From f10af7066d728df071d74759a4b45b2056e2ab59 Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Mon, 24 Feb 2025 18:45:14 +0100 Subject: [PATCH] fix(qav3): reset predictions normal distribution fitting MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Signed-off-by: Jérôme Benoit --- .../LightGBMRegressorQuickAdapterV35.py | 13 ++++++------- .../freqaimodels/XGBoostRegressorQuickAdapterV35.py | 13 ++++++------- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py index ae470ce..37f4d79 100644 --- a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py @@ -200,15 +200,14 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel): dk.data["extra_returns_per_train"][MAXIMA_THRESHOLD_COLUMN] = max_pred dk.data["labels_mean"], dk.data["labels_std"] = {}, {} - for label in dk.label_list + dk.unique_class_list: + for label in dk.label_list: if pred_df_full[label].dtype == object: continue - if not warmed_up: - f = [0, 0] - else: - f = spy.stats.norm.fit(pred_df_full[label]) - dk.data["labels_mean"][label] = f[0] - dk.data["labels_std"][label] = f[1] + # if not warmed_up: + f = [0, 0] + # else: + # f = spy.stats.norm.fit(pred_df_full[label]) + dk.data["labels_mean"][label], dk.data["labels_std"][label] = f[0], f[1] # fit the DI_threshold if not warmed_up: diff --git a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py index d0fd9c4..f83e83d 100644 --- a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py +++ b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py @@ -201,15 +201,14 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel): dk.data["extra_returns_per_train"][MAXIMA_THRESHOLD_COLUMN] = max_pred dk.data["labels_mean"], dk.data["labels_std"] = {}, {} - for label in dk.label_list + dk.unique_class_list: + for label in dk.label_list: if pred_df_full[label].dtype == object: continue - if not warmed_up: - f = [0, 0] - else: - f = spy.stats.norm.fit(pred_df_full[label]) - dk.data["labels_mean"][label] = f[0] - dk.data["labels_std"][label] = f[1] + # if not warmed_up: + f = [0, 0] + # else: + # f = spy.stats.norm.fit(pred_df_full[label]) + dk.data["labels_mean"][label], dk.data["labels_std"][label] = f[0], f[1] # fit the DI_threshold if not warmed_up: -- 2.43.0