""" arhs_matches_report.py -- [2026-10-01] The user: take the 150 playbook days most like ARHS at 9:35 (first 5 minutes), review each, mark the best entry and exit. Charts (same marks as the library: best holdable buy/sell, 1% stop never hit; second move) + a summary of what those 150 days did after 9:35, and a PDF. """ import gzip import json import statistics as st import sys from collections import Counter from datetime import datetime from pathlib import Path from zoneinfo import ZoneInfo import matplotlib matplotlib.use("Agg") import matplotlib.dates as md import matplotlib.pyplot as plt HERE = Path(__file__).resolve().parent TRADE = Path("/var/www/screener/trade") sys.path.insert(0, str(TRADE)); sys.path.insert(0, str(HERE)) import reference as REF import label_days as LD from alpaca_client import get_client ET = ZoneInfo("America/New_York") OUT = HERE / "arhs_0935" M = json.load(open(HERE / "arhs_0935_matches.json")) MATCH_M = M["m"] def draw(lab, B, path, rank=None, dist=None): ts = [x["t"].replace(tzinfo=None) for x in B] fig, (ax, axv) = plt.subplots(2, 1, figsize=(10.5, 5.0), gridspec_kw={"height_ratios": [3, 1]}, sharex=True) ax.plot(ts, [x["c"] for x in B], color="#1f3a5f", lw=1) ax.plot(ts, [x["vwap"] for x in B], color="#c0392b", lw=1.1) ax.axhline(B[0]["o"], color="grey", ls=":", lw=.8) t935 = B[0]["t"].replace(tzinfo=None, hour=9, minute=35, second=0) ax.axvline(t935, color="#e67e22", ls="--", lw=1) lo = min(x["l"] for x in B); hi = max(x["h"] for x in B); pad = (hi - lo) * .14 ax.set_ylim(lo - pad, hi + pad) for key, col in (("best_held", "#16a085"), ("leg2", "#2980b9")): mk = lab.get(key) if not mk: continue bi = next(x for x in B if x["m"] == mk["entry_m"]); bj = next(x for x in B if x["m"] == mk["exit_m"]) ax.scatter([bi["t"].replace(tzinfo=None)], [bi["c"]], marker="*", s=170, color=col, edgecolor="black", zorder=6) ax.scatter([bj["t"].replace(tzinfo=None)], [bj["c"]], marker="*", s=170, color="#8e44ad", edgecolor="black", zorder=6) ax.annotate(f"buy {bi['c']:.2f} ({bi['t']:%H:%M})", (bi["t"].replace(tzinfo=None), bi["c"]), xytext=(6, -14), textcoords="offset points", fontsize=7, color=col, fontweight="bold") ax.annotate(f"sell {bj['c']:.2f} ({bj['t']:%H:%M}) +{mk['gain_pct']:.1f}%", (bj["t"].replace(tzinfo=None), bj["c"]), xytext=(6, 7), textcoords="offset points", fontsize=7, color="#8e44ad", fontweight="bold") bh = lab.get("best_held") head = f"#{rank} " if rank else "" ax.set_title(f"{head}{lab['symbol']} {lab['date']} open->close {lab['open_to_close_pct']:+.1f}%" + (f" | match distance {dist:.3f}" if dist is not None else "") + (" | NO GOOD TRADE" if lab["no_trade"] else f" | best +{bh['gain_pct']:.1f}%: " + ", ".join(bh['entry']['tags']) + " -> " + ", ".join(bh['exit']['tags'])), fontsize=7.5) ax.grid(alpha=.3) axv.bar(ts, [x["v"] for x in B], width=1 / 1440, color=["#8e44ad" if x["volx"] >= 10 else "#1f3a5f" for x in B]) axv.xaxis.set_major_formatter(md.DateFormatter("%H:%M")); axv.grid(alpha=.3) plt.tight_layout(); plt.savefig(path, dpi=92); plt.close() def main(): OUT.mkdir(exist_ok=True) labels = {} want = {tuple(k.split("|")) for k in M["matches"]} for l in map(json.loads, open(LD.OUT)): if (l["date"], l["symbol"]) in want: labels[(l["date"], l["symbol"])] = l # ARHS itself d = datetime(2026, 10, 1, tzinfo=ET) raw = get_client().get_minute_bars("ARHS", start=d.replace(hour=9, minute=30), end=d.replace(hour=16), limit=1000) rows = [[int(b.timestamp.timestamp()), float(b.open), float(b.high), float(b.low), float(b.close), float(b.volume)] for b in raw] B = LD.build(rows, REF.load("2026-10-01", "ARHS")) arhs = LD.label("2026-10-01", "ARHS", B) draw(arhs, B, OUT / "000_ARHS_2026-10-01.png") stats = [] by_date = {} for rank, (k, dist) in enumerate(zip(M["matches"], M["dist"]), 1): day, s = k.split("|") by_date.setdefault(day, []).append((rank, s, dist)) for day, items in sorted(by_date.items()): dd = json.load(gzip.open(LD.BARS / f"bars_{day}.json.gz", "rt")) for rank, s, dist in items: ref = REF.load(day, s); lab = labels.get((day, s)) if not ref or not lab: continue Bm = LD.build(dd["symbols"][s]["bars"], ref) draw(lab, Bm, OUT / f"{rank:03d}_{s}_{day}.png", rank, dist) c935 = next(x["c"] for x in Bm if x["m"] >= MATCH_M) up = dn = False for x in Bm: if x["m"] <= MATCH_M or x["m"] > 385: continue if x["l"] <= c935 * .99: dn = True; break if x["h"] >= c935 * 1.02: up = True; break stats.append({"rank": rank, "lab": lab, "up": up, "dn": dn, "close_from_935": (Bm[-1]["c"] / c935 - 1) * 100, "max_from_935": (max(x["h"] for x in Bm if x["m"] > MATCH_M) / c935 - 1) * 100}) REF._CACHE.clear() bh = [s["lab"]["best_held"] for s in stats if s["lab"]["best_held"]] em = [b["entry_m"] for b in bh]; xm = [b["exit_m"] for b in bh] hm = lambda m: f"{9 + (30 + m) // 60}:{(30 + m) % 60:02d}" summ = { "n": len(stats), "no_trade": sum(s["lab"]["no_trade"] for s in stats), "best_held_median": round(st.median(b["gain_pct"] for b in bh), 2), "best_buy_median": hm(int(st.median(em))), "best_sell_median": hm(int(st.median(xm))), "best_buy_before_935": sum(m < MATCH_M for m in em), "best_buy_935_1000": sum(MATCH_M <= m < 30 for m in em), "best_buy_1000_1100": sum(30 <= m < 90 for m in em), "best_buy_after_1100": sum(m >= 90 for m in em), "up_first_from_935": sum(s["up"] for s in stats), "down_first_from_935": sum(s["dn"] for s in stats), "close_from_935_median": round(st.median(s["close_from_935"] for s in stats), 2), "up_days": sum(s["lab"]["open_to_close_pct"] > 0 for s in stats), "buy_tags": Counter(t.split(" (")[0] for b in bh for t in b["entry"]["tags"]).most_common(4), "sell_tags": Counter(t.split(" (")[0].split(" 1")[0].split(" 2")[0].split(" 3")[0].split(" 4")[0].split(" 5")[0] for b in bh for t in b["exit"]["tags"]).most_common(4), "arhs": {"best_held": arhs["best_held"]["gain_pct"] if arhs["best_held"] else None, "buy": hm(arhs["best_held"]["entry_m"]) if arhs["best_held"] else None, "sell": hm(arhs["best_held"]["exit_m"]) if arhs["best_held"] else None}, } json.dump(summ, open(OUT / "summary.json", "w"), indent=1, default=str) print(json.dumps(summ, indent=1, default=str)) if __name__ == "__main__": main()