Update app.py

app.py

@@ -23,13 +23,13 @@ COST = 2 * (COMMISSION + SLIPPAGE)
 REGIME_NAMES = ["TREND", "MEAN_REVERSION", "COMPRESSION"]
 HMM_K = 3
 TRAIN_FRAC, PURGE, EMBARGO = 0.60, 5, 3
-MIN_HMM, MIN_SIG = 200, 100
+MIN_HMM, MIN_SIG = 150, 80
 LEV_PRE = ("3L", "3S", "5L", "5S", "BULL", "BEAR", "UP", "DOWN")
 LEV_SUF = ("3LUSDT", "3SUSDT", "5LUSDT", "5SUSDT", "BULLUSDT", "BEARUSDT", "UPUSDT", "DOWNUSDT")
 FEAT_COLS = ["ret", "atr_norm", "ema_diff_norm", "efficiency", "rsi_dev", "dist_ma"]
 
-# OKX timeframe mapping: UI -> OKX bar string
 TF_MAP = {"15m": "15m", "1h": "1H", "4h": "4H", "1d": "1D"}
+TARGET_BARS = 1000
 
 
 # ---------- Helpers ----------
@@ -94,7 +94,6 @@ def _req(path, params, timeout=TIMEOUT):
 
 def fetch_pairs(n=30):
     """Fetch USDT spot pairs ranked by 24h quote volume on OKX."""
-    # 1) Instruments: get tradable SPOT USDT pairs
     inst = _req("/api/v5/public/instruments", {"instType": "SPOT"})
     if not inst:
         print("[RCEA] instruments unavailable", flush=True)
@@ -117,7 +116,6 @@ def fetch_pairs(n=30):
         print("[RCEA] no USDT spot pairs found", flush=True)
         return []
 
-    # 2) Tickers: rank by 24h quote volume (volCcy24h)
     tick = _req("/api/v5/market/tickers", {"instType": "SPOT"})
     if not tick:
         print("[RCEA] tickers unavailable", flush=True)
@@ -137,29 +135,58 @@ def fetch_pairs(n=30):
     return out
 
 
-def fetch_klines(inst_id, timeframe, limit=1000):
-    """Fetch OHLCV from OKX. Excludes unconfirmed candles (confirm=0)."""
+def fetch_klines(inst_id, timeframe, target_bars=TARGET_BARS):
+    """
+    Fetch OHLCV from OKX with pagination.
+    OKX returns max 300 bars per request, newest first.
+    Uses 'after' = oldest timestamp so far to page back in time.
+    """
     bar = TF_MAP[timeframe]
-    raw = _req("/api/v5/market/candles", {"instId": inst_id, "bar": bar, "limit": "300"})
-    if not raw:
-        return None
+    all_rows = []
+    after = None
+    max_pages = 10
+
+    for page in range(max_pages):
+        params = {"instId": inst_id, "bar": bar, "limit": "300"}
+        if after:
+            params["after"] = str(after)
+        raw = _req("/api/v5/market/candles", params)
+        if not raw:
+            break
+
+        got_new = 0
+        for k in raw:
+            if not isinstance(k, list) or len(k) < 9:
+                continue
+            if k[8] != "1":  # skip unconfirmed
+                continue
+            o, h, l, c, v = _f(k[1]), _f(k[2]), _f(k[3]), _f(k[4]), _f(k[5])
+            if None in (o, h, l, c, v) or min(o, h, l, c) <= 0:
+                continue
+            all_rows.append({"ts": int(k[0]),
+                             "open": o, "high": h, "low": l, "close": c, "volume": v})
+            got_new += 1
+
+        if got_new == 0:
+            break
 
-    rows = []
-    for k in raw:
-        if not isinstance(k, list) or len(k) < 9:
-            continue
-        # OKX kline format: [ts, o, h, l, c, vol, volCcy, volCcyQuote, confirm]
-        if k[8] != "1":  # skip unconfirmed candle
-            continue
-        o, h, l, c, v = _f(k[1]), _f(k[2]), _f(k[3]), _f(k[4]), _f(k[5])
-        if None in (o, h, l, c, v) or min(o, h, l, c) <= 0:
-            continue
-        rows.append({"open": o, "high": h, "low": l, "close": c, "volume": v})
+        try:
+            after = int(raw[-1][0])
+        except (IndexError, ValueError):
+            break
+
+        if len(all_rows) >= target_bars:
+            break
+        time.sleep(0.12)
 
-    if len(rows) < MIN_HMM:
+    if len(all_rows) < MIN_HMM:
         return None
-    # OKX returns newest first — reverse to chronological
-    return pd.DataFrame(rows[::-1]).reset_index(drop=True)
+
+    df = (pd.DataFrame(all_rows)
+          .drop_duplicates(subset=["ts"])
+          .sort_values("ts")
+          .reset_index(drop=True))
+    return df[["open", "high", "low", "close", "volume"]]
 
 
 # ---------- Features ----------
@@ -279,7 +306,13 @@ def backtest(sym, f, rp, acc, pl, ps, thr, mconf, maxhold):
     atr = f["atr"].values
     trades = []; in_pos = False; ei = eprice = d = sp = tp = 0
     reg = ""; rconf = 0.0
-    start = max(MIN_SIG, int(n * TRAIN_FRAC) + PURGE + EMBARGO)
+
+    # Start right after HMM training window + purge + embargo.
+    train_end = int(n * TRAIN_FRAC)
+    start = min(n - 2, train_end + PURGE + EMBARGO)
+    if start < MIN_SIG:
+        start = MIN_SIG
+
     for i in range(start, n):
         if not in_pos:
             p = rp[i]; dom = int(np.argmax(p)); conf = float(p[dom])
@@ -420,7 +453,8 @@ def run(timeframe, n_coins, thr, lam, mconf, maxhold, progress=gr.Progress()):
             f"**Threshold:** {thr} | **λ:** {lam} | **MinConf:** {mconf} | **MaxHold:** {maxhold}",
             f"**UTC:** {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M:%S')}"]
     if len(trades) < 30:
-        scan.append(f"\n⚠️ Only {len(trades)} trades — target ≥30. Metrics are descriptive only.")
+        scan.append(f"\n⚠️ Only {len(trades)} trades — target ≥30. "
+                    f"Try lowering threshold to ~0.10 or increasing coins.")
     scan_report = "\n".join(scan)
 
     if signals:
@@ -498,7 +532,8 @@ with gr.Blocks(title="RCEA Lite v1.0 — OKX") as demo:
         with gr.Tab("🪙 Coins"): coin_tbl = gr.Dataframe(interactive=False)
     btn.click(run, inputs=[tf, nc, thr_i, lam_i, mc_i, mh_i],
               outputs=[scan_out, met_out, sig_tbl, tr_tbl, reg_tbl, coin_tbl])
-    gr.Markdown("---\n**Data source:** OKX public REST API. Net of 0.10% commission + 0.05% slippage per side.")
+    gr.Markdown("---\n**Data source:** OKX public REST API. "
+                "Net of 0.10% commission + 0.05% slippage per side.")
 
 
 if __name__ == "__main__":