From: Jérôme Benoit <jerome.benoit@piment-noir.org>
Date: Wed, 26 Feb 2025 19:57:40 +0000 (+0100)
Subject: refactor(qav3)!: sensible name for prediction thresholds smoothing
X-Git-Url: https://git.piment-noir.org/?a=commitdiff_plain;h=3ed4d987f7b13f3a27c6c71f59a11287777b060f;p=freqai-strategies.git

refactor(qav3)!: sensible name for prediction thresholds smoothing

Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
---

diff --git a/quickadapter/user_data/config-template.json b/quickadapter/user_data/config-template.json
index e9a5931..ec72793 100644
--- a/quickadapter/user_data/config-template.json
+++ b/quickadapter/user_data/config-template.json
@@ -114,7 +114,7 @@
     "fit_live_predictions_candles": 300,
     "data_kitchen_thread_count": 6, // set to number of CPU threads / 4
     "track_performance": false,
-    "predictions_smoothing": "mean",
+    "prediction_thresholds_smoothing": "mean",
     "outlier_threshold": 0.999,
     "optuna_hyperopt": {
       "enabled": true,
diff --git a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py
index 625ddc3..91015a4 100644
--- a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py
+++ b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py
@@ -269,22 +269,24 @@ class LightGBMRegressorQuickAdapterV35(BaseRegressionModel):
         fit_live_predictions_candles: int,
         label_period_candles: int,
     ) -> tuple[float, float]:
-        predictions_smoothing = self.freqai_info.get("predictions_smoothing", "mean")
-        if predictions_smoothing == "quantile":
+        prediction_thresholds_smoothing = self.freqai_info.get(
+            "prediction_thresholds_smoothing", "mean"
+        )
+        if prediction_thresholds_smoothing == "quantile":
             return self.quantile_min_max_pred(
                 pred_df, fit_live_predictions_candles, label_period_candles
             )
-        elif predictions_smoothing == "mean":
+        elif prediction_thresholds_smoothing == "mean":
             return mean_min_max_pred(
                 pred_df, fit_live_predictions_candles, label_period_candles
             )
-        elif predictions_smoothing == "median":
+        elif prediction_thresholds_smoothing == "median":
             return median_min_max_pred(
                 pred_df, fit_live_predictions_candles, label_period_candles
             )
         else:
             raise ValueError(
-                f"Invalid predictions_smoothing value: '{predictions_smoothing}'"
+                f"Invalid prediction_thresholds_smoothing value: '{prediction_thresholds_smoothing}'"
             )
 
     def optuna_hp_enqueue_previous_best_trial(
diff --git a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py
index 58dd417..5e798fd 100644
--- a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py
+++ b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py
@@ -270,22 +270,24 @@ class XGBoostRegressorQuickAdapterV35(BaseRegressionModel):
         fit_live_predictions_candles: int,
         label_period_candles: int,
     ) -> tuple[float, float]:
-        predictions_smoothing = self.freqai_info.get("predictions_smoothing", "mean")
-        if predictions_smoothing == "quantile":
+        prediction_thresholds_smoothing = self.freqai_info.get(
+            "prediction_thresholds_smoothing", "mean"
+        )
+        if prediction_thresholds_smoothing == "quantile":
             return self.quantile_min_max_pred(
                 pred_df, fit_live_predictions_candles, label_period_candles
             )
-        elif predictions_smoothing == "mean":
+        elif prediction_thresholds_smoothing == "mean":
             return mean_min_max_pred(
                 pred_df, fit_live_predictions_candles, label_period_candles
             )
-        elif predictions_smoothing == "median":
+        elif prediction_thresholds_smoothing == "median":
             return median_min_max_pred(
                 pred_df, fit_live_predictions_candles, label_period_candles
             )
         else:
             raise ValueError(
-                f"Invalid predictions_smoothing value: '{predictions_smoothing}'"
+                f"Invalid prediction_thresholds_smoothing value: '{prediction_thresholds_smoothing}'"
             )
 
     def optuna_hp_enqueue_previous_best_trial(