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

auto build full_timerange and self manage training_timerange

Browse Source
This commit is contained in:
robcaulk 2022-05-05 15:35:51 +02:00
parent 764f9449b4
commit def71a0afe
4 changed files with 38 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
config_examples/config_freqai.example.json
View File

@ -49,12 +49,10 @@
}
],
"freqai": {
"btc_pair": "BTC/USDT",
"timeframes": [
"5m",
"15m"
],
"full_timerange": "20210601-20210901",
"train_period": 30,
"backtest_period": 7,
"identifier": "example",
@ -74,7 +72,6 @@
"LINK/USDT",
"DOT/USDT"
],
"training_timerange": "20211220-20220117",
"feature_parameters": {
"period": 12,
"shift": 1,

2
freqtrade/constants.py
View File

@ -478,13 +478,11 @@ CONF_SCHEMA = {
"type": "object",
"properties": {
"timeframes": {"type": "list"},
"full_timerange": {"type": "str"},
"train_period": {"type": "integer", "default": 0},
"backtest_period": {"type": "integer", "default": 7},
"identifier": {"type": "str", "default": "example"},
"base_features": {"type": "list"},
"corr_pairlist": {"type": "list"},
"training_timerange": {"type": "string", "default": None},
"feature_parameters": {
"type": "object",
"properties": {

41
freqtrade/freqai/data_handler.py
View File

@ -3,6 +3,7 @@ import datetime
import json
import logging
import pickle as pk
import shutil
from pathlib import Path
from typing import Any, Dict, List, Tuple
@ -30,15 +31,10 @@ class DataHandler:
def __init__(self, config: Dict[str, Any], dataframe: DataFrame):
self.full_dataframe = dataframe
(self.training_timeranges, self.backtesting_timeranges) = self.split_timerange(
config["freqai"]["full_timerange"],
config["freqai"]["train_period"],
config["freqai"]["backtest_period"],
)
self.data: Dict[Any, Any] = {}
self.data_dictionary: Dict[Any, Any] = {}
self.config = config
self.freq_config = config["freqai"]
self.freqai_config = config["freqai"]
self.predictions = np.array([])
self.do_predict = np.array([])
self.target_mean = np.array([])
@ -46,6 +42,16 @@ class DataHandler:
self.model_path = Path()
self.model_filename = ""
self.full_timerange = self.create_fulltimerange(
self.config["timerange"], self.freqai_config["train_period"]
)
(self.training_timeranges, self.backtesting_timeranges) = self.split_timerange(
self.full_timerange,
config["freqai"]["train_period"],
config["freqai"]["backtest_period"],
)
def save_data(self, model: Any) -> None:
"""
Saves all data associated with a model for a single sub-train time range
@ -539,6 +545,29 @@ class DataHandler:
return
def create_fulltimerange(self, backtest_tr: str, backtest_period: int) -> str:
backtest_timerange = TimeRange.parse_timerange(backtest_tr)
backtest_timerange.startts = backtest_timerange.startts - backtest_period * SECONDS_IN_DAY
start = datetime.datetime.utcfromtimestamp(backtest_timerange.startts)
stop = datetime.datetime.utcfromtimestamp(backtest_timerange.stopts)
full_timerange = start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d")
self.full_path = Path(
self.config["user_data_dir"]
/ "models"
/ str(full_timerange + self.freqai_config["identifier"])
)
if not self.full_path.is_dir():
self.full_path.mkdir(parents=True, exist_ok=True)
shutil.copy(
Path(self.config["config_files"][0]).name,
Path(self.full_path / self.config["config_files"][0]),
)
return full_timerange
def np_encoder(self, object):
if isinstance(object, np.generic):
return object.item()

19
freqtrade/freqai/freqai_interface.py
View File

@ -1,6 +1,5 @@
import gc
import logging
import shutil
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Any, Dict, Tuple
@ -32,24 +31,13 @@ class IFreqaiModel(ABC):
self.data_split_parameters = config["freqai"]["data_split_parameters"]
self.model_training_parameters = config["freqai"]["model_training_parameters"]
self.feature_parameters = config["freqai"]["feature_parameters"]
self.full_path = Path(
config["user_data_dir"]
/ "models"
/ str(self.freqai_info["full_timerange"] + self.freqai_info["identifier"])
)
self.backtest_timerange = config["timerange"]
self.time_last_trained = None
self.current_time = None
self.model = None
self.predictions = None
if not self.full_path.is_dir():
self.full_path.mkdir(parents=True, exist_ok=True)
shutil.copy(
self.config["config_files"][0],
Path(self.full_path / self.config["config_files"][0]),
)
def start(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
"""
Entry point to the FreqaiModel, it will train a new model if
@ -82,12 +70,11 @@ class IFreqaiModel(ABC):
gc.collect()
# self.config['timerange'] = tr_train
self.dh.data = {} # clean the pair specific data between models
self.freqai_info["training_timerange"] = tr_train
self.training_timerange = tr_train
dataframe_train = self.dh.slice_dataframe(tr_train, dataframe)
dataframe_backtest = self.dh.slice_dataframe(tr_backtest, dataframe)
logger.info("training %s for %s", self.pair, tr_train)
# self.dh.model_path = self.full_path + "/" + "sub-train" + "-" + str(tr_train) + "/"
self.dh.model_path = Path(self.full_path / str("sub-train" + "-" + str(tr_train)))
self.dh.model_path = Path(self.dh.full_path / str("sub-train" + "-" + str(tr_train)))
if not self.model_exists(self.pair, training_timerange=tr_train):
self.model = self.train(dataframe_train, metadata)
self.dh.save_data(self.model)