84 lines
2.9 KiB
Python
84 lines
2.9 KiB
Python
import logging
|
|
from abc import ABC, abstractmethod
|
|
from time import time
|
|
from typing import Any
|
|
|
|
import torch
|
|
from pandas import DataFrame
|
|
|
|
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
|
|
from freqtrade.freqai.freqai_interface import IFreqaiModel
|
|
from freqtrade.freqai.torch.PyTorchDataConvertor import PyTorchDataConvertor
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class BasePyTorchModel(IFreqaiModel, ABC):
|
|
"""
|
|
Base class for PyTorch type models.
|
|
User *must* inherit from this class and set fit() and predict() and
|
|
data_convertor property.
|
|
"""
|
|
|
|
def __init__(self, **kwargs):
|
|
super().__init__(config=kwargs["config"])
|
|
self.dd.model_type = "pytorch"
|
|
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
test_size = self.freqai_info.get('data_split_parameters', {}).get('test_size')
|
|
self.splits = ["train", "test"] if test_size != 0 else ["train"]
|
|
|
|
def train(
|
|
self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
|
|
) -> Any:
|
|
"""
|
|
Filter the training data and train a model to it. Train makes heavy use of the datakitchen
|
|
for storing, saving, loading, and analyzing the data.
|
|
:param unfiltered_df: Full dataframe for the current training period
|
|
:return:
|
|
:model: Trained model which can be used to inference (self.predict)
|
|
"""
|
|
|
|
logger.info(f"-------------------- Starting training {pair} --------------------")
|
|
|
|
start_time = time()
|
|
|
|
features_filtered, labels_filtered = dk.filter_features(
|
|
unfiltered_df,
|
|
dk.training_features_list,
|
|
dk.label_list,
|
|
training_filter=True,
|
|
)
|
|
|
|
# split data into train/test data.
|
|
data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
|
|
if not self.freqai_info.get("fit_live_predictions", 0) or not self.live:
|
|
dk.fit_labels()
|
|
# normalize all data based on train_dataset only
|
|
data_dictionary = dk.normalize_data(data_dictionary)
|
|
|
|
# optional additional data cleaning/analysis
|
|
self.data_cleaning_train(dk)
|
|
|
|
logger.info(
|
|
f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"
|
|
)
|
|
logger.info(f"Training model on {len(data_dictionary['train_features'])} data points")
|
|
|
|
model = self.fit(data_dictionary, dk)
|
|
end_time = time()
|
|
|
|
logger.info(f"-------------------- Done training {pair} "
|
|
f"({end_time - start_time:.2f} secs) --------------------")
|
|
|
|
return model
|
|
|
|
@property
|
|
@abstractmethod
|
|
def data_convertor(self) -> PyTorchDataConvertor:
|
|
"""
|
|
a class responsible for converting `*_features` & `*_labels` pandas dataframes
|
|
to pytorch tensors.
|
|
"""
|
|
raise NotImplementedError("Abstract property")
|