feat: Limit training dataset to 10,000 rows for improved processing speed and update success message with dataset information

modal_backend.py

@@ -38,6 +38,14 @@ def train_model(csv_content: str, target_col: str, task_type: str = "classificat
     """
     df = pd.read_csv(io.StringIO(csv_content))
 
+    # Limit training to 10,000 rows for faster processing
+    original_rows = len(df)
+    if original_rows > 10000:
+        df = df.head(10000)
+        print(f"Dataset contains {original_rows:,} rows. Using first 10,000 rows for training to speed up the process.")
+    else:
+        print(f"Dataset contains {original_rows:,} rows. Using all available data for training.")
+
     if target_col not in df.columns:
         raise ValueError(f"Target column '{target_col}' not found in dataset.")
 
@@ -100,10 +108,16 @@ def train_model(csv_content: str, target_col: str, task_type: str = "classificat
         json.dump({"columns": list(X.columns), "task_type": task_type}, f)
     volume.commit()
 
+    # Create training message with dataset info
+    if original_rows > 10000:
+        message = f"{task_type.capitalize()} model trained successfully on 10,000 rows (original dataset had {original_rows:,} rows)."
+    else:
+        message = f"{task_type.capitalize()} model trained successfully on {original_rows:,} rows."
+
     return {
         "model_id": model_id,
         "metrics": metrics,
-        "message": f"{task_type.capitalize()} model trained successfully.",
+        "message": message,
     }