PythagorasGoal/Old/scripts/waste/W05_enhanced_fractal.py

"""Strategia 5: Enhanced fractal features + binary classification + position management.
Miglioramenti rispetto a #4:
- Binary classification (up vs down, ignora flat)
- Feature engineering esteso: multi-window fractal indicators
- Migliore filtraggio segnali
- Position sizing basato su confidenza
- Trailing stop
"""
from __future__ import annotations
import sys
sys.path.insert(0, ".")

import numpy as np
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import accuracy_score
from src.data.downloader import load_data
from src.fractal.indicators import (
    hurst_exponent,
    fractal_dimension_higuchi,
    self_similarity_score,
    volatility_ratio,
)
from src.fractal.patterns import encode_candles, extract_body_ratios, extract_shadow_ratios

print("=" * 60)
print("  STRATEGIA 5: ENHANCED FRACTAL — BTC + ETH 1H")
print("=" * 60)

LOOKAHEADS = [3, 6, 12]
MIN_RETURN = 0.003  # 0.3% threshold for "up" label

for asset in ["BTC", "ETH"]:
    for LOOKAHEAD in LOOKAHEADS:
        print(f"\n{'#'*60}")
        print(f"  {asset} 1H — LOOKAHEAD={LOOKAHEAD}")
        print(f"{'#'*60}")

        df = load_data(asset, "1h")
        close = df["close"].values
        volume = df["volume"].values
        n = len(close)
        log_close = np.log(np.where(close == 0, 1e-10, close))
        returns = np.diff(log_close)

        candle_types = encode_candles(df)
        body_ratios = extract_body_ratios(df)
        shadow_ratios = extract_shadow_ratios(df)

        WINDOWS = [24, 48, 96, 192]
        features_list = []
        labels = []
        indices = []

        max_window = max(WINDOWS) + 50

        for i in range(max_window, n - LOOKAHEAD, 2):
            feats = []

            for w in WINDOWS:
                ret_w = returns[i - w : i - 1]
                close_w = close[i - w : i]

                h = hurst_exponent(ret_w, max_lag=min(len(ret_w) // 4, 20))
                fd = fractal_dimension_higuchi(ret_w, k_max=min(6, len(ret_w) // 4))
                vr = volatility_ratio(close_w, fast=min(12, w // 4), slow=w)

                mom = np.sum(ret_w)
                vol = np.std(ret_w)
                skew = float(pd.Series(ret_w).skew()) if len(ret_w) > 2 else 0
                kurt = float(pd.Series(ret_w).kurtosis()) if len(ret_w) > 3 else 0

                ma = np.mean(close_w)
                price_vs_ma = close[i - 1] / ma if ma > 0 else 1

                # Autocorrelation lag-1
                if len(ret_w) > 1 and np.std(ret_w) > 0:
                    ac1 = np.corrcoef(ret_w[:-1], ret_w[1:])[0, 1]
                    if not np.isfinite(ac1):
                        ac1 = 0
                else:
                    ac1 = 0

                feats.extend([h, fd, vr, mom, vol, skew, kurt, price_vs_ma, ac1])

            # Self-similarity multi-scale
            large_window = close[max(0, i - 192 * 4) : i]
            ss = self_similarity_score(large_window, 48)
            feats.append(ss)

            # Candle pattern features (last 12 candles)
            ct = candle_types[i - 12 : i]
            br = body_ratios[i - 12 : i]
            sr = shadow_ratios[i - 12 : i]

            feats.extend([
                np.mean(ct[-3:]),
                np.mean(ct[-6:]),
                np.mean(ct[-12:]),
                np.std(br[-6:]),
                np.mean(br[-3:]),
                np.mean(sr[-6:]),
                np.max(br[-6:]),
                np.min(br[-6:]),
            ])

            # Volume features
            vol_w = volume[i - 24 : i]
            if np.mean(vol_w) > 0:
                feats.append(volume[i - 1] / np.mean(vol_w))
                feats.append(np.std(vol_w) / np.mean(vol_w))
            else:
                feats.extend([1.0, 0.0])

            # Range/ATR proxy
            h_arr = df["high"].values[i - 14 : i]
            l_arr = df["low"].values[i - 14 : i]
            c_arr = close[i - 14 : i]
            tr = np.maximum(h_arr - l_arr, np.maximum(np.abs(h_arr - np.roll(c_arr, 1)), np.abs(l_arr - np.roll(c_arr, 1))))
            atr = np.mean(tr[1:])
            feats.append(atr / close[i - 1] if close[i - 1] > 0 else 0)

            # Label
            future_ret = (close[i + LOOKAHEAD - 1] - close[i - 1]) / close[i - 1]
            if abs(future_ret) < MIN_RETURN:
                continue  # skip flat zones

            label = 1 if future_ret > 0 else 0

            features_list.append(feats)
            labels.append(label)
            indices.append(i)

        X = np.array(features_list)
        y = np.array(labels)
        idx_arr = np.array(indices)

        X = np.nan_to_num(X, nan=0.0, posinf=1e6, neginf=-1e6)

        # Split
        split = int(len(X) * 0.7)
        X_train, X_test = X[:split], X[split:]
        y_train, y_test = y[:split], y[split:]
        idx_test = idx_arr[split:]

        print(f"Samples: {len(X)} (train={split}, test={len(X)-split})")
        print(f"Label balance: up={np.mean(y)*100:.1f}%")

        # Train
        model = GradientBoostingClassifier(
            n_estimators=300, max_depth=5, min_samples_leaf=30,
            learning_rate=0.03, subsample=0.8, random_state=42,
        )
        model.fit(X_train, y_train)

        y_pred = model.predict(X_test)
        proba = model.predict_proba(X_test)

        base_acc = accuracy_score(y_test, y_pred)
        print(f"Base accuracy: {base_acc*100:.1f}%")

        # Threshold sweep
        print(f"\n  Threshold sweep:")
        for thr in [0.50, 0.55, 0.60, 0.65, 0.70, 0.75, 0.80]:
            up_idx = model.classes_.tolist().index(1)

            sigs = []
            accs = []
            for k in range(len(X_test)):
                p_up = proba[k][up_idx]
                i = idx_test[k]
                actual = (close[i + LOOKAHEAD - 1] - close[i - 1]) / close[i - 1]

                if p_up >= thr:
                    sigs.append(("long", i))
                    accs.append(1 if actual > 0 else 0)
                elif p_up <= (1 - thr):
                    sigs.append(("short", i))
                    accs.append(1 if actual < 0 else 0)

            if not accs:
                print(f"    thr={thr:.2f}: no signals")
                continue

            acc = np.mean(accs) * 100
            # Simple PnL estimate
            pnl = 0
            capital = 1000
            for direction, i in sigs:
                entry = close[i - 1]
                exit_ = close[i + LOOKAHEAD - 1]
                if direction == "long":
                    ret = (exit_ - entry) / entry
                else:
                    ret = (entry - exit_) / entry
                ret -= 0.002  # fees round-trip
                pnl += capital * ret * 0.5  # 50% per trade
                capital += capital * ret * 0.5

            total_ret = (capital - 1000) / 1000 * 100
            trades_per_year = len(sigs) / ((n - max_window) / (24 * 365))
            print(f"    thr={thr:.2f}: signals={len(sigs):5d} acc={acc:.1f}% ret={total_ret:+.1f}% trades/yr={trades_per_year:.0f}")