Community Scripts

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:01:39
# Model            : Gradient Boosting
# Feature Eng.     : BB (20,2.0), ATR 14 + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/USDJPY_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── Bollinger Bands (period=20, std_dev=2.0) ──────────────────────────────
    bb_period = 20
    bb_std    = 2.0

    bb_mid   = close.rolling(bb_period).mean()
    bb_sigma = close.rolling(bb_period).std(ddof=0)
    bb_upper = bb_mid + bb_std * bb_sigma
    bb_lower = bb_mid - bb_std * bb_sigma

    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower

    # bb_width: normalised band width (volatility proxy)
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid

    # bb_pct: position of close within the band [0, 1]
    band_range = bb_upper - bb_lower
    df["bb_pct"] = (close - bb_lower) / band_range

    # Distance from close to mid in units of band width
    df["bb_dist_mid"] = (close - bb_mid) / bb_mid

    # ── ATR (period=14) ───────────────────────────────────────────────────────
    atr_period = 14
    prev_close = close.shift(1)
    tr = pd.concat([
        high - low,
        (high - prev_close).abs(),
        (low  - prev_close).abs()
    ], axis=1).max(axis=1)

    atr  = tr.ewm(span=atr_period, min_periods=atr_period, adjust=False).mean()
    natr = atr / close

    df["atr"]  = atr
    df["natr"] = natr

    # ── Momentum / trend features ─────────────────────────────────────────────
    # Rate of change at multiple horizons
    for n in [1, 4, 8, 16]:
        df[f"roc_{n}"] = close.pct_change(n)

    # RSI (14)
    rsi_period = 14
    delta  = close.diff()
    gain   = delta.clip(lower=0)
    loss   = (-delta).clip(lower=0)
    avg_gain = gain.ewm(span=rsi_period, min_periods=rsi_period, adjust=False).mean()
    avg_loss = loss.ewm(span=rsi_period, min_periods=rsi_period, adjust=False).mean()
    rs  = avg_gain / (avg_loss + 1e-10)
    rsi = 100 - (100 / (1 + rs))
    df["rsi_14"] = rsi

    # RSI derived: distance from 50 (centred, normalised)
    df["rsi_dev"] = (rsi - 50) / 50

    # ── MACD (12, 26, 9) ──────────────────────────────────────────────────────
    ema12 = close.ewm(span=12, adjust=False).mean()
    ema26 = close.ewm(span=26, adjust=False).mean()
    macd_line   = ema12 - ema26
    macd_signal = macd_line.ewm(span=9, adjust=False).mean()
    macd_hist   = macd_line - macd_signal

    df["macd_line"]   = macd_line
    df["macd_signal"] = macd_signal
    df["macd_hist"]   = macd_hist

    # ── Trend (SMA 50) ────────────────────────────────────────────────────────
    sma50 = close.rolling(50).mean()
    df["sma_50"]        = sma50
    df["close_vs_sma50"] = (close - sma50) / sma50   # normalised distance

    # ── Volume / candle structure features ────────────────────────────────────
    body      = (close - open_).abs()
    candle_rng = high - low
    df["body_ratio"]  = body / (candle_rng + 1e-10)   # body as fraction of range
    df["upper_wick"]  = (high  - pd.concat([close, open_], axis=1).max(axis=1)) / (candle_rng + 1e-10)
    df["lower_wick"]  = (pd.concat([close, open_], axis=1).min(axis=1) - low)   / (candle_rng + 1e-10)
    df["candle_dir"]  = np.where(close > open_, 1.0, -1.0)  # bullish / bearish bar

    # ── Lagged bb_pct & rsi (to give the model recent history) ───────────────
    for lag in [1, 2, 3]:
        df[f"bb_pct_lag{lag}"] = df["bb_pct"].shift(lag)
        df[f"rsi_lag{lag}"]    = df["rsi_14"].shift(lag)
        df[f"macd_hist_lag{lag}"] = df["macd_hist"].shift(lag)

    # ── Volatility regime flag ────────────────────────────────────────────────
    natr_ma = natr.rolling(50).mean()
    df["vol_regime"] = np.where(natr > natr_ma, 1.0, 0.0)   # 1 = high-vol regime

    # ── BB squeeze detection ──────────────────────────────────────────────────
    bb_width_ma = df["bb_width"].rolling(50).mean()
    df["bb_squeeze"] = np.where(df["bb_width"] < bb_width_ma, 1.0, 0.0)

    # ── Mean-reversion signal strength ────────────────────────────────────────
    # Positive → oversold (close below lower band), Negative → overbought
    df["mr_signal"] = 0.5 - df["bb_pct"]   # centred: +0.5 at lower band, -0.5 at upper

    # ── Fill NaN from warm-up ─────────────────────────────────────────────────
    df = df.bfill().ffill()

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "USD/JPY BB Mean-Reversion + ATR Gradient Boost",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":      500,
            "max_depth":         4,
            "learning_rate":     0.03,
            "subsample":         0.8,
            "min_samples_leaf":  20,
            "max_features":      "sqrt",
            "validation_fraction": 0.1,
            "n_iter_no_change":  30,
            "tol":               1e-4,
            "random_state":      42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   None,
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximise Sharpe ratio via a Gradient Boosting classifier trained on "
            "Bollinger Band position (bb_pct), normalised bandwidth (bb_width), "
            "ATR/NATR, RSI, MACD histogram, candle structure, and lagged features. "
            "GBM chosen for its ability to capture non-linear interactions between "
            "volatility (ATR) and mean-reversion (BB) signals. n_iter_no_change "
            "acts as early stopping to prevent overfitting on the 15-min USDJPY series. "
            "SL=0.5% / TP=1.0% gives a 1:2 risk-reward; threshold=0.55 reduces noise trades."
        ),
        "notes": (
            "Bollinger Bands are the primary mean-reversion anchor; ATR/NATR filter "
            "entries to adequate volatility bars. RSI and MACD provide momentum context "
            "to avoid fading strong trends. Lagged features (up to 3 bars) give the model "
            "short-term regime memory without look-ahead. vol_regime and bb_squeeze flags "
            "allow the model to differentiate trending vs. ranging conditions automatically. "
            "No session filter applied — USDJPY is liquid across Asian and European sessions."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:16:23
# Model            : Gradient Boosting
# Feature Eng.     : RSI 14, MACD (12,26,9) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/NZDUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── RSI 14 ──────────────────────────────────────────────────────────────
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = -delta.clip(upper=0)
    avg_gain = gain.ewm(com=13, min_periods=14, adjust=False).mean()
    avg_loss = loss.ewm(com=13, min_periods=14, adjust=False).mean()
    rs = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # RSI derived signals
    df["rsi_overbought"] = np.where(df["rsi_14"] > 70, 1, 0)
    df["rsi_oversold"]   = np.where(df["rsi_14"] < 30, 1, 0)
    df["rsi_mid_cross"]  = np.where(df["rsi_14"] > 50, 1, -1)

    # RSI momentum (rate of change of RSI)
    df["rsi_roc"] = df["rsi_14"].diff(3)

    # ── MACD (12, 26, 9) ────────────────────────────────────────────────────
    ema_12 = close.ewm(span=12, adjust=False).mean()
    ema_26 = close.ewm(span=26, adjust=False).mean()
    macd_line   = ema_12 - ema_26
    signal_line = macd_line.ewm(span=9, adjust=False).mean()
    macd_hist   = macd_line - signal_line

    df["macd_line"]   = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"]   = macd_hist

    # MACD derived signals
    df["macd_cross"] = np.where(macd_line > signal_line, 1, -1)
    df["macd_hist_sign"]  = np.where(macd_hist > 0, 1, -1)
    df["macd_hist_accel"] = macd_hist.diff()

    # ── ATR (14) ─────────────────────────────────────────────────────────────
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    df["atr_14"] = tr.ewm(com=13, min_periods=14, adjust=False).mean()
    df["natr_14"] = df["atr_14"] / close

    # ── Bollinger Bands (20, 2) ──────────────────────────────────────────────
    sma_20 = close.rolling(20).mean()
    std_20 = close.rolling(20).std()
    bb_upper = sma_20 + 2 * std_20
    bb_lower = sma_20 - 2 * std_20
    df["bb_width"]    = (bb_upper - bb_lower) / sma_20
    df["bb_position"] = (close - bb_lower) / (bb_upper - bb_lower).replace(0, np.nan)
    df["bb_squeeze"]  = np.where(df["bb_width"] < df["bb_width"].rolling(50).mean(), 1, 0)

    # ── Trend / SMA filters ──────────────────────────────────────────────────
    df["sma_20"]  = sma_20
    df["sma_50"]  = close.rolling(50).mean()
    df["sma_200"] = close.rolling(200).mean()
    df["price_above_sma50"]  = np.where(close > df["sma_50"],  1, -1)
    df["price_above_sma200"] = np.where(close > df["sma_200"], 1, -1)
    df["sma50_above_sma200"] = np.where(df["sma_50"] > df["sma_200"], 1, -1)

    # ── Momentum / ROC ───────────────────────────────────────────────────────
    df["roc_4"]  = close.pct_change(4)
    df["roc_8"]  = close.pct_change(8)
    df["roc_16"] = close.pct_change(16)

    # ── Candlestick / price structure ────────────────────────────────────────
    df["body"]        = (close - open_) / close
    df["upper_wick"]  = (high - close.clip(lower=open_)) / close
    df["lower_wick"]  = (open_.clip(upper=close) - low)  / close
    df["hl_range"]    = (high - low) / close
    df["gap"]         = (open_ - close.shift(1)) / close.shift(1)

    # ── Volume-free spread proxy ─────────────────────────────────────────────
    df["spread_ratio"] = df["hl_range"] / df["atr_14"].replace(0, np.nan)

    # ── Stochastic RSI proxy ─────────────────────────────────────────────────
    rsi_min = df["rsi_14"].rolling(14).min()
    rsi_max = df["rsi_14"].rolling(14).max()
    df["stoch_rsi"] = (df["rsi_14"] - rsi_min) / (rsi_max - rsi_min).replace(0, np.nan)

    # ── Williams %R (14) ─────────────────────────────────────────────────────
    highest_high = high.rolling(14).max()
    lowest_low   = low.rolling(14).min()
    df["williams_r"] = -100 * (highest_high - close) / (highest_high - lowest_low).replace(0, np.nan)

    # ── Lagged features ──────────────────────────────────────────────────────
    for lag in [1, 2, 3, 4]:
        df[f"rsi_lag{lag}"]       = df["rsi_14"].shift(lag)
        df[f"macd_hist_lag{lag}"] = df["macd_hist"].shift(lag)
        df[f"roc4_lag{lag}"]      = df["roc_4"].shift(lag)

    # ── Fill NaN from indicator warm-up ─────────────────────────────────────
    df = df.bfill().ffill()
    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "NZD/USD MACD+RSI Gradient Boosting Risk-Adjusted",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":     400,
            "max_depth":        4,
            "learning_rate":    0.03,
            "subsample":        0.8,
            "min_samples_leaf": 20,
            "max_features":     "sqrt",
            "validation_fraction": 0.1,
            "n_iter_no_change": 30,
            "tol":              1e-4,
            "random_state":     42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [0, 23],
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) on NZD/USD 15-min data. "
            "GradientBoostingClassifier chosen for strong generalisation with tabular features, "
            "low learning rate + early stopping prevents overfitting. "
            "SL=0.5%, TP=1.0% gives 1:2 R:R ratio. Threshold=0.55 filters marginal signals."
        ),
        "notes": (
            "Core features: RSI-14, MACD(12,26,9) with histogram momentum. "
            "Supplementary: ATR, Bollinger Bands, SMA trend, Williams %R, StochRSI, "
            "candlestick structure, lagged RSI/MACD/ROC. "
            "reverse on opposite signal captures trend continuation. "
            "target_horizon=4 bars (1 hour) aligns with typical MACD/RSI signal duration."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:54:56
# Model            : Gradient Boosting
# Feature Eng.     : BB (20,2.0), RSI 14, Stochastic (14,3) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/NZDUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── Bollinger Bands (20, 2) ──────────────────────────────────────────────
    bb_period = 20
    bb_std    = 2.0
    bb_mid    = close.rolling(bb_period).mean()
    bb_std_   = close.rolling(bb_period).std(ddof=0)
    bb_upper  = bb_mid + bb_std * bb_std_
    bb_lower  = bb_mid - bb_std * bb_std_

    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    df["bb_pct"]   = (close - bb_lower) / (bb_upper - bb_lower)

    # ── RSI (14) ─────────────────────────────────────────────────────────────
    rsi_period = 14
    delta      = close.diff()
    gain       = delta.clip(lower=0)
    loss       = -delta.clip(upper=0)
    avg_gain   = gain.ewm(com=rsi_period - 1, min_periods=rsi_period).mean()
    avg_loss   = loss.ewm(com=rsi_period - 1, min_periods=rsi_period).mean()
    rs         = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi"]  = 100 - (100 / (1 + rs))

    # ── Stochastic Oscillator (K=14, D=3) ────────────────────────────────────
    stoch_k_period = 14
    stoch_d_period = 3
    lowest_low   = low.rolling(stoch_k_period).min()
    highest_high = high.rolling(stoch_k_period).max()
    stoch_range  = (highest_high - lowest_low).replace(0, np.nan)
    df["stoch_k"] = 100 * (close - lowest_low) / stoch_range
    df["stoch_d"] = df["stoch_k"].rolling(stoch_d_period).mean()
    df["stoch_kd_diff"] = df["stoch_k"] - df["stoch_d"]

    # ── ATR (14) — for normalised volatility / min_atr filter ────────────────
    atr_period = 14
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    atr = tr.ewm(com=atr_period - 1, min_periods=atr_period).mean()
    df["atr"]  = atr
    df["natr"] = atr / close          # normalised ATR used by min_atr filter

    # ── Price momentum / rate-of-change ──────────────────────────────────────
    df["roc_4"]  = close.pct_change(4)    # 1-hour momentum on 15-min bars
    df["roc_8"]  = close.pct_change(8)    # 2-hour momentum
    df["roc_16"] = close.pct_change(16)   # 4-hour momentum

    # ── EMA trend context ─────────────────────────────────────────────────────
    df["ema_20"]  = close.ewm(span=20,  adjust=False).mean()
    df["ema_50"]  = close.ewm(span=50,  adjust=False).mean()
    df["ema_100"] = close.ewm(span=100, adjust=False).mean()
    df["sma_50"]  = close.rolling(50).mean()   # used by trend_filter

    df["ema_cross_20_50"]  = df["ema_20"]  - df["ema_50"]
    df["ema_cross_50_100"] = df["ema_50"]  - df["ema_100"]
    df["close_vs_ema20"]   = (close - df["ema_20"]) / df["ema_20"]

    # ── Candlestick body / wick features ─────────────────────────────────────
    df["body"]       = (close - open_).abs()
    df["candle_dir"] = np.where(close >= open_, 1.0, -1.0)
    df["upper_wick"] = high - pd.concat([close, open_], axis=1).max(axis=1)
    df["lower_wick"] = pd.concat([close, open_], axis=1).min(axis=1) - low
    df["body_ratio"] = df["body"] / (high - low).replace(0, np.nan)

    # ── Volume-proxy: realised range rolling stats ────────────────────────────
    df["hl_range"]      = high - low
    df["hl_range_ma8"]  = df["hl_range"].rolling(8).mean()
    df["hl_range_ratio"]= df["hl_range"] / df["hl_range_ma8"]

    # ── RSI derived signals ───────────────────────────────────────────────────
    df["rsi_overbought"]  = np.where(df["rsi"] > 70, 1.0, 0.0)
    df["rsi_oversold"]    = np.where(df["rsi"] < 30, 1.0, 0.0)
    df["rsi_momentum"]    = df["rsi"].diff(4)

    # ── Stochastic derived signals ────────────────────────────────────────────
    df["stoch_overbought"] = np.where(df["stoch_k"] > 80, 1.0, 0.0)
    df["stoch_oversold"]   = np.where(df["stoch_k"] < 20, 1.0, 0.0)

    # ── BB squeeze: width vs rolling mean of width ────────────────────────────
    df["bb_width_ma20"]  = df["bb_width"].rolling(20).mean()
    df["bb_squeeze"]     = np.where(df["bb_width"] < df["bb_width_ma20"], 1.0, 0.0)

    # ── Interaction features ──────────────────────────────────────────────────
    df["rsi_bb_pct"]      = df["rsi"] * df["bb_pct"]
    df["stoch_k_bb_pct"]  = df["stoch_k"] * df["bb_pct"]
    df["rsi_stoch_diff"]  = df["rsi"] - df["stoch_k"]

    # ── Lagged features (avoids look-ahead) ──────────────────────────────────
    for lag in [1, 2, 3, 4]:
        df[f"rsi_lag{lag}"]     = df["rsi"].shift(lag)
        df[f"stoch_k_lag{lag}"] = df["stoch_k"].shift(lag)
        df[f"bb_pct_lag{lag}"]  = df["bb_pct"].shift(lag)
        df[f"roc4_lag{lag}"]    = df["roc_4"].shift(lag)

    # ── Fill NaN from warm-up ─────────────────────────────────────────────────
    df = df.bfill().ffill()
    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "NZD/USD Stoch+BB+RSI Gradient Boosting Mean-Revert",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":     400,
            "max_depth":        4,
            "learning_rate":    0.04,
            "subsample":        0.8,
            "min_samples_leaf": 20,
            "max_features":     "sqrt",
            "validation_fraction": 0.1,
            "n_iter_no_change": 30,
            "tol":              1e-4,
            "random_state":     42,
        },
        "signal_threshold": 0.56,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [7, 20],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximise risk-adjusted return (Sharpe / Calmar) on NZD/USD 15-min. "
            "GradientBoostingClassifier selected for its strong generalisation on "
            "structured tabular data with noisy financial features. n_estimators=400 "
            "with early stopping (n_iter_no_change=30) prevents overfitting. "
            "max_depth=4 keeps trees shallow to reduce variance. subsample=0.8 + "
            "max_features=sqrt add stochasticity for robustness. SL 0.5% / TP 1.0% "
            "gives a minimum 2:1 reward-risk ratio. Session filter 07-20 UTC covers "
            "Sydney open through NY overlap, maximising NZD/USD liquidity. "
            "Reverse on opposite signal keeps the model continuously positioned in "
            "the highest-confidence direction. min_atr filter avoids flat/illiquid "
            "periods where the model edges degrade."
        ),
        "notes": (
            "Features: Bollinger Bands (20,2) width & %B, RSI(14), Stochastic K/D "
            "(14,3), ATR(14)/NATR, EMA cross (20/50/100), SMA50 trend context, "
            "price ROC (4/8/16 bars), candlestick body/wick ratios, HL range "
            "normalisation, BB squeeze flag, RSI/Stoch overbought-oversold flags, "
            "interaction terms (RSI*%B, StochK*%B), and 4 lags each of RSI, StochK, "
            "%B and ROC4. Threshold 0.56 slightly above 0.50 to filter marginal "
            "signals without sacrificing too many trades."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-08 02:08:02
# Model            : XGBoost
# Feature Eng.     : Auto-add features: ON
# Signal / Entry   : —
# Optimization     : —
# Risk Mgmt        : —
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/USDJPY_1min.parquet"
START_DATE = "2026-05-04 00:00:00"
END_DATE   = "2026-05-07 00:00:00"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.6993736951983298

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # --- Returns over multiple horizons ---
    for n in [1, 3, 5, 10, 20]:
        df[f"ret_{n}"] = close.pct_change(n)

    # --- RSI 14 ---
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = -delta.clip(upper=0)
    avg_gain = gain.ewm(com=13, min_periods=14).mean()
    avg_loss = loss.ewm(com=13, min_periods=14).mean()
    rs = avg_gain / (avg_loss + 1e-10)
    df["rsi_14"] = 100.0 - (100.0 / (1.0 + rs))

    # --- RSI derived features ---
    df["rsi_14_zscore"] = (df["rsi_14"] - df["rsi_14"].rolling(50).mean()) / (df["rsi_14"].rolling(50).std() + 1e-10)
    df["rsi_overbought"] = np.where(df["rsi_14"] > 70, 1, 0)
    df["rsi_oversold"]   = np.where(df["rsi_14"] < 30, 1, 0)

    # --- Bollinger Bands 20, 2 ---
    bb_mid   = close.rolling(20).mean()
    bb_std   = close.rolling(20).std()
    bb_upper = bb_mid + 2.0 * bb_std
    bb_lower = bb_mid - 2.0 * bb_std
    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"]  = (bb_upper - bb_lower) / (bb_mid + 1e-10)
    df["bb_pct_b"]  = (close - bb_lower) / (bb_upper - bb_lower + 1e-10)
    df["bb_above"]  = np.where(close > bb_upper, 1, 0)
    df["bb_below"]  = np.where(close < bb_lower, 1, 0)

    # --- Moving Averages ---
    for w in [50, 100, 200]:
        df[f"sma_{w}"] = close.rolling(w).mean()
        df[f"price_vs_sma_{w}"] = (close - df[f"sma_{w}"]) / (df[f"sma_{w}"] + 1e-10)

    # --- MA crossover signals ---
    df["sma50_vs_sma100"] = np.where(df["sma_50"] > df["sma_100"], 1, -1)
    df["sma50_vs_sma200"] = np.where(df["sma_50"] > df["sma_200"], 1, -1)
    df["sma100_vs_sma200"] = np.where(df["sma_100"] > df["sma_200"], 1, -1)

    # --- ATR 14 ---
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    df["atr_14"] = tr.ewm(com=13, min_periods=14).mean()
    df["natr_14"] = df["atr_14"] / (close + 1e-10)

    # --- Momentum / rate of change ---
    for n in [5, 10, 20]:
        df[f"mom_{n}"] = close - close.shift(n)
        df[f"roc_{n}"] = (close - close.shift(n)) / (close.shift(n) + 1e-10)

    # --- Volume features (if volume exists) ---
    if "volume" in df.columns:
        vol = df["volume"].replace(0, np.nan)
        df["vol_sma_20"]   = vol.rolling(20).mean()
        df["vol_ratio_20"] = vol / (df["vol_sma_20"] + 1e-10)
    else:
        df["vol_ratio_20"] = 1.0

    # --- Price spread & body features ---
    df["hl_spread"]  = (high - low) / (close + 1e-10)
    df["body_ratio"] = (close - open_).abs() / (high - low + 1e-10)
    df["upper_wick"] = (high - pd.concat([close, open_], axis=1).max(axis=1)) / (high - low + 1e-10)
    df["lower_wick"] = (pd.concat([close, open_], axis=1).min(axis=1) - low) / (high - low + 1e-10)
    df["bull_candle"] = np.where(close > open_, 1, 0)

    # --- Lagged returns for autocorrelation signal ---
    for lag in [1, 2, 3, 5]:
        df[f"ret1_lag{lag}"] = df["ret_1"].shift(lag)

    # --- Rolling volatility ---
    df["vol_10"]  = df["ret_1"].rolling(10).std()
    df["vol_20"]  = df["ret_1"].rolling(20).std()
    df["vol_50"]  = df["ret_1"].rolling(50).std()

    # --- Z-score of close over 20 and 50 bars ---
    df["zscore_20"] = (close - close.rolling(20).mean()) / (close.rolling(20).std() + 1e-10)
    df["zscore_50"] = (close - close.rolling(50).mean()) / (close.rolling(50).std() + 1e-10)

    # --- Relative distance of price from BB bands ---
    df["dist_upper"] = (bb_upper - close) / (close + 1e-10)
    df["dist_lower"] = (close - bb_lower) / (close + 1e-10)

    # --- EMA 9 and 21 for short-term momentum ---
    df["ema_9"]  = close.ewm(span=9, min_periods=9).mean()
    df["ema_21"] = close.ewm(span=21, min_periods=21).mean()
    df["ema9_vs_ema21"] = np.where(df["ema_9"] > df["ema_21"], 1, -1)
    df["price_vs_ema9"]  = (close - df["ema_9"]) / (df["ema_9"] + 1e-10)
    df["price_vs_ema21"] = (close - df["ema_21"]) / (df["ema_21"] + 1e-10)

    # --- MACD-like signal ---
    ema_12 = close.ewm(span=12, min_periods=12).mean()
    ema_26 = close.ewm(span=26, min_periods=26).mean()
    macd_line   = ema_12 - ema_26
    signal_line = macd_line.ewm(span=9, min_periods=9).mean()
    df["macd"]         = macd_line
    df["macd_signal"]  = signal_line
    df["macd_hist"]    = macd_line - signal_line
    df["macd_cross"]   = np.where(macd_line > signal_line, 1, -1)

    # --- Fill NaN from warm-up periods ---
    df = df.bfill().ffill()

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "USD/JPY Multi-MA + RSI/BB XGBoost Sharpe",
        "model_type":       "XGBClassifier",
        "model_params":     {
            "n_estimators":     400,
            "max_depth":        4,
            "learning_rate":    0.04,
            "subsample":        0.75,
            "colsample_bytree": 0.75,
            "min_child_weight": 5,
            "gamma":            0.1,
            "reg_alpha":        0.1,
            "reg_lambda":       1.5,
            "objective":        "binary:logistic",
            "tree_method":      "hist",
            "random_state":     42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.0008,
        "take_profit":      0.0016,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "close_only",
        "session_filter":   None,
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   5,
        "objective":        (
            "Maximize Sharpe ratio on USD/JPY 1-min data using XGBoost with "
            "returns, RSI, Bollinger Bands, multiple MAs (50/100/200), MACD, "
            "ATR, and candle-body features. Stop-loss and take-profit set at "
            "a 1:2 risk/reward to filter noise and improve Sharpe. n_estimators "
            "and moderate depth balance bias-variance. Regularization (alpha/lambda) "
            "reduces overfitting on short date range."
        ),
        "notes":            (
            "Target horizon of 5 bars (5 minutes) is chosen to capture short-term "
            "directional moves on 1-min data without excessive label noise. "
            "colsample_bytree and subsample add stochasticity to reduce variance. "
            "close_only on opposite signal avoids whipsaw from rapid reversals. "
            "No session filter applied since USD/JPY has liquidity around the clock."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:37:19
# Model            : XGBoost
# Feature Eng.     : SMA (20,50,200), BB (20,2.0), RSI 14, MACD (12,26,9), ATR 14 + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/USDCAD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):

    # ── SMA & distance features ──────────────────────────────────────────────
    for p in [20, 50, 200]:
        sma = close.rolling(p).mean()
        df[f"sma_{p}"] = sma
        df[f"dm_sma_{p}"] = (close - sma) / sma

    # SMA slope (rate of change of SMA over 5 bars)
    for p in [20, 50]:
        sma = df[f"sma_{p}"]
        df[f"sma_{p}_slope"] = sma.diff(5) / sma.shift(5)

    # SMA cross signals
    df["sma_20_50_cross"] = np.where(df["sma_20"] > df["sma_50"], 1.0, -1.0)
    df["sma_50_200_cross"] = np.where(df["sma_50"] > df["sma_200"], 1.0, -1.0)

    # ── Bollinger Bands ───────────────────────────────────────────────────────
    bb_mid = close.rolling(20).mean()
    bb_std = close.rolling(20).std()
    bb_upper = bb_mid + 2.0 * bb_std
    bb_lower = bb_mid - 2.0 * bb_std
    df["bb_mid"] = bb_mid
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    bb_range = bb_upper - bb_lower
    df["bb_pct"] = np.where(bb_range != 0, (close - bb_lower) / bb_range, 0.5)

    # Bollinger Band squeeze: width vs its own 20-bar average
    df["bb_squeeze"] = df["bb_width"] / df["bb_width"].rolling(20).mean()

    # Price position relative to bands
    df["bb_above_upper"] = np.where(close > bb_upper, 1.0, 0.0)
    df["bb_below_lower"] = np.where(close < bb_lower, 1.0, 0.0)

    # ── RSI ───────────────────────────────────────────────────────────────────
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = (-delta).clip(lower=0)
    avg_gain = gain.ewm(alpha=1/14, adjust=False).mean()
    avg_loss = loss.ewm(alpha=1/14, adjust=False).mean()
    rs = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # RSI derived features
    df["rsi_norm"] = (df["rsi_14"] - 50) / 50          # centred & scaled
    df["rsi_ob"] = np.where(df["rsi_14"] > 70, 1.0, 0.0)
    df["rsi_os"] = np.where(df["rsi_14"] < 30, 1.0, 0.0)
    df["rsi_slope"] = df["rsi_14"].diff(3)

    # RSI divergence proxy: price up but RSI down (5-bar)
    price_chg_5 = close.diff(5)
    rsi_chg_5 = df["rsi_14"].diff(5)
    df["rsi_bear_div"] = np.where((price_chg_5 > 0) & (rsi_chg_5 < 0), 1.0, 0.0)
    df["rsi_bull_div"] = np.where((price_chg_5 < 0) & (rsi_chg_5 > 0), 1.0, 0.0)

    # ── MACD ──────────────────────────────────────────────────────────────────
    ema_fast = close.ewm(span=12, adjust=False).mean()
    ema_slow = close.ewm(span=26, adjust=False).mean()
    macd_line = ema_fast - ema_slow
    signal_line = macd_line.ewm(span=9, adjust=False).mean()
    df["macd_line"] = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"] = macd_line - signal_line

    # MACD normalised by close price
    df["macd_line_norm"] = macd_line / close
    df["macd_hist_norm"] = df["macd_hist"] / close

    # MACD histogram slope and sign change
    df["macd_hist_slope"] = df["macd_hist"].diff(2)
    df["macd_cross"] = np.where(macd_line > signal_line, 1.0, -1.0)

    # ── ATR ───────────────────────────────────────────────────────────────────
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    df["atr_14"] = tr.ewm(alpha=1/14, adjust=False).mean()
    df["natr"]   = df["atr_14"] / close

    # ATR regime: current ATR vs 50-bar rolling mean
    df["atr_regime"] = df["atr_14"] / df["atr_14"].rolling(50).mean()

    # ── Momentum / Price Action features ─────────────────────────────────────
    # Returns at multiple horizons
    for h in [1, 2, 4, 8, 16]:
        df[f"ret_{h}"] = close.pct_change(h)

    # Candle body & shadow
    body = (close - open_).abs()
    total_range = (high - low).replace(0, np.nan)
    df["body_ratio"] = body / total_range
    df["candle_dir"] = np.where(close >= open_, 1.0, -1.0)
    upper_shadow = high - pd.concat([close, open_], axis=1).max(axis=1)
    lower_shadow = pd.concat([close, open_], axis=1).min(axis=1) - low
    df["upper_shadow_ratio"] = upper_shadow / total_range
    df["lower_shadow_ratio"] = lower_shadow / total_range

    # Rolling price z-score (mean reversion signal)
    for w in [20, 50]:
        roll_mean = close.rolling(w).mean()
        roll_std  = close.rolling(w).std().replace(0, np.nan)
        df[f"zscore_{w}"] = (close - roll_mean) / roll_std

    # Volume of volatility: rolling std of returns
    df["vol_10"] = close.pct_change().rolling(10).std()
    df["vol_20"] = close.pct_change().rolling(20).std()

    # Efficiency ratio: directional move / path length (20 bars)
    direction_move = (close - close.shift(20)).abs()
    path_length = close.diff().abs().rolling(20).sum().replace(0, np.nan)
    df["efficiency_ratio"] = direction_move / path_length

    # ── Interaction / Cross features ─────────────────────────────────────────
    # RSI × MACD hist — captures momentum agreement
    df["rsi_macd_agree"] = df["rsi_norm"] * df["macd_hist_norm"]

    # BB pct × RSI — oversold/overbought near bands
    df["bb_rsi_interact"] = df["bb_pct"] * df["rsi_norm"]

    # Trend strength: distance from SMA50 scaled by ATR
    df["trend_atr_50"] = df["dm_sma_50"] / df["natr"].replace(0, np.nan)

    # ── Session / Time features ───────────────────────────────────────────────
    if hasattr(df.index, "hour"):
        hour = df.index.hour
        df["hour_sin"] = np.sin(2 * np.pi * hour / 24)
        df["hour_cos"] = np.cos(2 * np.pi * hour / 24)
        # London session flag
        df["london_session"] = np.where((hour >= 7) & (hour < 16), 1.0, 0.0)
        # NY session flag
        df["ny_session"] = np.where((hour >= 13) & (hour < 21), 1.0, 0.0)

    if hasattr(df.index, "dayofweek"):
        dow = df.index.dayofweek
        df["dow_sin"] = np.sin(2 * np.pi * dow / 5)
        df["dow_cos"] = np.cos(2 * np.pi * dow / 5)

    # ── Fill NaN from warm-up ─────────────────────────────────────────────────
    df = df.bfill().ffill()

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "USD/CAD Momentum-Reversion Hybrid (XGBoost, v2)",
        "model_type":       "XGBClassifier",
        "model_params": {
            "n_estimators":     600,
            "max_depth":        4,
            "learning_rate":    0.03,
            "subsample":        0.75,
            "colsample_bytree": 0.70,
            "min_child_weight": 5,
            "gamma":            0.2,
            "reg_alpha":        0.5,
            "reg_lambda":       2.0,
            "objective":        "binary:logistic",
            "tree_method":      "hist",
            "n_jobs":           -1,
            "random_state":     42,
        },
        "signal_threshold": 0.54,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [7, 21],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximise risk-adjusted return (Sharpe/Calmar). "
            "Deeper ensemble (600 trees) with aggressive regularisation "
            "(reg_alpha=0.5, reg_lambda=2, gamma=0.2, min_child_weight=5) "
            "to prevent overfitting on 15-min USDCAD. "
            "Rich feature set adds z-scores, efficiency ratio, session dummies, "
            "RSI divergence, candle shape and cross-indicator interactions "
            "beyond the prior attempt's plain indicators. "
            "0.5% SL / 1.0% TP gives 1:2 R:R; session filter restricts to "
            "liquid London+NY overlap hours."
        ),
        "notes": (
            "Prior attempt used plain RSI/MACD/BB/ATR/SMA and scored PF=0.98. "
            "This version adds: rolling z-scores (20,50), efficiency ratio, "
            "candle body/shadow ratios, multi-horizon returns, ATR regime, "
            "BB squeeze, RSI divergence proxies, time-of-day sin/cos encoding, "
            "and interaction terms (rsi_macd_agree, bb_rsi_interact, trend_atr). "
            "Model regularised more heavily to combat the short date range. "
            "Signal threshold lifted slightly to 0.54 to reduce marginal trades."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:36:58
# Model            : XGBoost
# Feature Eng.     : BB (20,2.0), ATR 14 + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/USDCAD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── Bollinger Bands (20, 2) ──────────────────────────────────────────────
    bb_period = 20
    bb_std    = 2.0

    bb_mid   = close.rolling(bb_period).mean()
    bb_sigma = close.rolling(bb_period).std(ddof=0)
    bb_upper = bb_mid + bb_std * bb_sigma
    bb_lower = bb_mid - bb_std * bb_sigma

    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    df["bb_pct"]   = (close - bb_lower) / (bb_upper - bb_lower)

    # ── ATR (14) & Normalised ATR ────────────────────────────────────────────
    atr_period = 14
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)

    atr  = tr.ewm(alpha=1.0 / atr_period, min_periods=atr_period, adjust=False).mean()
    natr = atr / close

    df["atr"]  = atr
    df["natr"] = natr

    # ── Price momentum / returns ─────────────────────────────────────────────
    df["ret_1"]  = close.pct_change(1)
    df["ret_4"]  = close.pct_change(4)
    df["ret_8"]  = close.pct_change(8)
    df["ret_16"] = close.pct_change(16)

    # ── Distance from Bollinger mid / bands ──────────────────────────────────
    df["close_minus_mid"]   = (close - bb_mid)   / bb_mid
    df["close_minus_upper"] = (close - bb_upper) / bb_mid
    df["close_minus_lower"] = (close - bb_lower) / bb_mid

    # ── BB squeeze flag: width below rolling median ───────────────────────────
    bb_width_med = df["bb_width"].rolling(50).median()
    df["bb_squeeze"] = np.where(df["bb_width"] < bb_width_med, 1.0, 0.0)

    # ── BB mean-reversion z-score ────────────────────────────────────────────
    df["bb_z"] = (close - bb_mid) / (bb_sigma + 1e-12)

    # ── Candle body / wick features ──────────────────────────────────────────
    body       = (close - open_).abs()
    candle_rng = (high - low).replace(0, np.nan)
    df["body_ratio"]  = body / candle_rng
    df["upper_wick"]  = (high  - pd.concat([close, open_], axis=1).max(axis=1)) / candle_rng
    df["lower_wick"]  = (pd.concat([close, open_], axis=1).min(axis=1) - low)   / candle_rng
    df["bull_candle"]  = np.where(close > open_, 1.0, 0.0)

    # ── RSI (14) built from scratch ──────────────────────────────────────────
    rsi_period = 14
    delta  = close.diff()
    gain   = delta.clip(lower=0)
    loss   = (-delta).clip(lower=0)
    avg_g  = gain.ewm(alpha=1.0 / rsi_period, min_periods=rsi_period, adjust=False).mean()
    avg_l  = loss.ewm(alpha=1.0 / rsi_period, min_periods=rsi_period, adjust=False).mean()
    rs     = avg_g / (avg_l + 1e-12)
    rsi    = 100.0 - (100.0 / (1.0 + rs))
    df["rsi_14"] = rsi

    # RSI deviation from neutral 50
    df["rsi_dev"] = (rsi - 50.0) / 50.0

    # ── MACD (12, 26, 9) ─────────────────────────────────────────────────────
    ema12      = close.ewm(span=12, adjust=False).mean()
    ema26      = close.ewm(span=26, adjust=False).mean()
    macd_line  = ema12 - ema26
    macd_sig   = macd_line.ewm(span=9, adjust=False).mean()
    df["macd"]      = macd_line / close
    df["macd_hist"] = (macd_line - macd_sig) / close

    # ── Rolling volatility (realised over 20 bars) ───────────────────────────
    df["vol_20"] = df["ret_1"].rolling(20).std()

    # ── ATR z-score vs 50-bar rolling mean ───────────────────────────────────
    atr_mean     = atr.rolling(50).mean()
    atr_std      = atr.rolling(50).std(ddof=0)
    df["atr_z"]  = (atr - atr_mean) / (atr_std + 1e-12)

    # ── Volume-of-BB-touches over last 10 bars ───────────────────────────────
    near_upper = (close >= bb_upper * 0.998).astype(float)
    near_lower = (close <= bb_lower * 1.002).astype(float)
    df["touch_upper_10"] = near_upper.rolling(10).sum()
    df["touch_lower_10"] = near_lower.rolling(10).sum()

    # ── SMA 50 (trend filter helper) ─────────────────────────────────────────
    df["sma_50"]       = close.rolling(50).mean()
    df["close_vs_sma"] = (close - df["sma_50"]) / df["sma_50"]

    # ── EMA cross (9 / 21) ───────────────────────────────────────────────────
    ema9  = close.ewm(span=9,  adjust=False).mean()
    ema21 = close.ewm(span=21, adjust=False).mean()
    df["ema_cross"] = (ema9 - ema21) / close

    # ── Bar-of-day / session ─────────────────────────────────────────────────
    if hasattr(df.index, "hour"):
        df["hour_sin"] = np.sin(2 * np.pi * df.index.hour / 24.0)
        df["hour_cos"] = np.cos(2 * np.pi * df.index.hour / 24.0)
    else:
        df["hour_sin"] = 0.0
        df["hour_cos"] = 1.0

    # ── Lag features on bb_pct and rsi ───────────────────────────────────────
    for lag in [1, 2, 4]:
        df[f"bb_pct_lag{lag}"]  = df["bb_pct"].shift(lag)
        df[f"rsi_14_lag{lag}"]  = df["rsi_14"].shift(lag)
        df[f"macd_hist_lag{lag}"] = df["macd_hist"].shift(lag)

    # ── Fill NaN from warm-up ─────────────────────────────────────────────────
    df = df.bfill().ffill()

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "USD/CAD BB Mean-Reversion + ATR XGBoost",
        "model_type":       "XGBClassifier",
        "model_params": {
            "n_estimators":      400,
            "max_depth":         4,
            "learning_rate":     0.04,
            "subsample":         0.75,
            "colsample_bytree":  0.70,
            "min_child_weight":  3,
            "gamma":             0.15,
            "reg_alpha":         0.10,
            "reg_lambda":        1.50,
            "objective":         "binary:logistic",
            "random_state":      42,
            "n_jobs":            -1,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [7, 20],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximise risk-adjusted return (Sharpe/Calmar) on USD/CAD 15-min "
            "using Bollinger Band mean-reversion signals augmented by ATR, RSI, "
            "MACD, and EMA-cross features fed into a regularised XGBoost classifier. "
            "SL=0.5% / TP=1.0% gives a 1:2 RR floor. Conservative depth (4) and "
            "strong L1/L2 regularisation prevent overfitting on a single year of data."
        ),
        "notes": (
            "BB squeeze flag and bb_z capture regime; atr_z filters noisy bars. "
            "Session filter 07-20 UTC covers London + NY overlap for tighter spreads. "
            "min_atr=0.0002 avoids dead-market whipsaws. Lag features on bb_pct and "
            "rsi_14 give the model short-term momentum context without look-ahead."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:47:56
# Model            : Gradient Boosting
# Feature Eng.     : SMA (20,50,200) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/GBPUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── SMA features (required) ──────────────────────────────────────────────
    for period in [20, 50, 200]:
        sma = close.rolling(period).mean()
        df[f"sma_{period}"] = sma
        df[f"dm_sma_{period}"] = (close - sma) / sma

    # ── SMA crossover signals ────────────────────────────────────────────────
    sma_20 = close.rolling(20).mean()
    sma_50 = close.rolling(50).mean()
    sma_200 = close.rolling(200).mean()

    df["sma_20_50_cross"] = np.where(sma_20 > sma_50, 1.0, -1.0)
    df["sma_20_200_cross"] = np.where(sma_20 > sma_200, 1.0, -1.0)
    df["sma_50_200_cross"] = np.where(sma_50 > sma_200, 1.0, -1.0)

    # ── Price momentum features ──────────────────────────────────────────────
    for lag in [1, 2, 4, 8, 16]:
        df[f"ret_{lag}"] = close.pct_change(lag)

    # ── Volatility: rolling std of returns ──────────────────────────────────
    ret_1 = close.pct_change(1)
    for window in [8, 20, 50]:
        df[f"vol_{window}"] = ret_1.rolling(window).std()

    # ── ATR (Average True Range) ─────────────────────────────────────────────
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)

    for atr_period in [14, 50]:
        atr = tr.rolling(atr_period).mean()
        df[f"atr_{atr_period}"] = atr
        df[f"natr_{atr_period}"] = atr / close

    # ── RSI ──────────────────────────────────────────────────────────────────
    for rsi_period in [14, 28]:
        delta = close.diff()
        gain  = delta.clip(lower=0).rolling(rsi_period).mean()
        loss  = (-delta.clip(upper=0)).rolling(rsi_period).mean()
        rs    = gain / (loss + 1e-10)
        df[f"rsi_{rsi_period}"] = 100 - (100 / (1 + rs))

    # ── MACD ─────────────────────────────────────────────────────────────────
    ema_12 = close.ewm(span=12, adjust=False).mean()
    ema_26 = close.ewm(span=26, adjust=False).mean()
    macd_line   = ema_12 - ema_26
    signal_line = macd_line.ewm(span=9, adjust=False).mean()
    df["macd"]           = macd_line
    df["macd_signal"]    = signal_line
    df["macd_hist"]      = macd_line - signal_line
    df["macd_hist_norm"] = (macd_line - signal_line) / (close + 1e-10)

    # ── Bollinger Bands ───────────────────────────────────────────────────────
    for bb_period in [20, 50]:
        bb_mid  = close.rolling(bb_period).mean()
        bb_std  = close.rolling(bb_period).std()
        bb_upper = bb_mid + 2.0 * bb_std
        bb_lower = bb_mid - 2.0 * bb_std
        bb_width = (bb_upper - bb_lower) / (bb_mid + 1e-10)
        bb_pos   = (close - bb_lower) / (bb_upper - bb_lower + 1e-10)
        df[f"bb_width_{bb_period}"] = bb_width
        df[f"bb_pos_{bb_period}"]   = bb_pos

    # ── Stochastic Oscillator ────────────────────────────────────────────────
    for stoch_period in [14, 28]:
        lowest_low   = low.rolling(stoch_period).min()
        highest_high = high.rolling(stoch_period).max()
        stoch_k = (close - lowest_low) / (highest_high - lowest_low + 1e-10) * 100
        stoch_d = stoch_k.rolling(3).mean()
        df[f"stoch_k_{stoch_period}"] = stoch_k
        df[f"stoch_d_{stoch_period}"] = stoch_d

    # ── Rate of Change (ROC) ──────────────────────────────────────────────────
    for roc_period in [5, 10, 20]:
        df[f"roc_{roc_period}"] = close.pct_change(roc_period)

    # ── Candle body and shadow features ──────────────────────────────────────
    body        = (close - open_).abs()
    candle_range = (high - low).abs()
    df["body_ratio"]       = body / (candle_range + 1e-10)
    df["upper_shadow"]     = (high - pd.concat([close, open_], axis=1).max(axis=1)) / (candle_range + 1e-10)
    df["lower_shadow"]     = (pd.concat([close, open_], axis=1).min(axis=1) - low) / (candle_range + 1e-10)
    df["bullish_candle"]   = np.where(close > open_, 1.0, -1.0)

    # ── Volume-proxy: candle range as volatility proxy ────────────────────────
    df["range_norm"] = candle_range / (close + 1e-10)
    df["range_ma_ratio"] = candle_range / (candle_range.rolling(20).mean() + 1e-10)

    # ── Lag features for return predictors ───────────────────────────────────
    for col_lag in ["rsi_14", "macd_hist", "bb_pos_20"]:
        for lag in [1, 2, 3]:
            df[f"{col_lag}_lag{lag}"] = df[col_lag].shift(lag)

    # ── Distance of close from recent high/low ────────────────────────────────
    for lookback in [10, 20, 50]:
        roll_high = high.rolling(lookback).max()
        roll_low  = low.rolling(lookback).min()
        df[f"dist_high_{lookback}"] = (close - roll_high) / (roll_high + 1e-10)
        df[f"dist_low_{lookback}"]  = (close - roll_low)  / (roll_low  + 1e-10)

    # ── Trend strength: ADX proxy ─────────────────────────────────────────────
    adx_period = 14
    tr_adx  = tr.copy()
    plus_dm  = pd.Series(np.where((high.diff() > 0) & (high.diff() > -low.diff()), high.diff(), 0.0), index=close.index)
    minus_dm = pd.Series(np.where((-low.diff() > 0) & (-low.diff() > high.diff()), -low.diff(), 0.0), index=close.index)
    atr_adx  = tr_adx.rolling(adx_period).mean()
    plus_di  = 100 * plus_dm.rolling(adx_period).mean()  / (atr_adx + 1e-10)
    minus_di = 100 * minus_dm.rolling(adx_period).mean() / (atr_adx + 1e-10)
    dx       = (100 * (plus_di - minus_di).abs() / (plus_di + minus_di + 1e-10))
    df["adx"]       = dx.rolling(adx_period).mean()
    df["plus_di"]   = plus_di
    df["minus_di"]  = minus_di

    # ── Fill NaN from indicator warm-up ──────────────────────────────────────
    df = df.bfill().ffill()

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "GBP/USD SMA Trend Gradient Boosting Risk-Adj",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":     400,
            "max_depth":        4,
            "learning_rate":    0.04,
            "subsample":        0.75,
            "min_samples_leaf": 20,
            "max_features":     "sqrt",
            "n_iter_no_change": 30,
            "validation_fraction": 0.1,
            "tol":              1e-4,
            "random_state":     42,
        },
        "signal_threshold": 0.57,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [6, 18],
        "min_atr":          0.0002,
        "trend_filter":     "sma_50",
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) on GBP/USD 15-min data. "
            "GradientBoostingClassifier chosen for its strong bias-variance tradeoff "
            "on medium-sized tabular datasets without needing GPU. "
            "Hyperparameters: moderate depth=4 prevents overfitting, learning_rate=0.04 "
            "with 400 estimators balances convergence vs generalisation, subsample=0.75 "
            "adds stochasticity to reduce variance, min_samples_leaf=20 enforces statistical "
            "significance at each leaf. Early stopping via n_iter_no_change guards against "
            "overfit on the training fold. Signal threshold 0.57 filters marginal signals "
            "to improve precision. SL=0.5%, TP=1.0% gives 1:2 RR. Session filter 6-18 UTC "
            "covers London+NY overlap — highest GBP/USD liquidity and tighter spreads. "
            "sma_50 trend filter ensures we only trade in the direction of medium-term trend, "
            "reducing whipsaw losses. target_horizon=4 bars (1 hour) gives the model enough "
            "time for moves to develop while staying relevant for intraday trading."
        ),
        "notes": (
            "Features: SMA 20/50/200 with distance metrics (core requirement), RSI 14/28, "
            "MACD, Bollinger Bands 20/50, Stochastic 14/28, ATR 14/50, NATR, ROC, ADX, "
            "candle body/shadow ratios, lagged RSI/MACD/BB features, distance from rolling "
            "high/low, SMA crossover signals, multi-lag return features. "
            "All features are backward-looking only (no lookahead bias). "
            "on_opposite=reverse for fast trend-following entries without missing reversals."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:54:13
# Model            : Gradient Boosting
# Feature Eng.     : EMA (9,21), RSI 14 + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/NZDUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── EMA 9 and EMA 21 (required) ──────────────────────────────────────────
    ema_9  = close.ewm(span=9,  adjust=False).mean()
    ema_21 = close.ewm(span=21, adjust=False).mean()

    df["ema_9"]    = ema_9
    df["ema_21"]   = ema_21
    df["dm_ema_9"]  = (close - ema_9)  / ema_9
    df["dm_ema_21"] = (close - ema_21) / ema_21

    # EMA crossover signal: positive when fast > slow
    df["ema_cross"] = ema_9 - ema_21

    # Rate of change of the crossover (momentum of the cross)
    df["ema_cross_roc"] = df["ema_cross"].diff(3)

    # ── RSI 14 (required) ────────────────────────────────────────────────────
    delta  = close.diff()
    gain   = delta.clip(lower=0)
    loss   = (-delta).clip(lower=0)
    avg_gain = gain.ewm(com=13, adjust=False).mean()
    avg_loss = loss.ewm(com=13, adjust=False).mean()
    rs     = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # RSI normalised to [-1, 1]
    df["rsi_norm"] = (df["rsi_14"] - 50) / 50

    # RSI momentum (1-bar diff of RSI)
    df["rsi_diff"] = df["rsi_14"].diff(1)

    # RSI overbought / oversold flags (np.where, no pd.cut)
    df["rsi_ob"] = np.where(df["rsi_14"] > 70, 1, 0)
    df["rsi_os"] = np.where(df["rsi_14"] < 30, 1, 0)

    # ── ATR 14 ───────────────────────────────────────────────────────────────
    prev_close = close.shift(1)
    tr = pd.concat([
        high - low,
        (high - prev_close).abs(),
        (low  - prev_close).abs()
    ], axis=1).max(axis=1)
    atr_14 = tr.ewm(com=13, adjust=False).mean()
    df["atr_14"]  = atr_14
    df["natr_14"] = atr_14 / close  # normalised ATR

    # ── MACD-style fast/slow difference (12/26 EMA) ─────────────────────────
    ema_12 = close.ewm(span=12, adjust=False).mean()
    ema_26 = close.ewm(span=26, adjust=False).mean()
    macd_line   = ema_12 - ema_26
    macd_signal = macd_line.ewm(span=9, adjust=False).mean()
    df["macd_line"]   = macd_line / close
    df["macd_signal"] = macd_signal / close
    df["macd_hist"]   = (macd_line - macd_signal) / close

    # ── Bollinger Bands (20, 2) ───────────────────────────────────────────────
    bb_mid  = close.rolling(20).mean()
    bb_std  = close.rolling(20).std()
    bb_up   = bb_mid + 2 * bb_std
    bb_lo   = bb_mid - 2 * bb_std
    bb_bw   = (bb_up - bb_lo) / bb_mid          # bandwidth
    bb_pct  = (close - bb_lo) / (bb_up - bb_lo) # %B position
    df["bb_bandwidth"] = bb_bw
    df["bb_pct"]       = bb_pct

    # ── Stochastic %K / %D (14, 3) ───────────────────────────────────────────
    low14  = low.rolling(14).min()
    high14 = high.rolling(14).max()
    stoch_k = 100 * (close - low14) / (high14 - low14).replace(0, np.nan)
    stoch_d = stoch_k.rolling(3).mean()
    df["stoch_k"] = stoch_k
    df["stoch_d"] = stoch_d
    df["stoch_kd_diff"] = stoch_k - stoch_d

    # ── Price momentum (returns over multiple horizons) ───────────────────────
    df["ret_1"]  = close.pct_change(1)
    df["ret_3"]  = close.pct_change(3)
    df["ret_6"]  = close.pct_change(6)
    df["ret_12"] = close.pct_change(12)

    # ── Candle body & shadow ratios ───────────────────────────────────────────
    body      = (close - open_).abs()
    candle_rng = (high - low).replace(0, np.nan)
    df["body_ratio"]       = body / candle_rng
    df["upper_shadow"]     = (high - pd.concat([close, open_], axis=1).max(axis=1)) / candle_rng
    df["lower_shadow"]     = (pd.concat([close, open_], axis=1).min(axis=1) - low) / candle_rng
    df["body_direction"]   = np.sign(close - open_)

    # ── Volume proxy: volatility-based (OHLC spread) ─────────────────────────
    df["hl_spread"] = (high - low) / close

    # ── Rolling volatility (std of returns) ──────────────────────────────────
    df["vol_6"]  = df["ret_1"].rolling(6).std()
    df["vol_24"] = df["ret_1"].rolling(24).std()

    # ── Z-score of close relative to 20-bar rolling mean ─────────────────────
    roll_mean_20 = close.rolling(20).mean()
    roll_std_20  = close.rolling(20).std()
    df["zscore_20"] = (close - roll_mean_20) / roll_std_20.replace(0, np.nan)

    # ── Trend strength: R² of close over 20 bars ─────────────────────────────
    x = np.arange(20)
    x_demeaned = x - x.mean()
    ss_x = (x_demeaned ** 2).sum()

    def rolling_r2(series, window=20):
        arr = series.values
        n   = len(arr)
        out = np.full(n, np.nan)
        for i in range(window - 1, n):
            y = arr[i - window + 1: i + 1]
            if np.any(np.isnan(y)):
                continue
            y_m = y - y.mean()
            slope = np.dot(x_demeaned, y_m) / ss_x
            y_hat = slope * x_demeaned + y.mean()
            ss_res = ((y - y_hat) ** 2).sum()
            ss_tot = ((y - y.mean()) ** 2).sum()
            out[i] = 1 - ss_res / ss_tot if ss_tot > 0 else 0.0
        return out

    df["trend_r2_20"] = rolling_r2(close, 20)

    # ── SMA 50 (for trend filter reference; also used as feature) ─────────────
    sma_50 = close.rolling(50).mean()
    df["sma_50"]       = sma_50
    df["close_vs_sma50"] = (close - sma_50) / sma_50

    # ── Higher-timeframe EMA proxy (4-bar resample = 1h equivalent) ──────────
    ema_4h = close.ewm(span=4 * 21, adjust=False).mean()
    df["dm_ema_4h"] = (close - ema_4h) / ema_4h

    # ── Cross confirmation: EMA cross direction × RSI regime ─────────────────
    df["cross_x_rsi"] = np.sign(df["ema_cross"]) * df["rsi_norm"]

    # ── Fill NaN from indicator warm-up ──────────────────────────────────────
    df = df.bfill().ffill()

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "NZD/USD EMA Cross (9/21) + RSI Gradient Boost",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":      400,
            "max_depth":         4,
            "learning_rate":     0.04,
            "subsample":         0.75,
            "min_samples_leaf":  20,
            "max_features":      "sqrt",
            "validation_fraction": 0.1,
            "n_iter_no_change":  25,
            "tol":               1e-4,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [0, 23],
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective":        (
            "Maximise risk-adjusted return (Sharpe) on NZD/USD 15-min data. "
            "GradientBoostingClassifier chosen for its strong out-of-box performance on "
            "tabular financial data, built-in regularisation via subsample/max_features, "
            "and early-stopping via n_iter_no_change. Depth-4 trees with 400 estimators "
            "and lr=0.04 balance bias-variance. SL=0.5% / TP=1.0% gives 1:2 R:R. "
            "4-bar horizon (~1 hour) aligns with EMA-cross momentum persistence. "
            "Threshold 0.55 filters marginal signals while preserving trade frequency."
        ),
        "notes":            (
            "Features: EMA 9/21 cross + distances, RSI 14 with OB/OS flags, MACD histogram, "
            "Bollinger %B + bandwidth, Stochastic K/D, multi-horizon returns, candle body "
            "ratios, rolling volatility, 20-bar z-score, trend R² and SMA50 distance. "
            "No session filter applied — NZD/USD has meaningful liquidity across Asian + "
            "London sessions. Reverse on opposite signal for continuous market exposure."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:41:21
# Model            : Gradient Boosting
# Feature Eng.     : SMA (20,50,200), BB (20,2.0), RSI 14, MACD (12,26,9), ATR 14 + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/GBPUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):

    # ── SMA 20, 50, 200 + distance from close ──────────────────────────────
    for period in [20, 50, 200]:
        sma = close.rolling(period).mean()
        df[f"sma_{period}"] = sma
        df[f"dm_sma_{period}"] = (close - sma) / sma

    # ── Bollinger Bands (20, 2) ─────────────────────────────────────────────
    bb_mid   = close.rolling(20).mean()
    bb_std   = close.rolling(20).std(ddof=0)
    bb_upper = bb_mid + 2.0 * bb_std
    bb_lower = bb_mid - 2.0 * bb_std
    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    bb_range       = bb_upper - bb_lower
    df["bb_pct"]   = np.where(bb_range != 0, (close - bb_lower) / bb_range, 0.5)

    # ── RSI 14 ─────────────────────────────────────────────────────────────
    delta     = close.diff()
    gain      = delta.clip(lower=0)
    loss      = (-delta).clip(lower=0)
    avg_gain  = gain.ewm(com=13, min_periods=14, adjust=False).mean()
    avg_loss  = loss.ewm(com=13, min_periods=14, adjust=False).mean()
    rs        = np.where(avg_loss != 0, avg_gain / avg_loss, 100.0)
    df["rsi_14"] = 100.0 - (100.0 / (1.0 + rs))

    # ── MACD (12, 26, 9) ───────────────────────────────────────────────────
    ema_12          = close.ewm(span=12, adjust=False).mean()
    ema_26          = close.ewm(span=26, adjust=False).mean()
    macd_line       = ema_12 - ema_26
    signal_line     = macd_line.ewm(span=9, adjust=False).mean()
    df["macd_line"] = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"] = macd_line - signal_line

    # ── ATR 14 + NATR ──────────────────────────────────────────────────────
    prev_close  = close.shift(1)
    tr          = pd.concat([
        high - low,
        (high - prev_close).abs(),
        (low  - prev_close).abs()
    ], axis=1).max(axis=1)
    atr         = tr.ewm(com=13, min_periods=14, adjust=False).mean()
    df["atr_14"] = atr
    df["natr"]   = np.where(close != 0, atr / close, 0.0)

    # ── Price momentum (returns over multiple horizons) ────────────────────
    for lag in [1, 4, 8, 16]:
        df[f"ret_{lag}"] = close.pct_change(lag)

    # ── Candle body & wick features ────────────────────────────────────────
    body             = (close - open_).abs()
    candle_range     = (high - low).replace(0, np.nan)
    df["body_ratio"] = body / candle_range
    df["upper_wick"] = np.where(
        candle_range.notna(),
        (high - close.combine(open_, max)) / candle_range,
        0.0
    )
    df["lower_wick"] = np.where(
        candle_range.notna(),
        (close.combine(open_, min) - low) / candle_range,
        0.0
    )
    df["candle_dir"] = np.where(close >= open_, 1.0, -1.0)

    # ── Volume proxy: normalised candle range ──────────────────────────────
    rolling_range    = candle_range.rolling(20).mean()
    df["norm_range"] = np.where(
        rolling_range != 0,
        (high - low) / rolling_range,
        1.0
    )

    # ── RSI derived features ───────────────────────────────────────────────
    df["rsi_ob"]    = np.where(df["rsi_14"] > 70, 1.0, 0.0)
    df["rsi_os"]    = np.where(df["rsi_14"] < 30, 1.0, 0.0)
    df["rsi_mid"]   = df["rsi_14"] - 50.0
    df["rsi_slope"] = df["rsi_14"].diff(3)

    # ── MACD histogram slope ───────────────────────────────────────────────
    df["macd_hist_slope"] = df["macd_hist"].diff(2)
    df["macd_cross"]      = np.where(
        (df["macd_hist"] > 0) & (df["macd_hist"].shift(1) <= 0), 1.0,
        np.where(
            (df["macd_hist"] < 0) & (df["macd_hist"].shift(1) >= 0), -1.0,
            0.0
        )
    )

    # ── Bollinger squeeze (low volatility precursor) ───────────────────────
    bb_width_ma         = df["bb_width"].rolling(20).mean()
    df["bb_squeeze"]    = np.where(df["bb_width"] < bb_width_ma, 1.0, 0.0)

    # ── SMA slope features ─────────────────────────────────────────────────
    df["sma_20_slope"] = df["sma_20"].pct_change(4)
    df["sma_50_slope"] = df["sma_50"].pct_change(8)

    # ── Cross-SMA alignment (trend structure) ──────────────────────────────
    df["sma20_above_50"]  = np.where(df["sma_20"] > df["sma_50"],  1.0, 0.0)
    df["sma50_above_200"] = np.where(df["sma_50"] > df["sma_200"], 1.0, 0.0)
    df["close_above_200"] = np.where(close > df["sma_200"],        1.0, 0.0)

    # ── Lagged close returns as additional features ────────────────────────
    for lag in [1, 2, 3]:
        df[f"close_lag_{lag}"] = close.shift(lag)

    # ── Rolling volatility (std of returns) ────────────────────────────────
    df["vol_10"]  = close.pct_change().rolling(10).std()
    df["vol_20"]  = close.pct_change().rolling(20).std()
    df["vol_ratio"] = np.where(
        df["vol_20"] != 0,
        df["vol_10"] / df["vol_20"],
        1.0
    )

    # ── Hour-of-day (London/NY session proxy) ──────────────────────────────
    if hasattr(df.index, "hour"):
        df["hour_sin"] = np.sin(2 * np.pi * df.index.hour / 24.0)
        df["hour_cos"] = np.cos(2 * np.pi * df.index.hour / 24.0)
    else:
        df["hour_sin"] = 0.0
        df["hour_cos"] = 1.0

    # ── Fill NaN from warm-up periods ──────────────────────────────────────
    df = df.bfill().ffill()

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "GBP/USD Gradient Boosting Trend + Mean-Reversion",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":     400,
            "max_depth":        4,
            "learning_rate":    0.04,
            "subsample":        0.8,
            "min_samples_leaf": 20,
            "max_features":     "sqrt",
            "validation_fraction": 0.1,
            "n_iter_no_change": 30,
            "tol":              1e-4,
            "random_state":     42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [6, 20],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) on GBP/USD 15-min. "
            "GradientBoostingClassifier with 400 shallow trees (depth 4) and a "
            "conservative learning rate of 0.04 avoids overfitting while capturing "
            "non-linear interactions between trend (SMA alignment, slope), momentum "
            "(MACD histogram, RSI), and volatility (ATR, BB squeeze) features. "
            "SL=0.5% / TP=1.0% gives 1:2 R/R. Session filter 06-20 UTC covers "
            "London open through NY close where GBP/USD liquidity is highest. "
            "min_atr filter avoids flat/illiquid bars."
        ),
        "notes": (
            "Features include multi-period SMA distances, Bollinger Band pct/width, "
            "RSI with overbought/oversold flags, MACD histogram slope and crossover, "
            "ATR-normalised volatility, candle body/wick ratios, rolling vol ratio, "
            "and hour-of-day cyclical encoding. target_horizon=4 (1-hour forward) "
            "balances signal frequency against predictability at 15-min resolution."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:51:31
# Model            : XGBoost
# Feature Eng.     : BB (20,2.0), RSI 14, Stochastic (14,3) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/AUDUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):

    # ── Bollinger Bands (20, 2) ──────────────────────────────────────────────
    bb_period = 20
    bb_std    = 2.0
    bb_mid    = close.rolling(bb_period).mean()
    bb_std_val = close.rolling(bb_period).std(ddof=0)
    bb_upper  = bb_mid + bb_std * bb_std_val
    bb_lower  = bb_mid - bb_std * bb_std_val

    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    df["bb_pct"]   = (close - bb_lower) / (bb_upper - bb_lower)

    # ── RSI (14) ─────────────────────────────────────────────────────────────
    rsi_period = 14
    delta      = close.diff()
    gain       = delta.clip(lower=0)
    loss       = -delta.clip(upper=0)
    avg_gain   = gain.ewm(com=rsi_period - 1, min_periods=rsi_period).mean()
    avg_loss   = loss.ewm(com=rsi_period - 1, min_periods=rsi_period).mean()
    rs         = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi"]  = 100 - (100 / (1 + rs))

    # ── Stochastic Oscillator (K=14, D=3) ────────────────────────────────────
    stoch_k_period = 14
    stoch_d_period = 3
    lowest_low     = low.rolling(stoch_k_period).min()
    highest_high   = high.rolling(stoch_k_period).max()
    denom          = (highest_high - lowest_low).replace(0, np.nan)
    df["stoch_k"]  = 100 * (close - lowest_low) / denom
    df["stoch_d"]  = df["stoch_k"].rolling(stoch_d_period).mean()
    df["stoch_kd_diff"] = df["stoch_k"] - df["stoch_d"]

    # ── Additional derived features ──────────────────────────────────────────

    # RSI overbought / oversold zone flags
    df["rsi_ob"]   = np.where(df["rsi"] > 70, 1, 0)
    df["rsi_os"]   = np.where(df["rsi"] < 30, 1, 0)
    df["rsi_mid"]  = df["rsi"] - 50.0

    # Stochastic overbought / oversold zone flags
    df["stoch_ob"] = np.where(df["stoch_k"] > 80, 1, 0)
    df["stoch_os"] = np.where(df["stoch_k"] < 20, 1, 0)

    # BB position regime: price relative to bands
    df["price_above_bb_upper"] = np.where(close > bb_upper, 1, 0)
    df["price_below_bb_lower"] = np.where(close < bb_lower, 1, 0)
    df["price_vs_bb_mid"]      = close - bb_mid

    # ATR-based volatility (14-bar)
    atr_period = 14
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    df["atr14"]  = tr.ewm(com=atr_period - 1, min_periods=atr_period).mean()
    df["natr14"] = df["atr14"] / close

    # SMA trend context
    df["sma_20"]  = close.rolling(20).mean()
    df["sma_50"]  = close.rolling(50).mean()
    df["sma_200"] = close.rolling(200).mean()
    df["price_vs_sma20"]  = (close - df["sma_20"]) / df["sma_20"]
    df["price_vs_sma50"]  = (close - df["sma_50"]) / df["sma_50"]
    df["sma20_vs_sma50"]  = (df["sma_20"] - df["sma_50"]) / df["sma_50"]

    # Momentum: rate of change
    df["roc_5"]  = close.pct_change(5)
    df["roc_10"] = close.pct_change(10)
    df["roc_20"] = close.pct_change(20)

    # MACD-style (EMA 12 - EMA 26)
    ema12        = close.ewm(span=12, min_periods=12).mean()
    ema26        = close.ewm(span=26, min_periods=26).mean()
    macd_line    = ema12 - ema26
    macd_signal  = macd_line.ewm(span=9, min_periods=9).mean()
    df["macd"]        = macd_line
    df["macd_signal"] = macd_signal
    df["macd_hist"]   = macd_line - macd_signal

    # Candle body / wick ratios
    body          = (close - open_).abs()
    candle_range  = (high - low).replace(0, np.nan)
    df["body_ratio"]  = body / candle_range
    df["upper_wick"]  = (high - pd.concat([close, open_], axis=1).max(axis=1)) / candle_range
    df["lower_wick"]  = (pd.concat([close, open_], axis=1).min(axis=1) - low) / candle_range
    df["bullish_bar"]  = np.where(close > open_, 1, 0)

    # Lagged RSI / Stoch features (1 and 2 bars back)
    df["rsi_lag1"]     = df["rsi"].shift(1)
    df["rsi_lag2"]     = df["rsi"].shift(2)
    df["stoch_k_lag1"] = df["stoch_k"].shift(1)
    df["bb_pct_lag1"]  = df["bb_pct"].shift(1)

    # RSI slope
    df["rsi_slope"] = df["rsi"] - df["rsi"].shift(3)

    # Stoch K crossing D (momentum signal)
    df["stoch_cross_up"]   = np.where((df["stoch_k"] > df["stoch_d"]) &
                                       (df["stoch_k"].shift(1) <= df["stoch_d"].shift(1)), 1, 0)
    df["stoch_cross_down"] = np.where((df["stoch_k"] < df["stoch_d"]) &
                                       (df["stoch_k"].shift(1) >= df["stoch_d"].shift(1)), 1, 0)

    # Volume (if present)
    if "volume" in df.columns:
        vol_ma = df["volume"].rolling(20).mean()
        df["vol_ratio"] = df["volume"] / vol_ma.replace(0, np.nan)
    else:
        df["vol_ratio"] = 1.0

    # ── Fill NaN from warm-up ────────────────────────────────────────────────
    df = df.bfill().ffill()

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "AUD/USD Stoch+BB+RSI Mean-Reversion XGBoost",
        "model_type":       "XGBClassifier",
        "model_params": {
            "n_estimators":       400,
            "max_depth":          4,
            "learning_rate":      0.04,
            "subsample":          0.75,
            "colsample_bytree":   0.70,
            "min_child_weight":   5,
            "gamma":              0.15,
            "reg_alpha":          0.10,
            "reg_lambda":         1.50,
            "objective":          "binary:logistic",
            "random_state":       42,
            "n_jobs":             -1,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [0, 23],
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe / Calmar). "
            "XGBoost chosen for its ability to capture non-linear interactions "
            "between Stochastic, Bollinger Bands, and RSI regimes. "
            "Shallow trees (max_depth=4) + high regularisation (reg_lambda=1.5, gamma=0.15) "
            "prevent overfitting on 15-min FX data. "
            "2:1 TP:SL ratio (1.0% / 0.5%) improves expectancy per trade. "
            "Reverse on opposite signal minimises flat time and captures regime flips."
        ),
        "notes": (
            "Features include BB width/pct, RSI(14) with overbought/oversold flags, "
            "Stochastic K/D crossovers, MACD histogram, ATR volatility, SMA trend context, "
            "candle body ratios, lagged indicators, and momentum ROC. "
            "signal_threshold=0.55 balances precision vs recall on directional calls. "
            "session_filter covers full 24h to capture Asia + London + NY sessions for AUD/USD."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-07 01:38:25
# Model            : XGBoost
# Feature Eng.     : EMA crossover trend (9/21) with RSI 14 confirmation on EURUSD 15min + Auto-add features: ON
# Signal / Entry   : —
# Optimization     : —
# Risk Mgmt        : —
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# QUANTIFY ME — STRATEGY MODULE
# EMA Crossover + RSI Confirmation (XGBoost, Sharpe Optimization)
# ============================================================

import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/EURUSD_15min.parquet"
START_DATE = "2026-03-28"
END_DATE   = "2026-04-25"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7


# ============================================================
# SECTION 1 — FEATURE ENGINEERING
# ============================================================

def feature_engineering(df, close, open_, high, low):
    """
    Add EMA crossover trend features + RSI confirmation.
    
    Features:
      - EMA 9 and EMA 21 for trend direction
      - RSI 14 for momentum confirmation
      - EMA crossover signal
      - Price deviation from EMA 21
      - High/Low proximity ratios
      - Volume-based volatility (NATR)
    """
    
    # EMA 9 and EMA 21 for trend
    df['ema_9'] = close.ewm(span=9, adjust=False).mean()
    df['ema_21'] = close.ewm(span=21, adjust=False).mean()
    df['ema_crossover'] = np.where(df['ema_9'] > df['ema_21'], 1, -1)
    
    # EMA crossover signal (1 when 9 crosses above 21, -1 when crosses below)
    df['ema_cross_signal'] = df['ema_crossover'].diff().fillna(0)
    df['ema_cross_signal'] = np.where(df['ema_cross_signal'] != 0, df['ema_cross_signal'], 0)
    
    # Price deviation from EMA 21 (normalized)
    df['price_ema_deviation'] = (close - df['ema_21']) / df['ema_21']
    
    # RSI 14 for momentum confirmation
    delta = close.diff()
    gain = np.where(delta > 0, delta, 0)
    loss = np.where(delta < 0, -delta, 0)
    
    avg_gain = pd.Series(gain, index=close.index).ewm(span=14, adjust=False).mean()
    avg_loss = pd.Series(loss, index=close.index).ewm(span=14, adjust=False).mean()
    
    rs = avg_gain / (avg_loss + 1e-10)
    df['rsi_14'] = 100 - (100 / (1 + rs))
    
    # RSI signal: overbought/oversold
    df['rsi_overbought'] = np.where(df['rsi_14'] > 70, 1, 0)
    df['rsi_oversold'] = np.where(df['rsi_14'] < 30, 1, 0)
    
    # High/Low proximity (distance from recent extremes)
    df['high_20'] = high.rolling(window=20).max()
    df['low_20'] = low.rolling(window=20).min()
    df['price_position'] = (close - df['low_20']) / (df['high_20'] - df['low_20'] + 1e-10)
    
    # NATR (Normalized ATR) for volatility
    atr_period = 14
    tr1 = high - low
    tr2 = np.abs(high - close.shift(1))
    tr3 = np.abs(low - close.shift(1))
    tr = np.maximum(tr1, np.maximum(tr2, tr3))
    atr = pd.Series(tr, index=close.index).rolling(window=atr_period).mean()
    df['natr'] = (atr / close) * 100
    
    # EMA momentum (rate of change in EMA)
    df['ema_9_roc'] = df['ema_9'].pct_change(periods=3)
    df['ema_21_roc'] = df['ema_21'].pct_change(periods=3)
    
    # Close relative to open (intrabar direction)
    df['close_above_open'] = np.where(close > open_, 1, 0)
    
    # Volume-based features (if available; otherwise skip)
    if 'volume' in df.columns:
        df['volume_ma'] = df['volume'].rolling(window=20).mean()
        df['volume_ratio'] = df['volume'] / (df['volume_ma'] + 1e-10)
    else:
        df['volume_ratio'] = 1.0
    
    # Fill NaN from indicator warm-up
    df = df.bfill().ffill()
    
    return df


# ============================================================
# SECTION 2 — STRATEGY CONFIG
# ============================================================

def strategy_config():
    """
    XGBoost strategy optimized for Sharpe ratio on EMA/RSI signals.
    
    Hyperparameters tuned for:
      - Fast learning (learning_rate=0.08)
      - Shallow trees (max_depth=4) to avoid overfitting on 15min data
      - Moderate boosting (n_estimators=250) for good generalization
      - Regularization (subsample=0.85, colsample_bytree=0.8)
      - Balanced class weights via scale_pos_weight
    
    Signal threshold 0.55 chosen to be moderately selective while maintaining
    good trade frequency on the EMA crossover setup.
    """
    
    return {
        # Model specification
        "model_type": "XGBClassifier",
        "model_params": {
            "n_estimators": 250,
            "max_depth": 4,
            "learning_rate": 0.08,
            "subsample": 0.85,
            "colsample_bytree": 0.8,
            "min_child_weight": 1,
            "gamma": 0.5,
            "reg_alpha": 0.1,
            "reg_lambda": 1.0,
            "random_state": 42,
            "verbosity": 0,
        },
        
        # Entry signal
        "signal_threshold": 0.55,
        
        # Position management
        "direction": "both",
        "max_positions": 1,
        "on_opposite": "reverse",
        "cooldown": 0,
        
        # Risk management
        "stop_loss": 0.008,
        "take_profit": 0.015,
        
        # Filters
        "session_filter": None,
        "min_atr": None,
        "trend_filter": None,
        
        # Target
        "target_horizon": 4,
        
        # Metadata
        "title": "EMA Crossover + RSI Confirmation (XGBoost)",
        "objective": "Maximize Sharpe ratio with EMA 9/21 trend + RSI 14 momentum confirmation",
        "notes": (
            "Strategy uses fast EMA (9) crossover above/below slow EMA (21) "
            "as primary trend signal, confirmed by RSI 14 momentum. "
            "XGBoost learns non-linear interactions between these features. "
            "Moderate SL/TP (0.8%/1.5%) and bidirectional trading for scalping efficiency. "
            "Optimized for EURUSD 15min with 70/30 train/test split."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:51:04
# Model            : XGBoost
# Feature Eng.     : RSI 14, MACD (12,26,9) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/NZDUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── RSI 14 ──────────────────────────────────────────────────────────────
    period = 14
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = -delta.clip(upper=0)
    avg_gain = gain.ewm(com=period - 1, min_periods=period).mean()
    avg_loss = loss.ewm(com=period - 1, min_periods=period).mean()
    rs = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # RSI derived features
    df["rsi_14_norm"] = (df["rsi_14"] - 50) / 50          # centred & scaled
    df["rsi_14_ob"]   = np.where(df["rsi_14"] > 70, 1, 0) # overbought flag
    df["rsi_14_os"]   = np.where(df["rsi_14"] < 30, 1, 0) # oversold flag
    df["rsi_14_mom"]  = df["rsi_14"].diff(3)               # 3-bar momentum

    # ── MACD (12, 26, 9) ────────────────────────────────────────────────────
    ema_12 = close.ewm(span=12, adjust=False).mean()
    ema_26 = close.ewm(span=26, adjust=False).mean()
    macd_line   = ema_12 - ema_26
    signal_line = macd_line.ewm(span=9, adjust=False).mean()
    macd_hist   = macd_line - signal_line

    df["macd_line"]   = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"]   = macd_hist

    # MACD derived features
    df["macd_hist_mom"]   = macd_hist.diff(2)              # histogram momentum
    df["macd_cross_bull"] = np.where(
        (macd_line > signal_line) & (macd_line.shift(1) <= signal_line.shift(1)), 1, 0
    )
    df["macd_cross_bear"] = np.where(
        (macd_line < signal_line) & (macd_line.shift(1) >= signal_line.shift(1)), 1, 0
    )
    df["macd_zero_cross"] = np.where(
        (macd_line > 0) & (macd_line.shift(1) <= 0), 1,
        np.where((macd_line < 0) & (macd_line.shift(1) >= 0), -1, 0)
    )

    # ── Additional price-action features ────────────────────────────────────
    # ATR (14) for volatility context
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    atr_14 = tr.ewm(span=14, adjust=False).mean()
    df["atr_14"]  = atr_14
    df["natr_14"] = atr_14 / close                         # normalised ATR

    # Bollinger Bands (20, 2) — mean-reversion context
    sma_20  = close.rolling(20).mean()
    std_20  = close.rolling(20).std()
    bb_up   = sma_20 + 2 * std_20
    bb_lo   = sma_20 - 2 * std_20
    df["bb_pct"]   = (close - bb_lo) / (bb_up - bb_lo + 1e-12)  # 0-1 position
    df["bb_width"] = (bb_up - bb_lo) / sma_20                   # band width

    # SMA filters
    df["sma_20"]  = sma_20
    df["sma_50"]  = close.rolling(50).mean()
    df["price_vs_sma20"] = (close - sma_20) / (sma_20 + 1e-12)
    df["price_vs_sma50"] = (close - df["sma_50"]) / (df["sma_50"] + 1e-12)

    # Rate of change
    df["roc_5"]  = close.pct_change(5)
    df["roc_10"] = close.pct_change(10)
    df["roc_20"] = close.pct_change(20)

    # Candlestick body / shadow ratios
    body        = (close - open_).abs()
    candle_rng  = (high - low).replace(0, np.nan)
    df["body_ratio"]   = body / candle_rng
    df["upper_shadow"]  = (high - pd.concat([close, open_], axis=1).max(axis=1)) / candle_rng
    df["lower_shadow"]  = (pd.concat([close, open_], axis=1).min(axis=1) - low) / candle_rng
    df["bar_direction"] = np.where(close >= open_, 1, -1)

    # Volume-proxy: realised range / ATR ratio
    df["range_vs_atr"] = candle_rng / (atr_14 + 1e-12)

    # Stochastic %K (14)
    lowest_14  = low.rolling(14).min()
    highest_14 = high.rolling(14).max()
    stoch_k    = 100 * (close - lowest_14) / (highest_14 - lowest_14 + 1e-12)
    df["stoch_k"]   = stoch_k
    df["stoch_d"]   = stoch_k.rolling(3).mean()
    df["stoch_diff"] = df["stoch_k"] - df["stoch_d"]

    # RSI × MACD interaction
    df["rsi_macd_interact"] = df["rsi_14_norm"] * macd_hist

    # Lagged features (1 and 2 bars back) for key signals
    for col in ["rsi_14_norm", "macd_hist", "bb_pct", "roc_5"]:
        df[f"{col}_lag1"] = df[col].shift(1)
        df[f"{col}_lag2"] = df[col].shift(2)

    # ── Fill NaN from warm-up ────────────────────────────────────────────────
    df = df.bfill().ffill()
    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "NZD/USD MACD+RSI Momentum (XGBoost, Risk-Adj)",
        "model_type":       "XGBClassifier",
        "model_params": {
            "n_estimators":       400,
            "max_depth":          4,
            "learning_rate":      0.04,
            "subsample":          0.75,
            "colsample_bytree":   0.70,
            "min_child_weight":   3,
            "gamma":              0.15,
            "reg_alpha":          0.10,
            "reg_lambda":         1.50,
            "objective":          "binary:logistic",
            "tree_method":        "hist",
            "random_state":       42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [0, 23],
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximise risk-adjusted return (Sharpe/Calmar) on NZD/USD 15-min data. "
            "XGBoost chosen for its strong performance on tabular financial data. "
            "Moderate depth (4) and high regularisation (gamma, alpha, lambda) prevent "
            "overfitting on a relatively small forex dataset. Subsample + colsample_bytree "
            "add stochastic diversity. SL 0.5% / TP 1.0% gives a 1:2 R:R ratio to support "
            "positive expectancy even with a sub-60% win rate. Threshold 0.55 filters marginal "
            "signals while keeping trade frequency acceptable. Target horizon of 4 bars (1 hour) "
            "aligns with typical MACD/RSI signal resolution on 15-min charts."
        ),
        "notes": (
            "Features: RSI-14 (raw, normalised, OB/OS flags, momentum), MACD(12,26,9) "
            "(line, signal, histogram, crosses, zero-cross), Bollinger Bands %B & width, "
            "ATR/NATR, SMA20/50 price deviations, Stochastic %K/%D, ROC(5/10/20), "
            "candlestick body/shadow ratios, RSI×MACD interaction term, and lagged "
            "versions (lag1, lag2) of key signals to capture short-term persistence."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:58:30
# Model            : XGBoost
# Feature Eng.     : BB (20,2.0), RSI 14, Stochastic (14,3) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/USDCAD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── Bollinger Bands (20, 2) ──────────────────────────────────────────────
    bb_period = 20
    bb_std    = 2.0
    bb_mid    = close.rolling(bb_period).mean()
    bb_std_s  = close.rolling(bb_period).std(ddof=0)
    bb_upper  = bb_mid + bb_std * bb_std_s
    bb_lower  = bb_mid - bb_std * bb_std_s

    df["bb_mid"]   = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    df["bb_pct"]   = (close - bb_lower) / (bb_upper - bb_lower)

    # ── RSI (14) ─────────────────────────────────────────────────────────────
    rsi_period = 14
    delta      = close.diff()
    gain       = delta.clip(lower=0)
    loss       = (-delta).clip(lower=0)
    avg_gain   = gain.ewm(com=rsi_period - 1, min_periods=rsi_period).mean()
    avg_loss   = loss.ewm(com=rsi_period - 1, min_periods=rsi_period).mean()
    rs         = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi"]  = 100 - (100 / (1 + rs))

    # ── Stochastic Oscillator (K=14, D=3) ────────────────────────────────────
    stoch_k_period = 14
    stoch_d_period = 3
    lowest_low   = low.rolling(stoch_k_period).min()
    highest_high = high.rolling(stoch_k_period).max()
    stoch_k_raw  = 100 * (close - lowest_low) / (highest_high - lowest_low).replace(0, np.nan)
    df["stoch_k"] = stoch_k_raw
    df["stoch_d"] = stoch_k_raw.rolling(stoch_d_period).mean()

    # ── Derived Stochastic features ──────────────────────────────────────────
    df["stoch_kd_diff"] = df["stoch_k"] - df["stoch_d"]   # K-D divergence
    df["stoch_k_prev"]  = df["stoch_k"].shift(1)
    df["stoch_d_prev"]  = df["stoch_d"].shift(1)
    # Bullish crossover: K crosses above D
    df["stoch_cross_up"] = np.where(
        (df["stoch_k"] > df["stoch_d"]) & (df["stoch_k_prev"] <= df["stoch_d_prev"]), 1.0, 0.0
    )
    # Bearish crossover: K crosses below D
    df["stoch_cross_dn"] = np.where(
        (df["stoch_k"] < df["stoch_d"]) & (df["stoch_k_prev"] >= df["stoch_d_prev"]), 1.0, 0.0
    )

    # ── RSI-derived features ─────────────────────────────────────────────────
    df["rsi_prev"]     = df["rsi"].shift(1)
    df["rsi_slope"]    = df["rsi"] - df["rsi_prev"]
    df["rsi_ob"]       = np.where(df["rsi"] >= 70, 1.0, 0.0)   # overbought flag
    df["rsi_os"]       = np.where(df["rsi"] <= 30, 1.0, 0.0)   # oversold flag

    # ── BB-derived features ──────────────────────────────────────────────────
    df["bb_pct_prev"]  = df["bb_pct"].shift(1)
    df["bb_pct_slope"] = df["bb_pct"] - df["bb_pct_prev"]
    df["price_vs_mid"] = (close - bb_mid) / bb_mid             # normalised distance from mid
    # Squeeze: narrow bands relative to recent history
    df["bb_squeeze"]   = np.where(
        df["bb_width"] < df["bb_width"].rolling(50).mean(), 1.0, 0.0
    )

    # ── ATR (14) — volatility context ────────────────────────────────────────
    atr_period = 14
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low  - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    df["atr"]  = tr.ewm(com=atr_period - 1, min_periods=atr_period).mean()
    df["natr"] = df["atr"] / close

    # ── Momentum / price change features ─────────────────────────────────────
    df["ret_1"]  = close.pct_change(1)
    df["ret_4"]  = close.pct_change(4)
    df["ret_16"] = close.pct_change(16)

    # ── Trend context: SMA 50 & 200 ──────────────────────────────────────────
    df["sma_50"]        = close.rolling(50).mean()
    df["sma_200"]       = close.rolling(200).mean()
    df["price_vs_50"]   = (close - df["sma_50"])  / df["sma_50"]
    df["price_vs_200"]  = (close - df["sma_200"]) / df["sma_200"]
    df["trend_up"]      = np.where(df["sma_50"] > df["sma_200"], 1.0, 0.0)

    # ── Volume proxy: candle body / range ratio ───────────────────────────────
    candle_range = (high - low).replace(0, np.nan)
    df["body_ratio"] = (close - open_).abs() / candle_range
    df["bull_bar"]   = np.where(close > open_, 1.0, 0.0)

    # ── MACD-like momentum: EMA12 - EMA26 ────────────────────────────────────
    ema12        = close.ewm(span=12, adjust=False).mean()
    ema26        = close.ewm(span=26, adjust=False).mean()
    df["macd"]   = ema12 - ema26
    df["macd_signal"] = df["macd"].ewm(span=9, adjust=False).mean()
    df["macd_hist"]   = df["macd"] - df["macd_signal"]

    # ── Rolling volatility (std of returns) ──────────────────────────────────
    df["vol_10"] = df["ret_1"].rolling(10).std()

    # ── Hour-of-day and day-of-week (cyclical) ────────────────────────────────
    if hasattr(df.index, "hour"):
        df["hour_sin"] = np.sin(2 * np.pi * df.index.hour / 24)
        df["hour_cos"] = np.cos(2 * np.pi * df.index.hour / 24)
        df["dow_sin"]  = np.sin(2 * np.pi * df.index.dayofweek / 5)
        df["dow_cos"]  = np.cos(2 * np.pi * df.index.dayofweek / 5)

    # ── Combined signal: RSI + Stoch confluence ───────────────────────────────
    df["conf_bull"] = np.where((df["rsi"] < 50) & (df["stoch_k"] < 50), 1.0, 0.0)
    df["conf_bear"] = np.where((df["rsi"] > 50) & (df["stoch_k"] > 50), 1.0, 0.0)

    # ── Fill NaN from warm-up periods ────────────────────────────────────────
    df = df.bfill().ffill()

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "USD/CAD Stoch+BB+RSI Mean-Reversion (XGBoost)",
        "model_type":       "XGBClassifier",
        "model_params": {
            "n_estimators":     400,
            "max_depth":        4,
            "learning_rate":    0.04,
            "subsample":        0.80,
            "colsample_bytree": 0.75,
            "min_child_weight": 3,
            "gamma":            0.10,
            "reg_alpha":        0.10,
            "reg_lambda":       1.50,
            "objective":        "binary:logistic",
            "tree_method":      "hist",
            "random_state":     42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [7, 20],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) by combining "
            "Stochastic (14,3), Bollinger Bands (20,2) and RSI(14) mean-reversion "
            "signals with XGBoost. Regularisation (reg_alpha, reg_lambda, gamma, "
            "min_child_weight) and column/row subsampling control overfitting. "
            "A 0.55 confidence threshold filters low-conviction trades. "
            "Session filter [7,20] UTC focuses on liquid London+NY overlap hours. "
            "SL=0.5% / TP=1.0% gives a 1:2 risk-reward per trade."
        ),
        "notes": (
            "target_horizon=4 bars (1 hour on 15-min data) suits intraday mean-reversion. "
            "Cyclical time features (hour_sin/cos, dow_sin/cos) capture intraday seasonality. "
            "MACD histogram and rolling volatility provide trend/momentum context alongside "
            "the core BB/RSI/Stoch mean-reversion suite. "
            "reverse on_opposite allows the model to flip positions when conviction is high "
            "in the opposing direction without waiting for flat cooldown."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:23:23
# Model            : XGBoost
# Feature Eng.     : RSI 14, MACD (12,26,9) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/GBPUSD_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):

    # --- RSI 14 ---
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = -delta.clip(upper=0)
    avg_gain = gain.ewm(com=13, min_periods=14).mean()
    avg_loss = loss.ewm(com=13, min_periods=14).mean()
    rs = avg_gain / (avg_loss + 1e-12)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # RSI derived features
    df["rsi_zscore"] = (df["rsi_14"] - df["rsi_14"].rolling(50).mean()) / (df["rsi_14"].rolling(50).std() + 1e-12)
    df["rsi_slope"] = df["rsi_14"].diff(3)
    df["rsi_above_50"] = np.where(df["rsi_14"] > 50, 1, 0)
    df["rsi_overbought"] = np.where(df["rsi_14"] > 70, 1, 0)
    df["rsi_oversold"] = np.where(df["rsi_14"] < 30, 1, 0)
    # RSI divergence proxy: price direction vs RSI direction
    price_dir_3 = np.sign(close.diff(3))
    rsi_dir_3 = np.sign(df["rsi_14"].diff(3))
    df["rsi_divergence"] = np.where(price_dir_3 != rsi_dir_3, 1, 0)

    # --- MACD (12, 26, 9) ---
    ema12 = close.ewm(span=12, adjust=False).mean()
    ema26 = close.ewm(span=26, adjust=False).mean()
    macd_line = ema12 - ema26
    signal_line = macd_line.ewm(span=9, adjust=False).mean()
    macd_hist = macd_line - signal_line
    df["macd_line"] = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"] = macd_hist

    # MACD derived features
    df["macd_hist_slope"] = macd_hist.diff(2)
    df["macd_cross_up"] = np.where((macd_line > signal_line) & (macd_line.shift(1) <= signal_line.shift(1)), 1, 0)
    df["macd_cross_dn"] = np.where((macd_line < signal_line) & (macd_line.shift(1) >= signal_line.shift(1)), 1, 0)
    df["macd_hist_positive"] = np.where(macd_hist > 0, 1, 0)
    df["macd_hist_expanding"] = np.where(macd_hist.abs() > macd_hist.abs().shift(1), 1, 0)
    df["macd_normalized"] = macd_line / (close + 1e-12)

    # --- ATR 14 ---
    tr1 = high - low
    tr2 = (high - close.shift(1)).abs()
    tr3 = (low - close.shift(1)).abs()
    tr = pd.concat([tr1, tr2, tr3], axis=1).max(axis=1)
    atr14 = tr.ewm(com=13, min_periods=14).mean()
    df["atr_14"] = atr14
    df["natr_14"] = atr14 / (close + 1e-12)

    # ATR regime: high vs low volatility
    atr_ma = atr14.rolling(50).mean()
    df["atr_high_vol"] = np.where(atr14 > atr_ma * 1.2, 1, 0)
    df["atr_low_vol"] = np.where(atr14 < atr_ma * 0.8, 1, 0)

    # --- Bollinger Bands (20, 2) ---
    bb_mid = close.rolling(20).mean()
    bb_std = close.rolling(20).std()
    bb_upper = bb_mid + 2 * bb_std
    bb_lower = bb_mid - 2 * bb_std
    df["bb_pct_b"] = (close - bb_lower) / (bb_upper - bb_lower + 1e-12)
    df["bb_width"] = (bb_upper - bb_lower) / (bb_mid + 1e-12)
    df["bb_squeeze"] = np.where(df["bb_width"] < df["bb_width"].rolling(50).quantile(0.2), 1, 0)
    df["bb_upper_touch"] = np.where(close >= bb_upper * 0.999, 1, 0)
    df["bb_lower_touch"] = np.where(close <= bb_lower * 1.001, 1, 0)

    # --- Keltner Channel (20, 1.5x ATR) ---
    kc_mid = close.ewm(span=20, adjust=False).mean()
    kc_upper = kc_mid + 1.5 * atr14
    kc_lower = kc_mid - 1.5 * atr14
    df["kc_pct"] = (close - kc_lower) / (kc_upper - kc_lower + 1e-12)
    # Squeeze: BB inside KC
    df["kc_bb_squeeze"] = np.where((bb_upper < kc_upper) & (bb_lower > kc_lower), 1, 0)

    # --- Volume-like proxy: bar range & body ---
    bar_range = high - low
    bar_body = (close - open_).abs()
    df["range_norm"] = bar_range / (atr14 + 1e-12)
    df["body_ratio"] = bar_body / (bar_range + 1e-12)
    df["close_position"] = (close - low) / (bar_range + 1e-12)
    df["bullish_bar"] = np.where(close > open_, 1, 0)

    # --- Momentum & ROC ---
    df["roc_5"] = close.pct_change(5)
    df["roc_10"] = close.pct_change(10)
    df["roc_20"] = close.pct_change(20)
    df["momentum_10"] = close - close.shift(10)
    df["momentum_20"] = close - close.shift(20)

    # --- Moving Average features ---
    ema8 = close.ewm(span=8, adjust=False).mean()
    ema21 = close.ewm(span=21, adjust=False).mean()
    ema50 = close.ewm(span=50, adjust=False).mean()
    sma20 = close.rolling(20).mean()
    sma50 = close.rolling(50).mean()
    sma100 = close.rolling(100).mean()

    df["ema8_21_gap"] = (ema8 - ema21) / (close + 1e-12)
    df["ema21_50_gap"] = (ema21 - ema50) / (close + 1e-12)
    df["price_vs_ema50"] = (close - ema50) / (close + 1e-12)
    df["price_vs_sma20"] = (close - sma20) / (close + 1e-12)
    df["price_vs_sma100"] = (close - sma100) / (close + 1e-12)
    df["ema8_slope"] = ema8.diff(3) / (close + 1e-12)
    df["ema21_slope"] = ema21.diff(3) / (close + 1e-12)
    df["ema8_above_ema21"] = np.where(ema8 > ema21, 1, 0)
    df["ema21_above_ema50"] = np.where(ema21 > ema50, 1, 0)
    df["triple_ma_align_bull"] = np.where((ema8 > ema21) & (ema21 > ema50), 1, 0)
    df["triple_ma_align_bear"] = np.where((ema8 < ema21) & (ema21 < ema50), 1, 0)

    # --- Stochastic %K %D (14, 3) ---
    lowest_low_14 = low.rolling(14).min()
    highest_high_14 = high.rolling(14).max()
    stoch_k = 100 * (close - lowest_low_14) / (highest_high_14 - lowest_low_14 + 1e-12)
    stoch_d = stoch_k.rolling(3).mean()
    df["stoch_k"] = stoch_k
    df["stoch_d"] = stoch_d
    df["stoch_kd_diff"] = stoch_k - stoch_d
    df["stoch_overbought"] = np.where(stoch_k > 80, 1, 0)
    df["stoch_oversold"] = np.where(stoch_k < 20, 1, 0)
    df["stoch_cross_up"] = np.where((stoch_k > stoch_d) & (stoch_k.shift(1) <= stoch_d.shift(1)), 1, 0)
    df["stoch_cross_dn"] = np.where((stoch_k < stoch_d) & (stoch_k.shift(1) >= stoch_d.shift(1)), 1, 0)

    # --- Williams %R (14) ---
    df["willr_14"] = -100 * (highest_high_14 - close) / (highest_high_14 - lowest_low_14 + 1e-12)

    # --- CCI (20) ---
    tp = (high + low + close) / 3
    tp_ma = tp.rolling(20).mean()
    tp_mad = tp.rolling(20).apply(lambda x: np.mean(np.abs(x - np.mean(x))), raw=True)
    df["cci_20"] = (tp - tp_ma) / (0.015 * tp_mad + 1e-12)
    df["cci_above_zero"] = np.where(df["cci_20"] > 0, 1, 0)
    df["cci_extreme_bull"] = np.where(df["cci_20"] > 100, 1, 0)
    df["cci_extreme_bear"] = np.where(df["cci_20"] < -100, 1, 0)

    # --- Donchian Channel (20) ---
    don_high = high.rolling(20).max()
    don_low = low.rolling(20).min()
    df["donchian_pct"] = (close - don_low) / (don_high - don_low + 1e-12)
    df["donchian_breakout_up"] = np.where(close >= high.rolling(20).max().shift(1), 1, 0)
    df["donchian_breakout_dn"] = np.where(close <= low.rolling(20).min().shift(1), 1, 0)

    # --- Price pattern features ---
    df["higher_high"] = np.where((high > high.shift(1)) & (high.shift(1) > high.shift(2)), 1, 0)
    df["lower_low"] = np.where((low < low.shift(1)) & (low.shift(1) < low.shift(2)), 1, 0)
    df["inside_bar"] = np.where((high < high.shift(1)) & (low > low.shift(1)), 1, 0)
    df["outside_bar"] = np.where((high > high.shift(1)) & (low < low.shift(1)), 1, 0)

    # --- Lag features for key indicators ---
    for lag in [1, 2, 3, 4]:
        df[f"rsi_14_lag{lag}"] = df["rsi_14"].shift(lag)
        df[f"macd_hist_lag{lag}"] = df["macd_hist"].shift(lag)
        df[f"bb_pct_b_lag{lag}"] = df["bb_pct_b"].shift(lag)

    # --- Interaction features (avoiding lookahead) ---
    df["rsi_macd_bull"] = np.where((df["rsi_14"] > 50) & (df["macd_hist"] > 0), 1, 0)
    df["rsi_macd_bear"] = np.where((df["rsi_14"] < 50) & (df["macd_hist"] < 0), 1, 0)
    df["rsi_bb_oversold_bounce"] = np.where((df["rsi_14"] < 35) & (df["bb_pct_b"] < 0.2), 1, 0)
    df["rsi_bb_overbought_fade"] = np.where((df["rsi_14"] > 65) & (df["bb_pct_b"] > 0.8), 1, 0)
    df["triple_bull"] = np.where(
        (df["rsi_14"] > 50) & (df["macd_hist"] > 0) & (df["stoch_k"] > 50), 1, 0
    )
    df["triple_bear"] = np.where(
        (df["rsi_14"] < 50) & (df["macd_hist"] < 0) & (df["stoch_k"] < 50), 1, 0
    )

    # --- Volatility regime ---
    realized_vol = close.pct_change().rolling(20).std() * np.sqrt(96)
    df["realized_vol_20"] = realized_vol
    df["vol_regime_high"] = np.where(realized_vol > realized_vol.rolling(100).median(), 1, 0)

    # --- Session-aware time features ---
    if hasattr(df.index, 'hour'):
        df["hour_sin"] = np.sin(2 * np.pi * df.index.hour / 24)
        df["hour_cos"] = np.cos(2 * np.pi * df.index.hour / 24)
        df["london_session"] = np.where((df.index.hour >= 7) & (df.index.hour < 16), 1, 0)
        df["ny_session"] = np.where((df.index.hour >= 13) & (df.index.hour < 21), 1, 0)
        df["overlap_session"] = np.where((df.index.hour >= 13) & (df.index.hour < 16), 1, 0)
        df["asian_session"] = np.where((df.index.hour >= 0) & (df.index.hour < 7), 1, 0)
        df["day_of_week"] = df.index.dayofweek
        df["dow_sin"] = np.sin(2 * np.pi * df["day_of_week"] / 5)
        df["dow_cos"] = np.cos(2 * np.pi * df["day_of_week"] / 5)

    df = df.bfill().ffill()
    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "GBP/USD RSI-MACD Momentum + Volatility Regime XGBoost",
        "model_type":       "XGBClassifier",
        "model_params":     {
            "n_estimators":     500,
            "max_depth":        4,
            "learning_rate":    0.03,
            "subsample":        0.75,
            "colsample_bytree": 0.65,
            "min_child_weight": 5,
            "gamma":            0.15,
            "reg_alpha":        0.3,
            "reg_lambda":       1.5,
            "scale_pos_weight": 1,
            "objective":        "binary:logistic",
            "tree_method":      "hist",
            "random_state":     42,
        },
        "signal_threshold": 0.56,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [7, 21],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective":        (
            "Maximize risk-adjusted return (Sharpe/Calmar) by combining RSI momentum "
            "divergence, MACD histogram dynamics, Bollinger squeeze, Stochastic crossovers, "
            "volatility regime, and session-aware time features. XGBoost with moderate depth "
            "and strong regularization prevents overfitting on 15-min GBP/USD data. "
            "Signal threshold 0.56 filters weak signals, SL/TP at 0.5%/1.0% gives 1:2 RR."
        ),
        "notes":            (
            "Differentiating from prior attempts (PF=1.08) by: (1) adding Keltner Channel "
            "squeeze interaction with Bollinger, (2) CCI and Williams %R as confirmation, "
            "Donchian breakout detection, (3) session-aware features (London/NY/overlap), "
            "(4) richer MACD/RSI interaction flags, (5) realized volatility regime, "
            "(6) stronger XGBoost regularization (alpha=0.3, lambda=1.5, min_child=5) "
            "to reduce false signals in choppy GBP/USD conditions."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:52:32
# Model            : XGBoost
# Feature Eng.     : BB (20,2.0), RSI 14, Stochastic (14,3) + Auto-add features: ON
# Signal / Entry   : Enter when model confidence > threshold; exit on opposite signal or SL/TP
# Optimization     : Maximize risk-adjusted return
# Risk Mgmt        : Stop loss 0.5%, Take profit 1.0%
# Risk Filter      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# SECTION 0 — IMPORTS & CONSTANTS
import numpy as np
import pandas as pd

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/USDCHF_15min.parquet"
START_DATE = "2025-04-24"
END_DATE   = "2026-04-24"
VALIDATION_DATE = ""
TRAIN_SPLIT = 0.7

# SECTION 1 — FEATURE ENGINEERING
def feature_engineering(df, close, open_, high, low):
    # ── RSI 14 ──────────────────────────────────────────────────────────────
    period_rsi = 14
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = -delta.clip(upper=0)
    avg_gain = gain.ewm(com=period_rsi - 1, min_periods=period_rsi).mean()
    avg_loss = loss.ewm(com=period_rsi - 1, min_periods=period_rsi).mean()
    rs = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # ── Bollinger Bands (20, 2) ──────────────────────────────────────────────
    bb_period = 20
    bb_std = 2.0
    bb_mid = close.rolling(bb_period).mean()
    bb_std_val = close.rolling(bb_period).std(ddof=0)
    bb_upper = bb_mid + bb_std * bb_std_val
    bb_lower = bb_mid - bb_std * bb_std_val
    df["bb_mid"] = bb_mid
    df["bb_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    bb_range = (bb_upper - bb_lower).replace(0, np.nan)
    df["bb_pct"] = (close - bb_lower) / bb_range

    # ── Stochastic Oscillator (K=14, D=3) ───────────────────────────────────
    stoch_k_period = 14
    stoch_d_period = 3
    lowest_low = low.rolling(stoch_k_period).min()
    highest_high = high.rolling(stoch_k_period).max()
    stoch_range = (highest_high - lowest_low).replace(0, np.nan)
    df["stoch_k"] = 100 * (close - lowest_low) / stoch_range
    df["stoch_d"] = df["stoch_k"].rolling(stoch_d_period).mean()
    df["stoch_kd_diff"] = df["stoch_k"] - df["stoch_d"]

    # ── Additional derived features ──────────────────────────────────────────

    # RSI momentum & zone flags
    df["rsi_lag1"] = df["rsi_14"].shift(1)
    df["rsi_momentum"] = df["rsi_14"] - df["rsi_lag1"]
    df["rsi_oversold"] = np.where(df["rsi_14"] < 30, 1, 0)
    df["rsi_overbought"] = np.where(df["rsi_14"] > 70, 1, 0)

    # BB squeeze: width below rolling 20-bar median of bb_width
    bb_width_median = df["bb_width"].rolling(20).median()
    df["bb_squeeze"] = np.where(df["bb_width"] < bb_width_median, 1, 0)

    # BB position zone
    df["bb_below_lower"] = np.where(close < bb_lower, 1, 0)
    df["bb_above_upper"] = np.where(close > bb_upper, 1, 0)

    # Stochastic zone flags
    df["stoch_oversold"] = np.where(df["stoch_k"] < 20, 1, 0)
    df["stoch_overbought"] = np.where(df["stoch_k"] > 80, 1, 0)

    # Price momentum (rate of change)
    df["roc_4"] = close.pct_change(4)
    df["roc_8"] = close.pct_change(8)
    df["roc_16"] = close.pct_change(16)

    # ATR (14-bar) for volatility context
    atr_period = 14
    tr = pd.concat([
        high - low,
        (high - close.shift(1)).abs(),
        (low - close.shift(1)).abs()
    ], axis=1).max(axis=1)
    df["atr_14"] = tr.ewm(com=atr_period - 1, min_periods=atr_period).mean()
    df["natr_14"] = df["atr_14"] / close

    # EMA crossover signals
    ema_fast = close.ewm(span=8, min_periods=8).mean()
    ema_slow = close.ewm(span=21, min_periods=21).mean()
    df["ema_fast"] = ema_fast
    df["ema_slow"] = ema_slow
    df["ema_cross"] = ema_fast - ema_slow
    df["ema_cross_sign"] = np.where(df["ema_cross"] > 0, 1, -1)

    # SMA 50 trend context
    df["sma_50"] = close.rolling(50).mean()
    df["close_vs_sma50"] = (close - df["sma_50"]) / df["sma_50"]

    # Candle body and direction
    df["candle_body"] = (close - open_).abs()
    df["candle_range"] = (high - low).replace(0, np.nan)
    df["body_ratio"] = df["candle_body"] / df["candle_range"]
    df["candle_dir"] = np.where(close >= open_, 1, -1)

    # Volume-proxy: range relative to rolling average range
    df["rel_range"] = (high - low) / (high - low).rolling(20).mean()

    # Lag features for RSI, stoch_k, bb_pct
    for lag in [1, 2, 3]:
        df[f"rsi_14_lag{lag}"] = df["rsi_14"].shift(lag)
        df[f"stoch_k_lag{lag}"] = df["stoch_k"].shift(lag)
        df[f"bb_pct_lag{lag}"] = df["bb_pct"].shift(lag)
        df[f"ema_cross_lag{lag}"] = df["ema_cross"].shift(lag)

    # Divergence proxy: price making new high but RSI not
    price_high_4 = close.rolling(4).max()
    rsi_high_4 = df["rsi_14"].rolling(4).max()
    df["bearish_div_proxy"] = np.where(
        (close >= price_high_4.shift(1)) & (df["rsi_14"] < rsi_high_4.shift(1)), 1, 0
    )
    price_low_4 = close.rolling(4).min()
    rsi_low_4 = df["rsi_14"].rolling(4).min()
    df["bullish_div_proxy"] = np.where(
        (close <= price_low_4.shift(1)) & (df["rsi_14"] > rsi_low_4.shift(1)), 1, 0
    )

    # Combined confluence signals
    df["long_confluence"] = np.where(
        (df["rsi_14"] < 45) & (df["stoch_k"] < 50) & (df["bb_pct"] < 0.5), 1, 0
    )
    df["short_confluence"] = np.where(
        (df["rsi_14"] > 55) & (df["stoch_k"] > 50) & (df["bb_pct"] > 0.5), 1, 0
    )

    # Fill NaN from warm-up
    df = df.bfill().ffill()
    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title": "USD/CHF Stoch+BB+RSI Mean-Reversion (XGBoost)",
        "model_type": "XGBClassifier",
        "model_params": {
            "n_estimators": 400,
            "max_depth": 4,
            "learning_rate": 0.04,
            "subsample": 0.8,
            "colsample_bytree": 0.75,
            "min_child_weight": 5,
            "gamma": 0.1,
            "reg_alpha": 0.05,
            "reg_lambda": 1.5,
            "objective": "binary:logistic",
            "tree_method": "hist",
            "random_state": 42,
            "n_jobs": -1,
        },
        "signal_threshold": 0.55,
        "direction": "both",
        "stop_loss": 0.005,
        "take_profit": 0.01,
        "cooldown": 0,
        "max_positions": 1,
        "on_opposite": "reverse",
        "session_filter": [7, 17],
        "min_atr": None,
        "trend_filter": None,
        "target_horizon": 4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) on USD/CHF 15-min data. "
            "Uses Stochastic (14,3), Bollinger Bands (20,2), and RSI-14 as core features "
            "with confluence signals, divergence proxies, and EMA crossover context. "
            "XGBoost chosen for its strong performance on tabular data with regularization "
            "parameters (gamma, alpha, lambda) tuned to reduce overfitting on short date "
            "ranges. SL=0.5%/TP=1.0% gives 1:2 R:R ratio. Session filter [7,17] UTC targets "
            "London/NY overlap for higher-quality moves. Signal threshold 0.55 filters noise "
            "while preserving trade frequency."
        ),
        "notes": (
            "Feature set combines mean-reversion indicators (RSI, Stochastic, BB percentile) "
            "with trend context (EMA cross, SMA50 distance) and volatility measures (ATR, "
            "BB width/squeeze). Lag features (1-3 bars) capture recent indicator momentum. "
            "Bullish/bearish divergence proxies add signal quality. Shallow trees (max_depth=4) "
            "with high n_estimators and slow learning rate reduce variance. Colsample and "
            "subsample add stochastic regularization."
        ),
    }