Merged in feature/median-cost-analysis (pull request #912)

Add median

* Add median


Approved-by: Siddhant Medar

src/scripts/historical_cost_analysis.py

@@ -24,25 +24,28 @@ def _build_summary_row(df: pd.DataFrame, usage_key: str, file_count: int) -> dic
     caching_cost = usage_df.loc[is_cache, "total_cost"].sum()
 
     non_cache_df = usage_df.loc[~is_cache].copy()
+    median_cost_per_contract = 0.0
     if non_cache_df.empty:
         adjusted_total_cost = 0.0
     else:
         by_file = non_cache_df.groupby("file_name", dropna=False)["total_cost"].sum()
         outlier_file = by_file.idxmax()
-        adjusted_total_cost = non_cache_df.loc[
-            non_cache_df["file_name"] != outlier_file, "total_cost"
-        ].sum()
+        filtered_by_file = by_file.drop(index=outlier_file)
+        adjusted_total_cost = float(filtered_by_file.sum())
+        if not filtered_by_file.empty:
+            median_cost_per_contract = float(filtered_by_file.median())
 
     return {
         "Batch": os.path.basename(usage_key),
         "caching_cost": round(float(caching_cost), 6),
         "total_cost": round(float(adjusted_total_cost), 6),
         "file_count": int(file_count),
-        "cost_per_contract": (
+        "mean_cost_per_contract": (
             round(float(adjusted_total_cost) / float(file_count), 6)
             if file_count
             else 0.0
         ),
+        "median_cost_per_contract": round(float(median_cost_per_contract), 6),
     }
 
 
@@ -119,12 +122,19 @@ def run_historical_cost_analysis(
             "caching_cost",
             "total_cost",
             "file_count",
-            "cost_per_contract",
+            "mean_cost_per_contract",
+            "median_cost_per_contract",
         ],
     )
     if summary_df.empty:
         summary_df = pd.DataFrame(
-            columns=["caching_cost", "total_cost", "file_count", "cost_per_contract"]
+            columns=[
+                "caching_cost",
+                "total_cost",
+                "file_count",
+                "mean_cost_per_contract",
+                "median_cost_per_contract",
+            ]
         )
         summary_df.index.name = "Batch"
     else: