feat: implement BTC/ETH correlation features for improved model accuracy

- Added a new design document outlining the integration of BTC/ETH candle data as additional features in the XRP ML filter, enhancing prediction accuracy.
- Introduced `MultiSymbolStream` for combined WebSocket data retrieval of XRP, BTC, and ETH.
- Expanded feature set from 13 to 21 by including 8 new BTC/ETH-related features.
- Updated various scripts and modules to support the new feature set and data handling.
- Enhanced training and deployment scripts to accommodate the new dataset structure.

This commit lays the groundwork for improved model performance by leveraging the correlation between BTC and ETH with XRP.

tests/test_bot.py

@@ -35,6 +35,19 @@ def sample_df():
     })
 
 
+def test_bot_uses_multi_symbol_stream(config):
+    from src.data_stream import MultiSymbolStream
+    with patch("src.bot.BinanceFuturesClient"):
+        bot = TradingBot(config)
+    assert isinstance(bot.stream, MultiSymbolStream)
+
+def test_bot_stream_has_btc_eth_buffers(config):
+    with patch("src.bot.BinanceFuturesClient"):
+        bot = TradingBot(config)
+    assert "btcusdt" in bot.stream.buffers
+    assert "ethusdt" in bot.stream.buffers
+
+
 @pytest.mark.asyncio
 async def test_bot_processes_signal(config, sample_df):
     with patch("src.bot.BinanceFuturesClient") as MockExchange:

tests/test_data_stream.py

@@ -2,6 +2,43 @@ import pytest
 import asyncio
 from unittest.mock import AsyncMock, patch, MagicMock
 from src.data_stream import KlineStream
+from src.data_stream import MultiSymbolStream
+
+
+def test_multi_symbol_stream_has_three_buffers():
+    stream = MultiSymbolStream(
+        symbols=["XRPUSDT", "BTCUSDT", "ETHUSDT"],
+        interval="1m",
+    )
+    assert "xrpusdt" in stream.buffers
+    assert "btcusdt" in stream.buffers
+    assert "ethusdt" in stream.buffers
+
+def test_multi_symbol_stream_get_dataframe_returns_none_when_empty():
+    stream = MultiSymbolStream(
+        symbols=["XRPUSDT", "BTCUSDT", "ETHUSDT"],
+        interval="1m",
+    )
+    assert stream.get_dataframe("XRPUSDT") is None
+
+def test_multi_symbol_stream_get_dataframe_returns_df_when_full():
+    import pandas as pd
+    stream = MultiSymbolStream(
+        symbols=["XRPUSDT", "BTCUSDT", "ETHUSDT"],
+        interval="1m",
+        buffer_size=200,
+    )
+    candle = {
+        "timestamp": 1000, "open": 1.0, "high": 1.1,
+        "low": 0.9, "close": 1.05, "volume": 100.0, "is_closed": True,
+    }
+    for i in range(50):
+        c = candle.copy()
+        c["timestamp"] = 1000 + i
+        stream.buffers["xrpusdt"].append(c)
+    df = stream.get_dataframe("XRPUSDT")
+    assert df is not None
+    assert len(df) == 50
 
 
 @pytest.mark.asyncio

tests/test_dataset_builder.py

@@ -29,12 +29,16 @@ def test_returns_dataframe(sample_df):
 
 
 def test_has_required_columns(sample_df):
-    """FEATURE_COLS + label 컬럼이 모두 있어야 한다."""
-    from src.ml_features import FEATURE_COLS
+    """기본 13개 피처 + label 컬럼이 모두 있어야 한다."""
+    BASE_FEATURE_COLS = [
+        "rsi", "macd_hist", "bb_pct", "ema_align",
+        "stoch_k", "stoch_d", "atr_pct", "vol_ratio",
+        "ret_1", "ret_3", "ret_5", "signal_strength", "side",
+    ]
     result = generate_dataset_vectorized(sample_df)
     if len(result) > 0:
         assert "label" in result.columns
-        for col in FEATURE_COLS:
+        for col in BASE_FEATURE_COLS:
             assert col in result.columns, f"컬럼 없음: {col}"
 
 
@@ -45,6 +49,30 @@ def test_label_is_binary(sample_df):
         assert set(result["label"].unique()).issubset({0, 1})
 
 
+def test_generate_dataset_vectorized_with_btc_eth_has_21_feature_cols():
+    """BTC/ETH DataFrame을 전달하면 결과 컬럼이 21개 피처 + label이어야 한다."""
+    import pandas as pd
+    import numpy as np
+    from src.dataset_builder import generate_dataset_vectorized
+    from src.ml_features import FEATURE_COLS
+
+    np.random.seed(42)
+    n = 500
+    closes = np.cumprod(1 + np.random.randn(n) * 0.001) * 1.0
+    xrp_df = pd.DataFrame({
+        "open": closes * 0.999, "high": closes * 1.005,
+        "low": closes * 0.995, "close": closes,
+        "volume": np.random.rand(n) * 1000 + 500,
+    })
+    btc_df = xrp_df.copy() * 50000
+    eth_df = xrp_df.copy() * 3000
+
+    result = generate_dataset_vectorized(xrp_df, btc_df=btc_df, eth_df=eth_df)
+    if not result.empty:
+        assert set(FEATURE_COLS).issubset(set(result.columns))
+        assert len(result.columns) == len(FEATURE_COLS) + 1  # +1 for label
+
+
 def test_matches_original_generate_dataset(sample_df):
     """벡터화 버전과 기존 버전의 샘플 수가 유사해야 한다.
 

tests/test_ml_features.py

@@ -4,6 +4,56 @@ import pytest
 from src.ml_features import build_features, FEATURE_COLS
 
 
+def _make_df(n=10, base_price=1.0):
+    """테스트용 더미 캔들 DataFrame 생성."""
+    closes = [base_price * (1 + i * 0.001) for i in range(n)]
+    return pd.DataFrame({
+        "close": closes, "high": [c * 1.01 for c in closes],
+        "low": [c * 0.99 for c in closes],
+        "volume": [1000.0] * n,
+        "rsi": [50.0] * n, "macd": [0.0] * n, "macd_signal": [0.0] * n,
+        "macd_hist": [0.0] * n, "bb_upper": [c * 1.02 for c in closes],
+        "bb_lower": [c * 0.98 for c in closes], "ema9": closes,
+        "ema21": closes, "ema50": closes, "atr": [0.01] * n,
+        "stoch_k": [50.0] * n, "stoch_d": [50.0] * n,
+        "vol_ma20": [1000.0] * n,
+    })
+
+
+def test_build_features_with_btc_eth_has_21_features():
+    xrp_df = _make_df(10, base_price=1.0)
+    btc_df = _make_df(10, base_price=50000.0)
+    eth_df = _make_df(10, base_price=3000.0)
+    features = build_features(xrp_df, "LONG", btc_df=btc_df, eth_df=eth_df)
+    assert len(features) == 21
+
+def test_build_features_without_btc_eth_has_13_features():
+    xrp_df = _make_df(10, base_price=1.0)
+    features = build_features(xrp_df, "LONG")
+    assert len(features) == 13
+
+def test_build_features_btc_ret_1_correct():
+    xrp_df = _make_df(10, base_price=1.0)
+    btc_df = _make_df(10, base_price=50000.0)
+    eth_df = _make_df(10, base_price=3000.0)
+    features = build_features(xrp_df, "LONG", btc_df=btc_df, eth_df=eth_df)
+    btc_closes = btc_df["close"]
+    expected_btc_ret_1 = (btc_closes.iloc[-1] - btc_closes.iloc[-2]) / btc_closes.iloc[-2]
+    assert abs(features["btc_ret_1"] - expected_btc_ret_1) < 1e-6
+
+def test_build_features_rs_zero_when_btc_ret_zero():
+    xrp_df = _make_df(10, base_price=1.0)
+    btc_df = _make_df(10, base_price=50000.0)
+    btc_df["close"] = 50000.0  # 모든 캔들 동일
+    eth_df = _make_df(10, base_price=3000.0)
+    features = build_features(xrp_df, "LONG", btc_df=btc_df, eth_df=eth_df)
+    assert features["xrp_btc_rs"] == 0.0
+
+def test_feature_cols_has_21_items():
+    from src.ml_features import FEATURE_COLS
+    assert len(FEATURE_COLS) == 21
+
+
 def make_df(n=100):
     """테스트용 최소 DataFrame 생성"""
     np.random.seed(42)
@@ -27,13 +77,19 @@ def test_build_features_returns_series():
     assert isinstance(features, pd.Series)
 
 
+BASE_FEATURE_COLS = [
+    "rsi", "macd_hist", "bb_pct", "ema_align",
+    "stoch_k", "stoch_d", "atr_pct", "vol_ratio",
+    "ret_1", "ret_3", "ret_5", "signal_strength", "side",
+]
+
 def test_build_features_has_all_cols():
     from src.indicators import Indicators
     df = make_df(100)
     ind = Indicators(df)
     df_ind = ind.calculate_all()
     features = build_features(df_ind, signal="LONG")
-    for col in FEATURE_COLS:
+    for col in BASE_FEATURE_COLS:
         assert col in features.index, f"피처 누락: {col}"