Merge pull request #7260 from JohanVlugt/develop

Example FreqAI hybrid strategy
This commit is contained in:
Matthias 2022-08-29 06:34:45 +02:00 committed by GitHub
commit 8be8a12cc4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 259 additions and 1 deletions

View File

@ -75,7 +75,6 @@
"weight_factor": 0.9,
"principal_component_analysis": false,
"use_SVM_to_remove_outliers": true,
"stratify_training_data": 0,
"indicator_max_period_candles": 20,
"indicator_periods_candles": [10, 20]
},

View File

@ -0,0 +1,259 @@
import logging
import numpy as np
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from technical import qtpylib
from freqtrade.strategy import IntParameter, IStrategy, merge_informative_pair
logger = logging.getLogger(__name__)
class FreqaiExampleHybridStrategy(IStrategy):
"""
Example of a hybrid FreqAI strat, designed to illustrate how a user may employ
FreqAI to bolster a typical Freqtrade strategy.
Launching this strategy would be:
freqtrade trade --strategy FreqaiExampleHyridStrategy --strategy-path freqtrade/templates
--freqaimodel CatboostClassifier --config config_examples/config_freqai.example.json
or the user simply adds this to their config:
"freqai": {
"enabled": true,
"purge_old_models": true,
"train_period_days": 15,
"identifier": "uniqe-id",
"feature_parameters": {
"include_timeframes": [
"3m",
"15m",
"1h"
],
"include_corr_pairlist": [
"BTC/USDT",
"ETH/USDT"
],
"label_period_candles": 20,
"include_shifted_candles": 2,
"DI_threshold": 0.9,
"weight_factor": 0.9,
"principal_component_analysis": false,
"use_SVM_to_remove_outliers": true,
"indicator_max_period_candles": 20,
"indicator_periods_candles": [10, 20]
},
"data_split_parameters": {
"test_size": 0,
"random_state": 1
},
"model_training_parameters": {
"n_estimators": 800
}
},
Thanks to @smarmau and @johanvulgt for developing and sharing the strategy.
"""
minimal_roi = {
"60": 0.01,
"30": 0.02,
"0": 0.04
}
plot_config = {
'main_plot': {
'tema': {},
},
'subplots': {
"MACD": {
'macd': {'color': 'blue'},
'macdsignal': {'color': 'orange'},
},
"RSI": {
'rsi': {'color': 'red'},
},
"Up_or_down": {
'&s-up_or_down': {'color': 'green'},
}
}
}
process_only_new_candles = True
stoploss = -0.05
use_exit_signal = True
startup_candle_count: int = 300
can_short = True
# Hyperoptable parameters
buy_rsi = IntParameter(low=1, high=50, default=30, space='buy', optimize=True, load=True)
sell_rsi = IntParameter(low=50, high=100, default=70, space='sell', optimize=True, load=True)
short_rsi = IntParameter(low=51, high=100, default=70, space='sell', optimize=True, load=True)
exit_short_rsi = IntParameter(low=1, high=50, default=30, space='buy', optimize=True, load=True)
# FreqAI required function, leave as is or add additional informatives to existing structure.
def informative_pairs(self):
whitelist_pairs = self.dp.current_whitelist()
corr_pairs = self.config["freqai"]["feature_parameters"]["include_corr_pairlist"]
informative_pairs = []
for tf in self.config["freqai"]["feature_parameters"]["include_timeframes"]:
for pair in whitelist_pairs:
informative_pairs.append((pair, tf))
for pair in corr_pairs:
if pair in whitelist_pairs:
continue # avoid duplication
informative_pairs.append((pair, tf))
return informative_pairs
# FreqAI required function, user can add or remove indicators, but general structure
# must stay the same.
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
"""
User feeds these indicators to FreqAI to train a classifier to decide
if the market will go up or down.
:param pair: pair to be used as informative
:param df: strategy dataframe which will receive merges from informatives
:param tf: timeframe of the dataframe which will modify the feature names
:param informative: the dataframe associated with the informative pair
"""
coin = pair.split('/')[0]
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
t = int(t)
informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
informative[f"%-{coin}sma-period_{t}"] = ta.SMA(informative, timeperiod=t)
informative[f"%-{coin}ema-period_{t}"] = ta.EMA(informative, timeperiod=t)
informative[f"%-{coin}roc-period_{t}"] = ta.ROC(informative, timeperiod=t)
informative[f"%-{coin}relative_volume-period_{t}"] = (
informative["volume"] / informative["volume"].rolling(t).mean()
)
# FreqAI needs the following lines in order to detect features and automatically
# expand upon them.
indicators = [col for col in informative if col.startswith("%")]
# This loop duplicates and shifts all indicators to add a sense of recency to data
for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
if n == 0:
continue
informative_shift = informative[indicators].shift(n)
informative_shift = informative_shift.add_suffix("_shift-" + str(n))
informative = pd.concat((informative, informative_shift), axis=1)
df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
skip_columns = [
(s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
]
df = df.drop(columns=skip_columns)
# User can set the "target" here (in present case it is the
# "up" or "down")
if set_generalized_indicators:
# User "looks into the future" here to figure out if the future
# will be "up" or "down". This same column name is available to
# the user
df['&s-up_or_down'] = np.where(df["close"].shift(-50) >
df["close"], 'up', 'down')
return df
# flake8: noqa: C901
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
# User creates their own custom strat here. Present example is a supertrend
# based strategy.
dataframe = self.freqai.start(dataframe, metadata, self)
# TA indicators to combine with the Freqai targets
# 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, df: DataFrame, metadata: dict) -> DataFrame:
df.loc[
(
# Signal: RSI crosses above 30
(qtpylib.crossed_above(df['rsi'], self.buy_rsi.value)) &
(df['tema'] <= df['bb_middleband']) & # Guard: tema below BB middle
(df['tema'] > df['tema'].shift(1)) & # Guard: tema is raising
(df['volume'] > 0) & # Make sure Volume is not 0
(df['do_predict'] == 1) & # Make sure Freqai is confident in the prediction
# Only enter trade if Freqai thinks the trend is in this direction
(df['&s-up_or_down'] == 'up')
),
'enter_long'] = 1
df.loc[
(
# Signal: RSI crosses above 70
(qtpylib.crossed_above(df['rsi'], self.short_rsi.value)) &
(df['tema'] > df['bb_middleband']) & # Guard: tema above BB middle
(df['tema'] < df['tema'].shift(1)) & # Guard: tema is falling
(df['volume'] > 0) & # Make sure Volume is not 0
(df['do_predict'] == 1) & # Make sure Freqai is confident in the prediction
# Only enter trade if Freqai thinks the trend is in this direction
(df['&s-up_or_down'] == 'down')
),
'enter_short'] = 1
return df
def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame:
df.loc[
(
# Signal: RSI crosses above 70
(qtpylib.crossed_above(df['rsi'], self.sell_rsi.value)) &
(df['tema'] > df['bb_middleband']) & # Guard: tema above BB middle
(df['tema'] < df['tema'].shift(1)) & # Guard: tema is falling
(df['volume'] > 0) # Make sure Volume is not 0
),
'exit_long'] = 1
df.loc[
(
# Signal: RSI crosses above 30
(qtpylib.crossed_above(df['rsi'], self.exit_short_rsi.value)) &
# Guard: tema below BB middle
(df['tema'] <= df['bb_middleband']) &
(df['tema'] > df['tema'].shift(1)) & # Guard: tema is raising
(df['volume'] > 0) # Make sure Volume is not 0
),
'exit_short'] = 1
return df