Community Scripts

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    return df

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

# ╔══════════════════════════════════════════════════════════════╗
# ║                  STRATEGY REQUEST LOG                       ║
# ╚══════════════════════════════════════════════════════════════╝
# Generated        : 2026-05-06 01:50:17
# 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 02:13:41
# 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/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 features (required) ──────────────────────────────────────────
    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 (momentum of the moving average itself) ────────────────
    for p in [20, 50, 200]:
        df[f"sma_{p}_slope"] = df[f"sma_{p}"].diff(5) / df[f"sma_{p}"].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 momentum / rate of change ──────────────────────────────────
    for p in [4, 8, 16, 32]:
        df[f"roc_{p}"] = close.pct_change(p)

    # ── RSI (manual, no external libs) ───────────────────────────────────
    def calc_rsi(series, period=14):
        delta = series.diff()
        gain  = delta.clip(lower=0)
        loss  = (-delta).clip(lower=0)
        avg_gain = gain.ewm(alpha=1.0 / period, min_periods=period, adjust=False).mean()
        avg_loss = loss.ewm(alpha=1.0 / period, min_periods=period, adjust=False).mean()
        rs  = avg_gain / avg_loss.replace(0, np.nan)
        rsi = 100 - (100 / (1 + rs))
        return rsi

    for p in [9, 14, 21]:
        df[f"rsi_{p}"] = calc_rsi(close, p)
        df[f"rsi_{p}_norm"] = (df[f"rsi_{p}"] - 50) / 50   # centre around 0

    # ── MACD (manual) ────────────────────────────────────────────────────
    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_signal"]  = macd_signal
    df["macd_hist"]    = macd_line - macd_signal
    df["macd_hist_chg"] = df["macd_hist"].diff()

    # ── Bollinger Bands ───────────────────────────────────────────────────
    for p in [20, 50]:
        mid  = close.rolling(p).mean()
        std  = close.rolling(p).std()
        df[f"bb_upper_{p}"] = mid + 2 * std
        df[f"bb_lower_{p}"] = mid - 2 * std
        denom = (df[f"bb_upper_{p}"] - df[f"bb_lower_{p}"]).replace(0, np.nan)
        df[f"bb_pct_{p}"]   = (close - df[f"bb_lower_{p}"]) / denom
        df[f"bb_width_{p}"] = denom / mid

    # ── ATR (manual) ─────────────────────────────────────────────────────
    def calc_atr(h, l, c, period=14):
        prev_c = c.shift(1)
        tr = pd.concat([
            h - l,
            (h - prev_c).abs(),
            (l - prev_c).abs()
        ], axis=1).max(axis=1)
        return tr.ewm(alpha=1.0 / period, min_periods=period, adjust=False).mean()

    for p in [7, 14]:
        atr = calc_atr(high, low, close, p)
        df[f"atr_{p}"]  = atr
        df[f"natr_{p}"] = atr / close   # normalised ATR

    # ── 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 - np.maximum(close, open_)) / candle_rng
    df["lower_wick"]   = (np.minimum(close, open_) - low) / candle_rng
    df["candle_dir"]   = np.sign(close - open_)

    # ── Rolling volatility ────────────────────────────────────────────────
    log_ret = np.log(close / close.shift(1))
    for p in [8, 16, 32]:
        df[f"vol_{p}"] = log_ret.rolling(p).std()

    # ── Volume (if available) — graceful fallback ─────────────────────────
    if "volume" in df.columns and df["volume"].sum() > 0:
        vol_ma = df["volume"].rolling(20).mean()
        df["vol_ratio"] = df["volume"] / vol_ma.replace(0, np.nan)
    else:
        df["vol_ratio"] = 1.0

    # ── Lagged returns ────────────────────────────────────────────────────
    for lag in [1, 2, 3, 4, 8]:
        df[f"ret_lag_{lag}"] = log_ret.shift(lag)

    # ── Higher-timeframe SMA context (4-bar = 1h proxy) ──────────────────
    close_1h = close.rolling(4).mean()
    for p in [20, 50]:
        sma_1h = close_1h.rolling(p).mean()
        df[f"1h_dm_sma_{p}"] = (close_1h - sma_1h) / sma_1h

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

    return df

# SECTION 2 — STRATEGY CONFIG
def strategy_config():
    return {
        "title":            "USD/CAD SMA Trend + Momentum XGBoost Scalper",
        "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":        0.1,
            "reg_lambda":       1.5,
            "objective":        "binary:logistic",
            "tree_method":      "hist",
            "random_state":     42,
        },
        "signal_threshold": 0.55,
        "direction":        "both",
        "stop_loss":        0.005,
        "take_profit":      0.010,
        "cooldown":         0,
        "max_positions":    1,
        "on_opposite":      "reverse",
        "session_filter":   [7, 20],
        "min_atr":          0.0002,
        "trend_filter":     "sma_50",
        "target_horizon":   4,
        "objective": (
            "Maximise risk-adjusted return on USD/CAD 15-min bars. "
            "XGBoost with deep feature set (multi-period SMA distances and crossovers, "
            "RSI, MACD, Bollinger Bands, ATR, candle structure, lagged returns). "
            "Regularised tree ensemble (gamma, L1/L2, min_child_weight) prevents "
            "overfitting on the ~1-year window. 2:1 TP:SL ratio locks in positive "
            "expectancy; session filter restricts trading to liquid London/NY overlap."
        ),
        "notes": (
            "SMA-trio (20/50/200) distances are the primary trend-context features. "
            "MACD histogram momentum + RSI multi-period confirm entry timing. "
            "ATR normalisation makes volatility features scale-invariant. "
            "sma_50 trend filter ensures long trades only above 50-SMA and shorts below, "
            "aligning ML signals with dominant trend and improving Sharpe ratio."
        ),
    }

# ╔══════════════════════════════════════════════════════════════╗
# ║                  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."
        ),
    }