Oracle

Oracle/deepfundingoracle.py

@@ -357,28 +357,33 @@ def visualize_feature_distributions(df):
     plt.show()
 
 
-def normalize_and_clip_weights(df,group_col="parent",weight_col ="final_weight"):
+def normalize_and_clip_weights(df, group_col="parent", weight_col="final_weight"):
     """
-    Ensures all weights are non-negative and sum to 1 within each group.
+    Ensures weights are non-negative and sum to 1 per group.
     """
-    #Clip negative weights to zero
+    if df is None:
+        raise ValueError("DataFrame is None, cannot normalize weights.")
+    if weight_col not in df.columns:
+        raise KeyError(f"`{weight_col}` column not found in DataFrame.")
+    # Clip negatives
     df[weight_col] = df[weight_col].clip(lower=0)
-
-    #Normalize weights within each group
-def normalize_group(x):
-    total = x.sum()
-    if total>0:
-        return x/total
-    return np.ones_like(x)/ len(x)
+    # Normalize within each group
+    def normalize_group(x):
+        total = x.sum()
+        if total > 0:
+            return x / total
+        return np.ones_like(x) / len(x)
     df[weight_col] = df.groupby(group_col)[weight_col].transform(normalize_group)
     return df
 
-
 def normalize_funding(df):
     """
     Normalize funding weights for child repositories grouped by parent.
     """
     print("[INFO] Normalizing funding weights...", flush=True)
+    if df is None or df.empty:
+        print("[WARN] Skipping normalization: DataFrame is None or empty.", flush=True)
+        return df
     df = normalize_and_clip_weights(df)
     print("[INFO] Funding weights normalized successfully.", flush=True)
     return df