feat: complete BTC ML trading strategy optimizer

Multi-machine optimization loop: - VPS orchestrator coordinates training and LLM analysis - Windows PC (RTX 4070 Ti) runs XGBoost/LightGBM/CatBoost with GPU - Mac Mini runs qwen3.5:27b via Ollama for strategy analysis Includes 60+ technical features, walk-forward validation, confidence-scaled position sizing, and automated convergence detection. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-19 21:25:44 +00:00
parent 7b9a4bfde7
commit 8ff35c1a86
13 changed files with 1420 additions and 2 deletions
@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""Fetch BTC/USDT OHLCV data from Binance using ccxt."""
+
+import os
+import sys
+import time
+import ccxt
+import pandas as pd
+from datetime import datetime, timezone
+
+DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "data")
+SYMBOL = "BTC/USDT"
+EXCHANGE_ID = "binance"
+YEARS_HISTORY = 2
+LIMIT_PER_REQUEST = 1000  # Binance max
+
+
+def fetch_ohlcv(timeframe: str) -> pd.DataFrame:
+    """Fetch OHLCV data for a given timeframe."""
+    exchange = ccxt.binance({"enableRateLimit": True})
+
+    # Calculate start time
+    now_ms = int(time.time() * 1000)
+    if timeframe == "1h":
+        ms_per_candle = 3600 * 1000
+    elif timeframe == "4h":
+        ms_per_candle = 4 * 3600 * 1000
+    else:
+        raise ValueError(f"Unsupported timeframe: {timeframe}")
+
+    since = now_ms - (YEARS_HISTORY * 365 * 24 * 3600 * 1000)
+
+    all_candles = []
+    print(f"  Fetching {SYMBOL} {timeframe} from {datetime.fromtimestamp(since / 1000, tz=timezone.utc).strftime('%Y-%m-%d')}...")
+
+    while since < now_ms:
+        try:
+            candles = exchange.fetch_ohlcv(SYMBOL, timeframe, since=since, limit=LIMIT_PER_REQUEST)
+        except Exception as e:
+            print(f"  Warning: fetch error, retrying in 5s — {e}")
+            time.sleep(5)
+            continue
+
+        if not candles:
+            break
+
+        all_candles.extend(candles)
+        since = candles[-1][0] + ms_per_candle
+        sys.stdout.write(f"\r  Downloaded {len(all_candles)} candles...")
+        sys.stdout.flush()
+        time.sleep(exchange.rateLimit / 1000)
+
+    print(f"\r  Downloaded {len(all_candles)} candles total.")
+
+    df = pd.DataFrame(all_candles, columns=["timestamp", "open", "high", "low", "close", "volume"])
+    df["timestamp"] = pd.to_datetime(df["timestamp"], unit="ms", utc=True)
+    df = df.drop_duplicates(subset=["timestamp"]).sort_values("timestamp").reset_index(drop=True)
+    return df
+
+
+def main():
+    os.makedirs(DATA_DIR, exist_ok=True)
+
+    for tf in ["1h", "4h"]:
+        print(f"\n[*] Fetching {tf} data...")
+        df = fetch_ohlcv(tf)
+        out_path = os.path.join(DATA_DIR, f"btc_{tf}.csv")
+        df.to_csv(out_path, index=False)
+        print(f"  Saved {len(df)} rows to {out_path}")
+        print(f"  Range: {df['timestamp'].iloc[0]} → {df['timestamp'].iloc[-1]}")
+
+    print("\nData fetch complete!")
+
+
+if __name__ == "__main__":
+    main()