freqtrade_origin/freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py

import logging
import sys
from pathlib import Path
from typing import Any, Dict

from catboost import CatBoostRegressor, Pool

from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen


logger = logging.getLogger(__name__)


class CatboostRegressorMultiTarget(BaseRegressionModel):
    """
    User created prediction model. The class inherits IFreqaiModel, which
    means it has full access to all Frequency AI functionality. Typically,
    users would use this to override the common `fit()`, `train()`, or
    `predict()` methods to add their custom data handling tools or change
    various aspects of the training that cannot be configured via the
    top level config.json file.
    """

    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
        """
        User sets up the training and test data to fit their desired model here
        :param data_dictionary: the dictionary holding all data for train, test,
            labels, weights
        :param dk: The datakitchen object for the current coin/model
        """

        cbr = CatBoostRegressor(
            allow_writing_files=True,
            train_dir=Path(dk.data_path),
            **self.model_training_parameters,
        )

        X = data_dictionary["train_features"]
        y = data_dictionary["train_labels"]

        sample_weight = data_dictionary["train_weights"]

        eval_sets = [None] * y.shape[1]

        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
            eval_sets = [None] * data_dictionary['test_labels'].shape[1]

            for i in range(data_dictionary['test_labels'].shape[1]):
                eval_sets[i] = Pool(
                    data=data_dictionary["test_features"],
                    label=data_dictionary["test_labels"].iloc[:, i],
                    weight=data_dictionary["test_weights"],
                )

        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],  'init_model': init_models[i],
                    'log_cout': sys.stdout, 'log_cerr': sys.stderr,
                 })

        model = FreqaiMultiOutputRegressor(estimator=cbr)
        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)

        return model