freqtrade-实战 7- 超参数优化终极指南
一、优化说明
We'll cover the important parts of Freqtrade hyperparameter optimization, including:
我们将介绍 Freqtrade 超参数优化的重要部分，包括：
What can be optimized? 哪些可以优化？
Understanding Loss Functions: The goal of your optimization.
了解损失函数：优化的目标。
Fine-tuning Guards, Triggers, and Indicator Parameters for Buy/Sell signals and more.
微调 Buy/Sell 信号的 Guards、Triggers 和 Indicator 参数等。
Using the Optimize Command with different arguments.
使用具有不同参数的 Optimize 命令。
Exploring the Optimize-Show and Optimize-List features.
探索 Optimize-Show 和 Optimize-List 功能。
Applying Optimized Settings to Backtest and Live/Dry Trades.
将优化设置应用于回溯测试和 Live/Dry 交易。
Solutions for fixing Out-of-Memory Errors.
修复内存不足错误的解决方案。
二、超参数优化
# The Ultimate Guide to Freqtrade Hyperparameter Optimization: Boost Your Trading Strategy!
## 1. Running Hyperopt with Smaller Search Space
Link: https://www.freqtrade.io/en/stable/hyperopt/#running-hyperopt-with-smaller-search-space
## 2. Loss-functions
Link: https://www.freqtrade.io/en/2024.4/hyperopt/#loss-functions
## 3. Parameter options
Link: https://www.freqtrade.io/en/2024.4/hyperopt/#parameter-options
## 4. Hyperopt command
freqtrade hyperopt --strategy AwesomeStrategy3 --spaces buy sell roi stoploss --hyperopt-loss SharpeHyperOptLossDaily --config user_data/config_binance_spot.json --timeframe 1h --timeframe-detail 5m -e 100 --timerange 20240201-20240801
## 5. Default ROI Search Space
Link: https://www.freqtrade.io/en/2024.4/hyperopt/#default-roi-search-space
## 6. Default Stoploss Search Space
Link: https://www.freqtrade.io/en/2024.4/hyperopt/#default-stoploss-search-space
## 7. Guards and Triggers
Link: https://www.freqtrade.io/en/stable/hyperopt/#configure-your-guards-and-triggers
## 8. Parameter types
Link: https://www.freqtrade.io/en/stable/hyperopt/#parameter-types
## 9. Optimizing an indicator parameter
Link: https://www.freqtrade.io/en/stable/hyperopt/#optimizing-an-indicator-parameter
## 10. Reproducible results
Link: https://www.freqtrade.io/en/stable/hyperopt/#reproducible-results
## 11. List Hyperopt results
Link: https://www.freqtrade.io/en/stable/utils/#list-hyperopt-results
freqtrade hyperopt-list --profitable --no-details
## 12. Show details of Hyperopt results
Link: https://www.freqtrade.io/en/stable/utils/#show-details-of-hyperopt-results
freqtrade hyperopt-show -n 61
## 13. Backtesting
freqtrade backtesting --strategy AwesomeStrategy3 --timeframe 1h --timerange 20240201-20240801 --breakdown month -c user_data/config_binance_spot.json --timeframe-detail 5m
## 14. Out of Memory errors
Link: https://www.freqtrade.io/en/stable/hyperopt/#out-of-memory-errorsAwesomeStrategy1.py 策略文件：
# pragma pylint: disable=missing-docstring, invalid-name, pointless-string-statement
# flake8: noqa: F401
# isort: skip_file
# --- Do not remove these libs ---
import numpy as np
import pandas as pd
from pandas import DataFrame
from datetime import datetime
from typing import Optional, Union
from freqtrade.strategy import (BooleanParameter, CategoricalParameter, DecimalParameter,
IntParameter, IStrategy, merge_informative_pair)
# --------------------------------
# Add your lib to import here
import talib.abstract as ta
import pandas_ta as pta
from technical import qtpylib
class AwesomeStrategy1(IStrategy):
"""
This is a strategy template to get you started.
More information in https://www.freqtrade.io/en/latest/strategy-customization/
You can:
:return: a Dataframe with all mandatory indicators for the strategies
- Rename the class name (Do not forget to update class_name)
- Add any methods you want to build your strategy
- Add any lib you need to build your strategy
You must keep:
- the lib in the section "Do not remove these libs"
- the methods: populate_indicators, populate_entry_trend, populate_exit_trend
You should keep:
- timeframe, minimal_roi, stoploss, trailing_*
"""
# Strategy interface version - allow new iterations of the strategy interface.
# Check the documentation or the Sample strategy to get the latest version.
INTERFACE_VERSION = 3
# Optimal timeframe for the strategy.
timeframe = '5m'
# Can this strategy go short?
can_short: bool = False
# Minimal ROI designed for the strategy.
# This attribute will be overridden if the config file contains "minimal_roi".
minimal_roi = {
"60": 0.01,
"30": 0.02,
"0": 0.04
}
# Optimal stoploss designed for the strategy.
# This attribute will be overridden if the config file contains "stoploss".
stoploss = -0.10
# Trailing stoploss
trailing_stop = False
# trailing_only_offset_is_reached = False
# trailing_stop_positive = 0.01
# trailing_stop_positive_offset = 0.0 # Disabled / not configured
# Run "populate_indicators()" only for new candle.
process_only_new_candles = True
# These values can be overridden in the config.
use_exit_signal = True
exit_profit_only = False
ignore_roi_if_entry_signal = False
# Number of candles the strategy requires before producing valid signals
startup_candle_count: int = 150
# Strategy parameters
buy_rsi = IntParameter(10, 40, default=30, space="buy", optimize=True, load=True)
sell_rsi = IntParameter(60, 90, default=70, space="sell", optimize=True, load=True)
# Optional order type mapping.
order_types = {
'entry': 'limit',
'exit': 'limit',
'stoploss': 'market',
'stoploss_on_exchange': False
}
# Optional order time in force.
order_time_in_force = {
'entry': 'GTC',
'exit': 'GTC'
}
@property
def plot_config(self):
return {
# Main plot indicators (Moving averages, ...)
'main_plot': {
'tema': {},
'sar': {'color': 'white'},
},
'subplots': {
# Subplots - each dict defines one additional plot
"MACD": {
'macd': {'color': 'blue'},
'macdsignal': {'color': 'orange'},
},
"RSI": {
'rsi': {'color': 'red'},
}
}
}
def informative_pairs(self):
"""
Define additional, informative pair/interval combinations to be cached from the exchange.
These pair/interval combinations are non-tradeable, unless they are part
of the whitelist as well.
For more information, please consult the documentation
:return: List of tuples in the format (pair, interval)
Sample: return [("ETH/USDT", "5m"),
("BTC/USDT", "15m"),
]
"""
return []
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
# RSI
dataframe['rsi'] = ta.RSI(dataframe)
# Bollinger Bands
bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2)
dataframe['bb_lowerband'] = bollinger['lower']
dataframe['bb_middleband'] = bollinger['mid']
dataframe['bb_upperband'] = bollinger['upper']
dataframe["bb_percent"] = (
(dataframe["close"] - dataframe["bb_lowerband"]) /
(dataframe["bb_upperband"] - dataframe["bb_lowerband"])
)
dataframe["bb_width"] = (
(dataframe["bb_upperband"] - dataframe["bb_lowerband"]) / dataframe["bb_middleband"]
)
# TEMA - Triple Exponential Moving Average
dataframe['tema'] = ta.TEMA(dataframe, timeperiod=9)
return dataframe
def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
dataframe.loc[
(
(qtpylib.crossed_above(dataframe['rsi'], self.buy_rsi.value)) & # Signal: RSI crosses above buy_rsi
(dataframe['tema'] <= dataframe['bb_middleband']) & # Guard: tema below BB middle
(dataframe['tema'] > dataframe['tema'].shift(1)) & # Guard: tema is raising
(dataframe['volume'] > 0) # Make sure Volume is not 0
),
'enter_long'] = 1
return dataframe
def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
dataframe.loc[
(
(qtpylib.crossed_above(dataframe['rsi'], self.sell_rsi.value)) & # Signal: RSI crosses above sell_rsi
(dataframe['tema'] > dataframe['bb_middleband']) & # Guard: tema above BB middle
(dataframe['tema'] < dataframe['tema'].shift(1)) & # Guard: tema is falling
(dataframe['volume'] > 0) # Make sure Volume is not 0
),
'exit_long'] = 1
return dataframe
AwesomeStrategy2.py 策略文件：
# pragma pylint: disable=missing-docstring, invalid-name, pointless-string-statement
# flake8: noqa: F401
# isort: skip_file
# --- Do not remove these libs ---
import numpy as np
import pandas as pd
from pandas import DataFrame
from datetime import datetime
from typing import Optional, Union
from functools import reduce
from freqtrade.strategy import (BooleanParameter, CategoricalParameter, DecimalParameter,
IntParameter, IStrategy, merge_informative_pair)
# --------------------------------
# Add your lib to import here
import talib.abstract as ta
import pandas_ta as pta
from technical import qtpylib
class AwesomeStrategy2(IStrategy):
"""
This is a strategy template to get you started.
More information in https://www.freqtrade.io/en/latest/strategy-customization/
You can:
:return: a Dataframe with all mandatory indicators for the strategies
- Rename the class name (Do not forget to update class_name)
- Add any methods you want to build your strategy
- Add any lib you need to build your strategy
You must keep:
- the lib in the section "Do not remove these libs"
- the methods: populate_indicators, populate_entry_trend, populate_exit_trend
You should keep:
- timeframe, minimal_roi, stoploss, trailing_*
"""
# Strategy interface version - allow new iterations of the strategy interface.
# Check the documentation or the Sample strategy to get the latest version.
INTERFACE_VERSION = 3
# Optimal timeframe for the strategy.
timeframe = '5m'
# Can this strategy go short?
can_short: bool = False
# Minimal ROI designed for the strategy.
# This attribute will be overridden if the config file contains "minimal_roi".
minimal_roi = {
"60": 0.01,
"30": 0.02,
"0": 0.04
}
# Optimal stoploss designed for the strategy.
# This attribute will be overridden if the config file contains "stoploss".
stoploss = -0.10
# Trailing stoploss
trailing_stop = False
# trailing_only_offset_is_reached = False
# trailing_stop_positive = 0.01
# trailing_stop_positive_offset = 0.0 # Disabled / not configured
# Run "populate_indicators()" only for new candle.
process_only_new_candles = True
# These values can be overridden in the config.
use_exit_signal = True
exit_profit_only = False
ignore_roi_if_entry_signal = False
# Number of candles the strategy requires before producing valid signals
startup_candle_count: int = 150
# Strategy parameters
buy_rsi = IntParameter(10, 40, default=30, space="buy")
sell_rsi = IntParameter(60, 90, default=70, space="sell")
buy_adx_enabled = BooleanParameter(default=True, space="buy")
# buy_adx_enabled = CategoricalParameter([True, False], default=True, space="buy")
buy_adx = DecimalParameter(20, 40, decimals=1, default=30.1, space="buy")
# Optional order type mapping.
order_types = {
'entry': 'limit',
'exit': 'limit',
'stoploss': 'market',
'stoploss_on_exchange': False
}
# Optional order time in force.
order_time_in_force = {
'entry': 'GTC',
'exit': 'GTC'
}
@property
def plot_config(self):
return {
# Main plot indicators (Moving averages, ...)
'main_plot': {
'tema': {},
'sar': {'color': 'white'},
},
'subplots': {
# Subplots - each dict defines one additional plot
"MACD": {
'macd': {'color': 'blue'},
'macdsignal': {'color': 'orange'},
},
"RSI": {
'rsi': {'color': 'red'},
}
}
}
def informative_pairs(self):
"""
Define additional, informative pair/interval combinations to be cached from the exchange.
These pair/interval combinations are non-tradeable, unless they are part
of the whitelist as well.
For more information, please consult the documentation
:return: List of tuples in the format (pair, interval)
Sample: return [("ETH/USDT", "5m"),
("BTC/USDT", "15m"),
]
"""
return []
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
# ADX
dataframe['adx'] = ta.ADX(dataframe)
# RSI
dataframe['rsi'] = ta.RSI(dataframe)
# Bollinger Bands
bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2)
dataframe['bb_lowerband'] = bollinger['lower']
dataframe['bb_middleband'] = bollinger['mid']
dataframe['bb_upperband'] = bollinger['upper']
dataframe["bb_percent"] = (
(dataframe["close"] - dataframe["bb_lowerband"]) /
(dataframe["bb_upperband"] - dataframe["bb_lowerband"])
)
dataframe["bb_width"] = (
(dataframe["bb_upperband"] - dataframe["bb_lowerband"]) / dataframe["bb_middleband"]
)
# TEMA - Triple Exponential Moving Average
dataframe['tema'] = ta.TEMA(dataframe, timeperiod=9)
return dataframe
def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
conditions = []
if self.buy_adx_enabled.value:
conditions.append(dataframe['adx'] > self.buy_adx.value)
conditions.append(
(
(qtpylib.crossed_above(dataframe['rsi'], self.buy_rsi.value)) & # Signal: RSI crosses above buy_rsi
(dataframe['tema'] <= dataframe['bb_middleband']) & # Guard: tema below BB middle
(dataframe['tema'] > dataframe['tema'].shift(1)) & # Guard: tema is raising
(dataframe['volume'] > 0) # Make sure Volume is not 0
)
)
if conditions:
dataframe.loc[
reduce(lambda x, y: x & y, conditions),
'enter_long'] = 1
return dataframe
def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
dataframe.loc[
(
(qtpylib.crossed_above(dataframe['rsi'], self.sell_rsi.value)) & # Signal: RSI crosses above sell_rsi
(dataframe['tema'] > dataframe['bb_middleband']) & # Guard: tema above BB middle
(dataframe['tema'] < dataframe['tema'].shift(1)) & # Guard: tema is falling
(dataframe['volume'] > 0) # Make sure Volume is not 0
),
'exit_long'] = 1
return dataframe
AwesomeStrategy3.py 策略文件：
# pragma pylint: disable=missing-docstring, invalid-name, pointless-string-statement
# flake8: noqa: F401
# isort: skip_file
# --- Do not remove these libs ---
import numpy as np
import pandas as pd
from pandas import DataFrame
from datetime import datetime
from typing import Optional, Union
from functools import reduce
from freqtrade.strategy import (BooleanParameter, CategoricalParameter, DecimalParameter,
IntParameter, IStrategy, merge_informative_pair)
# --------------------------------
# Add your lib to import here
import talib.abstract as ta
import pandas_ta as pta
from technical import qtpylib
class AwesomeStrategy3(IStrategy):
"""
This is a strategy template to get you started.
More information in https://www.freqtrade.io/en/latest/strategy-customization/
You can:
:return: a Dataframe with all mandatory indicators for the strategies
- Rename the class name (Do not forget to update class_name)
- Add any methods you want to build your strategy
- Add any lib you need to build your strategy
You must keep:
- the lib in the section "Do not remove these libs"
- the methods: populate_indicators, populate_entry_trend, populate_exit_trend
You should keep:
- timeframe, minimal_roi, stoploss, trailing_*
"""
# Strategy interface version - allow new iterations of the strategy interface.
# Check the documentation or the Sample strategy to get the latest version.
INTERFACE_VERSION = 3
# Optimal timeframe for the strategy.
timeframe = '5m'
# Can this strategy go short?
can_short: bool = False
# Minimal ROI designed for the strategy.
# This attribute will be overridden if the config file contains "minimal_roi".
minimal_roi = {
"60": 0.01,
"30": 0.02,
"0": 0.04
}
# Optimal stoploss designed for the strategy.
# This attribute will be overridden if the config file contains "stoploss".
stoploss = -0.10
# Trailing stoploss
trailing_stop = False
# trailing_only_offset_is_reached = False
# trailing_stop_positive = 0.01
# trailing_stop_positive_offset = 0.0 # Disabled / not configured
# Run "populate_indicators()" only for new candle.
process_only_new_candles = True
# These values can be overridden in the config.
use_exit_signal = True
exit_profit_only = False
ignore_roi_if_entry_signal = False
# Number of candles the strategy requires before producing valid signals
startup_candle_count: int = 150
# Strategy parameters
buy_rsi = IntParameter(10, 40, default=30, space="buy")
sell_rsi = IntParameter(60, 90, default=70, space="sell")
buy_adx_enabled = BooleanParameter(default=True, space="buy")
# buy_adx_enabled = CategoricalParameter([True, False], default=True, space="buy")
buy_adx = DecimalParameter(20, 40, decimals=1, default=30.1, space="buy")
buy_tema = IntParameter(5, 30, default=9, space="buy")
# Optional order type mapping.
order_types = {
'entry': 'limit',
'exit': 'limit',
'stoploss': 'market',
'stoploss_on_exchange': False
}
# Optional order time in force.
order_time_in_force = {
'entry': 'GTC',
'exit': 'GTC'
}
@property
def plot_config(self):
return {
# Main plot indicators (Moving averages, ...)
'main_plot': {
'tema': {},
'sar': {'color': 'white'},
},
'subplots': {
# Subplots - each dict defines one additional plot
"MACD": {
'macd': {'color': 'blue'},
'macdsignal': {'color': 'orange'},
},
"RSI": {
'rsi': {'color': 'red'},
}
}
}
def informative_pairs(self):
"""
Define additional, informative pair/interval combinations to be cached from the exchange.
These pair/interval combinations are non-tradeable, unless they are part
of the whitelist as well.
For more information, please consult the documentation
:return: List of tuples in the format (pair, interval)
Sample: return [("ETH/USDT", "5m"),
("BTC/USDT", "15m"),
]
"""
return []
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
# ADX
dataframe['adx'] = ta.ADX(dataframe)
# RSI
dataframe['rsi'] = ta.RSI(dataframe)
# Bollinger Bands
bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2)
dataframe['bb_lowerband'] = bollinger['lower']
dataframe['bb_middleband'] = bollinger['mid']
dataframe['bb_upperband'] = bollinger['upper']
dataframe["bb_percent"] = (
(dataframe["close"] - dataframe["bb_lowerband"]) /
(dataframe["bb_upperband"] - dataframe["bb_lowerband"])
)
dataframe["bb_width"] = (
(dataframe["bb_upperband"] - dataframe["bb_lowerband"]) / dataframe["bb_middleband"]
)
# TEMA - Triple Exponential Moving Average
for val in self.buy_tema.range:
dataframe[f'tema_{val}'] = ta.TEMA(dataframe, timeperiod=val)
return dataframe
def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
conditions = []
if self.buy_adx_enabled.value:
conditions.append(dataframe['adx'] > self.buy_adx.value)
conditions.append(
(
(qtpylib.crossed_above(dataframe['rsi'], self.buy_rsi.value)) & # Signal: RSI crosses above buy_rsi
(dataframe[f'tema_{self.buy_tema.value}'] <= dataframe['bb_middleband']) & # Guard: tema below BB middle
(dataframe[f'tema_{self.buy_tema.value}'] > dataframe[f'tema_{self.buy_tema.value}'].shift(1)) & # Guard: tema is raising
(dataframe['volume'] > 0) # Make sure Volume is not 0
)
)
if conditions:
dataframe.loc[
reduce(lambda x, y: x & y, conditions),
'enter_long'] = 1
return dataframe
def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
dataframe.loc[
(
(qtpylib.crossed_above(dataframe['rsi'], self.sell_rsi.value)) & # Signal: RSI crosses above sell_rsi
(dataframe[f'tema_{self.buy_tema.value}'] > dataframe['bb_middleband']) & # Guard: tema above BB middle
(dataframe[f'tema_{self.buy_tema.value}'] < dataframe[f'tema_{self.buy_tema.value}'].shift(1)) & # Guard: tema is falling
(dataframe['volume'] > 0) # Make sure Volume is not 0
),
'exit_long'] = 1
return dataframe
相关文章：
05 The Ultimate Guide to Freqtrade Hyperparameter Optimization: Boost Your Trading Strategy!
为者常成，行者常至
自由转载-非商用-非衍生-保持署名（创意共享3.0许可证）
