feat: implement EURGBP volume proxy divergence 5m strategy (closes #212)

ideas/idea-009-eurgbp-volume-proxy-divergence-5m.md

@@ -41,4 +41,4 @@ EURGBP may show repeatable behavior when volume proxy divergence conditions alig
 
 This idea is intentionally Markdown-only. A future template can add `strategy.py`, `quant.config.json`, and a focused README once PPE results justify turning the idea into executable code.
 
-Closes #17
+Closes #212

templates/eurgbp-volume-proxy-divergence-5m/README.md

@@ -0,0 +1,47 @@
+# EURGBP Volume proxy divergence 5m
+
+This strategy implements a volume proxy divergence approach for EURGBP on 5-minute candles using HistGradientBoostingClassifier.
+
+## Overview
+
+- **Pair**: EURGBP
+- **Timeframe**: 5m
+- **Model**: HistGradientBoostingClassifier with feature engineering focused on volume-price divergence
+- **Goal**: Identify divergences between price action and volume-weighted price action to predict reversals
+
+## Features Engineered
+
+1. **Returns**: 1, 3, 6, 12 period returns
+2. **ATR-normalized candle range and close location value** (from idea)
+3. **Volume proxy divergence**:
+   - Price RSI (momentum of price changes)
+   - Volume-price RSI (momentum of volume-weighted price changes)
+   - Volume proxy divergence (difference between the two RSIs)
+   - Volume MACD, signal line, histogram
+4. **Distance from EMAs** (from idea): 20, 50, and 200 period EMAs
+5. **Prior swing high and swing low distance** (from idea)
+6. **Volume features**: Z-score and ratio to moving average
+7. **Rolling volatility percentile** (from idea): Fast/slow volatility ratio, volatility percentile
+
+## Configuration
+
+See `quant.config.json` for hyperparameters:
+- `lookback`: 100 candles for prediction
+- `horizon`: 5 candles forward for labeling (5m timeframe)
+- `threshold`: 0.0006 (6 pips) for ATR-normalized breakout
+- `min_confidence`: 0.50 minimum probability for signal generation
+
+## Usage
+
+This template follows the PyP Quant Mode contract:
+```python
+def train(data, config):
+    return model, metrics
+
+def predict(model, market_data, config):
+    return {"signal": "UP|DOWN|HOLD", "confidence": 0.0, "metadata": {}}
+```
+
+## Disclaimer
+
+Educational template only. Not financial advice. Past performance does not guarantee future results.

templates/eurgbp-volume-proxy-divergence-5m/quant.config.json

@@ -0,0 +1,28 @@
+{
+  "pair": "EURGBP",
+  "timeframe": "5m",
+  "model_family": "sklearn HistGradientBoostingClassifier",
+  "runtime_target": "edge",
+  "artifact_format": "weights_bundle",
+  "parameters": {
+    "lookback": 100,
+    "horizon": 5,
+    "threshold": 0.0006,
+    "min_confidence": 0.5
+  },
+  "training_requirements": [
+    "numpy",
+    "pandas",
+    "scikit-learn",
+    "joblib"
+  ],
+  "inference_requirements": [
+    "numpy",
+    "pandas",
+    "scikit-learn",
+    "joblib"
+  ],
+  "symbol": "EURGBP",
+  "description": "EURGBP volume proxy divergence strategy using HistGradientBoostingClassifier",
+  "disclaimer": "Educational template only. Not financial advice."
+}

templates/eurgbp-volume-proxy-divergence-5m/strategy.py

@@ -0,0 +1,177 @@
+import numpy as np
+import pandas as pd
+from sklearn.experimental import enable_hist_gradient_boosting  # noqa
+from sklearn.ensemble import HistGradientBoostingClassifier
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+
+SYMBOL = "EURGBP"
+MODEL_NAME = "eurgbp-volume-proxy-divergence-5m"
+
+
+def _normalise(data):
+    df = data.copy()
+    df.columns = [str(c).lower() for c in df.columns]
+    if "volume" not in df.columns:
+        df["volume"] = 1.0
+    for col in ["open", "high", "low", "close", "volume"]:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+    return df.dropna(subset=["open", "high", "low", "close"]).reset_index(drop=True)
+
+
+def _features(df):
+    c = df["close"]
+    h = df["high"]
+    l = df["low"]
+    v = df["volume"]
+    
+    # Basic returns
+    out = pd.DataFrame(index=df.index)
+    out["ret1"] = c.pct_change()
+    out["ret3"] = c.pct_change(3)
+    out["ret6"] = c.pct_change(6)
+    out["ret12"] = c.pct_change(12)
+    
+    # ATR for normalization
+    tr = np.maximum(h - l, np.maximum(abs(h - c.shift(1)), abs(l - c.shift(1))))
+    atr = pd.Series(tr).rolling(14).mean()
+    out["atr"] = atr
+    
+    # ATR-normalized candle range and close location value
+    out["range_pct"] = (h - l) / c
+    out["body_pct"] = (c - df["open"]) / (h - l).replace(0, np.nan)
+    out["close_pos"] = (c - l) / (h - l).replace(0, np.nan)
+    
+    # Volume proxy divergence features
+    # Price-Volume divergence (similar to RSI but with volume)
+    # Calculate price changes
+    price_change = c.diff()
+    
+    # Volume-weighted price change
+    vol_price_change = price_change * v
+    
+    # RSI of price changes
+    gain = price_change.where(price_change > 0, 0)
+    loss = (-price_change.where(price_change < 0, 0))
+    avg_gain = gain.rolling(14).mean()
+    avg_loss = loss.rolling(14).mean()
+    rs = avg_gain / (avg_loss + 1e-9)
+    price_rsi = 100 - (100 / (1 + rs))
+    out["price_rsi"] = price_rsi
+    
+    # RSI of volume-weighted price changes (volume proxy)
+    vol_gain = vol_price_change.where(vol_price_change > 0, 0)
+    vol_loss = (-vol_price_change.where(vol_price_change < 0, 0))
+    vol_avg_gain = vol_gain.rolling(14).mean()
+    vol_avg_loss = vol_loss.rolling(14).mean()
+    vol_rs = vol_avg_gain / (vol_avg_loss + 1e-9)
+    vol_price_rsi = 100 - (100 / (1 + vol_rs))
+    out["vol_price_rsi"] = vol_price_rsi
+    
+    # Volume proxy divergence (difference between price RSI and volume-price RSI)
+    out["vol_price_divergence"] = out["price_rsi"] - out["vol_price_rsi"]
+    
+    # Volume moving average convergence/divergence
+    vol_fast_ma = v.ewm(span=12, adjust=False).mean()
+    vol_slow_ma = v.ewm(span=26, adjust=False).mean()
+    out["vol_macd"] = vol_fast_ma - vol_slow_ma
+    out["vol_macd_signal"] = out["vol_macd"].ewm(span=9, adjust=False).mean()
+    out["vol_macd_hist"] = out["vol_macd"] - out["vol_macd_signal"]
+    
+    # Distance from EMAs (from idea)
+    out["ema20_dist"] = (c - c.ewm(span=20, adjust=False).mean()) / c
+    out["ema50_dist"] = (c - c.ewm(span=50, adjust=False).mean()) / c
+    out["ema200_dist"] = (c - c.ewm(span=200, adjust=False).mean()) / c
+    
+    # Prior swing high and swing low distance (from idea)
+    swing_high = h.rolling(20, center=False).max().shift(1)
+    swing_low = l.rolling(20, center=False).min().shift(1)
+    out["dist_to_swing_high"] = (swing_high - c) / c
+    out["dist_to_swing_low"] = (c - swing_low) / c
+    
+    # Volume features
+    out["volume_z"] = (v - v.rolling(48).mean()) / (v.rolling(48).std() + 1e-9)
+    out["volume_ratio"] = v / v.rolling(20).mean()
+    
+    # Rolling volatility percentile (from idea)
+    returns = c.pct_change()
+    out["volatility_fast"] = returns.rolling(16).std()
+    out["volatility_slow"] = returns.rolling(64).std()
+    out["volatility_ratio"] = out["volatility_fast"] / (out["volatility_slow"] + 1e-9)
+    out["volatility_percentile"] = out["volatility_fast"].rolling(200).apply(
+        lambda x: pd.Series(x).rank(pct=True).iloc[-1] if len(x) > 0 else 0.5, raw=False)
+    
+    return out.replace([np.inf, -np.inf], np.nan).dropna()
+
+
+def _labels(close, index, horizon, threshold):
+    fwd = close.pct_change(horizon).shift(-horizon)
+    y = pd.Series(1, index=close.index)
+    y[fwd > threshold] = 2
+    y[fwd < -threshold] = 0
+    return y.reindex(index).fillna(1).astype(int)
+
+
+def train(data, config):
+    params = config.get("parameters", {})
+    horizon = int(params.get("horizon", 5))  # 5m horizon for 5m timeframe
+    threshold = float(params.get("threshold", 0.0006))
+    df = _normalise(data)
+    feat = _features(df)
+    y = _labels(df["close"], feat.index, horizon, threshold)
+    
+    model = Pipeline([
+        ("scaler", StandardScaler()),
+        ("clf", HistGradientBoostingClassifier(
+            learning_rate=0.08,
+            max_iter=120,
+            max_depth=6,
+            min_samples_leaf=12,
+            l2_regularization=0.1,
+            random_state=42
+        )),
+    ])
+    model.fit(feat.values.astype(np.float32), y.values)
+    preds = model.predict(feat.values.astype(np.float32))
+    
+    metrics = {
+        "training_bars": int(len(feat)),
+        "feature_count": int(feat.shape[1]),
+        "buy_signals": int((preds == 2).sum()),
+        "sell_signals": int((preds == 0).sum()),
+        "hold_signals": int((preds == 1).sum()),
+    }
+    return {"model": model, "features": list(feat.columns), "symbol": SYMBOL}, metrics
+
+
+def predict(model, market_data, config):
+    params = config.get("parameters", {})
+    lookback = int(params.get("lookback", 100))
+    min_conf = float(params.get("min_confidence", 0.5))
+    candles = market_data.get("candles", [])
+    
+    if len(candles) < lookback:
+        return {"signal": "HOLD", "confidence": 0.0, "metadata": {"reason": "not_enough_candles", "model": MODEL_NAME}}
+    
+    df = _normalise(pd.DataFrame(candles, columns=["open", "high", "low", "close", "volume"]))
+    feat = _features(df).tail(1)
+    
+    if feat.empty:
+        return {"signal": "HOLD", "confidence": 0.0, "metadata": {"reason": "no_features", "model": MODEL_NAME}}
+    
+    proba = model["model"].predict_proba(feat.values.astype(np.float32))[0]
+    klass = int(np.argmax(proba))
+    conf = float(proba[klass])
+    signal = {0: "DOWN", 1: "HOLD", 2: "UP"}[klass]
+    
+    if conf < min_conf:
+        signal = "HOLD"
+    
+    return {"signal": signal, "confidence": round(conf, 4), "metadata": {
+        "p_sell": round(float(proba[0]), 4), 
+        "p_hold": round(float(proba[1]), 4), 
+        "p_buy": round(float(proba[2]), 4), 
+        "model": MODEL_NAME, 
+        "symbol": SYMBOL
+    }}