"""Read what the tight-recurring clusters actually contain (pass-mark criterion 3).

  python3 sample_clusters.py summary_embeddings.json summaries_clean.json [k] [seed]

Uses the same clustering and the same definitions as measure.py, picks three
tight-recurring clusters at random (seeded, so the pick is reproducible and is
not chosen by looking), and prints each member's cleaned summary with the story
it came from. The question for a human reader: is each one recognisably ONE
kind of situation, or a prose register, or a shared vocabulary?
"""
import json, pathlib, random, statistics, sys

emb = sys.argv[1] if len(sys.argv) > 1 else 'summary_embeddings.json'
summ = sys.argv[2] if len(sys.argv) > 2 else 'summaries_clean.json'
K = int(sys.argv[3]) if len(sys.argv) > 3 else 60
SEED = int(sys.argv[4]) if len(sys.argv) > 4 else 11

sys.argv = ['measure.py', emb]
src = pathlib.Path('measure.py').read_text(encoding='utf-8')
exec(src.split("print(f'{path.name}")[0])     # loading, kmeans, describe, constants

summaries = json.loads(pathlib.Path(summ).read_text(encoding='utf-8'))['summaries']
text = {x['chunk']: x['summary'] for x in summaries}

clusters = kmeans(K, SEED)
rows = [(c, describe(c)) for c in clusters]
sized = [(c, d) for c, d in rows if d[0] >= MIN_SIZE]
cut = statistics.median(d[3] for _, d in sized)
tight = [(c, d) for c, d in sized if d[1] >= MIN_STORIES and d[2] <= MAX_DOMINANT and d[3] >= cut]
print(f'{emb}: k={K} seed={SEED}: {len(tight)} tight-recurring clusters of {len(sized)} sized\n')

for n, (c, (size, nst, dom, coh)) in enumerate(random.Random(SEED).sample(tight, min(3, len(tight))), 1):
    print(f'=== sample {n}: size {size}, {nst} stories, dominant {dom:.0%}, coherence {coh:.3f}')
    for i in c:
        print(f"  [{chunks[i]['title'][:28]:28}] {text.get(i, '(no summary)')}")
    print()