import logging from typing import Tuple 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 return_values(self, dataframe: DataFrame, dk: FreqaiDataKitchen) -> DataFrame: """ User uses this function to add any additional return values to the dataframe. e.g. dataframe['volatility'] = dk.volatility_values """ return dataframe def train( self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen ) -> Tuple[DataFrame, DataFrame]: """ 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. :params: :unfiltered_dataframe: Full dataframe for the current training period :metadata: pair metadata from strategy. :returns: :model: Trained model which can be used to inference (self.predict) """ logger.info("-------------------- Starting training " f"{pair} --------------------") # filter the features requested by user in the configuration file and elegantly handle NaNs features_filtered, labels_filtered = dk.filter_features( unfiltered_dataframe, dk.training_features_list, dk.label_list, training_filter=True, ) start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d") end_date = unfiltered_dataframe["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. data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered) if not self.freqai_info.get('fit_live_predictions', 0): 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) if pair not in self.dd.historic_predictions: self.set_initial_historic_predictions( data_dictionary['train_features'], model, dk, pair) elif self.freqai_info.get('fit_live_predictions_candles', 0): dk.fit_live_predictions() self.dd.save_historic_predictions_to_disk() logger.info(f"--------------------done training {pair}--------------------") return model def predict( self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False ) -> Tuple[DataFrame, DataFrame]: """ Filter the prediction features data and predict with it. :param: unfiltered_dataframe: 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_dataframe) filtered_dataframe, _ = dk.filter_features( unfiltered_dataframe, dk.training_features_list, training_filter=False ) filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe) dk.data_dictionary["prediction_features"] = filtered_dataframe # optional additional data cleaning/analysis self.data_cleaning_predict(dk, filtered_dataframe) predictions = self.model.predict(dk.data_dictionary["prediction_features"]) pred_df = DataFrame(predictions, columns=dk.label_list) for label in dk.label_list: pred_df[label] = ( (pred_df[label] + 1) * (dk.data["labels_max"][label] - dk.data["labels_min"][label]) / 2 ) + dk.data["labels_min"][label] return (pred_df, dk.do_predict)