From: Jérôme Benoit <jerome.benoit@sap.com>
Date: Mon, 24 Feb 2025 17:45:14 +0000 (+0100)
Subject: fix(qav3): reset predictions normal distribution fitting
X-Git-Url: https://git.piment-noir.org/?a=commitdiff_plain;h=f10af7066d728df071d74759a4b45b2056e2ab59;p=freqai-strategies.git

fix(qav3): reset predictions normal distribution fitting

Signed-off-by: Jérôme Benoit <jerome.benoit@sap.com>
---

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: