stable/freqtrade/edge/__init__.py

406 lines
16 KiB
Python
Raw Normal View History

2018-09-24 17:22:30 +00:00
# pragma pylint: disable=W0603
""" Edge positioning package """
2018-09-21 15:41:31 +00:00
import logging
2018-09-24 17:22:30 +00:00
from typing import Any, Dict
2018-09-21 15:41:31 +00:00
import arrow
2018-09-23 02:51:53 +00:00
2018-09-27 10:23:46 +00:00
import numpy as np
import utils_find_1st as utf1st
2018-09-24 17:22:30 +00:00
from pandas import DataFrame
2018-09-21 15:41:31 +00:00
import freqtrade.optimize as optimize
from freqtrade.arguments import Arguments
from freqtrade.arguments import TimeRange
2018-09-21 15:41:31 +00:00
from freqtrade.strategy.interface import SellType
from freqtrade.strategy.resolver import IStrategy, StrategyResolver
from collections import namedtuple
2018-09-23 02:51:53 +00:00
2018-09-21 15:41:31 +00:00
logger = logging.getLogger(__name__)
2018-09-24 17:22:30 +00:00
2018-09-21 15:41:31 +00:00
class Edge():
"""
Calculates Win Rate, Risk Reward Ratio, Expectancy
against historical data for a give set of markets and a strategy
it then adjusts stoploss and position size accordingly
and force it into the strategy
Author: https://github.com/mishaker
"""
2018-09-21 15:41:31 +00:00
config: Dict = {}
_cached_pairs: Dict[str, Any] = {} # Keeps a list of pairs
2018-09-21 15:41:31 +00:00
2018-09-24 17:22:30 +00:00
def __init__(self, config: Dict[str, Any], exchange=None) -> None:
2018-09-21 15:41:31 +00:00
self.config = config
self.exchange = exchange
2018-09-21 15:41:31 +00:00
self.strategy: IStrategy = StrategyResolver(self.config).strategy
self.ticker_interval = self.strategy.ticker_interval
self.tickerdata_to_dataframe = self.strategy.tickerdata_to_dataframe
self.get_timeframe = optimize.get_timeframe
2018-09-26 15:03:10 +00:00
self.advise_sell = self.strategy.advise_sell
self.advise_buy = self.strategy.advise_buy
2018-09-24 17:22:30 +00:00
self.edge_config = self.config.get('edge', {})
# pair info data type
self._pair_info = namedtuple(
'pair_info', 'stoploss, winrate, risk_reward_ratio, required_risk_reward, expectancy')
self._cached_pairs: Dict[str, Any] = {} # Keeps a list of pairs
self._total_capital: float = self.edge_config.get('total_capital_in_stake_currency')
self._allowed_risk: float = self.edge_config.get('allowed_risk')
self._since_number_of_days: int = self.edge_config.get('calculate_since_number_of_days', 14)
self._last_updated: int = 0 # Timestamp of pairs last updated time
self._stoploss_range_min = float(self.edge_config.get('stoploss_range_min', -0.01))
self._stoploss_range_max = float(self.edge_config.get('stoploss_range_max', -0.05))
self._stoploss_range_step = float(self.edge_config.get('stoploss_range_step', -0.001))
# calculating stoploss range
self._stoploss_range = np.arange(
self._stoploss_range_min,
self._stoploss_range_max,
self._stoploss_range_step
)
self._timerange: TimeRange = Arguments.parse_timerange("%s-" % arrow.now().shift(
days=-1 * self._since_number_of_days).format('YYYYMMDD'))
2018-09-21 15:41:31 +00:00
self.fee = self.exchange.get_fee()
def calculate(self) -> bool:
pairs = self.config['exchange']['pair_whitelist']
heartbeat = self.edge_config.get('process_throttle_secs')
2018-09-21 15:41:31 +00:00
if (self._last_updated > 0) and (
2018-09-27 10:23:46 +00:00
self._last_updated + heartbeat > arrow.utcnow().timestamp):
2018-09-21 15:41:31 +00:00
return False
2018-09-26 14:03:51 +00:00
data: Dict[str, Any] = {}
2018-09-21 15:41:31 +00:00
logger.info('Using stake_currency: %s ...', self.config['stake_currency'])
logger.info('Using local backtesting data (using whitelist in given config) ...')
data = optimize.load_data(
self.config['datadir'],
pairs=pairs,
ticker_interval=self.ticker_interval,
2018-11-03 13:33:17 +00:00
refresh_pairs=True,
2018-09-21 15:41:31 +00:00
exchange=self.exchange,
timerange=self._timerange
2018-09-21 15:41:31 +00:00
)
if not data:
logger.critical("No data found. Edge is stopped ...")
2018-09-26 14:03:51 +00:00
return False
2018-09-24 17:22:30 +00:00
2018-09-21 15:41:31 +00:00
preprocessed = self.tickerdata_to_dataframe(data)
# Print timeframe
min_date, max_date = self.get_timeframe(preprocessed)
logger.info(
'Measuring data from %s up to %s (%s days) ...',
min_date.isoformat(),
max_date.isoformat(),
(max_date - min_date).days
)
headers = ['date', 'buy', 'open', 'close', 'sell', 'high', 'low']
2018-09-26 13:20:53 +00:00
trades: list = []
2018-09-21 15:41:31 +00:00
for pair, pair_data in preprocessed.items():
2018-09-24 17:22:30 +00:00
# Sorting dataframe by date and reset index
2018-09-21 15:41:31 +00:00
pair_data = pair_data.sort_values(by=['date'])
pair_data = pair_data.reset_index(drop=True)
2018-09-26 15:09:20 +00:00
2018-09-26 15:03:10 +00:00
ticker_data = self.advise_sell(
self.advise_buy(pair_data, {'pair': pair}), {'pair': pair})[headers].copy()
2018-09-21 15:41:31 +00:00
trades += self._find_trades_for_stoploss_range(ticker_data, pair, self._stoploss_range)
2018-09-21 15:41:31 +00:00
2018-10-05 15:06:17 +00:00
# If no trade found then exit
if len(trades) == 0:
return False
2018-09-24 17:22:30 +00:00
2018-10-05 15:06:17 +00:00
# Fill missing, calculable columns, profit, duration , abs etc.
trades_df = self._fill_calculable_fields(DataFrame(trades))
2018-09-26 13:20:53 +00:00
self._cached_pairs = self._process_expectancy(trades_df)
2018-09-21 15:41:31 +00:00
self._last_updated = arrow.utcnow().timestamp
# Not a nice hack but probably simplest solution:
# When backtest load data it loads the delta between disk and exchange
2018-09-28 12:28:05 +00:00
# The problem is that exchange consider that recent.
# it is but it is incomplete (c.f. _async_get_candle_history)
# So it causes get_signal to exit cause incomplete ticker_hist
2018-09-28 12:28:05 +00:00
# A patch to that would be update _pairs_last_refresh_time of exchange
# so it will download again all pairs
# Another solution is to add new data to klines instead of reassigning it:
# self.klines[pair].update(data) instead of self.klines[pair] = data in exchange package.
# But that means indexing timestamp and having a verification so that
# there is no empty range between two timestaps (recently added and last
# one)
self.exchange._pairs_last_refresh_time = {}
2018-09-21 15:41:31 +00:00
return True
2018-09-24 17:22:30 +00:00
def stake_amount(self, pair: str) -> float:
stoploss = self._cached_pairs[pair].stoploss
2018-09-26 13:20:53 +00:00
allowed_capital_at_risk = round(self._total_capital * self._allowed_risk, 5)
position_size = abs(round((allowed_capital_at_risk / stoploss), 5))
return position_size
def stoploss(self, pair: str) -> float:
return self._cached_pairs[pair].stoploss
2018-09-26 13:20:53 +00:00
def filter(self, pairs) -> list:
final = []
for pair, info in self._cached_pairs.items():
if info.expectancy > float(self.edge_config.get('minimum_expectancy', 0.2)) and \
info.winrate > float(self.edge_config.get('minimum_winrate', 0.60)) and \
pair in pairs:
2018-11-04 17:43:57 +00:00
final.append(pair)
if final:
logger.info(
'Edge validated only %s',
final
)
else:
logger.info('Edge removed all pairs as no pair with minimum expectancy was found !')
return final
2018-09-24 17:22:30 +00:00
2018-10-02 09:55:14 +00:00
def _fill_calculable_fields(self, result: DataFrame) -> DataFrame:
2018-09-21 15:41:31 +00:00
"""
2018-09-26 13:20:53 +00:00
The result frame contains a number of columns that are calculable
2018-10-02 09:53:59 +00:00
from other columns. These are left blank till all rows are added,
2018-09-21 15:41:31 +00:00
to be populated in single vector calls.
Columns to be populated are:
- Profit
- trade duration
- profit abs
2018-09-26 13:20:53 +00:00
:param result Dataframe
:return: result Dataframe
2018-09-21 15:41:31 +00:00
"""
# stake and fees
# stake = 0.015
# 0.05% is 0.0005
# fee = 0.001
stake = self.config.get('stake_amount')
fee = self.fee
2018-10-05 15:06:17 +00:00
2018-09-21 15:41:31 +00:00
open_fee = fee / 2
close_fee = fee / 2
2018-09-26 13:20:53 +00:00
result['trade_duration'] = result['close_time'] - result['open_time']
2018-09-21 15:41:31 +00:00
2018-09-27 10:23:46 +00:00
result['trade_duration'] = result['trade_duration'].map(
lambda x: int(x.total_seconds() / 60))
2018-09-26 14:50:17 +00:00
# Spends, Takes, Profit, Absolute Profit
2018-09-26 13:20:53 +00:00
2018-09-21 15:41:31 +00:00
# Buy Price
2018-09-26 13:20:53 +00:00
result['buy_vol'] = stake / result['open_rate'] # How many target are we buying
result['buy_fee'] = stake * open_fee
result['buy_spend'] = stake + result['buy_fee'] # How much we're spending
2018-09-21 15:41:31 +00:00
# Sell price
2018-09-26 13:20:53 +00:00
result['sell_sum'] = result['buy_vol'] * result['close_rate']
result['sell_fee'] = result['sell_sum'] * close_fee
result['sell_take'] = result['sell_sum'] - result['sell_fee']
2018-09-21 15:41:31 +00:00
# profit_percent
2018-09-27 10:23:46 +00:00
result['profit_percent'] = (result['sell_take'] - result['buy_spend']) / result['buy_spend']
2018-09-26 14:50:17 +00:00
2018-09-21 15:41:31 +00:00
# Absolute profit
2018-09-26 13:20:53 +00:00
result['profit_abs'] = result['sell_take'] - result['buy_spend']
2018-09-21 15:41:31 +00:00
2018-09-26 13:20:53 +00:00
return result
2018-09-21 15:41:31 +00:00
def _process_expectancy(self, results: DataFrame) -> Dict[str, Any]:
2018-09-21 15:41:31 +00:00
"""
This calculates WinRate, Required Risk Reward, Risk Reward and Expectancy of all pairs
2018-09-24 17:22:30 +00:00
The calulation will be done per pair and per strategy.
2018-09-21 15:41:31 +00:00
"""
# Removing pairs having less than min_trades_number
min_trades_number = self.edge_config.get('min_trade_number', 10)
results = results.groupby(['pair', 'stoploss']).filter(lambda x: len(x) > min_trades_number)
2018-09-21 15:41:31 +00:00
###################################
2018-09-24 17:22:30 +00:00
# Removing outliers (Only Pumps) from the dataset
2018-09-21 15:41:31 +00:00
# The method to detect outliers is to calculate standard deviation
# Then every value more than (standard deviation + 2*average) is out (pump)
#
# Removing Pumps
if self.edge_config.get('remove_pumps', False):
results = results.groupby(['pair', 'stoploss']).apply(
lambda x: x[x['profit_abs'] < 2 * x['profit_abs'].std() + x['profit_abs'].mean()])
2018-09-21 15:41:31 +00:00
##########################################################################
# Removing trades having a duration more than X minutes (set in config)
max_trade_duration = self.edge_config.get('max_trade_duration_minute', 1440)
2018-09-21 15:41:31 +00:00
results = results[results.trade_duration < max_trade_duration]
#######################################################################
2018-10-18 09:09:10 +00:00
if results.empty:
return {}
2018-10-18 09:09:10 +00:00
groupby_aggregator = {
'profit_abs': [
('nb_trades', 'count'), # number of all trades
('profit_sum', lambda x: x[x > 0].sum()), # cumulative profit of all winning trades
('loss_sum', lambda x: abs(x[x < 0].sum())), # cumulative loss of all losing trades
('nb_win_trades', lambda x: x[x > 0].count()) # number of winning trades
],
'trade_duration': [('avg_trade_duration', 'mean')]
}
# Group by (pair and stoploss) by applying above aggregator
df = results.groupby(['pair', 'stoploss'])['profit_abs', 'trade_duration'].agg(
groupby_aggregator).reset_index(col_level=1)
# Dropping level 0 as we don't need it
df.columns = df.columns.droplevel(0)
# Calculating number of losing trades, average win and average loss
df['nb_loss_trades'] = df['nb_trades'] - df['nb_win_trades']
df['average_win'] = df['profit_sum'] / df['nb_win_trades']
df['average_loss'] = df['loss_sum'] / df['nb_loss_trades']
# Win rate = number of profitable trades / number of trades
df['winrate'] = df['nb_win_trades'] / df['nb_trades']
# risk_reward_ratio = average win / average loss
df['risk_reward_ratio'] = df['average_win'] / df['average_loss']
# required_risk_reward = (1 / winrate) - 1
df['required_risk_reward'] = (1 / df['winrate']) - 1
# expectancy = (risk_reward_ratio * winrate) - (lossrate)
df['expectancy'] = (df['risk_reward_ratio'] * df['winrate']) - (1 - df['winrate'])
# sort by expectancy and stoploss
df = df.sort_values(by=['expectancy', 'stoploss'], ascending=False).groupby(
2018-10-18 09:09:10 +00:00
'pair').first().sort_values(by=['expectancy'], ascending=False).reset_index()
final = {}
for x in df.itertuples():
2018-11-04 17:43:57 +00:00
info = {
'stoploss': x.stoploss,
'winrate': x.winrate,
'risk_reward_ratio': x.risk_reward_ratio,
'required_risk_reward': x.required_risk_reward,
'expectancy': x.expectancy
}
final[x.pair] = self._pair_info(**info)
2018-09-24 17:22:30 +00:00
# Returning a list of pairs in order of "expectancy"
return final
2018-09-21 15:41:31 +00:00
2018-09-26 13:20:53 +00:00
def _find_trades_for_stoploss_range(self, ticker_data, pair, stoploss_range):
buy_column = ticker_data['buy'].values
sell_column = ticker_data['sell'].values
date_column = ticker_data['date'].values
ohlc_columns = ticker_data[['open', 'high', 'low', 'close']].values
2018-09-26 14:50:17 +00:00
2018-09-26 13:20:53 +00:00
result: list = []
for stoploss in stoploss_range:
result += self._detect_next_stop_or_sell_point(
2018-09-26 14:50:17 +00:00
buy_column, sell_column, date_column, ohlc_columns, round(stoploss, 6), pair
2018-09-27 10:23:46 +00:00
)
2018-09-26 13:20:53 +00:00
return result
def _detect_next_stop_or_sell_point(
2018-09-26 14:50:17 +00:00
self,
buy_column,
sell_column,
date_column,
ohlc_columns,
stoploss,
pair,
2018-09-27 10:23:46 +00:00
start_point=0):
2018-09-26 14:50:17 +00:00
2018-09-26 13:20:53 +00:00
result: list = []
open_trade_index = utf1st.find_1st(buy_column, 1, utf1st.cmp_equal)
# return empty if we don't find trade entry (i.e. buy==1) or
# we find a buy but at the of array
if open_trade_index == -1 or open_trade_index == len(buy_column) - 1:
2018-09-26 13:20:53 +00:00
return []
else:
open_trade_index += 1 # when a buy signal is seen,
# trade opens in reality on the next candle
2018-09-26 13:20:53 +00:00
stop_price_percentage = stoploss + 1
open_price = ohlc_columns[open_trade_index, 0]
2018-09-26 13:20:53 +00:00
stop_price = (open_price * stop_price_percentage)
# Searching for the index where stoploss is hit
2018-09-27 10:23:46 +00:00
stop_index = utf1st.find_1st(
ohlc_columns[open_trade_index:, 2], stop_price, utf1st.cmp_smaller)
2018-09-26 13:20:53 +00:00
# If we don't find it then we assume stop_index will be far in future (infinite number)
if stop_index == -1:
stop_index = float('inf')
# Searching for the index where sell is hit
sell_index = utf1st.find_1st(sell_column[open_trade_index:], 1, utf1st.cmp_equal)
2018-09-26 13:20:53 +00:00
# If we don't find it then we assume sell_index will be far in future (infinite number)
if sell_index == -1:
sell_index = float('inf')
# Check if we don't find any stop or sell point (in that case trade remains open)
# It is not interesting for Edge to consider it so we simply ignore the trade
# And stop iterating there is no more entry
2018-09-26 13:20:53 +00:00
if stop_index == sell_index == float('inf'):
return []
if stop_index <= sell_index:
exit_index = open_trade_index + stop_index
2018-09-26 13:20:53 +00:00
exit_type = SellType.STOP_LOSS
exit_price = stop_price
elif stop_index > sell_index:
# if exit is SELL then we exit at the next candle
2018-09-26 13:20:53 +00:00
exit_index = open_trade_index + sell_index + 1
# check if we have the next candle
if len(ohlc_columns) - 1 < exit_index:
return []
2018-09-26 13:20:53 +00:00
exit_type = SellType.SELL_SIGNAL
exit_price = ohlc_columns[exit_index, 0]
2018-09-26 13:20:53 +00:00
2018-09-26 14:03:51 +00:00
trade = {'pair': pair,
'stoploss': stoploss,
'profit_percent': '',
'profit_abs': '',
'open_time': date_column[open_trade_index],
2018-09-26 14:03:51 +00:00
'close_time': date_column[exit_index],
'open_index': start_point + open_trade_index,
2018-09-26 14:03:51 +00:00
'close_index': start_point + exit_index,
'trade_duration': '',
'open_rate': round(open_price, 15),
'close_rate': round(exit_price, 15),
'exit_type': exit_type
}
2018-09-26 13:20:53 +00:00
result.append(trade)
# Calling again the same function recursively but giving
# it a view of exit_index till the end of array
return result + self._detect_next_stop_or_sell_point(
2018-09-26 13:20:53 +00:00
buy_column[exit_index:],
sell_column[exit_index:],
date_column[exit_index:],
ohlc_columns[exit_index:],
stoploss,
pair,
(start_point + exit_index)
)