refactor: Improve data handling and representation in eval tests and prompts (#740)

rdagent/components/coder/data_science/raw_data_loader/eval_tests/data_loader_test.txt

@@ -33,11 +33,11 @@ X, y, X_test, test_ids = debug_info_print(load_data)()
 
 
 def get_length(data):
-    return len(data) if isinstance(data, list) else data.shape[0]
+    return data.shape[0] if hasattr(data, 'shape') else len(data)
 
 
 def get_width(data):
-    return 1 if isinstance(data, list) else data.shape[1:]
+    return data.shape[1:] if hasattr(data, 'shape') else 1
 
 
 def get_column_list(data):

rdagent/components/coder/data_science/raw_data_loader/prompts.yaml

@@ -410,9 +410,7 @@ data_loader_eval:
     The data loader is part of the whole workflow. The user has executed the entire pipeline and provided additional stdout.
 
     **Workflow Code:**
-    ```python
     {{ workflow_code }}
-    ```
 
     You should evaluate both the data loader test results and the overall workflow execution. **Approve the code only if both tests pass.**
     {% endif %}