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

add dynamic trade expiration time

Browse Source
This commit is contained in:
longyu 2022-11-11 22:33:11 +01:00
parent a541943edf
commit d6ed8f1980
2 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
freqtrade/freqai/data_kitchen.py
View File

@ -244,7 +244,7 @@ class FreqaiDataKitchen:
self.data["filter_drop_index_training"] = drop_index self.data["filter_drop_index_training"] = drop_index
else: else:
if len(self.data['constant_features_list']): if len(self.data.get('constant_features_list', [])):
filtered_df = self.check_pred_labels(filtered_df) filtered_df = self.check_pred_labels(filtered_df)
# we are backtesting so we need to preserve row number to send back to strategy, # we are backtesting so we need to preserve row number to send back to strategy,
# so now we use do_predict to avoid any prediction based on a NaN # so now we use do_predict to avoid any prediction based on a NaN

20
user_data/strategies/FreqaiBinaryClassStrategy_v4.py
View File

@ -208,12 +208,16 @@ class FreqaiBinaryClassStrategy_v4(IStrategy):
stoploss = -0.05 stoploss = -0.05
use_exit_signal = True use_exit_signal = True
startup_candle_count: int = 300 startup_candle_count: int = 300
can_short = True can_short = False
linear_roi_offset = DecimalParameter( linear_roi_offset = DecimalParameter(
0.00, 0.02, default=0.005, space="sell", optimize=False, load=True 0.00, 0.02, default=0.005, space="sell", optimize=False, load=True
) )
max_roi_time_long = IntParameter(0, 800, default=400, space="sell", optimize=False, load=True) # max roi time long in minutes
# max_roi_time_long = IntParameter(0, 800, default=341, space="sell", optimize=True, load=True) # BTC
max_roi_time_long = IntParameter(0, 800, default=400, space="sell", optimize=True, load=False)
entry_thr = DecimalParameter(0.5, 1.0, default=0.7, space="buy", optimize=True, load=False)
exit_thr = DecimalParameter(0.5, 1.0, default=0.7, space="sell", optimize=True, load=False)
def informative_pairs(self): def informative_pairs(self):
whitelist_pairs = self.dp.current_whitelist() whitelist_pairs = self.dp.current_whitelist()
@ -360,7 +364,7 @@ class FreqaiBinaryClassStrategy_v4(IStrategy):
def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame: def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame:
hours_candle_stability = 4 hours_candle_stability = 4
if df["do_predict"].rolling(12 * hours_candle_stability).sum().iloc[-1] == 12 * hours_candle_stability: # enter the market if last `hours_candle_stability` are stable if df["do_predict"].rolling(12 * hours_candle_stability).sum().iloc[-1] == 12 * hours_candle_stability: # enter the market if last `hours_candle_stability` are stable
enter_long_conditions = [df["do_predict"] == 1, df["min"] >= self.minima_threhsold] enter_long_conditions = [df["do_predict"] == 1, df["min"] >= self.entry_thr.value]
if enter_long_conditions: if enter_long_conditions:
df.loc[ df.loc[
@ -368,7 +372,7 @@ class FreqaiBinaryClassStrategy_v4(IStrategy):
] = (1, "long") ] = (1, "long")
if self.can_short: if self.can_short:
enter_short_conditions = [df["do_predict"] == 1, df["max"] >= self.maxima_threhsold] enter_short_conditions = [df["do_predict"] == 1, df["max"] >= self.exit_thr.value]
if enter_short_conditions: if enter_short_conditions:
df.loc[ df.loc[
@ -379,13 +383,13 @@ class FreqaiBinaryClassStrategy_v4(IStrategy):
return df return df
def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame: def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame:
exit_long_conditions = [df["do_predict"] == 1, df["max"] >= self.maxima_threhsold] exit_long_conditions = [df["do_predict"] == 1, df["max"] >= self.exit_thr.value]
if exit_long_conditions: if exit_long_conditions:
df.loc[reduce(lambda x, y: x & y, exit_long_conditions), df.loc[reduce(lambda x, y: x & y, exit_long_conditions),
["exit_long", "exit_tag"]] = (1, "exit signal") ["exit_long", "exit_tag"]] = (1, "exit signal")
if self.can_short: if self.can_short:
exit_short_conditions = [df["do_predict"] == 1, df["min"] >= self.minima_threhsold] exit_short_conditions = [df["do_predict"] == 1, df["min"] >= self.entry_thr.value]
if exit_short_conditions: if exit_short_conditions:
df.loc[reduce(lambda x, y: x & y, exit_short_conditions), "exit_short"] = 1 df.loc[reduce(lambda x, y: x & y, exit_short_conditions), "exit_short"] = 1
return df return df
@ -409,7 +413,9 @@ class FreqaiBinaryClassStrategy_v4(IStrategy):
if dataframe["do_predict"].iloc[-1] != 1: if dataframe["do_predict"].iloc[-1] != 1:
return f"OOD_{trade.enter_tag}_Exit" return f"OOD_{trade.enter_tag}_Exit"
if (current_time - trade.open_date_utc).seconds > self.max_roi_time_long.value * 60: time_alpha = (1 + current_profit / (self.minimal_roi[0] - self.stoploss))
time_alpha = 1.
if (current_time - trade.open_date_utc).seconds > (self.max_roi_time_long.value * 60 * time_alpha):
return f"{trade.enter_tag}_Expired" return f"{trade.enter_tag}_Expired"
def confirm_trade_exit( def confirm_trade_exit(