update

app.py

@@ -298,17 +298,29 @@ if uploaded_file:
     print("CatBoost:\n", pd.Series(catboost_probs).describe())
     print("XGBoost:\n", pd.Series(xgb_probs).describe())
 
-    # ✅ Apply Threshold to Convert Probabilities into Binary Predictions
-    THRESHOLD = 0.7  # Adjust to control false positives
+    # ✅ Dynamically Adjust Threshold Based on Probability Distribution
+    THRESHOLD = np.percentile(catboost_probs, 95)  # Use 95th percentile
+    print(f"✅ Adjusted CatBoost Threshold: {THRESHOLD:.3f}")
+
     catboost_preds = (catboost_probs >= THRESHOLD).astype(int)
-    xgb_preds = (xgb_probs >= THRESHOLD).astype(int)
+    xgb_preds = (xgb_probs >= 0.7).astype(int)  # Keep static for comparison
 
+    # ✅ Debugging: Count of 1s and 0s after thresholding
+    print("\nPost-threshold Distribution:")
+    print(f"CatBoost 1s: {np.sum(catboost_preds)} / {len(catboost_preds)}")
+    print(f"XGBoost 1s: {np.sum(xgb_preds)} / {len(xgb_preds)}")
+
+    # ✅ Fix `predictions_df` After Thresholding
     predictions_df = pd.DataFrame({
         "CatBoost": catboost_preds,
-        "XGBoost": xgb_preds,
-      #  "RandomForest": rf_preds
+        "XGBoost": xgb_preds
     })
 
+    # ✅ Ensure Not All Are Predicted as Clicks
+    if predictions_df["CatBoost"].sum() == len(predictions_df) or predictions_df["XGBoost"].sum() == len(
+            predictions_df):
+        print("⚠ Warning: Model is predicting only 1s! Consider adjusting thresholds.")
+
     # Apply "at least one model predicts 1" rule
     predictions_df["is_click_predicted"] = predictions_df.max(axis=1)