Oracle weight assigning update

Oracle/deepfundingoracle.py

@@ -25,6 +25,7 @@ import signal
 from tqdm import tqdm
 import sys
 import re
+import json
 
 from sklearn.model_selection import train_test_split, RandomizedSearchCV
 from sklearn.ensemble import RandomForestRegressor
@@ -231,7 +232,7 @@ def timeout_handler(signum, frame):
 #     logging.info(f"[INFO] Base weights assigned successfully in {end_time - start_time:.2f} seconds.")
 #     return df
 
-import json
+
 
 def assign_base_weight(df, max_workers=32):
     """
@@ -276,17 +277,22 @@ def assign_base_weight(df, max_workers=32):
         }
         print(f"[INFO] Using default feature weights: {feature_weights}", flush=True)
 
-    # Step 2: Programmatically calculate weights for each repository
+    # Step 2: Ensure all feature columns are numeric
+    for feature in feature_weights.keys():
+        if feature in df.columns:
+            df[feature] = pd.to_numeric(df[feature], errors='coerce').fillna(0)
+
+    # Step 3: Programmatically calculate weights for each repository
     def calculate_weight(row):
         weight = 0
         for feature, feature_weight in feature_weights.items():
-            if feature in row and pd.notna(row[feature]):
+            if feature in row:
                 weight += row[feature] * feature_weight
         return weight
 
     df["base_weight_raw"] = df.apply(calculate_weight, axis=1)
 
-    # Step 3: Normalize weights per parent
+    # Step 4: Normalize weights per parent
     df["base_weight"] = df.groupby("parent")["base_weight_raw"].transform(
         lambda s: (s - s.min()) / (s.max() - s.min() if s.max() != s.min() else 1)
     )