Community Scripts

# ╔══════════════════════════════════════════════════════════════╗
# ║                  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 02:56:13
# Model            : XGBoost
# 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/EURUSD_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 core 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 slope (momentum of the moving average itself) ─────────────────
    for period in [20, 50, 200]:
        df[f"sma_{period}_slope"] = df[f"sma_{period}"].diff(5) / df[f"sma_{period}"].shift(5)

    # ── SMA crossover signals ─────────────────────────────────────────────
    df["sma_20_50_cross"]  = df["sma_20"] - df["sma_50"]
    df["sma_50_200_cross"] = df["sma_50"] - df["sma_200"]
    df["sma_20_200_cross"] = df["sma_20"] - df["sma_200"]

    # ── Price vs SMA alignment score (how many SMAs price is above) ───────
    above_20  = np.where(close > df["sma_20"],  1, -1)
    above_50  = np.where(close > df["sma_50"],  1, -1)
    above_200 = np.where(close > df["sma_200"], 1, -1)
    df["sma_alignment"] = (above_20 + above_50 + above_200).astype(float)

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

    # ── Log returns ───────────────────────────────────────────────────────
    df["log_ret_1"] = np.log(close / close.shift(1))
    df["log_ret_4"] = np.log(close / close.shift(4))

    # ── ATR (14-period) ───────────────────────────────────────────────────
    tr1 = high - low
    tr2 = (high - close.shift(1)).abs()
    tr3 = (low  - close.shift(1)).abs()
    true_range = pd.concat([tr1, tr2, tr3], axis=1).max(axis=1)
    atr_14 = true_range.rolling(14).mean()
    df["atr_14"]  = atr_14
    df["natr_14"] = atr_14 / close

    # ── ATR ratio (current TR vs average — volatility burst) ──────────────
    df["atr_ratio"] = true_range / atr_14

    # ── 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
    bb_width = (bb_upper - bb_lower) / bb_mid
    df["bb_pct_b"]  = (close - bb_lower) / (bb_upper - bb_lower + 1e-12)
    df["bb_width"]  = bb_width
    df["bb_zscore"] = (close - bb_mid) / (bb_std + 1e-12)

    # ── RSI (14) ──────────────────────────────────────────────────────────
    delta  = close.diff()
    gain   = delta.clip(lower=0).rolling(14).mean()
    loss   = (-delta.clip(upper=0)).rolling(14).mean()
    rs     = gain / (loss + 1e-12)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # ── RSI momentum ─────────────────────────────────────────────────────
    df["rsi_14_diff"] = df["rsi_14"].diff(2)

    # ── 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()
    df["macd_line"]   = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"]   = macd_line - signal_line
    df["macd_hist_diff"] = df["macd_hist"].diff(1)

    # ── Stochastic %K / %D (14, 3) ───────────────────────────────────────
    low_14  = low.rolling(14).min()
    high_14 = high.rolling(14).max()
    stoch_k = 100 * (close - low_14) / (high_14 - 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

    # ── Williams %R (14) ─────────────────────────────────────────────────
    df["williams_r"] = -100 * (high_14 - close) / (high_14 - low_14 + 1e-12)

    # ── CCI (20) ─────────────────────────────────────────────────────────
    typical_price = (high + low + close) / 3
    tp_sma  = typical_price.rolling(20).mean()
    tp_mad  = typical_price.rolling(20).apply(lambda x: np.mean(np.abs(x - x.mean())), raw=True)
    df["cci_20"] = (typical_price - tp_sma) / (0.015 * tp_mad + 1e-12)

    # ── Rate of Change (10) ───────────────────────────────────────────────
    df["roc_10"] = (close - close.shift(10)) / (close.shift(10) + 1e-12) * 100

    # ── Volume / candle-body features (no volume data assumed) ────────────
    df["body_size"]   = (close - open_).abs() / (high - low + 1e-12)
    df["upper_wick"]  = (high - np.maximum(close, open_)) / (high - low + 1e-12)
    df["lower_wick"]  = (np.minimum(close, open_) - low)  / (high - low + 1e-12)
    df["is_bullish"]  = np.where(close > open_, 1.0, 0.0)

    # ── Rolling volatility (realised) ────────────────────────────────────
    df["vol_8"]  = df["log_ret_1"].rolling(8).std()
    df["vol_20"] = df["log_ret_1"].rolling(20).std()
    df["vol_ratio"] = df["vol_8"] / (df["vol_20"] + 1e-12)

    # ── High-low range relative to SMA ───────────────────────────────────
    df["hl_range_sma20"] = (high - low) / (df["sma_20"] + 1e-12)

    # ── Price position within recent n-bar range ──────────────────────────
    for n in [8, 20]:
        roll_low  = low.rolling(n).min()
        roll_high = high.rolling(n).max()
        df[f"price_pos_{n}"] = (close - roll_low) / (roll_high - roll_low + 1e-12)

    # ── Lagged returns as autoregressive features ─────────────────────────
    for lag in [1, 2, 3, 4, 8]:
        df[f"lag_ret_{lag}"] = df["ret_1"].shift(lag)

    # ── Distance from 20-bar high/low ────────────────────────────────────
    df["dist_high_20"] = (high.rolling(20).max() - close) / (close + 1e-12)
    df["dist_low_20"]  = (close - low.rolling(20).min())  / (close + 1e-12)

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

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "EUR/USD SMA Trend + Multi-Indicator XGBoost",
        "model_type":       "XGBClassifier",
        "model_params":     {
            "n_estimators":     500,
            "max_depth":        4,
            "learning_rate":    0.03,
            "subsample":        0.8,
            "colsample_bytree": 0.7,
            "min_child_weight": 3,
            "gamma":            0.1,
            "reg_alpha":        0.05,
            "reg_lambda":       1.0,
            "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":   [6, 18],
        "min_atr":          None,
        "trend_filter":     "sma_200",
        "target_horizon":   4,
        "objective":        (
            "Maximize risk-adjusted return (Sharpe/Calmar) on EUR/USD 15-min data. "
            "SMA triple-stack (20/50/200) provides trend context; supplementary "
            "momentum (RSI, MACD, Stochastic), volatility (ATR, BB), and "
            "mean-reversion (CCI, Williams %R) features give the XGBoost model a "
            "rich multi-regime signal set. XGBoost chosen for its ability to rank "
            "feature importance and handle non-linear interactions. Shallow trees "
            "(max_depth=4) with high n_estimators and low learning_rate reduce "
            "overfitting. 2:1 reward:risk (SL 0.5% / TP 1.0%) ensures positive "
            "expectancy even at moderate win rates. Session filter 06-18 UTC "
            "concentrates trades in liquid London/NY overlap."
        ),
        "notes":            (
            "trend_filter=sma_200 aligns trades with the dominant trend — longs "
            "only above the 200-SMA, shorts only below — acting as a regime gate "
            "to suppress counter-trend noise. signal_threshold=0.55 slightly above "
            "0.50 to reduce false positives without starving signal count. "
            "colsample_bytree=0.7 introduces randomisation across features to "
            "decorrelate trees and improve generalisation on forex data."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  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        : 2026-05-06 03:01:00
# 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      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# Bollinger Bands Squeeze Breakout — GradientBoosting Strategy
# ============================================================

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

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/EURUSD_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

    # Required derived features
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid
    df["bb_pct"]   = (close - bb_lower) / (bb_upper - bb_lower)

    # ── ATR (14) ─────────────────────────────────────────────────────────────
    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(span=atr_period, min_periods=atr_period, adjust=False).mean()

    df["atr"]  = atr
    df["natr"] = atr / close

    # ── Squeeze Detection ────────────────────────────────────────────────────
    # Squeeze = BB width is near its lowest over recent N bars (compression)
    squeeze_window = 20
    bb_width_min = df["bb_width"].rolling(squeeze_window).min()
    bb_width_max = df["bb_width"].rolling(squeeze_window).max()
    # Normalised squeeze score: 0 = fully squeezed, 1 = fully expanded
    df["squeeze_score"] = (df["bb_width"] - bb_width_min) / (bb_width_max - bb_width_min + 1e-10)

    # Squeeze flag: 1 if currently squeezed (bottom 20th percentile of width)
    df["in_squeeze"] = np.where(df["squeeze_score"] < 0.20, 1, 0)

    # Breakout direction: momentum after squeeze
    df["squeeze_breakout_up"]   = np.where((df["in_squeeze"].shift(1) == 1) & (close > bb_upper), 1, 0)
    df["squeeze_breakout_down"] = np.where((df["in_squeeze"].shift(1) == 1) & (close < bb_lower), 1, 0)

    # ── 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)

    # ── 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)
    df["rsi_14"] = 100 - (100 / (1 + rs))

    # RSI distance from 50 (overbought/oversold)
    df["rsi_dist50"] = df["rsi_14"] - 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_signal = macd_line.ewm(span=9, adjust=False).mean()
    df["macd_line"]   = macd_line
    df["macd_signal"] = macd_signal
    df["macd_hist"]   = macd_line - macd_signal

    # Normalise MACD by ATR to make scale-invariant
    df["macd_hist_norm"] = df["macd_hist"] / (atr + 1e-10)

    # ── Volume / Candle Body Features ────────────────────────────────────────
    body        = (close - open_).abs()
    candle_range = high - low
    df["body_ratio"]   = body / (candle_range + 1e-10)   # 0=doji, 1=full body
    df["close_pos"]    = (close - low) / (candle_range + 1e-10)  # position within bar

    # ── Trend / SMA Features ─────────────────────────────────────────────────
    df["sma_20"]  = bb_mid  # reuse already computed
    df["sma_50"]  = close.rolling(50).mean()
    df["sma_100"] = close.rolling(100).mean()

    df["price_vs_sma20"]  = (close - df["sma_20"])  / (atr + 1e-10)
    df["price_vs_sma50"]  = (close - df["sma_50"])  / (atr + 1e-10)
    df["price_vs_sma100"] = (close - df["sma_100"]) / (atr + 1e-10)

    # SMA cross: 20 vs 50
    df["sma20_vs_sma50"] = (df["sma_20"] - df["sma_50"]) / (atr + 1e-10)

    # ── BB Width Rate-of-Change (squeeze momentum) ───────────────────────────
    df["bb_width_roc3"]  = df["bb_width"].pct_change(3)
    df["bb_width_roc8"]  = df["bb_width"].pct_change(8)

    # ── Lagged BB features ───────────────────────────────────────────────────
    df["bb_pct_lag1"] = df["bb_pct"].shift(1)
    df["bb_pct_lag2"] = df["bb_pct"].shift(2)
    df["bb_pct_lag4"] = df["bb_pct"].shift(4)

    df["bb_width_lag1"] = df["bb_width"].shift(1)
    df["bb_width_lag4"] = df["bb_width"].shift(4)

    # ── Volatility Regime ────────────────────────────────────────────────────
    natr_ma = df["natr"].rolling(40).mean()
    df["vol_regime"] = np.where(df["natr"] > natr_ma, 1, 0)   # 1=high vol, 0=low vol

    # ── Price Distance from Bands (ATR-normalised) ───────────────────────────
    df["dist_upper"] = (bb_upper - close) / (atr + 1e-10)
    df["dist_lower"] = (close - bb_lower) / (atr + 1e-10)

    # ── Hour / Session (cyclical) ────────────────────────────────────────────
    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)

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

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "BB Squeeze Breakout + ATR Filter (GBM)",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":      400,
            "max_depth":         4,
            "learning_rate":     0.04,
            "subsample":         0.75,
            "max_features":      "sqrt",
            "min_samples_leaf":  20,
            "min_samples_split": 40,
            "n_iter_no_change":  30,
            "validation_fraction": 0.12,
            "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). "
            "GradientBoosting chosen for its strong performance on tabular data with "
            "structured non-linear interactions. Shallow trees (depth=4) with high "
            "n_estimators and low learning_rate reduce overfitting. subsample=0.75 "
            "adds stochasticity. Early stopping via n_iter_no_change avoids "
            "over-training on the 15-min EURUSD regime. SL=0.5%/TP=1.0% gives 2:1 "
            "reward-risk, consistent with a squeeze-breakout edge. session_filter "
            "[6,20] UTC captures London+NY sessions where BB squeezes resolve cleanly. "
            "min_atr guards against ultra-low-volatility false breakouts."
        ),
        "notes": (
            "Features centre on BB squeeze mechanics: bb_width, squeeze_score, "
            "in_squeeze flag, breakout_up/down, width RoC, and lagged bb_pct. "
            "Complemented by RSI, MACD histogram (ATR-normalised), SMA trend "
            "distances, candle body ratio, and cyclical hour encoding. "
            "target_horizon=4 bars (1 hour) aligns with the typical squeeze "
            "resolution time on 15-min EURUSD. Signal threshold 0.55 filters "
            "marginal signals while preserving sufficient trade frequency."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 03:05:53
# 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/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):
    # ── 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))

    # ── MACD (12, 26, 9) ────────────────────────────────────────────────────
    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()
    macd_hist = macd_line - signal_line
    df["macd_line"] = macd_line
    df["macd_signal"] = signal_line
    df["macd_hist"] = macd_hist

    # ── RSI derived features ─────────────────────────────────────────────────
    df["rsi_14_lag1"] = df["rsi_14"].shift(1)
    df["rsi_14_lag2"] = df["rsi_14"].shift(2)
    df["rsi_14_delta"] = df["rsi_14"] - df["rsi_14_lag1"]
    df["rsi_ob"] = np.where(df["rsi_14"] > 70, 1, 0)
    df["rsi_os"] = np.where(df["rsi_14"] < 30, 1, 0)

    # ── MACD derived features ────────────────────────────────────────────────
    df["macd_hist_lag1"] = macd_hist.shift(1)
    df["macd_hist_delta"] = macd_hist - macd_hist.shift(1)
    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_above_zero"] = np.where(macd_line > 0, 1, 0)
    df["macd_hist_positive"] = np.where(macd_hist > 0, 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(span=14, adjust=False).mean()
    df["atr_14"] = atr_14
    df["natr_14"] = atr_14 / close

    # ── 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).replace(0, np.nan)
    df["bb_width"] = (bb_upper - bb_lower) / bb_mid.replace(0, np.nan)
    df["bb_squeeze"] = np.where(df["bb_width"] < df["bb_width"].rolling(50).mean(), 1, 0)

    # ── Price momentum features ───────────────────────────────────────────────
    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)

    # ── Rolling volatility ────────────────────────────────────────────────────
    df["vol_8"] = df["ret_1"].rolling(8).std()
    df["vol_20"] = df["ret_1"].rolling(20).std()

    # ── EMA trend features ───────────────────────────────────────────────────
    ema_20 = close.ewm(span=20, adjust=False).mean()
    ema_50 = close.ewm(span=50, adjust=False).mean()
    df["ema_20"] = ema_20
    df["ema_50"] = ema_50
    df["price_vs_ema20"] = (close - ema_20) / ema_20
    df["price_vs_ema50"] = (close - ema_50) / ema_50
    df["ema20_vs_ema50"] = (ema_20 - ema_50) / ema_50

    # ── 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"] = (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["bull_candle"] = np.where(close > open_, 1, 0)

    # ── Rolling high/low position ─────────────────────────────────────────────
    roll_high_20 = high.rolling(20).max()
    roll_low_20 = low.rolling(20).min()
    roll_range_20 = (roll_high_20 - roll_low_20).replace(0, np.nan)
    df["price_position_20"] = (close - roll_low_20) / roll_range_20

    # ── RSI + MACD interaction ────────────────────────────────────────────────
    df["rsi_macd_product"] = df["rsi_14"] * macd_hist
    df["rsi_norm"] = (df["rsi_14"] - 50) / 50

    # ── Session / time features ───────────────────────────────────────────────
    if hasattr(close.index, "hour"):
        df["hour"] = close.index.hour
        df["session_london"] = np.where((close.index.hour >= 7) & (close.index.hour < 16), 1, 0)
        df["session_ny"] = np.where((close.index.hour >= 13) & (close.index.hour < 21), 1, 0)
        df["session_asia"] = np.where((close.index.hour >= 22) | (close.index.hour < 7), 1, 0)
    else:
        df["hour"] = 0
        df["session_london"] = 0
        df["session_ny"] = 0
        df["session_asia"] = 0

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

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title": "AUD/USD RSI+MACD Gradient Boosting Scalper",
        "model_type": "GradientBoostingClassifier",
        "model_params": {
            "n_estimators": 400,
            "max_depth": 4,
            "learning_rate": 0.05,
            "subsample": 0.8,
            "min_samples_leaf": 20,
            "max_features": "sqrt",
            "validation_fraction": 0.1,
            "n_iter_no_change": 30,
            "tol": 1e-4,
        },
        "signal_threshold": 0.55,
        "direction": "both",
        "stop_loss": 0.005,
        "take_profit": 0.01,
        "cooldown": 0,
        "max_positions": 1,
        "on_opposite": "reverse",
        "session_filter": None,
        "min_atr": None,
        "trend_filter": None,
        "target_horizon": 4,
        "objective": (
            "Maximize risk-adjusted return on AUD/USD 15-min data using GradientBoostingClassifier. "
            "RSI-14 captures momentum extremes and divergence conditions; MACD (12,26,9) provides "
            "trend direction and momentum shifts via crossovers and histogram slope. Additional "
            "features (BB, ATR, EMA trend, candle structure, session timing) enrich the feature "
            "space. GradientBoosting with shallow trees (depth=4), moderate learning rate (0.05), "
            "and early stopping via n_iter_no_change prevents overfitting. SL=0.5%, TP=1.0% gives "
            "a 1:2 risk/reward ratio, improving Sharpe and Calmar. Threshold=0.55 filters low-confidence "
            "signals to reduce noise. Reverse on opposite signal maximizes capital efficiency."
        ),
        "notes": (
            "n_estimators=400 with early stopping balances bias-variance. max_depth=4 keeps trees "
            "shallow to reduce overfitting on FX microstructure noise. subsample=0.8 adds stochastic "
            "gradient boosting regularization. min_samples_leaf=20 prevents fitting to outlier bars. "
            "max_features='sqrt' adds feature randomization similar to random forests. "
            "target_horizon=4 (1 hour) aligns with typical AUD/USD intraday swing durations."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:21:53
# 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/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):
    # --- 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 and spread
    df["ema_cross"] = ema_9 - ema_21
    df["ema_cross_prev"] = df["ema_cross"].shift(1)
    df["ema_cross_sign"] = np.sign(df["ema_cross"])
    df["ema_cross_change"] = df["ema_cross_sign"] - np.sign(df["ema_cross_prev"])

    # --- RSI 14 (required) ---
    delta = close.diff()
    gain = delta.clip(lower=0)
    loss = -delta.clip(upper=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)
    rsi_14 = 100 - (100 / (1 + rs))
    df["rsi_14"] = rsi_14

    # RSI derived features
    df["rsi_14_norm"] = (rsi_14 - 50) / 50
    df["rsi_overbought"] = np.where(rsi_14 > 70, 1, 0)
    df["rsi_oversold"] = np.where(rsi_14 < 30, 1, 0)
    df["rsi_mid_cross"] = np.where(rsi_14 > 50, 1, -1)

    # --- Additional EMAs for context ---
    ema_50 = close.ewm(span=50, adjust=False).mean()
    ema_200 = close.ewm(span=200, adjust=False).mean()
    df["ema_50"] = ema_50
    df["ema_200"] = ema_200
    df["dm_ema_50"] = (close - ema_50) / ema_50
    df["dm_ema_200"] = (close - ema_200) / ema_200
    df["ema_50_200_spread"] = (ema_50 - ema_200) / ema_200

    # --- ATR (14 periods) ---
    tr1 = high - low
    tr2 = (high - close.shift(1)).abs()
    tr3 = (low - close.shift(1)).abs()
    true_range = pd.concat([tr1, tr2, tr3], axis=1).max(axis=1)
    atr_14 = true_range.ewm(com=13, adjust=False).mean()
    df["atr_14"] = atr_14
    df["natr_14"] = 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_upper"] = bb_upper
    df["bb_lower"] = bb_lower
    df["bb_pct_b"] = (close - bb_lower) / (bb_upper - bb_lower).replace(0, np.nan)
    df["bb_width"] = (bb_upper - bb_lower) / sma_20

    # --- 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
    macd_signal = macd_line.ewm(span=9, adjust=False).mean()
    macd_hist = macd_line - macd_signal
    df["macd_line"] = macd_line
    df["macd_signal_line"] = macd_signal
    df["macd_hist"] = macd_hist
    df["macd_hist_sign"] = np.sign(macd_hist)
    df["macd_hist_change"] = np.sign(macd_hist) - np.sign(macd_hist.shift(1))

    # --- Momentum & Rate of Change ---
    df["mom_5"] = close.pct_change(5)
    df["mom_10"] = close.pct_change(10)
    df["mom_20"] = close.pct_change(20)
    df["roc_3"] = close.pct_change(3)

    # --- Candlestick features ---
    df["body"] = (close - open_) / atr_14
    df["upper_wick"] = (high - pd.concat([close, open_], axis=1).max(axis=1)) / atr_14
    df["lower_wick"] = (pd.concat([close, open_], axis=1).min(axis=1) - low) / atr_14
    df["bar_range"] = (high - low) / atr_14

    # --- Volume-proxy: price range relative momentum ---
    df["high_low_ratio"] = (high - low) / close

    # --- Stochastic Oscillator (14, 3) ---
    lowest_low = low.rolling(14).min()
    highest_high = high.rolling(14).max()
    stoch_k = 100 * (close - lowest_low) / (highest_high - lowest_low).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

    # --- Rolling volatility ---
    df["vol_10"] = close.pct_change().rolling(10).std()
    df["vol_20"] = close.pct_change().rolling(20).std()
    df["vol_ratio"] = df["vol_10"] / df["vol_20"].replace(0, np.nan)

    # --- Lagged RSI and EMA cross (for sequential signal detection) ---
    df["rsi_14_lag1"] = rsi_14.shift(1)
    df["rsi_14_lag2"] = rsi_14.shift(2)
    df["ema_cross_lag1"] = df["ema_cross"].shift(1)
    df["ema_cross_lag2"] = df["ema_cross"].shift(2)

    # --- Trend alignment: both EMAs agree ---
    df["trend_aligned_bull"] = np.where((ema_9 > ema_21) & (ema_21 > ema_50), 1, 0)
    df["trend_aligned_bear"] = np.where((ema_9 < ema_21) & (ema_21 < ema_50), 1, 0)

    # --- RSI momentum divergence proxy ---
    price_chg_5 = close.pct_change(5)
    rsi_chg_5 = rsi_14.diff(5)
    df["rsi_price_div"] = np.where(
        (price_chg_5 > 0) & (rsi_chg_5 < 0), -1,
        np.where((price_chg_5 < 0) & (rsi_chg_5 > 0), 1, 0)
    )

    # --- SMA 50 distance (for trend_filter compatibility) ---
    df["sma_50"] = close.rolling(50).mean()

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


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title": "AUD/USD EMA Cross RSI Gradient Boost Scalper",
        "model_type": "GradientBoostingClassifier",
        "model_params": {
            "n_estimators": 400,
            "max_depth": 4,
            "learning_rate": 0.04,
            "subsample": 0.8,
            "max_features": "sqrt",
            "min_samples_leaf": 20,
            "min_samples_split": 40,
            "validation_fraction": 0.1,
            "n_iter_no_change": 30,
            "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": (
            "Maximize risk-adjusted return (Sharpe) on AUD/USD 15-min bars. "
            "GradientBoostingClassifier with shrinkage (lr=0.04), moderate depth (4), "
            "subsampling (0.8) and sqrt feature fraction controls overfitting on a noisy FX "
            "series. Early stopping (n_iter_no_change=30) prevents over-training. "
            "SL=0.5%/TP=1.0% gives 1:2 RR. Threshold=0.55 filters low-confidence signals. "
            "EMA 9/21 crossover with RSI 14 confirmation is the primary signal logic, "
            "reinforced by MACD, Bollinger Bands, Stochastic, and multi-period momentum."
        ),
        "notes": (
            "Features: EMA 9, 21, 50, 200 distances; RSI 14 with overbought/oversold flags; "
            "MACD histogram; Bollinger %B and width; Stochastic K/D; ATR-normalized candle "
            "body/wicks; 5/10/20-bar momentum; rolling volatility ratio; trend alignment flags; "
            "RSI-price divergence proxy. Target horizon 4 bars (1 hour ahead). "
            "All features are lagged or rolling — no lookahead bias."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:04:57
# 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      : —
# ══════════════════════════════════════════════════════════════

# ============================================================
# EUR/USD Multi-Indicator Momentum + Mean-Reversion (XGBoost)
# ============================================================

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

DATA_PATH = "/root/Desktop/QuantifyMe/data/ohlc/EURUSD_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 features ─────────────────────────────────────────────
    for lag in [1, 2, 4, 8]:
        df[f"ret_{lag}"] = close.pct_change(lag)

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

    # ── Volume-proxy: normalised range ─────────────────────────────────────
    df["norm_range"] = (high - low) / close.rolling(20).mean()

    # ── RSI derived ─────────────────────────────────────────────────────────
    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_cross"] = np.where(df["rsi_14"] > 50, 1.0, -1.0)

    # ── Trend alignment flags ───────────────────────────────────────────────
    df["above_sma_20"]  = np.where(close > df["sma_20"],  1.0, -1.0)
    df["above_sma_50"]  = np.where(close > df["sma_50"],  1.0, -1.0)
    df["above_sma_200"] = np.where(close > df["sma_200"], 1.0, -1.0)
    df["sma_20_50_cross"] = np.where(df["sma_20"] > df["sma_50"], 1.0, -1.0)

    # ── MACD cross flag ─────────────────────────────────────────────────────
    df["macd_cross"] = np.where(df["macd_line"] > df["macd_signal"], 1.0, -1.0)

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

    # ── Lagged RSI and MACD hist for regime detection ───────────────────────
    df["rsi_14_lag1"]   = df["rsi_14"].shift(1)
    df["macd_hist_lag1"] = df["macd_hist"].shift(1)
    df["rsi_slope"]     = df["rsi_14"] - df["rsi_14_lag1"]
    df["macd_hist_slope"] = df["macd_hist"] - df["macd_hist_lag1"]

    # ── Rolling volatility ratio ─────────────────────────────────────────────
    vol_short = close.pct_change().rolling(8).std()
    vol_long  = close.pct_change().rolling(32).std()
    df["vol_ratio"] = np.where(vol_long != 0, vol_short / vol_long, 1.0)

    # ── Hour-of-day (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 any NaN from warm-up ───────────────────────────────────────────
    df = df.bfill().ffill()

    return df


# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "EUR/USD SMA+RSI+MACD+BB Momentum XGBoost",
        "model_type":       "XGBClassifier",
        "model_params":     {
            "n_estimators":     600,
            "max_depth":        4,
            "learning_rate":    0.04,
            "subsample":        0.8,
            "colsample_bytree": 0.75,
            "min_child_weight": 3,
            "gamma":            0.1,
            "reg_alpha":        0.05,
            "reg_lambda":       1.5,
            "objective":        "binary:logistic",
            "random_state":     42,
            "n_jobs":           -1,
        },
        "signal_threshold": 0.54,
        "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":     "sma_50",
        "target_horizon":   4,
        "objective":        (
            "Maximize risk-adjusted return (Sharpe/Calmar) on EUR/USD 15-min. "
            "XGBoost with moderate depth and strong regularisation to avoid "
            "overfitting on noisy FX data. 2:1 TP:SL ratio with trend filter "
            "on SMA-50 to avoid counter-trend noise. Session filter 06-20 UTC "
            "covers London + NY overlap for best liquidity."
        ),
        "notes": (
            "Features: SMA cross distances, RSI overbought/oversold flags, "
            "MACD histogram slope, Bollinger squeeze, ATR normalisation, "
            "candle body/wick ratios, momentum returns at 1/2/4/8 bars, "
            "session encoding via hour sin/cos. "
            "Threshold 0.54 keeps precision high while capturing enough trades. "
            "Reverse on opposite signal maximises capital utilisation."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 02:24:20
# 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/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_   = close.rolling(bb_period).std(ddof=1)
    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"]  = 100.0 - (100.0 / (1.0 + rs))

    # ── Stochastic Oscillator (K=14, D=3) ────────────────────────────────────
    stoch_k = 14
    stoch_d = 3
    low_min  = low.rolling(stoch_k).min()
    high_max = high.rolling(stoch_k).max()
    k_raw    = 100.0 * (close - low_min) / (high_max - low_min).replace(0, np.nan)
    df["stoch_k"] = k_raw
    df["stoch_d"] = k_raw.rolling(stoch_d).mean()

    # ── ATR (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)
    df["atr"]  = tr.ewm(com=atr_period - 1, min_periods=atr_period).mean()
    df["natr"] = df["atr"] / close

    # ── Trend / Momentum features ─────────────────────────────────────────────
    df["sma_20"]  = close.rolling(20).mean()
    df["sma_50"]  = close.rolling(50).mean()
    df["sma_100"] = close.rolling(100).mean()

    df["price_vs_sma20"]  = (close - df["sma_20"])  / df["sma_20"]
    df["price_vs_sma50"]  = (close - df["sma_50"])  / df["sma_50"]
    df["price_vs_sma100"] = (close - df["sma_100"]) / df["sma_100"]
    df["sma20_vs_sma50"]  = (df["sma_20"] - df["sma_50"]) / df["sma_50"]

    # ── MACD (12, 26, 9) ─────────────────────────────────────────────────────
    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

    # ── Rate-of-Change features ───────────────────────────────────────────────
    for p in [4, 8, 16]:
        df[f"roc_{p}"] = close.pct_change(p)

    # ── Volatility regime ────────────────────────────────────────────────────
    df["vol_8"]  = close.pct_change().rolling(8).std()
    df["vol_20"] = close.pct_change().rolling(20).std()
    df["vol_ratio"] = df["vol_8"] / df["vol_20"].replace(0, np.nan)

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

    # ── RSI-derived features ──────────────────────────────────────────────────
    df["rsi_above_50"] = np.where(df["rsi"] > 50, 1, 0)
    df["rsi_overbought"] = np.where(df["rsi"] > 70, 1, 0)
    df["rsi_oversold"]   = np.where(df["rsi"] < 30, 1, 0)
    df["rsi_lag1"] = df["rsi"].shift(1)
    df["rsi_lag4"] = df["rsi"].shift(4)

    # ── Stochastic-derived features ───────────────────────────────────────────
    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)
    df["stoch_oversold"]   = np.where(df["stoch_k"] < 20, 1, 0)
    df["stoch_overbought"] = np.where(df["stoch_k"] > 80, 1, 0)

    # ── BB-derived features ───────────────────────────────────────────────────
    df["bb_squeeze"] = np.where(df["bb_width"] < df["bb_width"].rolling(50).quantile(0.20), 1, 0)
    df["above_bb_upper"] = np.where(close > bb_upper, 1, 0)
    df["below_bb_lower"] = np.where(close < bb_lower, 1, 0)
    df["bb_pct_lag1"]    = df["bb_pct"].shift(1)
    df["bb_pct_lag4"]    = df["bb_pct"].shift(4)

    # ── Session hour (UTC) ────────────────────────────────────────────────────
    df["hour_utc"] = df.index.hour if hasattr(df.index, "hour") else 0

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

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "AUD/USD Stochastic BB Mean-Reversion (GBM)",
        "model_type":       "GradientBoostingClassifier",
        "model_params":     {
            "n_estimators":      400,
            "max_depth":         4,
            "learning_rate":     0.04,
            "subsample":         0.80,
            "min_samples_leaf":  20,
            "max_features":      "sqrt",
            "n_iter_no_change":  30,
            "validation_fraction": 0.10,
            "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":   None,
        "min_atr":          None,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) on AUD/USD 15-min. "
            "GradientBoostingClassifier with moderate depth and learning rate chosen "
            "to balance bias-variance. 2:1 reward-to-risk (SL=0.5%, TP=1.0%). "
            "Stochastic crossovers, BB mean-reversion, and RSI regime signals "
            "form the core feature set; MACD, volatility, and candle features add "
            "context. Early stopping (n_iter_no_change=30) prevents overfitting."
        ),
        "notes": (
            "Features: Bollinger Bands (20,2) width/pct, RSI(14) with lag/regime flags, "
            "Stochastic(14,3) K/D with crossover detection, ATR/NATR volatility, MACD "
            "histogram, short/medium SMAs, ROC(4/8/16), volatility ratio, candle body "
            "ratios, and UTC session hour. No session or trend filter to allow full "
            "mean-reversion opportunities across all sessions."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:50:17
# 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/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)

    # ── ATR (14) & Normalised ATR ────────────────────────────────────────────
    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, adjust=False).mean()
    natr = atr / close

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

    # ── 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, adjust=False).mean()
    avg_loss   = loss.ewm(span=rsi_period, adjust=False).mean()
    rs         = avg_gain / avg_loss.replace(0, np.nan)
    df["rsi"]  = 100 - (100 / (1 + rs))

    # ── 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()
    df["macd"]     = macd_line
    df["macd_sig"] = macd_signal
    df["macd_hist"]= macd_line - macd_signal

    # ── SMA filters (50, 200) ────────────────────────────────────────────────
    df["sma_20"]  = close.rolling(20).mean()
    df["sma_50"]  = close.rolling(50).mean()
    df["sma_200"] = close.rolling(200).mean()

    # Price relative to moving averages
    df["close_vs_sma20"]  = (close - df["sma_20"])  / df["sma_20"]
    df["close_vs_sma50"]  = (close - df["sma_50"])  / df["sma_50"]
    df["close_vs_sma200"] = (close - df["sma_200"]) / df["sma_200"]

    # ── 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)
    df["ret_32"] = close.pct_change(32)

    # ── 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"]  = (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["close_dir"]   = np.sign(close - open_)

    # ── Volatility regime ────────────────────────────────────────────────────
    df["vol_ratio"]  = natr / natr.rolling(50).mean()         # ATR vs its own average
    df["bb_squeeze"] = np.where(df["bb_width"] < df["bb_width"].rolling(50).quantile(0.25), 1.0, 0.0)

    # ── 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

    # ── Rate-of-change ───────────────────────────────────────────────────────
    df["roc_10"] = (close - close.shift(10)) / close.shift(10)

    # ── Rolling z-score of close (20-bar) ────────────────────────────────────
    roll_mean = close.rolling(20).mean()
    roll_std  = close.rolling(20).std(ddof=0).replace(0, np.nan)
    df["zscore_20"] = (close - roll_mean) / roll_std

    # ── Volume-related (if volume column exists) ─────────────────────────────
    if "volume" in df.columns and df["volume"].sum() > 0:
        vol_ma          = df["volume"].rolling(20).mean().replace(0, np.nan)
        df["vol_ratio_20"] = df["volume"] / vol_ma

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

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title": "USD/CAD BB + ATR Gradient Boosting Mean-Rev",
        "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":   [7, 20],
        "min_atr":          0.0002,
        "trend_filter":     None,
        "target_horizon":   4,
        "objective": (
            "Maximize risk-adjusted return (Sharpe/Calmar) on USD/CAD 15-min data. "
            "GradientBoostingClassifier chosen for strong generalisation on noisy FX "
            "price data; moderate depth (4) and learning rate (0.04) with early stopping "
            "prevent overfitting. Features: Bollinger Bands (mean-reversion signal via "
            "bb_pct and bb_width), ATR/NATR (volatility filter), RSI, MACD, Stochastic, "
            "z-score, momentum returns, and candle-body ratios. 2:1 R:R (SL 0.5%, TP 1.0%) "
            "with session filter (07-20 UTC) to avoid illiquid overnight hours."
        ),
        "notes": (
            "session_filter [7,20] captures London + NY overlap on USD/CAD. "
            "min_atr 0.0002 avoids flat/choppy markets. on_opposite=reverse ensures "
            "the model flips direction quickly when sentiment changes. "
            "target_horizon=4 bars (1 hour) aligns with typical intraday FX moves."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  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 01:37:19
# 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 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 01:51:31
# 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."
        ),
    }