Data page

app/backend/data_engine.py

@@ -113,6 +113,15 @@ class DataEngine:
         for _, row in grouped_dataset_count.iterrows():
             dataset_num_map[row["group_name"]] = row["dataset_name"]
 
+        # Create a list of open datasets
+        open_datasets = []
+        for result in results_list:
+            if not result.get("is_closed", False):
+                open_datasets.append(result["dataset_name"])
+
+        # Count open datasets
+        open_dataset_count = len(open_datasets)
+
         grouped_model = df.groupby(["model_name", "group_name"]).agg({
             "ndcg_at_10": "mean",
         }).reset_index()
@@ -121,13 +130,18 @@ class DataEngine:
 
         # Rename columns
         pivot.columns = list(
-            map(lambda x: f"{x[1].capitalize()} Average ({dataset_num_map[x[1]]} datasets)" if x[
-                                                                                                   1] != 'text' else f"Average ({dataset_num_map[x[1]]} datasets)",
+            map(lambda x: f"{x[1].capitalize()} Average ({dataset_num_map[x[1]]} datasets)" if x[1] != 'text' else f"Average ({dataset_num_map[x[1]]} datasets)",
                 pivot.columns))
 
         pivot_dataset = df_result.pivot(index="model_name", columns="dataset_name", values="ndcg_at_10")
 
+        # Calculate open average
+        open_df = df_result[df_result["dataset_name"].isin(open_datasets)]
+        open_avg = open_df.groupby("model_name")["ndcg_at_10"].mean().reset_index()
+        open_avg = open_avg.rename(columns={"ndcg_at_10": f"Open average ({open_dataset_count} datasets)"})
+
         df = pd.merge(df_model, pivot, on="model_name")
+        df = pd.merge(df, open_avg, on="model_name")
         df = pd.merge(df, pivot_dataset, on="model_name")
 
         if df.empty: