neuron/tools/retrieval-eval/diag6.py

import numpy as np, json, urllib.request, collections, math, re, sys, time, pickle, os
SP="/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad"
EV="/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/"
np.seterr(all='ignore')
t0=time.time()
M=np.load(SP+'/emb.npy'); eids=open(SP+'/ids.txt',encoding='utf-8',errors='surrogateescape').read().split('\n')
eidx={k:i for i,k in enumerate(eids)}
d=json.load(open('/Users/timlingo/neuron-memory-backups/snapshot-pre-repair-20260806.json',encoding='utf-8',errors='surrogateescape'))
STRUCT={"identity","contains","superseded_by","references","embodies","demonstrated_by","canonical-self","depends_on","currently_holds","activates"}
adj=collections.defaultdict(list)
for e in d['edges']:
    if e.get('relation') not in STRUCT: continue
    w=float(e.get('weight') or 0.0)
    adj[e['from_id']].append((e['to_id'],w)); adj[e['to_id']].append((e['from_id'],w))
nodes=d['nodes']
N={n['id']:n for n in nodes}
PRINT=re.compile(r'^[\x20-\x7e]+$')
ids=[]; hay=[]; dl=[]; sal=[]; addressable=[]
for n in nodes:
    i=n.get('id') or ''
    h=((n.get('content') or '')+'\x00'+(n.get('label') or '')+'\x00'+(n.get('tags') or '')).lower()
    ids.append(i); hay.append(h); dl.append(len(h)); sal.append(float(n.get('salience') or 0.0))
    addressable.append(bool(PRINT.match(i)))
del d
NN=len(ids); avgdl=sum(dl)/NN
print("nodes=%d avgdl=%.0f  %.1fs"%(NN,avgdl,time.time()-t0),file=sys.stderr)
gold={q['id']:q for q in json.load(open(EV+"gold_set.json"),)['queries']}
CACHE={}
def emb(t):
    if t in CACHE: return CACHE[t]
    b=json.dumps({"model":"nomic-embed-text","prompt":t}).encode()
    r=urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=b,headers={"Content-Type":"application/json"})
    v=np.array(json.load(urllib.request.urlopen(r,timeout=60))["embedding"],dtype=np.float32)
    v=v/(np.linalg.norm(v)+1e-9); CACHE[t]=v; return v
K1,B=1.2,0.75
def lexleg(query, lim=10):
    toks=[]
    for w in query.split():
        wl=w.lower()
        if wl not in toks: toks.append(wl)
    nt=len(toks)
    masks=[]; df=[0]*nt
    for i in range(NN):
        if not addressable[i]: continue
        h=hay[i]; m=0; sc=0
        for t in range(nt):
            if toks[t] in h: m|=(1<<t); sc+=1; df[t]+=1
        if sc: masks.append((i,m,sc))
    idf=[math.log(1.0+(NN-df[t]+0.5)/(df[t]+0.5)) for t in range(nt)]
    scored=[]
    for i,m,sc in masks:
        norm=1.0-B+B*dl[i]/avgdl
        s=0.0
        for t in range(nt):
            if m&(1<<t): s+=idf[t]*(K1+1.0)/(1.0+K1*norm)
        scored.append((s,i))
    scored.sort(key=lambda x:(-x[0], -sal[x[1]]))
    return [ids[i] for s,i in scored[:lim]], len(masks), sum(df)
FIRE=0.02; DECAY=0.7; DEPTH=2; SEED_MIN=0.60; ASSOC_MAX=64
def assoc(seeds, s):
    act={x:1.0 for x in seeds}; seen={x:2 for x in seeds}
    Q=[(x,0) for x in seeds]; h=0
    while h<len(Q):
        cur,hop=Q[h]; h+=1
        if hop>=DEPTH: continue
        p=act[cur]
        for oid,w in adj.get(cur,()):
            n=N.get(oid)
            if not n or n.get('node_type') in ('Tag','InternalStateEvent'): continue
            na=p*w*DECAY*float(n.get('salience') or 0.0)
            if na<FIRE: continue
            if oid in seen and na<=act.get(oid,0): continue
            act[oid]=na
            if oid not in seen: seen[oid]=1
            Q.append((oid,hop+1))
    out=[]
    for k,v in seen.items():
        if v!=1 or k not in eidx: continue
        c=float(s[eidx[k]])
        if c<=0: continue
        out.append((c,k))
    out.sort(reverse=True)
    return [k for c,k in out[:ASSOC_MAX]]

LEGS={}
for qid,q in gold.items():
    v=emb(q['query']); s=M@v; s[~np.isfinite(s)]=-1
    L,nmatch,dfsum=lexleg(q['query'])
    ordr=np.argsort(-s)
    Sall=[eids[j] for j in ordr[:40] if PRINT.match(eids[j] or '')]
    seeds=[x for x in L[:3] if x in N]
    seeds=seeds+[eids[j] for j in ordr[:8] if eids[j] in N and eids[j] not in seeds and PRINT.match(eids[j] or '')]
    A=assoc(seeds,s) if seeds else []
    A=[x for x in A if PRINT.match(x or '')]
    LEGS[qid]=dict(L=L,Sall=Sall,A=A,scos={x:float(s[eidx[x]]) for x in set(Sall[:20]+A[:20]+list(q.get('relevant') or [])) if x in eidx},nmatch=nmatch)
pickle.dump(LEGS,open(SP+'/legs6.pkl','wb'))

FOCUS=['q14','q17','q23','q24','q25','q30','q32','q33','q34','q35','q36','q37','q38']
for qid in FOCUS:
    q=gold[qid]; g=LEGS[qid]; rel=set(q.get('relevant') or [])
    def rk(lst):
        for i,x in enumerate(lst):
            if x in rel: return i+1
        return None
    print("%s %-12s nmatch=%-6d Lrank=%s Srank=%s Arank=%s |A|=%d"%(
        qid,q['category'],g['nmatch'],rk(g['L']),rk(g['Sall']),rk(g['A']),len(g['A'])))
    for r in list(rel)[:2]:
        print("     rel cos=%.3f"%(g['scos'].get(r,-9)))
    print("     topS cos:", ["%.3f"%g['scos'].get(x,-9) for x in g['Sall'][:3]])
print("elapsed %.1fs"%(time.time()-t0),file=sys.stderr)