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_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