution eligibility as a three-way gate (permissive / blocked /
ambiguous), never itself routing.

This script only repackages the frozen dev pool for the Go harness. It reuses
slice 18's feature builders and grouped-CV and slice 19's pair builder verbatim,
so the numbers the Go side reports are the same populations the accepts
measured. It writes:

    /tmp/mvn-s21/pool.json        dev rows: idx, text, n_text, route, y, tags,
                                  cv_fold, split_group, source_id, family
    /tmp/mvn-s21/pairs.json       capability-vs-action pairs (slice-19 builder)
    /tmp/mvn-s21/sparse_oof.json  slice-18 "both" grouped-CV OOF proba per row
                                  (for the §17 guard+sparse composition)

No training happens here and no label is changed. The guard itself is Go.
"""

import json
import os
import re
import sys

import numpy as np

HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE)

import slice18_sparse        # noqa: E402
import slice19_main          # noqa: E402

OUT_DIR = "/tmp/mvn-s21"
SPARSE_THRESHOLD = 0.715  # slice-18 §4 strict-operating-point (P>=0.95 best recall)


def main():
    # Population = the exact slice-20 dev pool (s19.load_dev): every dev_pool
    # row, fast-path included. The guard is evaluated on what slice 20 measured.
    meta, examples = slice18_sparse.load_data()
    dev = slice18_sparse.filter_dev_pool(examples)
    print(f"dev pool (all dev_pool rows): {len(dev)} rows")
    print(f"corpus meta: {meta.get('dev_count', '?')} dev rows declared, "
          f"{meta.get('route_counts', {}).get('action', '?')} action declared")

    n_texts = [slice18_sparse.normalize_match_text(e["text"]) for e in dev]

    rows = []
    by_route = {}
    by_family = {}
    for i, (e, nt) in enumerate(zip(dev, n_texts)):
        tags = sorted(set(e.get("tags", [])))
        route = e["route"]
        fam = slice19_main.family_of(set(tags))
        by_route[route] = by_route.get(route, 0) + 1
        by_family[fam] = by_family.get(fam, 0) + 1
        rows.append({
            "idx": i,
            "text": e["text"],
            "n_text": nt,
            "route": route,
            "y": 1 if route == "action" else 0,
            "tags": tags,
            "cv_fold": e["cv_fold"],
            "split_group": e["split_group"],
            "source_id": e["source_id"],
        })

    print("routes:", by_route)
    print("families:", by_family)

    # ── pairs (slice-19 builder, exact population) ─────────────────────────
    ldev = [{
        "text_orig": nt,
        "route": r["route"],
        "y": r["y"],
        "cv_fold": r["cv_fold"],
        "tags": set(r["tags"]),
        "source_id": r["source_id"],
    } for r, nt in zip(rows, n_texts)]
    pairs = slice19_main.build_pairs(ldev, n_texts)
    print(f"pairs: {len(pairs)}")

    # ── slice-18 "both" grouped-CV OOF proba, aligned to row index ────────
    y = [1 if r["route"] == "action" else 0 for r in rows]
    folds = [r["cv_fold"] for r in rows]
    X, _vec = slice18_sparse.build_features(n_texts, "both")
    print(f"sparse 'both' X: {X.shape}")
    yb = np.array(y)
    folds_arr = np.array(folds)
    idx_proba = {}
    for te_fold in sorted(set(folds)):
        tr = folds_arr != te_fold
        te = folds_arr == te_fold
        clf = slice18_sparse.LogisticRegression(
            C=1.0, max_iter=2000, solver="lbfgs", random_state=42)
        clf.fit(X[tr], yb[tr])
        p = clf.predict_proba(X[te])[:, 1]
        te_idx = np.where(te)[0]
        for k, i in enumerate(te_idx):
            idx_proba[int(i)] = float(p[k])
    assert len(idx_proba) == len(rows)
    sparse_oof = [{"idx": i, "proba": idx_proba[i]} for i in range(len(rows))]
    pred = [1 if idx_proba[i] >= 0.5 else 0 for i in range(len(rows))]
    tp = sum(1 for i in range(len(rows)) if y[i] == 1 and pred[i] == 1)
    fp = sum(1 for i in range(len(rows)) if y[i] == 0 and pred[i] == 1)
    fn = sum(1 for i in range(len(rows)) if y[i] == 1 and pred[i] == 0)
    print(f"sparse both OOF @0.5: P={tp/max(tp+fp,1):.3f} R={tp/max(tp+fn,1):.3f} "
          f"FA={fp} ({fp/len(rows):.4f})")
    pred21 = [1 if idx_proba[i] >= SPARSE_THRESHOLD else 0 for i in range(len(rows))]
    tp = sum(1 for i in range(len(rows)) if y[i] == 1 and pred21[i] == 1)
    fp = sum(1 for i in range(len(rows)) if y[i] == 0 and pred21[i] == 1)
    fn = sum(1 for i in range(len(rows)) if y[i] == 1 and pred21[i] == 0)
    print(f"sparse both OOF @{SPARSE_THRESHOLD}: P={tp/max(tp+fp,1):.3f} "
          f"R={tp/max(tp+fn,1):.3f} FA={fp} ({fp/len(rows):.4f})")

    os.makedirs(OUT_DIR, exist_ok=True)
    with open(os.path.join(OUT_DIR, "pool.json"), "w") as f:
        json.dump(rows, f, ensure_ascii=False, indent=1)
    with open(os.path.join(OUT_DIR, "pairs.json"), "w") as f:
        json.dump([[c, a] for c, a in pairs], f)
    with open(os.path.join(OUT_DIR, "sparse_oof.json"), "w") as f:
        json.dump(sparse_oof, f)
    print(f"wrote {OUT_DIR}/{{pool,pairs,sparse_oof}}.json")


if __name__ == "__main__":
    main()