freqtrade_origin/freqtrade/freqai/base_models/BaseRegressionModel.py

import logging
from time import time
from typing import Any, Tuple

import numpy as np
import numpy.typing as npt
from pandas import DataFrame

from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
from freqtrade.freqai.freqai_interface import IFreqaiModel


logger = logging.getLogger(__name__)


class BaseRegressionModel(IFreqaiModel):
    """
    Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
    User *must* inherit from this class and set fit() and predict(). See example scripts
    such as prediction_models/CatboostPredictionModel.py for guidance.
    """

    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
        :param metadata: pair metadata from strategy.
        :return:
        :model: Trained model which can be used to inference (self.predict)
        """

        logger.info(f"-------------------- Starting training {pair} --------------------")

        start_time = time()

        # filter the features requested by user in the configuration file and elegantly handle NaNs
        features_filtered, labels_filtered = dk.filter_features(
            unfiltered_df,
            dk.training_features_list,
            dk.label_list,
            training_filter=True,
        )

        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
        logger.info(f"-------------------- Training on data from {start_date} to "
                    f"{end_date} --------------------")
        # split data into train/test data.
        dd = dk.make_train_test_datasets(features_filtered, labels_filtered)
        if not self.freqai_info.get("fit_live_predictions_candles", 0) or not self.live:
            dk.fit_labels()
        dk.feature_pipeline = self.define_data_pipeline()
        dk.label_pipeline = self.define_label_pipeline()

        (dd["train_features"],
         dd["train_labels"],
         dd["train_weights"]) = dk.feature_pipeline.fit_transform(dd["train_features"],
                                                                  dd["train_labels"],
                                                                  dd["train_weights"])

        (dd["test_features"],
         dd["test_labels"],
         dd["test_weights"]) = dk.feature_pipeline.transform(dd["test_features"],
                                                             dd["test_labels"],
                                                             dd["test_weights"])

        dd["train_labels"], _, _ = dk.label_pipeline.fit_transform(dd["train_labels"])
        dd["test_labels"], _, _ = dk.label_pipeline.transform(dd["test_labels"])

        logger.info(
            f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"
        )
        logger.info(f"Training model on {len(dd['train_features'])} data points")

        model = self.fit(dd, dk)

        end_time = time()

        logger.info(f"-------------------- Done training {pair} "
                    f"({end_time - start_time:.2f} secs) --------------------")

        return model

    def predict(
        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
    ) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
        """
        Filter the prediction features data and predict with it.
        :param unfiltered_df: Full dataframe for the current backtest period.
        :return:
        :pred_df: dataframe containing the predictions
        :do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
        data (NaNs) or felt uncertain about data (PCA and DI index)
        """

        dk.find_features(unfiltered_df)
        dk.data_dictionary["prediction_features"], _ = dk.filter_features(
            unfiltered_df, dk.training_features_list, training_filter=False
        )

        dk.data_dictionary["prediction_features"], outliers, _ = dk.feature_pipeline.transform(
            dk.data_dictionary["prediction_features"], outlier_check=True)

        predictions = self.model.predict(dk.data_dictionary["prediction_features"])
        if self.CONV_WIDTH == 1:
            predictions = np.reshape(predictions, (-1, len(dk.label_list)))

        pred_df = DataFrame(predictions, columns=dk.label_list)

        pred_df, _, _ = dk.label_pipeline.inverse_transform(pred_df)
        if self.freqai_info.get("DI_threshold", 0) > 0:
            dk.DI_values = dk.feature_pipeline["di"].di_values
        else:
            dk.DI_values = np.zeros(len(outliers.index))
        dk.do_predict = outliers.to_numpy()

        return (pred_df, dk.do_predict)