"""G3: S1 floor, percentile against the same-size null, mandatory member floor (MMIN), optional W.

Builds on gate2 (similarities, word test, k-means). On first import it samples the same-size null
distribution of S1 and caches the sorted samples in null-samples.pkl.
"""
import bisect, pathlib, pickle, random
import gate2 as g

HERE = pathlib.Path(__file__).resolve().parent
_path = HERE / 'null-samples.pkl'
if _path.exists():
    NULLS = pickle.loads(_path.read_bytes())
else:
    rnd, NULLS = random.Random(3033), {}
    for m in range(5, 151):
        need, samples = (1000 if m <= 60 else 200), []
        while len(samples) < need:
            members = rnd.sample(range(g.n), m)
            if g.eligible(members):
                samples.append(g.cohesion(members)[0])
        NULLS[m] = sorted(samples)
    _path.write_bytes(pickle.dumps(NULLS))

def percentile(s1, size):
    samples = NULLS[min(max(size, 5), 150)]
    return bisect.bisect_left(samples, s1) / len(samples)

def signals(m):
    sig = g.signals(m)            # size, stories, dominant, S1, Z1, MMIN, W, W_word, S6_old
    sig['PCT'] = percentile(sig['S1'], sig['size'])
    return sig

def passes(sig, gate):
    if not (sig['size'] >= g.MIN_SIZE and sig['stories'] >= g.MIN_STORIES and sig['dominant'] <= g.MAX_DOMINANT):
        return False
    if sig['S1'] < gate['S1'] or sig['PCT'] < gate['PCT'] or sig['MMIN'] < gate['MMIN']:
        return False
    if gate.get('W') is not None and sig['W'] >= gate['W']:
        return False
    return True