From a044e51965c66c71d339dc204e04ec76b22ed1f7 Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Mon, 10 Feb 2025 22:01:56 +0100 Subject: [PATCH] refactor(qav3): code cleanups MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Signed-off-by: Jérôme Benoit --- .../freqaimodels/LightGBMRegressorQuickAdapterV35.py | 5 +++-- .../freqaimodels/XGBoostRegressorQuickAdapterV35.py | 9 ++++++--- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py index cdf4a34..a02cb20 100644 --- a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py @@ -242,11 +242,12 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel): def min_max_pred( pred_df: pd.DataFrame, fit_live_predictions_candles: int, label_period_candles: int ): + beta = 10.0 min_pred = pred_df.tail(label_period_candles).apply( - lambda col: smooth_min(col, beta=10.0) + lambda col: smooth_min(col, beta=beta) ) max_pred = pred_df.tail(label_period_candles).apply( - lambda col: smooth_max(col, beta=10.0) + lambda col: smooth_max(col, beta=beta) ) return min_pred, max_pred diff --git a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py index 9b8d629..22c7776 100644 --- a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py @@ -242,11 +242,12 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel): def min_max_pred( pred_df: pd.DataFrame, fit_live_predictions_candles: int, label_period_candles: int ): + beta = 10.0 min_pred = pred_df.tail(label_period_candles).apply( - lambda col: smooth_min(col, beta=10.0) + lambda col: smooth_min(col, beta=beta) ) max_pred = pred_df.tail(label_period_candles).apply( - lambda col: smooth_max(col, beta=10.0) + lambda col: smooth_max(col, beta=beta) ) return min_pred, max_pred @@ -325,7 +326,9 @@ def objective( min_label_period_candles = int(fit_live_predictions_candles / 10) max_label_period_candles = fit_live_predictions_candles label_period_candles = trial.suggest_int( - "label_period_candles", min_label_period_candles, max_label_period_candles + "label_period_candles", + min_label_period_candles, + max_label_period_candles, ) y_test = y_test.tail(label_period_candles) y_pred = y_pred[-label_period_candles:] -- 2.43.0