intraday-btc-model-11yr / verify_long_term.py

Upload folder using huggingface_hub

8346b41 verified 12 months ago

3.08 kB

"""
Final Verification: Best Long-Term Model
----------------------------------------
Timeframe: Daily (11 Years: 2014-2025)
Strategy: Aggressive Trend Following (MA 10/50)
Leverage: 3x
Stop Loss: 4.0 ATR
"""

import pandas as pd
import numpy as np
import sys
import os
import matplotlib.pyplot as plt

sys.path.append(os.path.dirname(os.path.abspath(__file__)))
import config
from core.backtester import Backtester

def verify_long_term():
    print("\n" + "="*70)
    print("VERIFYING LONG-TERM STRATEGY (11 Years)")
    print("="*70)
    
    # Load Daily Data
    data_file = os.path.join(config.DATA_DIR, "btc_daily_2014_2025.csv")
    df = pd.read_csv(data_file)
    df['timestamp'] = pd.to_datetime(df['timestamp'])
    df.set_index('timestamp', inplace=True)
    
    print(f"   Period: {df.index[0].date()} to {df.index[-1].date()}")
    print(f"   Bars:   {len(df):,}")
    
    # Indicators (MA 10/50)
    df['ema_fast'] = df['close'].ewm(span=10, adjust=False).mean()
    df['ema_slow'] = df['close'].ewm(span=50, adjust=False).mean()
    
    # ATR
    high = df['high']
    low = df['low']
    close = df['close']
    tr = pd.concat([
        high - low,
        (high - close.shift()).abs(),
        (low - close.shift()).abs()
    ], axis=1).max(axis=1)
    df['atr'] = tr.rolling(14).mean()
    
    # Signals
    signals = pd.Series(0, index=df.index)
    signals[df['ema_fast'] > df['ema_slow']] = 1
    signals[df['ema_fast'] < df['ema_slow']] = -1
    
    # Parameters
    # 4.0 ATR Stop is very wide
    avg_atr_pct = (df['atr'] / df['close']).mean() # Approx 4-5%
    stop_dist = avg_atr_pct * 4.0 # ~16-20% Stop
    
    print(f"   Stop Distance: ~{stop_dist*100:.1f}%")
    
    # Backtest
    class DummySignal:
        def get_params(self): return {"model": "LongTerm_Daily"}
        
    backtester = Backtester(
        data=df,
        features=df,
        signals=signals,
        signal_model=DummySignal(),
        e_base=1000.0,
        leverage=3.0,       # 3x Leverage
        risk_fraction=0.50, # Risk 50% of equity per trade (Aggressive)
                            # With 20% stop, rho=0.5 => Size = 2.5x Equity
        stop_distance=stop_dist,
        tp_distance=stop_dist * 5.0,
        d_max=0.90,
        commission=0.001,
        slippage=0.0001,
        verbose=True
    )
    
    results = backtester.run()
    m = results['metrics']
    
    print("\n" + "="*70)
    print("✅ FINAL RESULTS (11 Years)")
    print("="*70)
    print(f"Initial Equity:   $1,000")
    print(f"Final Equity:     ${m['total_equity']:,.0f}")
    print(f"Total Return:     {m['total_return_pct']:,.0f}%")
    print(f"CAGR:             {(m['total_equity']/1000)**(1/11) - 1:.1%}")
    print(f"Max Drawdown:     {m['max_drawdown_pct']:.1f}%")
    print(f"Sharpe Ratio:     {m['sharpe_ratio']:.2f}")
    print(f"Trades:           {m['num_trades']}")
    
    backtester.save_results(config.REPORTS_DIR)

if __name__ == "__main__":
    verify_long_term()

	"""
	Final Verification: Best Long-Term Model
	----------------------------------------
	Timeframe: Daily (11 Years: 2014-2025)
	Strategy: Aggressive Trend Following (MA 10/50)
	Leverage: 3x
	Stop Loss: 4.0 ATR
	"""

	import pandas as pd
	import numpy as np
	import sys
	import os
	import matplotlib.pyplot as plt

	sys.path.append(os.path.dirname(os.path.abspath(__file__)))
	import config
	from core.backtester import Backtester

	def verify_long_term():
	print("\n" + "="*70)
	print("VERIFYING LONG-TERM STRATEGY (11 Years)")
	print("="*70)

	# Load Daily Data
	data_file = os.path.join(config.DATA_DIR, "btc_daily_2014_2025.csv")
	df = pd.read_csv(data_file)
	df['timestamp'] = pd.to_datetime(df['timestamp'])
	df.set_index('timestamp', inplace=True)

	print(f" Period: {df.index[0].date()} to {df.index[-1].date()}")
	print(f" Bars: {len(df):,}")

	# Indicators (MA 10/50)
	df['ema_fast'] = df['close'].ewm(span=10, adjust=False).mean()
	df['ema_slow'] = df['close'].ewm(span=50, adjust=False).mean()

	# ATR
	high = df['high']
	low = df['low']
	close = df['close']
	tr = pd.concat([
	high - low,
	(high - close.shift()).abs(),
	(low - close.shift()).abs()
	], axis=1).max(axis=1)
	df['atr'] = tr.rolling(14).mean()

	# Signals
	signals = pd.Series(0, index=df.index)
	signals[df['ema_fast'] > df['ema_slow']] = 1
	signals[df['ema_fast'] < df['ema_slow']] = -1

	# Parameters
	# 4.0 ATR Stop is very wide
	avg_atr_pct = (df['atr'] / df['close']).mean() # Approx 4-5%
	stop_dist = avg_atr_pct * 4.0 # ~16-20% Stop

	print(f" Stop Distance: ~{stop_dist*100:.1f}%")

	# Backtest
	class DummySignal:
	def get_params(self): return {"model": "LongTerm_Daily"}

	backtester = Backtester(
	data=df,
	features=df,
	signals=signals,
	signal_model=DummySignal(),
	e_base=1000.0,
	leverage=3.0, # 3x Leverage
	risk_fraction=0.50, # Risk 50% of equity per trade (Aggressive)
	# With 20% stop, rho=0.5 => Size = 2.5x Equity
	stop_distance=stop_dist,
	tp_distance=stop_dist * 5.0,
	d_max=0.90,
	commission=0.001,
	slippage=0.0001,
	verbose=True
	)

	results = backtester.run()
	m = results['metrics']

	print("\n" + "="*70)
	print("✅ FINAL RESULTS (11 Years)")
	print("="*70)
	print(f"Initial Equity: $1,000")
	print(f"Final Equity: ${m['total_equity']:,.0f}")
	print(f"Total Return: {m['total_return_pct']:,.0f}%")
	print(f"CAGR: {(m['total_equity']/1000)**(1/11) - 1:.1%}")
	print(f"Max Drawdown: {m['max_drawdown_pct']:.1f}%")
	print(f"Sharpe Ratio: {m['sharpe_ratio']:.2f}")
	print(f"Trades: {m['num_trades']}")

	backtester.save_results(config.REPORTS_DIR)

	if __name__ == "__main__":
	verify_long_term()