265 lines
11 KiB
Python
265 lines
11 KiB
Python
"""Final statistics pass over all eval per_item logs (CPU only).
|
|
|
|
Produces results-loop/STATS.md + stats_final.json:
|
|
1. Wilson 95% CIs for every headline number (overall + hard bucket).
|
|
2. Exact McNemar tests for the key paired comparisons (same items).
|
|
3. Pooled hard bucket across MBPP + HumanEval + Rust (paired k>0 vs k0
|
|
within each item, pooled counts).
|
|
4. Label-robustness check: hard bucket redefined via consensus k0
|
|
failure across seeds instead of the single greedy labeling run.
|
|
"""
|
|
|
|
import json
|
|
import math
|
|
from pathlib import Path
|
|
|
|
OUT = Path(__file__).resolve().parent.parent / "results-loop"
|
|
|
|
|
|
def wilson(c, n, z=1.96):
|
|
if n == 0:
|
|
return (float("nan"), float("nan"))
|
|
p = c / n
|
|
d = 1 + z * z / n
|
|
ctr = (p + z * z / (2 * n)) / d
|
|
hw = z * math.sqrt(p * (1 - p) / n + z * z / (4 * n * n)) / d
|
|
return (ctr - hw, ctr + hw)
|
|
|
|
|
|
def binom_two_sided(k, n):
|
|
"""Exact two-sided binomial test p-value, p0=0.5 (for McNemar)."""
|
|
if n == 0:
|
|
return 1.0
|
|
def pmf(i):
|
|
return math.comb(n, i) * 0.5 ** n
|
|
pk = pmf(k)
|
|
return min(1.0, sum(pmf(i) for i in range(n + 1) if pmf(i) <= pk + 1e-12))
|
|
|
|
|
|
def mcnemar(pairs):
|
|
"""pairs: list of (a_ok, b_ok). Returns dict with discordants + p."""
|
|
b01 = sum(1 for a, b in pairs if not a and b) # b wins
|
|
b10 = sum(1 for a, b in pairs if a and not b) # a wins
|
|
return {"n": len(pairs), "a_only": b10, "b_only": b01,
|
|
"p": binom_two_sided(min(b01, b10), b01 + b10)}
|
|
|
|
|
|
def load_labels(path, key, lab_key="label"):
|
|
data = json.load(open(OUT / path))
|
|
return {it[key]: it[lab_key] for it in data
|
|
if it.get("split", "test") == "test"}
|
|
|
|
|
|
def per_item(fname, k):
|
|
d = json.load(open(OUT / fname))
|
|
v = d["ks"][str(k)]
|
|
key = "task_id" if "task_id" in v["per_item"][0] else "idx"
|
|
return {it[key]: it["ok"] for it in v["per_item"]}
|
|
|
|
|
|
def acc_ci(ok_map, subset=None):
|
|
ids = [i for i in ok_map if subset is None or i in subset]
|
|
c = sum(ok_map[i] for i in ids)
|
|
lo, hi = wilson(c, len(ids))
|
|
return {"acc": c / len(ids) if ids else float("nan"), "n": len(ids),
|
|
"ci": [round(lo, 3), round(hi, 3)]}
|
|
|
|
|
|
def fmt(r):
|
|
return f"{r['acc']:.3f} [{r['ci'][0]:.3f}, {r['ci'][1]:.3f}] (n={r['n']})"
|
|
|
|
|
|
def main():
|
|
mbpp_lab = load_labels("mbpp_data.json", "task_id")
|
|
he_lab = {k: ("hard" if v else "easy") # plan-reachable flag; hard needs k0-fail
|
|
for k, v in json.load(open(OUT / "humaneval_labels.json")).items()}
|
|
rust_lab = load_labels("rust_data.json", "task_id")
|
|
|
|
mbpp_hard = {t for t, l in mbpp_lab.items() if l == "hard"}
|
|
rust_hard = {t for t, l in rust_lab.items() if l == "hard"}
|
|
|
|
report = {}
|
|
lines = ["# Final statistics pass", ""]
|
|
|
|
# ---------- 1. headline numbers with Wilson CIs ----------
|
|
lines += ["## Headline numbers (Wilson 95% CIs)", ""]
|
|
ARMS = [
|
|
# (label, file, k, hard-subset)
|
|
("MBPP loop s0 k=0 (base)", "eval_code_code_s0_full.json", 0, mbpp_hard),
|
|
("MBPP loop s0 k=2", "eval_code_code_s0_full.json", 2, mbpp_hard),
|
|
("MBPP loop s0 k=4", "eval_code_code_s0_full.json", 4, mbpp_hard),
|
|
("MBPP distill s1 k=1 (FF)", "eval_code_distill_s1.json", 1, mbpp_hard),
|
|
("MBPP pause16 k=1", "eval_code_pause16.json", 1, mbpp_hard),
|
|
("MBPP stack-train k=4", "eval_code_stack_train.json", 4, mbpp_hard),
|
|
("MBPP distill-in-loopmode k=2", "eval_code_distill_loopmode.json", 2, mbpp_hard),
|
|
("Rust transfer k=0", "eval_rust_py_transfer.json", 0, rust_hard),
|
|
("Rust transfer k=4", "eval_rust_py_transfer.json", 4, rust_hard),
|
|
]
|
|
arm_maps = {}
|
|
for label, f, k, hard in ARMS:
|
|
m = per_item(f, k)
|
|
arm_maps[label] = (m, hard)
|
|
o, h = acc_ci(m), acc_ci(m, hard)
|
|
report[label] = {"overall": o, "hard": h}
|
|
lines.append(f"- **{label}**: overall {fmt(o)}; hard {fmt(h)}")
|
|
|
|
# HumanEval: hard = plan-reachable AND k0-fail (per its eval definition)
|
|
he_tr0 = per_item("eval_humaneval_trained.json", 0)
|
|
he_hard = {t for t in he_tr0 if he_lab.get(t) == "hard" and not he_tr0[t]}
|
|
for label, f, k in [("HumanEval loop k=4", "eval_humaneval_trained.json", 4),
|
|
("HumanEval distill k=1", "eval_humaneval_distill_transfer.json", 1)]:
|
|
m = per_item(f, k)
|
|
o, h = acc_ci(m), acc_ci(m, he_hard)
|
|
arm_maps[label] = (m, he_hard)
|
|
report[label] = {"overall": o, "hard": h}
|
|
lines.append(f"- **{label}**: overall {fmt(o)}; hard {fmt(h)}")
|
|
|
|
# best-of-3 / budget-CoT (no per_item; CI from counts)
|
|
for label, f in [("MBPP best-of-3 (compute-matched)", "eval_bestof3.json"),
|
|
("MBPP budget-CoT-50", "eval_budgetcot.json")]:
|
|
d = json.load(open(OUT / f))
|
|
n, nh = 500, len(mbpp_hard)
|
|
o = {"acc": d["acc"], "n": n,
|
|
"ci": [round(x, 3) for x in wilson(round(d["acc"] * n), n)]}
|
|
hacc = d["by_label"]["hard"]
|
|
h = {"acc": hacc, "n": nh,
|
|
"ci": [round(x, 3) for x in wilson(round(hacc * nh), nh)]}
|
|
report[label] = {"overall": o, "hard": h}
|
|
lines.append(f"- **{label}**: overall {fmt(o)}; hard {fmt(h)}")
|
|
|
|
# distill seed spread
|
|
hs, os_ = [], []
|
|
files = ["eval_code_code_distill.json"] + [
|
|
f"eval_code_distill_s{s}.json" for s in range(1, 8)]
|
|
for f in files:
|
|
try:
|
|
m = per_item(f, 1)
|
|
except FileNotFoundError:
|
|
continue
|
|
hs.append(acc_ci(m, mbpp_hard)["acc"])
|
|
os_.append(acc_ci(m)["acc"])
|
|
mean = sum(hs) / len(hs)
|
|
sd = (sum((x - mean) ** 2 for x in hs) / (len(hs) - 1)) ** 0.5
|
|
lines.append(f"- **MBPP distill, {len(hs)} runs (hard)**: mean {mean:.3f} "
|
|
f"± {sd:.3f} sd (range {min(hs):.3f}-{max(hs):.3f}); "
|
|
f"overall mean {sum(os_)/len(os_):.3f}")
|
|
report["distill_seed_spread"] = {"hard": hs, "overall": os_}
|
|
|
|
# loop seed spread (s0..s4 k=4)
|
|
lh = []
|
|
for tag in ["s0_full", "s1", "s2", "s3", "s4"]:
|
|
try:
|
|
m = per_item(f"eval_code_code_{tag}.json", 4)
|
|
lh.append(acc_ci(m, mbpp_hard)["acc"])
|
|
except (FileNotFoundError, KeyError):
|
|
pass
|
|
if lh:
|
|
mean = sum(lh) / len(lh)
|
|
sd = (sum((x - mean) ** 2 for x in lh) / max(1, len(lh) - 1)) ** 0.5
|
|
lines.append(f"- **MBPP loop seeds k=4 (hard)**: mean {mean:.3f} "
|
|
f"± {sd:.3f} sd (n_seeds={len(lh)})")
|
|
report["loop_seed_spread_hard"] = lh
|
|
|
|
# ---------- 2. McNemar paired tests ----------
|
|
lines += ["", "## McNemar exact tests (paired on items)", ""]
|
|
|
|
def pair(m_a, m_b, subset=None):
|
|
ids = [i for i in m_a if i in m_b
|
|
and (subset is None or i in subset)]
|
|
return [(m_a[i], m_b[i]) for i in ids]
|
|
|
|
loop0, _ = arm_maps["MBPP loop s0 k=0 (base)"]
|
|
loop4, _ = arm_maps["MBPP loop s0 k=4"]
|
|
dist1, _ = arm_maps["MBPP distill s1 k=1 (FF)"]
|
|
stack4, _ = arm_maps["MBPP stack-train k=4"]
|
|
|
|
TESTS = [
|
|
("loop k=4 vs k=0, overall", loop0, loop4, None),
|
|
("loop k=4 vs k=0, hard", loop0, loop4, mbpp_hard),
|
|
("distill k=1 vs loop k=4, overall", loop4, dist1, None),
|
|
("distill k=1 vs loop k=4, hard", loop4, dist1, mbpp_hard),
|
|
("stack-train k=4 vs distill k=1, hard", dist1, stack4, mbpp_hard),
|
|
("HumanEval loop k=4 vs k=0, overall", he_tr0,
|
|
arm_maps["HumanEval loop k=4"][0], None),
|
|
("HumanEval distill k=1 vs k=0, overall", he_tr0,
|
|
arm_maps["HumanEval distill k=1"][0], None),
|
|
("HumanEval trained vs UNTRAINED merge (k=2), overall",
|
|
per_item("eval_humaneval_untrained.json", 2),
|
|
per_item("eval_humaneval_trained.json", 2), None),
|
|
]
|
|
rust0 = arm_maps["Rust transfer k=0"][0]
|
|
rust4 = arm_maps["Rust transfer k=4"][0]
|
|
TESTS += [("Rust loop k=4 vs k=0, overall", rust0, rust4, None),
|
|
("Rust loop k=4 vs k=0, hard", rust0, rust4, rust_hard)]
|
|
|
|
report["mcnemar"] = {}
|
|
for name, a, b, subset in TESTS:
|
|
r = mcnemar(pair(a, b, subset))
|
|
report["mcnemar"][name] = r
|
|
sig = "**significant**" if r["p"] < 0.05 else "n.s."
|
|
lines.append(f"- {name}: A-only {r['a_only']}, B-only {r['b_only']}, "
|
|
f"n={r['n']}, p={r['p']:.4g} ({sig})")
|
|
|
|
# ---------- 3. pooled hard bucket across benchmarks ----------
|
|
lines += ["", "## Pooled hard bucket (MBPP + HumanEval + Rust)",
|
|
"", "Paired within-item k>0 vs k=0, counts pooled across "
|
|
"benchmarks (loop arm; distill pooled where available).", ""]
|
|
pooled_loop = (pair(loop0, loop4, mbpp_hard)
|
|
+ pair(he_tr0, arm_maps["HumanEval loop k=4"][0], he_hard)
|
|
+ pair(rust0, rust4, rust_hard))
|
|
r = mcnemar(pooled_loop)
|
|
c_base = sum(a for a, _ in pooled_loop)
|
|
c_loop = sum(b for _, b in pooled_loop)
|
|
n = len(pooled_loop)
|
|
lines.append(f"- **loop**: base {c_base}/{n} -> loop {c_loop}/{n} "
|
|
f"({c_base/n:.3f} -> {c_loop/n:.3f}, CI "
|
|
f"{[round(x,3) for x in wilson(c_loop, n)]}), "
|
|
f"McNemar p={r['p']:.3g}")
|
|
report["pooled_hard_loop"] = {"base": c_base, "arm": c_loop, "n": n,
|
|
"mcnemar": r}
|
|
pooled_dist = (pair(loop0, dist1, mbpp_hard)
|
|
+ pair(he_tr0, arm_maps["HumanEval distill k=1"][0], he_hard))
|
|
r = mcnemar(pooled_dist)
|
|
c_base = sum(a for a, _ in pooled_dist)
|
|
c_d = sum(b for _, b in pooled_dist)
|
|
n = len(pooled_dist)
|
|
lines.append(f"- **distill**: base {c_base}/{n} -> distill {c_d}/{n} "
|
|
f"({c_base/n:.3f} -> {c_d/n:.3f}, CI "
|
|
f"{[round(x,3) for x in wilson(c_d, n)]}), "
|
|
f"McNemar p={r['p']:.3g}")
|
|
report["pooled_hard_distill"] = {"base": c_base, "arm": c_d, "n": n,
|
|
"mcnemar": r}
|
|
|
|
# ---------- 4. label robustness: consensus-k0 hard set ----------
|
|
lines += ["", "## Label robustness (consensus-k0 hard set)", "",
|
|
"Hard bucket redefined as: labeled hard AND k=0 fails in "
|
|
"every seed's own eval run (removes single-greedy-run "
|
|
"selection noise).", ""]
|
|
k0maps = []
|
|
for tag in ["s0_full", "s1", "s2", "s3", "s4"]:
|
|
try:
|
|
k0maps.append(per_item(f"eval_code_code_{tag}.json", 0))
|
|
except (FileNotFoundError, KeyError):
|
|
pass
|
|
consensus = {t for t in mbpp_hard
|
|
if all(not m.get(t, False) for m in k0maps)}
|
|
lines.append(f"- consensus hard set: {len(consensus)} of "
|
|
f"{len(mbpp_hard)} labeled-hard items")
|
|
for label in ["MBPP loop s0 k=4", "MBPP distill s1 k=1 (FF)",
|
|
"MBPP stack-train k=4"]:
|
|
m, _ = arm_maps[label]
|
|
r0 = acc_ci(m, mbpp_hard)
|
|
rc = acc_ci(m, consensus)
|
|
lines.append(f"- {label}: labeled-hard {r0['acc']:.3f} -> "
|
|
f"consensus-hard {fmt(rc)}")
|
|
report.setdefault("consensus_hard", {})[label] = rc
|
|
|
|
(OUT / "STATS.md").write_text("\n".join(lines) + "\n")
|
|
json.dump(report, open(OUT / "stats_final.json", "w"), indent=1)
|
|
print("\n".join(lines))
|
|
print("\nwrote", OUT / "STATS.md", "and stats_final.json")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|