import numpy as np
import pandas as pd
from lightgbm import LGBMClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler


SYMBOL = "ETHUSDT"
MODEL_NAME = "ethusdt-adaptive-threshold-classifier-15m"


def _normalise(data):
    df = data.copy()
    df.columns = [str(c).lower() for c in df.columns]
    if "volume" not in df.columns:
        df["volume"] = 1.0
    for col in ["open", "high", "low", "close", "volume"]:
        df[col] = pd.to_numeric(df[col], errors="coerce")
    return df.dropna().reset_index(drop=True)


def _atr(df, n=14):
    h, l, c = df["high"], df["low"], df["close"]
    tr = pd.concat([(h - l), (h - c.shift()).abs(), (l - c.shift()).abs()], axis=1).max(axis=1)
    return tr.ewm(span=n, adjust=False).mean()


def _features(df):
    c = df["close"]
    v = df["volume"]
    h = df["high"]
    l = df["low"]
    ret = c.pct_change()
    f = pd.DataFrame(index=df.index)
    
    # Basic returns
    for n in [1, 2, 4, 8, 16, 32]:
        f[f"ret{n}"] = c.pct_change(n)
    
    # ATR-based features (from original)
    f["atr_pct"] = _atr(df, 14) / c
    f["atr_expansion"] = (_atr(df, 8) / (_atr(df, 50) + 1e-9)).clip(0, 5)
    f["rv_12"] = ret.rolling(12).std()
    f["rv_48"] = ret.rolling(48).std()
    f["vol_regime"] = f["rv_12"] / (f["rv_48"] + 1e-9)
    f["volume_z"] = (v - v.rolling(48).mean()) / (v.rolling(48).std() + 1e-9)
    f["ema_9_34"] = (c.ewm(span=9, adjust=False).mean() - c.ewm(span=34, adjust=False).mean()) / c
    f["ema_21_89"] = (c.ewm(span=21, adjust=False).mean() - c.ewm(span=89, adjust=False).mean()) / c
    
    # Adaptive threshold features
    # Dynamic threshold based on recent volatility
    f["adaptive_threshold"] = f["atr_pct"] * 2.0  # 2x ATR as threshold
    f["volatility_percentile"] = f["atr_pct"].rolling(100).apply(
        lambda x: pd.Series(x).rank(pct=True).iloc[-1] if len(x) > 0 else 0.5, raw=False)
    
    # Momentum features
    f["rsi"] = 100 - (100 / (1 + ret.rolling(14).apply(
        lambda x: x[x > 0].sum() / (-x[x < 0].sum() + 1e-9))))
    
    # Price position in recent range
    f["price_position"] = (c - l.rolling(20).min()) / (h.rolling(20).max() - l.rolling(20).min()).replace(0, np.nan)
    
    # Volume-price correlation
    f["volume_price_corr"] = ret.rolling(20).corr(v.pct_change())
    
    return f.replace([np.inf, -np.inf], np.nan).dropna()


def _labels(close, index, horizon, threshold):
    fwd = close.pct_change(horizon).shift(-horizon)
    y = pd.Series(1, index=close.index)
    y[fwd > threshold] = 2
    y[fwd < -threshold] = 0
    return y.reindex(index).fillna(1).astype(int)


def train(data, config):
    params = config.get("parameters", {})
    horizon = int(params.get("horizon", 3))  # 3 candles = 45 minutes for 15m timeframe
    threshold = float(params.get("threshold", 0.003))  # Base threshold, will be adapted
    df = _normalise(data)
    feat = _features(df)
    y = _labels(df["close"], feat.index, horizon, threshold)
    
    model = Pipeline([
        ("scaler", StandardScaler()),
        ("clf", LGBMClassifier(n_estimators=300, learning_rate=0.05, max_depth=6, random_state=42, verbose=-1))
    ])
    model.fit(feat.values, y.values)
    
    metrics = {
        "training_bars": int(len(feat)),
        "feature_count": int(feat.shape[1]),
        "buy_signals": int((model.predict(feat.values) == 2).sum()),
        "sell_signals": int((model.predict(feat.values) == 0).sum()),
        "hold_signals": int((model.predict(feat.values) == 1).sum()),
    }
    return {"model": model, "features": list(feat.columns), "symbol": SYMBOL}, metrics


def predict(model, market_data, config):
    params = config.get("parameters", {})
    lookback = int(params.get("lookback", 100))
    min_conf = float(params.get("min_confidence", 0.5))
    candles = market_data.get("candles", [])
    
    if len(candles) < lookback:
        return {"signal": "HOLD", "confidence": 0.0, "metadata": {"reason": "not_enough_candles", "model": MODEL_NAME}}
    
    df = _normalise(pd.DataFrame(candles, columns=["open", "high", "low", "close", "volume"]))
    feat = _features(df).tail(1)
    
    if feat.empty:
        return {"signal": "HOLD", "confidence": 0.0, "metadata": {"reason": "no_features", "model": MODEL_NAME}}
    
    prob = model["model"].predict_proba(feat.values)[0]
    klass = int(np.argmax(prob))
    conf = float(np.max(prob))
    signal = {0: "DOWN", 1: "HOLD", 2: "UP"}[klass]
    
    if conf < min_conf:
        signal = "HOLD"
    
    return {"signal": signal, "confidence": round(conf, 4), "metadata": {
        "p_sell": round(float(prob[0]), 4), 
        "p_hold": round(float(prob[1]), 4), 
        "p_buy": round(float(prob[2]), 4), 
        "model": MODEL_NAME, 
        "symbol": SYMBOL
    }}