From b3131acfa88b51c2dd93b428c021bf0ee5c76d58 Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Sun, 2 Feb 2025 19:23:44 +0100 Subject: [PATCH] refactor(qav3): execute only the code neede during warmup MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Signed-off-by: Jérôme Benoit --- .../LightGBMRegressorQuickAdapterV35.py | 32 +++++++++---------- .../XGBoostRegressorQuickAdapterV35.py | 32 +++++++++---------- 2 files changed, 32 insertions(+), 32 deletions(-) diff --git a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py index 111ad93..afab949 100644 --- a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py @@ -140,27 +140,27 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel): pred_df_full = ( self.dd.historic_predictions[pair].tail(num_candles).reset_index(drop=True) ) - pred_df_sorted = pd.DataFrame() - for label in pred_df_full.keys(): - if pred_df_full[label].dtype == object: - continue - pred_df_sorted[label] = pred_df_full[label] - - # pred_df_sorted = pred_df_sorted - for col in pred_df_sorted: - pred_df_sorted[col] = pred_df_sorted[col].sort_values( - ascending=False, ignore_index=True - ) - frequency = num_candles / ( - self.freqai_info["feature_parameters"]["label_period_candles"] * 2 - ) - max_pred = pred_df_sorted.iloc[: int(frequency)].mean() - min_pred = pred_df_sorted.iloc[-int(frequency) :].mean() if not warmed_up: dk.data["extra_returns_per_train"]["&s-maxima_sort_threshold"] = 2 dk.data["extra_returns_per_train"]["&s-minima_sort_threshold"] = -2 else: + pred_df_sorted = pd.DataFrame() + for label in pred_df_full.keys(): + if pred_df_full[label].dtype == object: + continue + pred_df_sorted[label] = pred_df_full[label] + + # pred_df_sorted = pred_df_sorted + for col in pred_df_sorted: + pred_df_sorted[col] = pred_df_sorted[col].sort_values( + ascending=False, ignore_index=True + ) + frequency = num_candles / ( + self.freqai_info["feature_parameters"]["label_period_candles"] * 2 + ) + max_pred = pred_df_sorted.iloc[: int(frequency)].mean() + min_pred = pred_df_sorted.iloc[-int(frequency) :].mean() dk.data["extra_returns_per_train"]["&s-maxima_sort_threshold"] = max_pred[ "&s-extrema" ] diff --git a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py index 5908892..1d347c8 100644 --- a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py @@ -137,27 +137,27 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel): pred_df_full = ( self.dd.historic_predictions[pair].tail(num_candles).reset_index(drop=True) ) - pred_df_sorted = pd.DataFrame() - for label in pred_df_full.keys(): - if pred_df_full[label].dtype == object: - continue - pred_df_sorted[label] = pred_df_full[label] - - # pred_df_sorted = pred_df_sorted - for col in pred_df_sorted: - pred_df_sorted[col] = pred_df_sorted[col].sort_values( - ascending=False, ignore_index=True - ) - frequency = num_candles / ( - self.freqai_info["feature_parameters"]["label_period_candles"] * 2 - ) - max_pred = pred_df_sorted.iloc[: int(frequency)].mean() - min_pred = pred_df_sorted.iloc[-int(frequency) :].mean() if not warmed_up: dk.data["extra_returns_per_train"]["&s-maxima_sort_threshold"] = 2 dk.data["extra_returns_per_train"]["&s-minima_sort_threshold"] = -2 else: + pred_df_sorted = pd.DataFrame() + for label in pred_df_full.keys(): + if pred_df_full[label].dtype == object: + continue + pred_df_sorted[label] = pred_df_full[label] + + # pred_df_sorted = pred_df_sorted + for col in pred_df_sorted: + pred_df_sorted[col] = pred_df_sorted[col].sort_values( + ascending=False, ignore_index=True + ) + frequency = num_candles / ( + self.freqai_info["feature_parameters"]["label_period_candles"] * 2 + ) + max_pred = pred_df_sorted.iloc[: int(frequency)].mean() + min_pred = pred_df_sorted.iloc[-int(frequency) :].mean() dk.data["extra_returns_per_train"]["&s-maxima_sort_threshold"] = max_pred[ "&s-extrema" ] -- 2.43.0