PythagorasGoal/scripts/waste/W01_baseline.py

"""Analisi baseline: distribuzione pattern frattali e prima strategia naive."""
from __future__ import annotations

import sys
sys.path.insert(0, ".")

import numpy as np
import pandas as pd
from src.data.downloader import load_data
from src.fractal.patterns import encode_candles, find_patterns, pattern_frequency
from src.backtest.engine import run_backtest, BacktestResult

print("=" * 60)
print("  ANALISI BASELINE — BTC 1H")
print("=" * 60)

df = load_data("BTC", "1h")
print(f"\nDati: {len(df)} candele [{df['datetime'].iloc[0]} → {df['datetime'].iloc[-1]}]")

# 1. Distribuzione pattern
print("\n--- DISTRIBUZIONE PATTERN (3-6 candele) ---")
candle_types = encode_candles(df)
unique, counts = np.unique(candle_types, return_counts=True)
type_map = {-1: "DOWN", 0: "DOJI", 1: "UP"}
for t, c in zip(unique, counts):
    print(f"  {type_map[t]}: {c} ({c/len(df)*100:.1f}%)")

patterns = find_patterns(df, min_len=3, max_len=6)
freq = pattern_frequency(patterns)
print(f"\nPattern unici: {len(freq)}")
print(f"\nTop 20 pattern più frequenti:")
print(freq.head(20).to_string(index=False))

# 2. Analisi predittiva: dopo ogni pattern, il prezzo sale o scende?
print("\n\n--- ANALISI PREDITTIVA PER PATTERN ---")
print("Per ogni pattern: % volte che il prezzo sale nelle N candele successive")

LOOKAHEAD = [1, 3, 6, 12, 24]
top_patterns = freq.head(30)["pattern"].tolist()

results = []
for code in top_patterns:
    matching = [p for p in patterns if p.code == code]
    if len(matching) < 50:
        continue

    row = {"pattern": code, "count": len(matching)}
    for ahead in LOOKAHEAD:
        ups = 0
        valid = 0
        for p in matching:
            future_idx = p.end_idx + ahead
            if future_idx >= len(df):
                continue
            valid += 1
            if df["close"].iloc[future_idx] > df["close"].iloc[p.end_idx - 1]:
                ups += 1
        if valid > 0:
            row[f"up_{ahead}h"] = round(ups / valid * 100, 1)
        else:
            row[f"up_{ahead}h"] = None
    results.append(row)

pred_df = pd.DataFrame(results)
print(pred_df.to_string(index=False))

# 3. Strategia naive: compra quando il pattern più bullish si presenta
print("\n\n--- STRATEGIA 1: PATTERN BULLISH NAIVE ---")
# Trova pattern con up_24h > 55%
bullish_patterns = pred_df[pred_df["up_24h"] > 55]["pattern"].tolist()
bearish_patterns = pred_df[pred_df["up_24h"] < 45]["pattern"].tolist()
print(f"Pattern bullish (>55% up in 24h): {len(bullish_patterns)}")
print(f"Pattern bearish (<45% up in 24h): {len(bearish_patterns)}")

# Genera segnali
signals = pd.Series(0, index=df.index)
all_patterns = find_patterns(df, min_len=3, max_len=6)
for p in all_patterns:
    if p.code in bullish_patterns:
        signals.iloc[p.end_idx - 1] = 1
    elif p.code in bearish_patterns:
        if signals.iloc[p.end_idx - 1] == 0:
            signals.iloc[p.end_idx - 1] = -1

# Train/test split: 70/30
split_idx = int(len(df) * 0.7)
train_df = df.iloc[:split_idx].reset_index(drop=True)
test_df = df.iloc[split_idx:].reset_index(drop=True)
train_signals = signals.iloc[:split_idx].reset_index(drop=True)
test_signals = signals.iloc[split_idx:].reset_index(drop=True)

train_result = run_backtest(train_df, train_signals, initial_capital=1000, fee_pct=0.001)
test_result = run_backtest(test_df, test_signals, initial_capital=1000, fee_pct=0.001)

print("\nRISULTATI TRAIN (70%):")
for k, v in train_result.summary().items():
    print(f"  {k}: {v}")

print("\nRISULTATI TEST (30%):")
for k, v in test_result.summary().items():
    print(f"  {k}: {v}")

# 4. Buy & Hold come benchmark
print("\n\n--- BENCHMARK: BUY & HOLD ---")
bh_signals = pd.Series(0, index=test_df.index)
bh_signals.iloc[0] = 1  # Compra al primo candle
bh_result = run_backtest(test_df, bh_signals, initial_capital=1000, fee_pct=0.001, max_hold_candles=len(test_df))
print("Buy & Hold (test period):")
for k, v in bh_result.summary().items():
    print(f"  {k}: {v}")