Merge pull request #7987 from stash86/bt-metrics
update calmar, sharpe, and sortino hyperopt losses to use latest formula
This commit is contained in:
commit
8d4f7341c9
@ -5,13 +5,11 @@ This module defines the alternative HyperOptLoss class which can be used for
|
||||
Hyperoptimization.
|
||||
"""
|
||||
from datetime import datetime
|
||||
from math import sqrt as msqrt
|
||||
from typing import Any, Dict
|
||||
|
||||
from pandas import DataFrame
|
||||
|
||||
from freqtrade.constants import Config
|
||||
from freqtrade.data.metrics import calculate_max_drawdown
|
||||
from freqtrade.data.metrics import calculate_calmar
|
||||
from freqtrade.optimize.hyperopt import IHyperOptLoss
|
||||
|
||||
|
||||
@ -23,42 +21,15 @@ class CalmarHyperOptLoss(IHyperOptLoss):
|
||||
"""
|
||||
|
||||
@staticmethod
|
||||
def hyperopt_loss_function(
|
||||
results: DataFrame,
|
||||
trade_count: int,
|
||||
min_date: datetime,
|
||||
max_date: datetime,
|
||||
config: Config,
|
||||
processed: Dict[str, DataFrame],
|
||||
backtest_stats: Dict[str, Any],
|
||||
*args,
|
||||
**kwargs
|
||||
) -> float:
|
||||
def hyperopt_loss_function(results: DataFrame, trade_count: int,
|
||||
min_date: datetime, max_date: datetime,
|
||||
config: Config, *args, **kwargs) -> float:
|
||||
"""
|
||||
Objective function, returns smaller number for more optimal results.
|
||||
|
||||
Uses Calmar Ratio calculation.
|
||||
"""
|
||||
total_profit = backtest_stats["profit_total"]
|
||||
days_period = (max_date - min_date).days
|
||||
|
||||
# adding slippage of 0.1% per trade
|
||||
total_profit = total_profit - 0.0005
|
||||
expected_returns_mean = total_profit.sum() / days_period * 100
|
||||
|
||||
# calculate max drawdown
|
||||
try:
|
||||
_, _, _, _, _, max_drawdown = calculate_max_drawdown(
|
||||
results, value_col="profit_abs"
|
||||
)
|
||||
except ValueError:
|
||||
max_drawdown = 0
|
||||
|
||||
if max_drawdown != 0:
|
||||
calmar_ratio = expected_returns_mean / max_drawdown * msqrt(365)
|
||||
else:
|
||||
# Define high (negative) calmar ratio to be clear that this is NOT optimal.
|
||||
calmar_ratio = -20.0
|
||||
|
||||
starting_balance = config['dry_run_wallet']
|
||||
calmar_ratio = calculate_calmar(results, min_date, max_date, starting_balance)
|
||||
# print(expected_returns_mean, max_drawdown, calmar_ratio)
|
||||
return -calmar_ratio
|
||||
|
@ -6,9 +6,10 @@ Hyperoptimization.
|
||||
"""
|
||||
from datetime import datetime
|
||||
|
||||
import numpy as np
|
||||
from pandas import DataFrame
|
||||
|
||||
from freqtrade.constants import Config
|
||||
from freqtrade.data.metrics import calculate_sharpe
|
||||
from freqtrade.optimize.hyperopt import IHyperOptLoss
|
||||
|
||||
|
||||
@ -22,25 +23,13 @@ class SharpeHyperOptLoss(IHyperOptLoss):
|
||||
@staticmethod
|
||||
def hyperopt_loss_function(results: DataFrame, trade_count: int,
|
||||
min_date: datetime, max_date: datetime,
|
||||
*args, **kwargs) -> float:
|
||||
config: Config, *args, **kwargs) -> float:
|
||||
"""
|
||||
Objective function, returns smaller number for more optimal results.
|
||||
|
||||
Uses Sharpe Ratio calculation.
|
||||
"""
|
||||
total_profit = results["profit_ratio"]
|
||||
days_period = (max_date - min_date).days
|
||||
|
||||
# adding slippage of 0.1% per trade
|
||||
total_profit = total_profit - 0.0005
|
||||
expected_returns_mean = total_profit.sum() / days_period
|
||||
up_stdev = np.std(total_profit)
|
||||
|
||||
if up_stdev != 0:
|
||||
sharp_ratio = expected_returns_mean / up_stdev * np.sqrt(365)
|
||||
else:
|
||||
# Define high (negative) sharpe ratio to be clear that this is NOT optimal.
|
||||
sharp_ratio = -20.
|
||||
|
||||
starting_balance = config['dry_run_wallet']
|
||||
sharp_ratio = calculate_sharpe(results, min_date, max_date, starting_balance)
|
||||
# print(expected_returns_mean, up_stdev, sharp_ratio)
|
||||
return -sharp_ratio
|
||||
|
@ -6,9 +6,10 @@ Hyperoptimization.
|
||||
"""
|
||||
from datetime import datetime
|
||||
|
||||
import numpy as np
|
||||
from pandas import DataFrame
|
||||
|
||||
from freqtrade.constants import Config
|
||||
from freqtrade.data.metrics import calculate_sortino
|
||||
from freqtrade.optimize.hyperopt import IHyperOptLoss
|
||||
|
||||
|
||||
@ -22,28 +23,13 @@ class SortinoHyperOptLoss(IHyperOptLoss):
|
||||
@staticmethod
|
||||
def hyperopt_loss_function(results: DataFrame, trade_count: int,
|
||||
min_date: datetime, max_date: datetime,
|
||||
*args, **kwargs) -> float:
|
||||
config: Config, *args, **kwargs) -> float:
|
||||
"""
|
||||
Objective function, returns smaller number for more optimal results.
|
||||
|
||||
Uses Sortino Ratio calculation.
|
||||
"""
|
||||
total_profit = results["profit_ratio"]
|
||||
days_period = (max_date - min_date).days
|
||||
|
||||
# adding slippage of 0.1% per trade
|
||||
total_profit = total_profit - 0.0005
|
||||
expected_returns_mean = total_profit.sum() / days_period
|
||||
|
||||
results['downside_returns'] = 0
|
||||
results.loc[total_profit < 0, 'downside_returns'] = results['profit_ratio']
|
||||
down_stdev = np.std(results['downside_returns'])
|
||||
|
||||
if down_stdev != 0:
|
||||
sortino_ratio = expected_returns_mean / down_stdev * np.sqrt(365)
|
||||
else:
|
||||
# Define high (negative) sortino ratio to be clear that this is NOT optimal.
|
||||
sortino_ratio = -20.
|
||||
|
||||
starting_balance = config['dry_run_wallet']
|
||||
sortino_ratio = calculate_sortino(results, min_date, max_date, starting_balance)
|
||||
# print(expected_returns_mean, down_stdev, sortino_ratio)
|
||||
return -sortino_ratio
|
||||
|
@ -48,8 +48,8 @@ def hyperopt_results():
|
||||
return pd.DataFrame(
|
||||
{
|
||||
'pair': ['ETH/USDT', 'ETH/USDT', 'ETH/USDT', 'ETH/USDT'],
|
||||
'profit_ratio': [-0.1, 0.2, -0.1, 0.3],
|
||||
'profit_abs': [-0.2, 0.4, -0.2, 0.6],
|
||||
'profit_ratio': [-0.1, 0.2, -0.12, 0.3],
|
||||
'profit_abs': [-0.2, 0.4, -0.21, 0.6],
|
||||
'trade_duration': [10, 30, 10, 10],
|
||||
'amount': [0.1, 0.1, 0.1, 0.1],
|
||||
'exit_reason': [ExitType.STOP_LOSS, ExitType.ROI, ExitType.STOP_LOSS, ExitType.ROI],
|
||||
|
Loading…
Reference in New Issue
Block a user