stable/freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py

65 lines
2.4 KiB
Python
Raw Normal View History

2022-07-22 10:40:51 +00:00
import logging
from typing import Any, Dict
from lightgbm import LGBMRegressor
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
2022-09-07 16:58:55 +00:00
2022-07-22 10:40:51 +00:00
logger = logging.getLogger(__name__)
class LightGBMRegressorMultiTarget(BaseRegressionModel):
2022-07-22 10:40:51 +00:00
"""
User created prediction model. The class needs to override three necessary
functions, predict(), train(), fit(). The class inherits ModelHandler which
has its own DataHandler where data is held, saved, loaded, and managed.
"""
2022-09-07 16:58:55 +00:00
def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
2022-07-22 10:40:51 +00:00
"""
User sets up the training and test data to fit their desired model here
2022-07-24 14:54:39 +00:00
:param data_dictionary: the dictionary constructed by DataHandler to hold
all the training and test data/labels.
2022-07-22 10:40:51 +00:00
"""
lgb = LGBMRegressor(**self.model_training_parameters)
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
sample_weight = data_dictionary["train_weights"]
eval_weights = None
eval_sets = [None] * y.shape[1]
if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
eval_weights = [data_dictionary["test_weights"]]
eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1] # type: ignore
for i in range(data_dictionary['test_labels'].shape[1]):
eval_sets[i] = ( # type: ignore
data_dictionary["test_features"],
data_dictionary["test_labels"].iloc[:, i]
)
init_model = self.get_init_model(dk.pair)
if init_model:
init_models = init_model.estimators_
else:
init_models = [None] * y.shape[1]
fit_params = []
for i in range(len(eval_sets)):
fit_params.append(
{'eval_set': eval_sets[i], 'eval_sample_weight': eval_weights,
'init_model': init_models[i]})
model = FreqaiMultiOutputRegressor(estimator=lgb)
thread_training = self.freqai_info.get('multitarget_parallel_training', False)
if thread_training:
model.n_jobs = y.shape[1]
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
2022-07-22 10:40:51 +00:00
return model