From 576ffdece616baeed5844646cc4fa1edff698cdb Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Tue, 4 Mar 2025 22:53:07 +0100 Subject: [PATCH] perf(qav3): refine default quantile value MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Signed-off-by: Jérôme Benoit --- .../LightGBMRegressorQuickAdapterV35.py | 14 +++++++------- .../XGBoostRegressorQuickAdapterV35.py | 14 +++++++------- 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py index 5fcd4d1..c095527 100644 --- a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py @@ -70,9 +70,9 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel): ) self.freqai_info["feature_parameters"][pair] = {} self.freqai_info["feature_parameters"][pair]["label_period_candles"] = ( - self.__optuna_period_params[pair].get( - "label_period_candles", self.ft_params["label_period_candles"] - ) + self.__optuna_period_params[ + pair + ].get("label_period_candles", self.ft_params["label_period_candles"]) ) def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: @@ -230,9 +230,9 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel): dk.data["extra_returns_per_train"]["DI_cutoff"] = cutoff dk.data["extra_returns_per_train"]["label_period_candles"] = ( - self.__optuna_period_params.get(pair, {}).get( - "label_period_candles", self.ft_params["label_period_candles"] - ) + self.__optuna_period_params.get( + pair, {} + ).get("label_period_candles", self.ft_params["label_period_candles"]) ) dk.data["extra_returns_per_train"]["hp_rmse"] = self.__optuna_hp_rmse.get( pair, -1 @@ -499,7 +499,7 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel): label_period_frequency: int = int( fit_live_predictions_candles / (label_period_candles * 2) ) - q = self.freqai_info.get("quantile", 0.67) + q = self.freqai_info.get("quantile", 0.75) min_pred = pred_df_sorted.iloc[-label_period_frequency:].quantile(1 - q) max_pred = pred_df_sorted.iloc[:label_period_frequency].quantile(q) return min_pred[EXTREMA_COLUMN], max_pred[EXTREMA_COLUMN] diff --git a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py index bdb9bdc..076b40e 100644 --- a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py @@ -70,9 +70,9 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel): ) self.freqai_info["feature_parameters"][pair] = {} self.freqai_info["feature_parameters"][pair]["label_period_candles"] = ( - self.__optuna_period_params[pair].get( - "label_period_candles", self.ft_params["label_period_candles"] - ) + self.__optuna_period_params[ + pair + ].get("label_period_candles", self.ft_params["label_period_candles"]) ) def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: @@ -231,9 +231,9 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel): dk.data["extra_returns_per_train"]["DI_cutoff"] = cutoff dk.data["extra_returns_per_train"]["label_period_candles"] = ( - self.__optuna_period_params.get(pair, {}).get( - "label_period_candles", self.ft_params["label_period_candles"] - ) + self.__optuna_period_params.get( + pair, {} + ).get("label_period_candles", self.ft_params["label_period_candles"]) ) dk.data["extra_returns_per_train"]["hp_rmse"] = self.__optuna_hp_rmse.get( pair, -1 @@ -500,7 +500,7 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel): label_period_frequency: int = int( fit_live_predictions_candles / (label_period_candles * 2) ) - q = self.freqai_info.get("quantile", 0.67) + q = self.freqai_info.get("quantile", 0.75) min_pred = pred_df_sorted.iloc[-label_period_frequency:].quantile(1 - q) max_pred = pred_df_sorted.iloc[:label_period_frequency].quantile(q) return min_pred[EXTREMA_COLUMN], max_pred[EXTREMA_COLUMN] -- 2.43.0