stable/freqtrade/optimize/backtesting.py

526 lines
23 KiB
Python
Raw Normal View History

# pragma pylint: disable=missing-docstring, W0212, too-many-arguments
2017-11-14 21:15:24 +00:00
"""
This module contains the backtesting logic
"""
2018-03-25 19:37:14 +00:00
import logging
2018-07-27 21:01:52 +00:00
from copy import deepcopy
2018-07-18 18:08:55 +00:00
from datetime import datetime, timedelta
from pathlib import Path
from typing import Any, Dict, List, NamedTuple, Optional
2018-03-17 21:44:47 +00:00
2018-03-29 18:16:25 +00:00
from pandas import DataFrame
from tabulate import tabulate
2017-09-28 21:26:28 +00:00
from freqtrade import OperationalException
from freqtrade.configuration import (TimeRange, remove_credentials,
validate_config_consistency)
2018-12-13 05:34:10 +00:00
from freqtrade.data import history
from freqtrade.data.converter import trim_dataframe
from freqtrade.data.dataprovider import DataProvider
2019-10-20 11:56:01 +00:00
from freqtrade.exchange import timeframe_to_minutes, timeframe_to_seconds
from freqtrade.misc import file_dump_json
2017-09-28 21:26:28 +00:00
from freqtrade.persistence import Trade
from freqtrade.resolvers import ExchangeResolver, StrategyResolver
from freqtrade.state import RunMode
from freqtrade.strategy.interface import IStrategy, SellType
2018-03-25 19:37:14 +00:00
logger = logging.getLogger(__name__)
2018-06-10 11:15:25 +00:00
class BacktestResult(NamedTuple):
"""
NamedTuple Defining BacktestResults inputs.
"""
pair: str
profit_percent: float
profit_abs: float
2018-06-10 11:32:07 +00:00
open_time: datetime
close_time: datetime
2018-06-10 18:52:42 +00:00
open_index: int
close_index: int
2018-06-10 11:15:25 +00:00
trade_duration: float
2018-06-10 11:37:53 +00:00
open_at_end: bool
open_rate: float
close_rate: float
2018-07-11 18:03:40 +00:00
sell_reason: SellType
2018-06-10 11:15:25 +00:00
2019-09-12 01:39:52 +00:00
class Backtesting:
"""
Backtesting class, this class contains all the logic to run a backtest
To run a backtest:
backtesting = Backtesting(config)
backtesting.start()
"""
2018-07-28 05:00:58 +00:00
def __init__(self, config: Dict[str, Any]) -> None:
self.config = config
# Reset keys for backtesting
remove_credentials(self.config)
2018-07-28 05:41:38 +00:00
self.strategylist: List[IStrategy] = []
self.exchange = ExchangeResolver.load_exchange(self.config['exchange']['name'], self.config)
if config.get('fee'):
self.fee = config['fee']
else:
self.fee = self.exchange.get_fee(symbol=self.config['exchange']['pair_whitelist'][0])
if self.config.get('runmode') != RunMode.HYPEROPT:
self.dataprovider = DataProvider(self.config, self.exchange)
IStrategy.dp = self.dataprovider
2018-07-28 05:41:38 +00:00
if self.config.get('strategy_list', None):
2018-07-28 05:55:59 +00:00
for strat in list(self.config['strategy_list']):
2018-07-28 05:41:38 +00:00
stratconf = deepcopy(self.config)
stratconf['strategy'] = strat
self.strategylist.append(StrategyResolver.load_strategy(stratconf))
validate_config_consistency(stratconf)
2018-07-28 05:41:38 +00:00
else:
2019-06-09 23:08:54 +00:00
# No strategy list specified, only one strategy
self.strategylist.append(StrategyResolver.load_strategy(self.config))
validate_config_consistency(self.config)
2019-06-09 23:08:54 +00:00
if "ticker_interval" not in self.config:
raise OperationalException("Ticker-interval needs to be set in either configuration "
"or as cli argument `--ticker-interval 5m`")
self.timeframe = str(self.config.get('ticker_interval'))
2019-12-11 06:12:37 +00:00
self.timeframe_min = timeframe_to_minutes(self.timeframe)
2019-10-20 11:56:01 +00:00
# Get maximum required startup period
self.required_startup = max([strat.startup_candle_count for strat in self.strategylist])
2019-06-09 23:08:54 +00:00
# Load one (first) strategy
2018-07-28 05:41:38 +00:00
self._set_strategy(self.strategylist[0])
2018-07-28 05:00:58 +00:00
def _set_strategy(self, strategy):
2018-07-28 04:54:33 +00:00
"""
Load strategy into backtesting
"""
self.strategy = strategy
# Set stoploss_on_exchange to false for backtesting,
# since a "perfect" stoploss-sell is assumed anyway
# And the regular "stoploss" function would not apply to that case
self.strategy.order_types['stoploss_on_exchange'] = False
2018-07-28 04:54:33 +00:00
def load_bt_data(self):
timerange = TimeRange.parse_timerange(None if self.config.get(
'timerange') is None else str(self.config.get('timerange')))
data = history.load_data(
2019-12-23 18:32:31 +00:00
datadir=self.config['datadir'],
pairs=self.config['exchange']['pair_whitelist'],
timeframe=self.timeframe,
timerange=timerange,
startup_candles=self.required_startup,
fail_without_data=True,
)
2019-12-17 22:06:03 +00:00
min_date, max_date = history.get_timerange(data)
logger.info(
'Loading data from %s up to %s (%s days)..',
min_date.isoformat(), max_date.isoformat(), (max_date - min_date).days
)
# Adjust startts forward if not enough data is available
2019-11-02 19:34:39 +00:00
timerange.adjust_start_if_necessary(timeframe_to_seconds(self.timeframe),
self.required_startup, min_date)
return data, timerange
def _generate_text_table(self, data: Dict[str, Dict], results: DataFrame,
skip_nan: bool = False) -> str:
"""
Generates and returns a text table for the given backtest data and the results dataframe
:return: pretty printed table with tabulate as str
"""
2018-06-02 11:43:51 +00:00
stake_currency = str(self.config.get('stake_currency'))
max_open_trades = self.config.get('max_open_trades')
floatfmt = ('s', 'd', '.2f', '.2f', '.8f', '.2f', 'd', '.1f', '.1f')
tabular_data = []
2018-07-08 17:55:04 +00:00
headers = ['pair', 'buy count', 'avg profit %', 'cum profit %',
'tot profit ' + stake_currency, 'tot profit %', 'avg duration',
'profit', 'loss']
for pair in data:
2018-06-10 11:15:25 +00:00
result = results[results.pair == pair]
if skip_nan and result.profit_abs.isnull().all():
continue
tabular_data.append([
pair,
len(result.index),
result.profit_percent.mean() * 100.0,
2018-07-08 17:55:04 +00:00
result.profit_percent.sum() * 100.0,
2018-06-10 11:15:25 +00:00
result.profit_abs.sum(),
result.profit_percent.sum() * 100.0 / max_open_trades,
2018-07-18 18:08:55 +00:00
str(timedelta(
minutes=round(result.trade_duration.mean()))) if not result.empty else '0:00',
2018-06-10 11:15:25 +00:00
len(result[result.profit_abs > 0]),
len(result[result.profit_abs < 0])
])
# Append Total
tabular_data.append([
'TOTAL',
len(results.index),
results.profit_percent.mean() * 100.0,
2018-07-11 12:50:04 +00:00
results.profit_percent.sum() * 100.0,
2018-06-10 11:15:25 +00:00
results.profit_abs.sum(),
results.profit_percent.sum() * 100.0 / max_open_trades,
2018-07-18 18:08:55 +00:00
str(timedelta(
minutes=round(results.trade_duration.mean()))) if not results.empty else '0:00',
2018-06-10 11:15:25 +00:00
len(results[results.profit_abs > 0]),
len(results[results.profit_abs < 0])
])
# Ignore type as floatfmt does allow tuples but mypy does not know that
return tabulate(tabular_data, headers=headers,
floatfmt=floatfmt, tablefmt="pipe") # type: ignore
2018-07-12 19:19:43 +00:00
def _generate_text_table_sell_reason(self, data: Dict[str, Dict], results: DataFrame) -> str:
"""
Generate small table outlining Backtest results
"""
tabular_data = []
headers = ['Sell Reason', 'Count', 'Profit', 'Loss']
2018-07-12 19:19:43 +00:00
for reason, count in results['sell_reason'].value_counts().iteritems():
profit = len(results[(results['sell_reason'] == reason) & (results['profit_abs'] >= 0)])
loss = len(results[(results['sell_reason'] == reason) & (results['profit_abs'] < 0)])
tabular_data.append([reason.value, count, profit, loss])
2018-07-12 19:19:43 +00:00
return tabulate(tabular_data, headers=headers, tablefmt="pipe")
2018-07-29 11:07:11 +00:00
def _generate_text_table_strategy(self, all_results: dict) -> str:
"""
Generate summary table per strategy
"""
stake_currency = str(self.config.get('stake_currency'))
max_open_trades = self.config.get('max_open_trades')
2018-07-29 11:07:11 +00:00
floatfmt = ('s', 'd', '.2f', '.2f', '.8f', '.2f', 'd', '.1f', '.1f')
2018-07-29 11:07:11 +00:00
tabular_data = []
headers = ['Strategy', 'buy count', 'avg profit %', 'cum profit %',
'tot profit ' + stake_currency, 'tot profit %', 'avg duration',
'profit', 'loss']
2018-07-29 11:07:11 +00:00
for strategy, results in all_results.items():
tabular_data.append([
strategy,
len(results.index),
results.profit_percent.mean() * 100.0,
results.profit_percent.sum() * 100.0,
results.profit_abs.sum(),
results.profit_percent.sum() * 100.0 / max_open_trades,
2018-07-29 11:07:11 +00:00
str(timedelta(
minutes=round(results.trade_duration.mean()))) if not results.empty else '0:00',
len(results[results.profit_abs > 0]),
len(results[results.profit_abs < 0])
])
# Ignore type as floatfmt does allow tuples but mypy does not know that
return tabulate(tabular_data, headers=headers,
floatfmt=floatfmt, tablefmt="pipe") # type: ignore
2018-07-29 11:07:11 +00:00
def _store_backtest_result(self, recordfilename: Path, results: DataFrame,
strategyname: Optional[str] = None) -> None:
2018-06-12 20:29:30 +00:00
records = [(t.pair, t.profit_percent, t.open_time.timestamp(),
t.close_time.timestamp(), t.open_index - 1, t.trade_duration,
2018-07-11 18:32:56 +00:00
t.open_rate, t.close_rate, t.open_at_end, t.sell_reason.value)
for index, t in results.iterrows()]
2018-06-12 20:29:30 +00:00
if records:
if strategyname:
# Inject strategyname to filename
recordfilename = Path.joinpath(
recordfilename.parent,
f'{recordfilename.stem}-{strategyname}').with_suffix(recordfilename.suffix)
logger.info(f'Dumping backtest results to {recordfilename}')
2018-06-12 20:29:30 +00:00
file_dump_json(recordfilename, records)
def _get_ticker_list(self, processed) -> Dict[str, DataFrame]:
"""
Helper function to convert a processed tickerlist into a list for performance reasons.
Used by backtest() - so keep this optimized for performance.
"""
headers = ['date', 'buy', 'open', 'close', 'sell', 'low', 'high']
ticker: Dict = {}
# Create ticker dict
for pair, pair_data in processed.items():
2019-11-03 09:38:21 +00:00
pair_data.loc[:, 'buy'] = 0 # cleanup from previous run
pair_data.loc[:, 'sell'] = 0 # cleanup from previous run
2019-09-18 19:57:17 +00:00
ticker_data = self.strategy.advise_sell(
self.strategy.advise_buy(pair_data, {'pair': pair}), {'pair': pair})[headers].copy()
# to avoid using data from future, we buy/sell with signal from previous candle
ticker_data.loc[:, 'buy'] = ticker_data['buy'].shift(1)
ticker_data.loc[:, 'sell'] = ticker_data['sell'].shift(1)
ticker_data.drop(ticker_data.head(1).index, inplace=True)
# Convert from Pandas to list for performance reasons
# (Looping Pandas is slow.)
ticker[pair] = [x for x in ticker_data.itertuples()]
return ticker
def _get_close_rate(self, sell_row, trade: Trade, sell, trade_dur) -> float:
"""
Get close rate for backtesting result
"""
# Special handling if high or low hit STOP_LOSS or ROI
if sell.sell_type in (SellType.STOP_LOSS, SellType.TRAILING_STOP_LOSS):
# Set close_rate to stoploss
return trade.stop_loss
elif sell.sell_type == (SellType.ROI):
2019-12-07 14:18:12 +00:00
roi_entry, roi = self.strategy.min_roi_reached_entry(trade_dur)
if roi is not None:
2019-12-14 22:10:09 +00:00
if roi == -1 and roi_entry % self.timeframe_min == 0:
# When forceselling with ROI=-1, the roi time will always be equal to trade_dur.
# If that entry is a multiple of the timeframe (so on candle open)
# - we'll use open instead of close
return sell_row.open
# - (Expected abs profit + open_rate + open_fee) / (fee_close -1)
close_rate = - (trade.open_rate * roi + trade.open_rate *
(1 + trade.fee_open)) / (trade.fee_close - 1)
if (trade_dur > 0 and trade_dur == roi_entry
2019-12-14 22:10:09 +00:00
and roi_entry % self.timeframe_min == 0
and sell_row.open > close_rate):
# new ROI entry came into effect.
# use Open rate if open_rate > calculated sell rate
return sell_row.open
# Use the maximum between close_rate and low as we
# cannot sell outside of a candle.
2019-12-07 14:18:12 +00:00
# Applies when a new ROI setting comes in place and the whole candle is above that.
return max(close_rate, sell_row.low)
2019-12-07 14:18:12 +00:00
else:
# This should not be reached...
return sell_row.open
else:
return sell_row.open
2018-03-17 21:43:36 +00:00
def _get_sell_trade_entry(
self, pair: str, buy_row: DataFrame,
partial_ticker: List, trade_count_lock: Dict,
stake_amount: float, max_open_trades: int) -> Optional[BacktestResult]:
2018-03-17 21:43:36 +00:00
trade = Trade(
2019-09-10 07:42:45 +00:00
pair=pair,
2018-07-05 18:20:52 +00:00
open_rate=buy_row.open,
open_date=buy_row.date,
stake_amount=stake_amount,
amount=stake_amount / buy_row.open,
fee_open=self.fee,
2019-09-10 07:42:45 +00:00
fee_close=self.fee,
is_open=True,
)
2019-09-11 20:32:08 +00:00
logger.debug(f"{pair} - Backtesting emulates creation of new trade: {trade}.")
# calculate win/lose forwards from buy point
for sell_row in partial_ticker:
if max_open_trades > 0:
# Increase trade_count_lock for every iteration
trade_count_lock[sell_row.date] = trade_count_lock.get(sell_row.date, 0) + 1
sell = self.strategy.should_sell(trade, sell_row.open, sell_row.date, sell_row.buy,
sell_row.sell, low=sell_row.low, high=sell_row.high)
2018-07-12 20:21:52 +00:00
if sell.sell_flag:
2018-08-17 05:07:50 +00:00
trade_dur = int((sell_row.date - buy_row.date).total_seconds() // 60)
closerate = self._get_close_rate(sell_row, trade, sell, trade_dur)
2018-06-10 11:15:25 +00:00
return BacktestResult(pair=pair,
profit_percent=trade.calc_profit_ratio(rate=closerate),
profit_abs=trade.calc_profit(rate=closerate),
2018-06-10 11:15:25 +00:00
open_time=buy_row.date,
close_time=sell_row.date,
2018-08-17 05:07:50 +00:00
trade_duration=trade_dur,
2018-06-12 20:29:30 +00:00
open_index=buy_row.Index,
close_index=sell_row.Index,
open_at_end=False,
2018-07-05 18:20:52 +00:00
open_rate=buy_row.open,
close_rate=closerate,
2018-07-12 20:21:52 +00:00
sell_reason=sell.sell_type
2018-06-10 11:15:25 +00:00
)
if partial_ticker:
# no sell condition found - trade stil open at end of backtest period
sell_row = partial_ticker[-1]
2019-09-10 07:42:45 +00:00
bt_res = BacktestResult(pair=pair,
profit_percent=trade.calc_profit_ratio(rate=sell_row.open),
2019-09-10 07:42:45 +00:00
profit_abs=trade.calc_profit(rate=sell_row.open),
open_time=buy_row.date,
close_time=sell_row.date,
trade_duration=int((
sell_row.date - buy_row.date).total_seconds() // 60),
open_index=buy_row.Index,
close_index=sell_row.Index,
open_at_end=True,
open_rate=buy_row.open,
close_rate=sell_row.open,
sell_reason=SellType.FORCE_SELL
)
2019-09-11 20:32:08 +00:00
logger.debug(f"{pair} - Force selling still open trade, "
2019-09-10 07:42:45 +00:00
f"profit percent: {bt_res.profit_percent}, "
f"profit abs: {bt_res.profit_abs}")
return bt_res
return None
2018-03-17 21:43:36 +00:00
def backtest(self, args: Dict) -> DataFrame:
"""
Implements backtesting functionality
NOTE: This method is used by Hyperopt at each iteration. Please keep it optimized.
Of course try to not have ugly code. By some accessor are sometime slower than functions.
Avoid, logging on this method
:param args: a dict containing:
stake_amount: btc amount to use for each trade
processed: a processed dictionary with format {pair, data}
max_open_trades: maximum number of concurrent trades (default: 0, disabled)
position_stacking: do we allow position stacking? (default: False)
:return: DataFrame
"""
2019-07-09 22:45:02 +00:00
# Arguments are long and noisy, so this is commented out.
# Uncomment if you need to debug the backtest() method.
# logger.debug(f"Start backtest, args: {args}")
processed = args['processed']
stake_amount = args['stake_amount']
max_open_trades = args.get('max_open_trades', 0)
position_stacking = args.get('position_stacking', False)
start_date = args['start_date']
end_date = args['end_date']
trades = []
2018-06-02 11:43:51 +00:00
trade_count_lock: Dict = {}
# Dict of ticker-lists for performance (looping lists is a lot faster than dataframes)
ticker: Dict = self._get_ticker_list(processed)
lock_pair_until: Dict = {}
2019-04-04 18:23:10 +00:00
# Indexes per pair, so some pairs are allowed to have a missing start.
2019-03-20 17:38:10 +00:00
indexes: Dict = {}
2019-12-11 06:12:37 +00:00
tmp = start_date + timedelta(minutes=self.timeframe_min)
2019-03-20 17:38:10 +00:00
2019-04-04 18:23:10 +00:00
# Loop timerange and get candle for each pair at that point in time
while tmp < end_date:
2019-03-20 17:38:10 +00:00
for i, pair in enumerate(ticker):
2019-03-20 17:38:10 +00:00
if pair not in indexes:
indexes[pair] = 0
try:
2019-03-20 17:38:10 +00:00
row = ticker[pair][indexes[pair]]
except IndexError:
# missing Data for one pair at the end.
# Warnings for this are shown during data loading
continue
# Waits until the time-counter reaches the start of the data for this pair.
2019-03-20 18:44:59 +00:00
if row.date > tmp.datetime:
2019-03-20 17:38:10 +00:00
continue
indexes[pair] += 1
if row.buy == 0 or row.sell == 1:
continue # skip rows where no buy signal or that would immediately sell off
if (not position_stacking and pair in lock_pair_until
and row.date <= lock_pair_until[pair]):
# without positionstacking, we can only have one open trade per pair.
continue
if max_open_trades > 0:
# Check if max_open_trades has already been reached for the given date
if not trade_count_lock.get(row.date, 0) < max_open_trades:
continue
trade_count_lock[row.date] = trade_count_lock.get(row.date, 0) + 1
# since indexes has been incremented before, we need to go one step back to
# also check the buying candle for sell conditions.
trade_entry = self._get_sell_trade_entry(pair, row, ticker[pair][indexes[pair]-1:],
trade_count_lock, stake_amount,
max_open_trades)
2018-06-10 11:15:25 +00:00
if trade_entry:
2019-09-11 20:32:08 +00:00
logger.debug(f"{pair} - Locking pair till "
2019-09-10 07:42:45 +00:00
f"close_time={trade_entry.close_time}")
lock_pair_until[pair] = trade_entry.close_time
trades.append(trade_entry)
else:
# Set lock_pair_until to end of testing period if trade could not be closed
2019-03-20 18:44:59 +00:00
lock_pair_until[pair] = end_date.datetime
# Move time one configured time_interval ahead.
2019-12-11 06:12:37 +00:00
tmp += timedelta(minutes=self.timeframe_min)
2018-06-10 11:15:25 +00:00
return DataFrame.from_records(trades, columns=BacktestResult._fields)
def start(self) -> None:
"""
Run a backtesting end-to-end
:return: None
"""
data: Dict[str, Any] = {}
2018-03-25 19:37:14 +00:00
logger.info('Using stake_currency: %s ...', self.config['stake_currency'])
logger.info('Using stake_amount: %s ...', self.config['stake_amount'])
2018-07-17 19:05:03 +00:00
# Use max_open_trades in backtesting, except --disable-max-market-positions is set
if self.config.get('use_max_market_positions', True):
max_open_trades = self.config['max_open_trades']
else:
2018-07-17 19:05:03 +00:00
logger.info('Ignoring max_open_trades (--disable-max-market-positions was used) ...')
max_open_trades = 0
data, timerange = self.load_bt_data()
all_results = {}
2018-07-28 05:41:38 +00:00
for strat in self.strategylist:
2018-07-28 04:54:33 +00:00
logger.info("Running backtesting for Strategy %s", strat.get_strategy_name())
2018-07-28 05:00:58 +00:00
self._set_strategy(strat)
2018-07-27 21:01:52 +00:00
# need to reprocess data every time to populate signals
preprocessed = self.strategy.tickerdata_to_dataframe(data)
2019-10-20 11:56:01 +00:00
# Trim startup period from analyzed dataframe
for pair, df in preprocessed.items():
preprocessed[pair] = trim_dataframe(df, timerange)
2019-12-17 22:06:03 +00:00
min_date, max_date = history.get_timerange(preprocessed)
2019-10-20 11:56:01 +00:00
logger.info(
'Backtesting with data from %s up to %s (%s days)..',
min_date.isoformat(), max_date.isoformat(), (max_date - min_date).days
)
2018-07-27 21:01:52 +00:00
# Execute backtest and print results
2018-07-28 04:54:33 +00:00
all_results[self.strategy.get_strategy_name()] = self.backtest(
2018-07-27 21:01:52 +00:00
{
'stake_amount': self.config.get('stake_amount'),
'processed': preprocessed,
'max_open_trades': max_open_trades,
'position_stacking': self.config.get('position_stacking', False),
'start_date': min_date,
'end_date': max_date,
2018-07-27 21:01:52 +00:00
}
)
2018-07-28 04:54:33 +00:00
for strategy, results in all_results.items():
2018-06-12 20:29:30 +00:00
2018-07-27 21:01:52 +00:00
if self.config.get('export', False):
self._store_backtest_result(Path(self.config['exportfilename']), results,
strategy if len(self.strategylist) > 1 else None)
print(f"Result for strategy {strategy}")
print(' BACKTESTING REPORT '.center(133, '='))
print(self._generate_text_table(data, results))
2018-07-12 19:19:43 +00:00
print(' SELL REASON STATS '.center(133, '='))
print(self._generate_text_table_sell_reason(data, results))
print(' LEFT OPEN TRADES REPORT '.center(133, '='))
print(self._generate_text_table(data, results.loc[results.open_at_end], True))
print()
2018-07-29 11:07:11 +00:00
if len(all_results) > 1:
# Print Strategy summary table
print(' Strategy Summary '.center(133, '='))
print(self._generate_text_table_strategy(all_results))
print('\nFor more details, please look at the detail tables above')