"""合成行业内中位数筛选：按有效观测数设置最低组规模。"""
import json
from collections import defaultdict
from decimal import Decimal as D
from statistics import median

rows = [("T1", "Tech", "10"), ("T2", "Tech", "20"), ("T3", "Tech", "30"),
        ("U1", "Utility", "4"), ("U2", "Utility", "6"), ("U3", "Utility", "8"),
        ("R1", "Rare", "2"), ("R2", "Rare", "4"), ("M1", None, "12"), ("T4", "Tech", None)]

def screen(records, minimum=3):
    groups = defaultdict(list)
    for symbol, industry, pe in records:
        if industry is not None and pe is not None and D(pe) > 0:
            groups[industry].append(D(pe))
    thresholds = {g: median(values) for g, values in groups.items() if len(values) >= minimum}
    results = {}
    for symbol, industry, pe in records:
        if industry is None:
            state = "missing_industry"
        elif pe is None:
            state = "missing_metric"
        elif industry not in thresholds:
            state = "small_group"
        else:
            state = "pass" if D(pe) > 0 and D(pe) <= thresholds[industry] else "fail"
        results[symbol] = state
    return thresholds, results, {g: len(values) for g, values in groups.items()}

thresholds, result, counts = screen(rows)
assert thresholds == {"Tech": D("20"), "Utility": D("6")}
assert sorted(s for s, state in result.items() if state == "pass") == ["T1", "T2", "U1", "U2"]
assert result["R1"] == result["R2"] == "small_group"
assert result["M1"] == "missing_industry" and result["T4"] == "missing_metric"
assert counts == {"Tech": 3, "Utility": 3, "Rare": 2}
assert screen(list(reversed(rows))) == (thresholds, result, counts)
print(json.dumps({"thresholds": {g: str(v) for g, v in thresholds.items()},
                  "valid_group_counts": counts, "states": result}, sort_keys=True))