adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Provide full backtest-statistics to Hyperopt loss functions

Browse Source 
closes #5223
This commit is contained in:
Matthias 2021-07-04 10:15:19 +02:00
parent e9dbd57da4
commit a4096318e0
3 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/advanced-hyperopt.md
View File

@ -32,6 +32,7 @@ class SuperDuperHyperOptLoss(IHyperOptLoss):
def hyperopt_loss_function(results: DataFrame, trade_count: int,
min_date: datetime, max_date: datetime,
config: Dict, processed: Dict[str, DataFrame],
backtest_stats: Dict[str, Any],
*args, **kwargs) -> float:
"""
Objective function, returns smaller number for better results
@ -53,7 +54,7 @@ class SuperDuperHyperOptLoss(IHyperOptLoss):
Currently, the arguments are:
* `results`: DataFrame containing the result
* `results`: DataFrame containing the resulting trades.
The following columns are available in results (corresponds to the output-file of backtesting when used with `--export trades`):
`pair, profit_ratio, profit_abs, open_date, open_rate, fee_open, close_date, close_rate, fee_close, amount, trade_duration, is_open, sell_reason, stake_amount, min_rate, max_rate, stop_loss_ratio, stop_loss_abs`
* `trade_count`: Amount of trades (identical to `len(results)`)
@ -61,6 +62,7 @@ Currently, the arguments are:
* `min_date`: End date of the timerange used
* `config`: Config object used (Note: Not all strategy-related parameters will be updated here if they are part of a hyperopt space).
* `processed`: Dict of Dataframes with the pair as keys containing the data used for backtesting.
* `backtest_stats`: Backtesting statistics using the same format as the backtesting file "strategy" substructure. Available fields can be seen in `generate_strategy_stats()` in `optimize_reports.py`.
This function needs to return a floating point number (`float`). Smaller numbers will be interpreted as better results. The parameters and balancing for this is up to you.

3
freqtrade/optimize/hyperopt.py
View File

@ -324,7 +324,8 @@ class Hyperopt:
loss = self.calculate_loss(results=backtesting_results['results'],
trade_count=trade_count,
min_date=min_date, max_date=max_date,
config=self.config, processed=processed)
config=self.config, processed=processed,
backtest_stats=strat_stats)
return {
'loss': loss,
'params_dict': params_dict,

3
freqtrade/optimize/hyperopt_loss_interface.py
View File

@ -5,7 +5,7 @@ This module defines the interface for the loss-function for hyperopt
from abc import ABC, abstractmethod
from datetime import datetime
from typing import Dict
from typing import Any, Dict
from pandas import DataFrame
@ -22,6 +22,7 @@ class IHyperOptLoss(ABC):
def hyperopt_loss_function(results: DataFrame, trade_count: int,
min_date: datetime, max_date: datetime,
config: Dict, processed: Dict[str, DataFrame],
backtest_stats: Dict[str, Any],
*args, **kwargs) -> float:
"""
Objective function, returns smaller number for better results