feat: joblib cache (#749)

* cache function

* fix test

* bin cache

* fix test

* fix test

* fix test

* cache for different source

* cache for localenv

* remove unnecessary log

* reformat

* remove unrelated modify

rdagent/components/coder/data_science/model/eval_tests/model_test.txt

@@ -35,6 +35,17 @@ print(f"test_ids length: {len(test_ids)}")
 
 train_X, val_X, train_y, val_y = train_test_split(X, y, test_size=0.8, random_state=42)
 
+
+import sys
+import reprlib
+from joblib.memory import MemorizedFunc
+
+
+def get_original_code(func):
+    if isinstance(func, MemorizedFunc):
+        return func.func.__code__
+    return func.__code__
+
 print("train_X:", aRepr.repr(train_X))
 print("train_y:", aRepr.repr(train_y))
 print("val_X:", aRepr.repr(val_X))
@@ -46,10 +57,12 @@ print(f"val_X.shape: {val_X.shape}" if hasattr(val_X, 'shape') else f"val_X leng
 print(f"val_y.shape: {val_y.shape}" if hasattr(val_y, 'shape') else f"val_y length: {len(val_y)}")
 
 
+
 def debug_info_print(func):
     def wrapper(*args, **kwargs):
+        original_code = get_original_code(func)
         def local_trace(frame, event, arg):
-            if event == "return" and frame.f_code == func.__code__:
+            if event == "return" and frame.f_code == original_code:
                 print("\n" + "="*20 + "Running model training code, local variable values:" + "="*20)
                 for k, v in frame.f_locals.items():
                     printed = aRepr.repr(v)

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

@@ -40,6 +40,11 @@ model_coder:
     {{ feature_code }}
     2. You should avoid using logging module to output information in your generated code, and instead use the print() function.
     3. If the model can both be implemented by PyTorch and Tensorflow, please use pytorch for broader compatibility.
+    4. You should use the following cache decorator to cache the results of the function:
+    ```python
+    from joblib import Memory
+    memory = Memory(location='/tmp/cache', verbose=0)
+    @memory.cache``
 
     ## Output Format
     {% if out_spec %}