"""Compare Claude's hand pass with the local pipeline, on files already on disk. No inference.

  cd probe/v2 && python3 claude/compare.py > claude/compare.log

1. Text: leakage of topic words (jobs, relationships, places) and capitalised names into the
   one-sentence predicaments, Claude vs qwen3:14b (same prompt rules).
2. Grouping: Claude's hand situations vs the k-means groups on the 14B predicament embeddings
   (k = 60; seed 24 is the review seed, 11-13 the measurement seeds).
"""
import collections, json, math, pathlib, re, statistics, sys
HERE = pathlib.Path(__file__).resolve().parent
sys.path.insert(0, str(HERE)); sys.path.insert(0, str(HERE.parent.parent))
from assign import ASSIGN
from topic_words import TOPIC_WORDS, PLACE_WORDS

chunks = json.load(open('chunks.json'))
n = len(chunks)
mine = {x['chunk']: x['summary'] for x in json.load(open(HERE / 'predicaments-claude.json'))['summaries']}
q14 = {x['chunk']: x['summary'] for x in json.load(open('predicaments_clean.json'))['summaries']}
q14raw = {x['chunk']: x.get('raw', x['summary']) for x in json.load(open('predicaments.json'))['summaries']}

def words(s): return re.findall(r"[a-zé']+", s.lower())
def caps_mid(s):
    toks = re.findall(r"[A-Za-z']+", s)
    return [t for t in toks[1:] if t[0].isupper() and t not in ('I',)]

print('== 1. Predicament text (839 scenes each) ==')
for name, d in (('claude', mine), ('qwen3:14b raw', q14raw), ('qwen3:14b after strip_names', q14)):
    tw = [set(words(d[i])) & TOPIC_WORDS for i in range(n)]
    pw = [set(words(d[i])) & PLACE_WORDS for i in range(n)]
    cm = [caps_mid(d[i]) for i in range(n)]
    lens = [len(d[i].split()) for i in range(n)]
    some = sum(1 for i in range(n) if d[i].lower().startswith('someone'))
    print(f'{name:30s} median words {statistics.median(lens):>4}  over 20 words {sum(l > 20 for l in lens):>3}  '
          f'with a topic word {sum(bool(x) for x in tw)/n:5.1%}  with a place word {sum(bool(x) for x in pw)/n:5.1%}  '
          f'capitalised mid-sentence {sum(bool(x) for x in cm):>3}  starts "Someone" {some/n:5.0%}')
    top = collections.Counter(w for x in tw for w in x).most_common(12)
    print(' ' * 32 + 'commonest topic words: ' + ', '.join(f'{w} {c}' for w, c in top))

# ---- 2. grouping agreement --------------------------------------------------------------
import os; EMB_FILE = os.environ.get('EMB_FILE', 'predicament_embeddings.json'); print('embeddings:', EMB_FILE); sys.argv = ['measure.py', EMB_FILE]
src = (HERE.parent.parent / 'measure.py').read_text(encoding='utf-8').split("print(f'{path.name}")[0]
exec(src)   # defines V, story, kmeans, describe, MIN_SIZE, MIN_STORIES, MAX_DOMINANT

def ari(labels_a, labels_b):
    pairs = collections.Counter(zip(labels_a, labels_b))
    a = collections.Counter(labels_a); b = collections.Counter(labels_b)
    c2 = lambda x: x * (x - 1) / 2
    idx = sum(c2(v) for v in pairs.values()); sa = sum(c2(v) for v in a.values()); sb = sum(c2(v) for v in b.values())
    exp = sa * sb / c2(len(labels_a)); mx = (sa + sb) / 2
    return (idx - exp) / (mx - exp) if mx != exp else 0.0

print('\n== 2. Claude hand situations vs 14B k-means groups (k = 60) ==')
print(f'Claude assigned {len(ASSIGN)} of {n} scenes to {len(set(ASSIGN.values()))} situations; the rest carry no recurring situation.')
for seed in (24, 11, 12, 13):
    groups = kmeans(60, seed)
    lab = {}
    for gi, g in enumerate(groups):
        for i in g: lab[i] = gi
    assigned = sorted(ASSIGN)
    a = ari([ASSIGN[i] for i in assigned], [lab[i] for i in assigned])
    cand = [g for g in groups if (lambda s: s[0] >= MIN_SIZE and s[1] >= MIN_STORIES and s[2] <= MAX_DOMINANT)(describe(g))]
    purities, unassigned = [], []
    for g in cand:
        sits = collections.Counter(ASSIGN[i] for i in g if i in ASSIGN)
        purities.append(sits.most_common(1)[0][1] / len(g) if sits else 0.0)
        unassigned.append(sum(1 for i in g if i not in ASSIGN) / len(g))
    print(f'seed {seed:>2}: ARI on assigned scenes {a:+.3f}; {len(cand)} candidate groups: median share of a group that is its '
          f'commonest Claude situation {statistics.median(purities):.0%}, median share with no situation {statistics.median(unassigned):.0%}')
    if seed == 24:
        spread = {}
        for s in sorted(set(ASSIGN.values())):
            mem = [i for i in ASSIGN if ASSIGN[i] == s]
            cl = collections.Counter(lab[i] for i in mem)
            spread[s] = (len(mem), len(cl), cl.most_common(1)[0][1] / len(mem))
        print('         how each Claude situation is scattered across the 14B groups at seed 24:')
        for s, (m, k, top) in sorted(spread.items(), key=lambda kv: -kv[1][0]):
            print(f'           {s:18s} {m:3d} scenes over {k:2d} groups; largest single group holds {top:4.0%}')
        rows = []
        for g in cand:
            sits = collections.Counter(ASSIGN[i] for i in g if i in ASSIGN)
            top = sits.most_common(1)[0] if sits else ('-', 0)
            rows.append((top[1] / len(g), len(g), top[0], sits))
        print('         the 14B candidate groups, purest first (share = scenes carrying the commonest Claude situation):')
        for share, size, s, sits in sorted(rows, reverse=True):
            other = ', '.join(f'{k} {v}' for k, v in sits.most_common()[1:4])
            print(f'           {share:4.0%} of {size:2d}  {s:18s} {("also " + other) if other else ""}')