[Feature] Update APPS (#985)

* update post process

* update post process

configs/datasets/apps/README.md

@@ -15,6 +15,8 @@ DatasetDict({
     })
 })
 ```
+We also offer an apps_mini subset, which includes 1500 questions divided proportionally of introductory, interview, and competition categories, with a ratio of 1:1:1(500 questions each).
+
 ## How to Use
 You can also filter the dataset based on difficulty level: introductory, interview and competition. Just pass a list of difficulty levels to the filter. For example, if you want the most challenging questions, you need to select the competition level:
 ```python

configs/datasets/apps/apps_gen.py

@@ -1,4 +1,4 @@
 from mmengine.config import read_base
 
 with read_base():
-    from .apps_gen_d82929 import APPS_datasets  # noqa: F401, F403
+    from .apps_gen_c7893a import APPS_datasets  # noqa: F401, F403

configs/datasets/apps/apps_gen_c7893a.py

@@ -8,7 +8,7 @@ APPS_reader_cfg = dict(input_columns=["question", "starter"], output_column="pro
 APPS_infer_cfg = dict(
     prompt_template=dict(
         type=PromptTemplate,
-        template="\nQUESTION:\n{question} {starter}\nANSWER:\n"),
+        template="Please write a python program to address the following QUESTION. Your ANSWER should be in a code block format like this: ```python # Write your code here ```. \nQUESTION:\n{question} {starter}\nANSWER:\n"),
     retriever=dict(type=ZeroRetriever),
     inferencer=dict(type=GenInferencer, max_out_len=512),
 )

opencompass/datasets/apps.py

@@ -89,14 +89,16 @@ EOF_STRINGS = ['\nQUESTION', '\n---', '\nANSWER', '<|endoftext|>']
 @ICL_EVALUATORS.register_module()
 class APPSEvaluator(BaseEvaluator):
 
-    def truncate_after_eof_strings(self, text):
-        pattern = '|'.join(re.escape(s) for s in EOF_STRINGS)
-        match = re.search(pattern, text)
-
-        if match:
-            return text[:match.start()]
-        else:
-            return text
+    def post_process(self, text):
+        if '```' in text:
+            blocks = re.findall(r'```(.*?)```', text, re.DOTALL)
+            if len(blocks) == 0:
+                text = text.split('```')[1]  # fall back to default strategy
+            else:
+                text = blocks[0]  # fetch the first code block
+                if not text.startswith('\n'):  # starting with ```python
+                    text = text[max(text.find('\n') + 1, 0):]
+        return text
 
     TIMEOUT = 10
 
@@ -226,7 +228,7 @@ class APPSEvaluator(BaseEvaluator):
         assert len(predictions) == len(references)
         generations = defaultdict(list)
         for refer, pred in zip(references, predictions):
-            pred = self.truncate_after_eof_strings(pred)
+            pred = self.post_process(pred)
             generations[refer].append(pred)
         # convert to non-duplicated version
         test_set = test_set.to_pandas()