improve model youth by constantly scanning pairs in dry/live and always training new models. Fix bug in DI return values
This commit is contained in:
robcaulk
commit
5e914d5756
@ -452,6 +452,24 @@ config:
|
||||
|
||||
which will automatically purge all models older than the two most recently trained ones.
|
||||
|
||||
## Defining model expirations
|
||||
|
||||
During dry/live, FreqAI trains each pair sequentially (on separate threads/GPU from the main
|
||||
Freqtrade bot). This means there is always an age discrepancy between models. If a user is training
|
||||
on 50 pairs, and each pair requires 5 minutes to train, the oldest model will be over 4 hours old.
|
||||
This may be undesirable if the characteristic time scale (read trade duration target) for a strategy
|
||||
is much less than 4 hours. The user can decide to only make trade entries if the model is less than
|
||||
a certain number of hours in age by setting the `expiration_hours` in the config file:
|
||||
|
||||
```json
|
||||
"freqai": {
|
||||
"expiration_hours": 0.5,
|
||||
}
|
||||
```
|
||||
|
||||
In the present example, the user will only allow predictions on models that are less than 1/2 hours
|
||||
old.
|
||||
|
||||
<!-- ## Dynamic target expectation
|
||||
|
||||
The labels used for model training have a unique statistical distribution for each separate model training.
|
||||
|
||||
@ -30,6 +30,7 @@ class FreqaiDataDrawer:
|
||||
def __init__(self, full_path: Path, config: dict, follow_mode: bool = False):
|
||||
|
||||
self.config = config
|
||||
self.freqai_info = config.get('freqai', {})
|
||||
# dictionary holding all pair metadata necessary to load in from disk
|
||||
self.pair_dict: Dict[str, Any] = {}
|
||||
# dictionary holding all actively inferenced models in memory given a model filename
|
||||
@ -107,7 +108,7 @@ class FreqaiDataDrawer:
|
||||
if isinstance(object, np.generic):
|
||||
return object.item()
|
||||
|
||||
def get_pair_dict_info(self, metadata: dict) -> Tuple[str, int, bool, bool]:
|
||||
def get_pair_dict_info(self, pair: str) -> Tuple[str, int, bool, bool]:
|
||||
"""
|
||||
Locate and load existing model metadata from persistent storage. If not located,
|
||||
create a new one and append the current pair to it and prepare it for its first
|
||||
@ -120,22 +121,22 @@ class FreqaiDataDrawer:
|
||||
coin_first: bool = If the coin is fresh without metadata
|
||||
return_null_array: bool = Follower could not find pair metadata
|
||||
"""
|
||||
pair_in_dict = self.pair_dict.get(metadata['pair'])
|
||||
data_path_set = self.pair_dict.get(metadata['pair'], {}).get('data_path', None)
|
||||
pair_in_dict = self.pair_dict.get(pair)
|
||||
data_path_set = self.pair_dict.get(pair, {}).get('data_path', None)
|
||||
return_null_array = False
|
||||
|
||||
if pair_in_dict:
|
||||
model_filename = self.pair_dict[metadata['pair']]['model_filename']
|
||||
trained_timestamp = self.pair_dict[metadata['pair']]['trained_timestamp']
|
||||
coin_first = self.pair_dict[metadata['pair']]['first']
|
||||
model_filename = self.pair_dict[pair]['model_filename']
|
||||
trained_timestamp = self.pair_dict[pair]['trained_timestamp']
|
||||
coin_first = self.pair_dict[pair]['first']
|
||||
elif not self.follow_mode:
|
||||
self.pair_dict[metadata['pair']] = {}
|
||||
model_filename = self.pair_dict[metadata['pair']]['model_filename'] = ''
|
||||
coin_first = self.pair_dict[metadata['pair']]['first'] = True
|
||||
trained_timestamp = self.pair_dict[metadata['pair']]['trained_timestamp'] = 0
|
||||
self.pair_dict[pair] = {}
|
||||
model_filename = self.pair_dict[pair]['model_filename'] = ''
|
||||
coin_first = self.pair_dict[pair]['first'] = True
|
||||
trained_timestamp = self.pair_dict[pair]['trained_timestamp'] = 0
|
||||
|
||||
if not data_path_set and self.follow_mode:
|
||||
logger.warning(f'Follower could not find current pair {metadata["pair"]} in '
|
||||
logger.warning(f'Follower could not find current pair {pair} in '
|
||||
f'pair_dictionary at path {self.full_path}, sending null values '
|
||||
'back to strategy.')
|
||||
return_null_array = True
|
||||
@ -168,6 +169,7 @@ class FreqaiDataDrawer:
|
||||
self.model_return_values[pair]['do_preds'] = dh.full_do_predict
|
||||
self.model_return_values[pair]['target_mean'] = dh.full_target_mean
|
||||
self.model_return_values[pair]['target_std'] = dh.full_target_std
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
self.model_return_values[pair]['DI_values'] = dh.full_DI_values
|
||||
|
||||
# if not self.follow_mode:
|
||||
@ -189,6 +191,7 @@ class FreqaiDataDrawer:
|
||||
|
||||
self.model_return_values[pair]['predictions'] = np.append(
|
||||
self.model_return_values[pair]['predictions'][i:], predictions[-1])
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
self.model_return_values[pair]['DI_values'] = np.append(
|
||||
self.model_return_values[pair]['DI_values'][i:], dh.DI_values[-1])
|
||||
self.model_return_values[pair]['do_preds'] = np.append(
|
||||
@ -202,6 +205,7 @@ class FreqaiDataDrawer:
|
||||
prepend = np.zeros(abs(length_difference) - 1)
|
||||
self.model_return_values[pair]['predictions'] = np.insert(
|
||||
self.model_return_values[pair]['predictions'], 0, prepend)
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
self.model_return_values[pair]['DI_values'] = np.insert(
|
||||
self.model_return_values[pair]['DI_values'], 0, prepend)
|
||||
self.model_return_values[pair]['do_preds'] = np.insert(
|
||||
@ -215,6 +219,7 @@ class FreqaiDataDrawer:
|
||||
dh.full_do_predict = copy.deepcopy(self.model_return_values[pair]['do_preds'])
|
||||
dh.full_target_mean = copy.deepcopy(self.model_return_values[pair]['target_mean'])
|
||||
dh.full_target_std = copy.deepcopy(self.model_return_values[pair]['target_std'])
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
dh.full_DI_values = copy.deepcopy(self.model_return_values[pair]['DI_values'])
|
||||
|
||||
# if not self.follow_mode:
|
||||
@ -227,6 +232,7 @@ class FreqaiDataDrawer:
|
||||
dh.full_do_predict = np.zeros(len_df)
|
||||
dh.full_target_mean = np.zeros(len_df)
|
||||
dh.full_target_std = np.zeros(len_df)
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
dh.full_DI_values = np.zeros(len_df)
|
||||
|
||||
def purge_old_models(self) -> None:
|
||||
|
||||
@ -71,7 +71,7 @@ class FreqaiDataKitchen:
|
||||
|
||||
self.data_drawer = data_drawer
|
||||
|
||||
def set_paths(self, metadata: dict, trained_timestamp: int = None,) -> None:
|
||||
def set_paths(self, pair: str, trained_timestamp: int = None,) -> None:
|
||||
"""
|
||||
Set the paths to the data for the present coin/botloop
|
||||
:params:
|
||||
@ -83,7 +83,7 @@ class FreqaiDataKitchen:
|
||||
str(self.freqai_config.get('identifier')))
|
||||
|
||||
self.data_path = Path(self.full_path / str("sub-train" + "-" +
|
||||
metadata['pair'].split("/")[0] +
|
||||
pair.split("/")[0] +
|
||||
str(trained_timestamp)))
|
||||
|
||||
return
|
||||
@ -151,6 +151,9 @@ class FreqaiDataKitchen:
|
||||
:model: User trained model which can be inferenced for new predictions
|
||||
"""
|
||||
|
||||
if not self.data_drawer.pair_dict[coin]['model_filename']:
|
||||
return None
|
||||
|
||||
if self.live:
|
||||
self.model_filename = self.data_drawer.pair_dict[coin]['model_filename']
|
||||
self.data_path = Path(self.data_drawer.pair_dict[coin]['data_path'])
|
||||
@ -670,7 +673,7 @@ class FreqaiDataKitchen:
|
||||
|
||||
self.full_predictions = np.append(self.full_predictions, predictions)
|
||||
self.full_do_predict = np.append(self.full_do_predict, do_predict)
|
||||
if self.freqai_config.get('feature_parameters', {}).get('DI-threshold', 0) > 0:
|
||||
if self.freqai_config.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
self.full_DI_values = np.append(self.full_DI_values, self.DI_values)
|
||||
self.full_target_mean = np.append(self.full_target_mean, target_mean)
|
||||
self.full_target_std = np.append(self.full_target_std, target_std)
|
||||
@ -686,7 +689,7 @@ class FreqaiDataKitchen:
|
||||
filler = np.zeros(len_dataframe - len(self.full_predictions)) # startup_candle_count
|
||||
self.full_predictions = np.append(filler, self.full_predictions)
|
||||
self.full_do_predict = np.append(filler, self.full_do_predict)
|
||||
if self.freqai_config.get('feature_parameters', {}).get('DI-threshold', 0) > 0:
|
||||
if self.freqai_config.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
self.full_DI_values = np.append(filler, self.full_DI_values)
|
||||
self.full_target_mean = np.append(filler, self.full_target_mean)
|
||||
self.full_target_std = np.append(filler, self.full_target_std)
|
||||
@ -722,6 +725,12 @@ class FreqaiDataKitchen:
|
||||
|
||||
return full_timerange
|
||||
|
||||
def check_if_model_expired(self, trained_timestamp: int) -> bool:
|
||||
time = datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
|
||||
elapsed_time = (time - trained_timestamp) / 3600 # hours
|
||||
max_time = self.freqai_config.get('expiration_hours', 0)
|
||||
return elapsed_time > max_time
|
||||
|
||||
def check_if_new_training_required(self, trained_timestamp: int) -> Tuple[bool,
|
||||
TimeRange, TimeRange]:
|
||||
|
||||
@ -747,7 +756,7 @@ class FreqaiDataKitchen:
|
||||
logger.warning('FreqAI could not detect max timeframe and therefore may not '
|
||||
'download the proper amount of data for training')
|
||||
|
||||
logger.info(f'Extending data download by {additional_seconds/SECONDS_IN_DAY:.2f} days')
|
||||
# logger.info(f'Extending data download by {additional_seconds/SECONDS_IN_DAY:.2f} days')
|
||||
|
||||
if trained_timestamp != 0:
|
||||
elapsed_time = (time - trained_timestamp) / SECONDS_IN_DAY
|
||||
@ -796,12 +805,12 @@ class FreqaiDataKitchen:
|
||||
|
||||
return retrain, trained_timerange, data_load_timerange
|
||||
|
||||
def set_new_model_names(self, metadata: dict, trained_timerange: TimeRange):
|
||||
def set_new_model_names(self, pair: str, trained_timerange: TimeRange):
|
||||
|
||||
coin, _ = metadata['pair'].split("/")
|
||||
coin, _ = pair.split("/")
|
||||
# set the new data_path
|
||||
self.data_path = Path(self.full_path / str("sub-train" + "-" +
|
||||
metadata['pair'].split("/")[0] +
|
||||
pair.split("/")[0] +
|
||||
str(int(trained_timerange.stopts))))
|
||||
|
||||
self.model_filename = "cb_" + coin.lower() + "_" + str(int(trained_timerange.stopts))
|
||||
@ -870,6 +879,8 @@ class FreqaiDataKitchen:
|
||||
|
||||
# check if newest candle is already appended
|
||||
df_dp = strategy.dp.get_pair_dataframe(pair, tf)
|
||||
if len(df_dp.index) == 0:
|
||||
continue
|
||||
if (
|
||||
str(history_data[pair][tf].iloc[-1]['date']) ==
|
||||
str(df_dp.iloc[-1:]['date'].iloc[-1])
|
||||
@ -918,7 +929,7 @@ class FreqaiDataKitchen:
|
||||
'trading_mode', 'spot'))
|
||||
|
||||
def get_base_and_corr_dataframes(self, timerange: TimeRange,
|
||||
metadata: dict) -> Tuple[Dict[Any, Any], Dict[Any, Any]]:
|
||||
pair: str) -> Tuple[Dict[Any, Any], Dict[Any, Any]]:
|
||||
"""
|
||||
Searches through our historic_data in memory and returns the dataframes relevant
|
||||
to the present pair.
|
||||
@ -927,6 +938,7 @@ class FreqaiDataKitchen:
|
||||
for training according to user defined train_period
|
||||
metadata: dict = strategy furnished pair metadata
|
||||
"""
|
||||
|
||||
with self.data_drawer.history_lock:
|
||||
corr_dataframes: Dict[Any, Any] = {}
|
||||
base_dataframes: Dict[Any, Any] = {}
|
||||
@ -936,11 +948,11 @@ class FreqaiDataKitchen:
|
||||
for tf in self.freqai_config.get('timeframes'):
|
||||
base_dataframes[tf] = self.slice_dataframe(
|
||||
timerange,
|
||||
historic_data[metadata['pair']][tf]
|
||||
historic_data[pair][tf]
|
||||
)
|
||||
if pairs:
|
||||
for p in pairs:
|
||||
if metadata['pair'] in p:
|
||||
if pair in p:
|
||||
continue # dont repeat anything from whitelist
|
||||
if p not in corr_dataframes:
|
||||
corr_dataframes[p] = {}
|
||||
@ -984,7 +996,7 @@ class FreqaiDataKitchen:
|
||||
def use_strategy_to_populate_indicators(self, strategy: IStrategy,
|
||||
corr_dataframes: dict,
|
||||
base_dataframes: dict,
|
||||
metadata: dict) -> DataFrame:
|
||||
pair: str) -> DataFrame:
|
||||
"""
|
||||
Use the user defined strategy for populating indicators during
|
||||
retrain
|
||||
@ -1003,19 +1015,19 @@ class FreqaiDataKitchen:
|
||||
|
||||
for tf in self.freqai_config.get("timeframes"):
|
||||
dataframe = strategy.populate_any_indicators(
|
||||
metadata,
|
||||
metadata['pair'],
|
||||
pair,
|
||||
pair,
|
||||
dataframe.copy(),
|
||||
tf,
|
||||
base_dataframes[tf],
|
||||
coin=metadata['pair'].split("/")[0] + "-"
|
||||
coin=pair.split("/")[0] + "-"
|
||||
)
|
||||
if pairs:
|
||||
for i in pairs:
|
||||
if metadata['pair'] in i:
|
||||
if pair in i:
|
||||
continue # dont repeat anything from whitelist
|
||||
dataframe = strategy.populate_any_indicators(
|
||||
metadata,
|
||||
pair,
|
||||
i,
|
||||
dataframe.copy(),
|
||||
tf,
|
||||
|
||||
@ -8,6 +8,7 @@ from abc import ABC, abstractmethod
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Tuple
|
||||
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
import pandas as pd
|
||||
from pandas import DataFrame
|
||||
@ -63,6 +64,9 @@ class IFreqaiModel(ABC):
|
||||
self.lock = threading.Lock()
|
||||
self.follow_mode = self.freqai_info.get('follow_mode', False)
|
||||
self.identifier = self.freqai_info.get('identifier', 'no_id_provided')
|
||||
self.scanning = False
|
||||
self.ready_to_scan = False
|
||||
self.first = True
|
||||
|
||||
def assert_config(self, config: Dict[str, Any]) -> None:
|
||||
|
||||
@ -91,17 +95,9 @@ class IFreqaiModel(ABC):
|
||||
# and we keep the flag self.training_on_separate_threaad in the current object to help
|
||||
# determine what the current pair will do
|
||||
if self.live:
|
||||
if (not self.training_on_separate_thread and
|
||||
self.data_drawer.pair_dict[metadata['pair']]['priority'] == 1):
|
||||
|
||||
self.dh = FreqaiDataKitchen(self.config, self.data_drawer,
|
||||
self.live, metadata["pair"])
|
||||
dh = self.start_live(dataframe, metadata, strategy, self.dh, trainable=True)
|
||||
else:
|
||||
# we will have at max 2 separate instances of the kitchen at once.
|
||||
self.dh_fg = FreqaiDataKitchen(self.config, self.data_drawer,
|
||||
self.live, metadata["pair"])
|
||||
dh = self.start_live(dataframe, metadata, strategy, self.dh_fg, trainable=False)
|
||||
dh = self.start_live(dataframe, metadata, strategy, self.dh)
|
||||
|
||||
# For backtesting, each pair enters and then gets trained for each window along the
|
||||
# sliding window defined by "train_period" (training window) and "backtest_period"
|
||||
@ -114,8 +110,37 @@ class IFreqaiModel(ABC):
|
||||
dh = self.start_backtesting(dataframe, metadata, self.dh)
|
||||
|
||||
return self.return_values(dataframe, dh)
|
||||
# return (dh.full_predictions, dh.full_do_predict,
|
||||
# dh.full_target_mean, dh.full_target_std)
|
||||
|
||||
@threaded
|
||||
def start_scanning(self, strategy: IStrategy) -> None:
|
||||
while 1:
|
||||
for pair in self.config.get('exchange', {}).get('pair_whitelist'):
|
||||
if self.data_drawer.pair_dict[pair]['priority'] != 1:
|
||||
continue
|
||||
dh = FreqaiDataKitchen(self.config, self.data_drawer,
|
||||
self.live, pair)
|
||||
|
||||
(model_filename,
|
||||
trained_timestamp,
|
||||
_, _) = self.data_drawer.get_pair_dict_info(pair)
|
||||
|
||||
file_exists = False
|
||||
|
||||
dh.set_paths(pair, trained_timestamp)
|
||||
file_exists = self.model_exists(pair,
|
||||
dh,
|
||||
trained_timestamp=trained_timestamp,
|
||||
model_filename=model_filename,
|
||||
scanning=True)
|
||||
|
||||
(retrain,
|
||||
new_trained_timerange,
|
||||
data_load_timerange) = dh.check_if_new_training_required(trained_timestamp)
|
||||
dh.set_paths(pair, new_trained_timerange.stopts)
|
||||
|
||||
if retrain or not file_exists:
|
||||
self.train_model_in_series(new_trained_timerange, pair,
|
||||
strategy, dh, data_load_timerange)
|
||||
|
||||
def start_backtesting(self, dataframe: DataFrame, metadata: dict,
|
||||
dh: FreqaiDataKitchen) -> FreqaiDataKitchen:
|
||||
@ -142,7 +167,7 @@ class IFreqaiModel(ABC):
|
||||
for tr_train, tr_backtest in zip(
|
||||
dh.training_timeranges, dh.backtesting_timeranges
|
||||
):
|
||||
(_, _, _, _) = self.data_drawer.get_pair_dict_info(metadata)
|
||||
(_, _, _, _) = self.data_drawer.get_pair_dict_info(metadata['pair'])
|
||||
gc.collect()
|
||||
dh.data = {} # clean the pair specific data between training window sliding
|
||||
self.training_timerange = tr_train
|
||||
@ -163,7 +188,7 @@ class IFreqaiModel(ABC):
|
||||
str(int(trained_timestamp.stopts))))
|
||||
if not self.model_exists(metadata["pair"], dh,
|
||||
trained_timestamp=trained_timestamp.stopts):
|
||||
self.model = self.train(dataframe_train, metadata, dh)
|
||||
self.model = self.train(dataframe_train, metadata['pair'], dh)
|
||||
self.data_drawer.pair_dict[metadata['pair']][
|
||||
'trained_timestamp'] = trained_timestamp.stopts
|
||||
dh.set_new_model_names(metadata, trained_timestamp)
|
||||
@ -184,8 +209,7 @@ class IFreqaiModel(ABC):
|
||||
return dh
|
||||
|
||||
def start_live(self, dataframe: DataFrame, metadata: dict,
|
||||
strategy: IStrategy, dh: FreqaiDataKitchen,
|
||||
trainable: bool) -> FreqaiDataKitchen:
|
||||
strategy: IStrategy, dh: FreqaiDataKitchen) -> FreqaiDataKitchen:
|
||||
"""
|
||||
The main broad execution for dry/live. This function will check if a retraining should be
|
||||
performed, and if so, retrain and reset the model.
|
||||
@ -203,10 +227,10 @@ class IFreqaiModel(ABC):
|
||||
self.data_drawer.update_follower_metadata()
|
||||
|
||||
# get the model metadata associated with the current pair
|
||||
(model_filename,
|
||||
(_,
|
||||
trained_timestamp,
|
||||
coin_first,
|
||||
return_null_array) = self.data_drawer.get_pair_dict_info(metadata)
|
||||
_,
|
||||
return_null_array) = self.data_drawer.get_pair_dict_info(metadata['pair'])
|
||||
|
||||
# if the metadata doesnt exist, the follower returns null arrays to strategy
|
||||
if self.follow_mode and return_null_array:
|
||||
@ -222,20 +246,18 @@ class IFreqaiModel(ABC):
|
||||
# if trainable, check if model needs training, if so compute new timerange,
|
||||
# then save model and metadata.
|
||||
# if not trainable, load existing data
|
||||
if (trainable or coin_first) and not self.follow_mode:
|
||||
file_exists = False
|
||||
if not self.follow_mode:
|
||||
# if trained_timestamp != 0: # historical model available
|
||||
# dh.set_paths(metadata['pair'], trained_timestamp)
|
||||
# # file_exists = self.model_exists(metadata['pair'],
|
||||
# # dh,
|
||||
# # trained_timestamp=trained_timestamp,
|
||||
# # model_filename=model_filename)
|
||||
|
||||
if trained_timestamp != 0: # historical model available
|
||||
dh.set_paths(metadata, trained_timestamp)
|
||||
file_exists = self.model_exists(metadata['pair'],
|
||||
dh,
|
||||
trained_timestamp=trained_timestamp,
|
||||
model_filename=model_filename)
|
||||
|
||||
(self.retrain,
|
||||
(_,
|
||||
new_trained_timerange,
|
||||
data_load_timerange) = dh.check_if_new_training_required(trained_timestamp)
|
||||
dh.set_paths(metadata, new_trained_timerange.stopts)
|
||||
dh.set_paths(metadata['pair'], new_trained_timerange.stopts)
|
||||
|
||||
# download candle history if it is not already in memory
|
||||
if not self.data_drawer.historic_data:
|
||||
@ -245,21 +267,22 @@ class IFreqaiModel(ABC):
|
||||
dh.download_all_data_for_training(data_load_timerange)
|
||||
dh.load_all_pair_histories(data_load_timerange)
|
||||
|
||||
# train the model on the trained timerange
|
||||
if self.retrain or not file_exists:
|
||||
if coin_first:
|
||||
self.train_model_in_series(new_trained_timerange, metadata,
|
||||
strategy, dh, data_load_timerange)
|
||||
else:
|
||||
self.training_on_separate_thread = True # acts like a lock
|
||||
self.retrain_model_on_separate_thread(new_trained_timerange,
|
||||
metadata, strategy,
|
||||
dh, data_load_timerange)
|
||||
if not self.scanning:
|
||||
self.scanning = True
|
||||
self.start_scanning(strategy)
|
||||
|
||||
elif not trainable and not self.follow_mode:
|
||||
logger.info(f'{metadata["pair"]} holds spot '
|
||||
f'{self.data_drawer.pair_dict[metadata["pair"]]["priority"]} '
|
||||
'in training queue')
|
||||
# train the model on the trained timerange
|
||||
# if coin_first and not self.scanning:
|
||||
# self.train_model_in_series(new_trained_timerange, metadata['pair'],
|
||||
# strategy, dh, data_load_timerange)
|
||||
# elif not coin_first and not self.scanning:
|
||||
# self.scanning = True
|
||||
# self.start_scanning(strategy)
|
||||
|
||||
# elif not trainable and not self.follow_mode:
|
||||
# logger.info(f'{metadata["pair"]} holds spot '
|
||||
# f'{self.data_drawer.pair_dict[metadata["pair"]]["priority"]} '
|
||||
# 'in training queue')
|
||||
elif self.follow_mode:
|
||||
dh.set_paths(metadata, trained_timestamp)
|
||||
logger.info('FreqAI instance set to follow_mode, finding existing pair'
|
||||
@ -268,25 +291,46 @@ class IFreqaiModel(ABC):
|
||||
# load the model and associated data into the data kitchen
|
||||
self.model = dh.load_data(coin=metadata['pair'])
|
||||
|
||||
if not self.model:
|
||||
logger.warning('No model ready, returning null values to strategy.')
|
||||
self.data_drawer.return_null_values_to_strategy(dataframe, dh)
|
||||
return dh
|
||||
|
||||
# ensure user is feeding the correct indicators to the model
|
||||
self.check_if_feature_list_matches_strategy(dataframe, dh)
|
||||
|
||||
self.build_strategy_return_arrays(dataframe, dh, metadata['pair'], trained_timestamp)
|
||||
|
||||
return dh
|
||||
|
||||
def build_strategy_return_arrays(self, dataframe: DataFrame,
|
||||
dh: FreqaiDataKitchen, pair: str,
|
||||
trained_timestamp: int) -> None:
|
||||
|
||||
# hold the historical predictions in memory so we are sending back
|
||||
# correct array to strategy FIXME currently broken, but only affecting
|
||||
# Frequi reporting. Signals remain unaffeted.
|
||||
if metadata['pair'] not in self.data_drawer.model_return_values:
|
||||
|
||||
if pair not in self.data_drawer.model_return_values:
|
||||
preds, do_preds = self.predict(dataframe, dh)
|
||||
dh.append_predictions(preds, do_preds, len(dataframe))
|
||||
dh.fill_predictions(len(dataframe))
|
||||
self.data_drawer.set_initial_return_values(metadata['pair'], dh)
|
||||
self.data_drawer.set_initial_return_values(pair, dh)
|
||||
return
|
||||
elif self.dh.check_if_model_expired(trained_timestamp):
|
||||
preds, do_preds, dh.DI_values = np.zeros(2), np.ones(2) * 2, np.zeros(2)
|
||||
logger.warning('Model expired, returning null values to strategy. Strategy '
|
||||
'construction should take care to consider this event with '
|
||||
'prediction == 0 and do_predict == 2')
|
||||
else:
|
||||
preds, do_preds = self.predict(dataframe.iloc[-2:], dh)
|
||||
self.data_drawer.append_model_predictions(metadata['pair'], preds, do_preds,
|
||||
dh.data["target_mean"],
|
||||
dh.data["target_std"], dh,
|
||||
len(dataframe))
|
||||
|
||||
return dh
|
||||
self.data_drawer.append_model_predictions(pair, preds, do_preds,
|
||||
dh.data["target_mean"],
|
||||
dh.data["target_std"],
|
||||
dh,
|
||||
len(dataframe))
|
||||
return
|
||||
|
||||
def check_if_feature_list_matches_strategy(self, dataframe: DataFrame,
|
||||
dh: FreqaiDataKitchen) -> None:
|
||||
@ -357,7 +401,7 @@ class IFreqaiModel(ABC):
|
||||
# dh.remove_outliers(predict=True) # creates dropped index
|
||||
|
||||
def model_exists(self, pair: str, dh: FreqaiDataKitchen, trained_timestamp: int = None,
|
||||
model_filename: str = '') -> bool:
|
||||
model_filename: str = '', scanning: bool = False) -> bool:
|
||||
"""
|
||||
Given a pair and path, check if a model already exists
|
||||
:param pair: pair e.g. BTC/USD
|
||||
@ -370,9 +414,9 @@ class IFreqaiModel(ABC):
|
||||
|
||||
path_to_modelfile = Path(dh.data_path / str(model_filename + "_model.joblib"))
|
||||
file_exists = path_to_modelfile.is_file()
|
||||
if file_exists:
|
||||
if file_exists and not scanning:
|
||||
logger.info("Found model at %s", dh.data_path / dh.model_filename)
|
||||
else:
|
||||
elif not scanning:
|
||||
logger.info("Could not find model at %s", dh.data_path / dh.model_filename)
|
||||
return file_exists
|
||||
|
||||
@ -382,7 +426,7 @@ class IFreqaiModel(ABC):
|
||||
str(self.freqai_info.get('identifier')))
|
||||
|
||||
@threaded
|
||||
def retrain_model_on_separate_thread(self, new_trained_timerange: TimeRange, metadata: dict,
|
||||
def retrain_model_on_separate_thread(self, new_trained_timerange: TimeRange, pair: str,
|
||||
strategy: IStrategy, dh: FreqaiDataKitchen,
|
||||
data_load_timerange: TimeRange):
|
||||
"""
|
||||
@ -403,14 +447,14 @@ class IFreqaiModel(ABC):
|
||||
# metadata)
|
||||
|
||||
corr_dataframes, base_dataframes = dh.get_base_and_corr_dataframes(data_load_timerange,
|
||||
metadata)
|
||||
pair)
|
||||
|
||||
# protecting from common benign errors associated with grabbing new data from exchange:
|
||||
try:
|
||||
unfiltered_dataframe = dh.use_strategy_to_populate_indicators(strategy,
|
||||
corr_dataframes,
|
||||
base_dataframes,
|
||||
metadata)
|
||||
pair)
|
||||
unfiltered_dataframe = dh.slice_dataframe(new_trained_timerange, unfiltered_dataframe)
|
||||
|
||||
except Exception as err:
|
||||
@ -420,25 +464,25 @@ class IFreqaiModel(ABC):
|
||||
return
|
||||
|
||||
try:
|
||||
model = self.train(unfiltered_dataframe, metadata, dh)
|
||||
model = self.train(unfiltered_dataframe, pair, dh)
|
||||
except ValueError:
|
||||
logger.warning('Value error encountered during training')
|
||||
self.training_on_separate_thread = False
|
||||
self.retrain = False
|
||||
return
|
||||
|
||||
self.data_drawer.pair_dict[metadata['pair']][
|
||||
self.data_drawer.pair_dict[pair][
|
||||
'trained_timestamp'] = new_trained_timerange.stopts
|
||||
dh.set_new_model_names(metadata, new_trained_timerange)
|
||||
dh.set_new_model_names(pair, new_trained_timerange)
|
||||
# logger.info('Training queue'
|
||||
# f'{sorted(self.data_drawer.pair_dict.items(), key=lambda item: item[1])}')
|
||||
|
||||
if self.data_drawer.pair_dict[metadata['pair']]['priority'] == 1:
|
||||
if self.data_drawer.pair_dict[pair]['priority'] == 1:
|
||||
with self.lock:
|
||||
self.data_drawer.pair_to_end_of_training_queue(metadata['pair'])
|
||||
dh.save_data(model, coin=metadata['pair'])
|
||||
self.training_on_separate_thread = False
|
||||
self.retrain = False
|
||||
self.data_drawer.pair_to_end_of_training_queue(pair)
|
||||
dh.save_data(model, coin=pair)
|
||||
# self.training_on_separate_thread = False
|
||||
# self.retrain = False
|
||||
|
||||
# each time we finish a training, we check the directory to purge old models.
|
||||
if self.freqai_info.get('purge_old_models', False):
|
||||
@ -446,7 +490,7 @@ class IFreqaiModel(ABC):
|
||||
|
||||
return
|
||||
|
||||
def train_model_in_series(self, new_trained_timerange: TimeRange, metadata: dict,
|
||||
def train_model_in_series(self, new_trained_timerange: TimeRange, pair: str,
|
||||
strategy: IStrategy, dh: FreqaiDataKitchen,
|
||||
data_load_timerange: TimeRange):
|
||||
"""
|
||||
@ -464,29 +508,35 @@ class IFreqaiModel(ABC):
|
||||
# corr_dataframes, base_dataframes = dh.load_pairs_histories(data_load_timerange,
|
||||
# metadata)
|
||||
corr_dataframes, base_dataframes = dh.get_base_and_corr_dataframes(data_load_timerange,
|
||||
metadata)
|
||||
pair)
|
||||
|
||||
unfiltered_dataframe = dh.use_strategy_to_populate_indicators(strategy,
|
||||
corr_dataframes,
|
||||
base_dataframes,
|
||||
metadata)
|
||||
pair)
|
||||
|
||||
unfiltered_dataframe = dh.slice_dataframe(new_trained_timerange, unfiltered_dataframe)
|
||||
|
||||
model = self.train(unfiltered_dataframe, metadata, dh)
|
||||
model = self.train(unfiltered_dataframe, pair, dh)
|
||||
|
||||
self.data_drawer.pair_dict[metadata['pair']][
|
||||
self.data_drawer.pair_dict[pair][
|
||||
'trained_timestamp'] = new_trained_timerange.stopts
|
||||
dh.set_new_model_names(metadata, new_trained_timerange)
|
||||
self.data_drawer.pair_dict[metadata['pair']]['first'] = False
|
||||
dh.save_data(model, coin=metadata['pair'])
|
||||
self.retrain = False
|
||||
dh.set_new_model_names(pair, new_trained_timerange)
|
||||
self.data_drawer.pair_dict[pair]['first'] = False
|
||||
if self.data_drawer.pair_dict[pair]['priority'] == 1 and self.scanning:
|
||||
with self.lock:
|
||||
self.data_drawer.pair_to_end_of_training_queue(pair)
|
||||
dh.save_data(model, coin=pair)
|
||||
|
||||
if self.freqai_info.get('purge_old_models', False):
|
||||
self.data_drawer.purge_old_models()
|
||||
# self.retrain = False
|
||||
|
||||
# Following methods which are overridden by user made prediction models.
|
||||
# See freqai/prediction_models/CatboostPredictionModlel.py for an example.
|
||||
|
||||
@abstractmethod
|
||||
def train(self, unfiltered_dataframe: DataFrame, metadata: dict, dh: FreqaiDataKitchen) -> Any:
|
||||
def train(self, unfiltered_dataframe: DataFrame, pair: str, dh: FreqaiDataKitchen) -> Any:
|
||||
"""
|
||||
Filter the training data and train a model to it. Train makes heavy use of the datahandler
|
||||
for storing, saving, loading, and analyzing the data.
|
||||
|
||||
@ -24,7 +24,7 @@ class CatboostPredictionModel(IFreqaiModel):
|
||||
dataframe["do_predict"] = dh.full_do_predict
|
||||
dataframe["target_mean"] = dh.full_target_mean
|
||||
dataframe["target_std"] = dh.full_target_std
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI-threshold', 0) > 0:
|
||||
if self.freqai_info.get('feature_parameters', {}).get('DI_threshold', 0) > 0:
|
||||
dataframe["DI"] = dh.full_DI_values
|
||||
|
||||
return dataframe
|
||||
@ -48,7 +48,7 @@ class CatboostPredictionModel(IFreqaiModel):
|
||||
return dataframe["s"]
|
||||
|
||||
def train(self, unfiltered_dataframe: DataFrame,
|
||||
metadata: dict, dh: FreqaiDataKitchen) -> Tuple[DataFrame, DataFrame]:
|
||||
pair: str, dh: FreqaiDataKitchen) -> Tuple[DataFrame, DataFrame]:
|
||||
"""
|
||||
Filter the training data and train a model to it. Train makes heavy use of the datahkitchen
|
||||
for storing, saving, loading, and analyzing the data.
|
||||
@ -60,7 +60,7 @@ class CatboostPredictionModel(IFreqaiModel):
|
||||
"""
|
||||
|
||||
logger.info('--------------------Starting training '
|
||||
f'{metadata["pair"]} --------------------')
|
||||
f'{pair} --------------------')
|
||||
|
||||
# create the full feature list based on user config info
|
||||
dh.training_features_list = dh.find_features(unfiltered_dataframe)
|
||||
@ -88,7 +88,7 @@ class CatboostPredictionModel(IFreqaiModel):
|
||||
|
||||
model = self.fit(data_dictionary)
|
||||
|
||||
logger.info(f'--------------------done training {metadata["pair"]}--------------------')
|
||||
logger.info(f'--------------------done training {pair}--------------------')
|
||||
|
||||
return model
|
||||
|
||||
|
||||
@ -532,7 +532,7 @@ class IStrategy(ABC, HyperStrategyMixin):
|
||||
"""
|
||||
return None
|
||||
|
||||
def populate_any_indicators(self, metadata: dict, pair: str, df: DataFrame, tf: str,
|
||||
def populate_any_indicators(self, basepair: str, pair: str, df: DataFrame, tf: str,
|
||||
informative: DataFrame = None, coin: str = "") -> DataFrame:
|
||||
"""
|
||||
Function designed to automatically generate, name and merge features
|
||||
|
||||
@ -116,7 +116,6 @@ class FreqaiExampleStrategy(IStrategy):
|
||||
informative[f"{coin}bb_upperband-period_{t}"]
|
||||
- informative[f"{coin}bb_lowerband-period_{t}"]
|
||||
) / informative[f"{coin}bb_middleband-period_{t}"]
|
||||
|
||||
informative[f"%-{coin}close-bb_lower-period_{t}"] = (
|
||||
informative["close"] / informative[f"{coin}bb_lowerband-period_{t}"]
|
||||
)
|
||||
@ -153,7 +152,7 @@ class FreqaiExampleStrategy(IStrategy):
|
||||
# Add generalized indicators here (because in live, it will call this
|
||||
# function to populate indicators during training). Notice how we ensure not to
|
||||
# add them multiple times
|
||||
if pair == metadata["pair"] and tf == self.timeframe:
|
||||
if pair == self.freqai_info['corr_pairlist'][0] and tf == self.timeframe:
|
||||
df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
|
||||
df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user