revise config file & remove csv file & add dataset info to dataset-index.yml

dataset-index.yml

@@ -1023,3 +1023,15 @@
     paper: https://arxiv.org/pdf/2402.09391
     configpath: opencompass/configs/datasets/SmolInstruct/smolinstruct_gen.py
     configpath_llmjudge: ''
+- medbullets:
+    name: Medbullets
+    category: Science /Medicine
+    paper: https://arxiv.org/pdf/2402.18060
+    configpath: opencompass/configs/datasets/Medbullets/medbullets_gen.py
+    configpath_llmjudge: opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen.py
+- medmcqa:
+    name: medmcqa
+    category: Science /Medicine
+    paper: https://arxiv.org/pdf/2203.14371
+    configpath: opencompass/configs/datasets/medmcqa/medmcqa_gen.py
+    configpath_llmjudge: opencompass/configs/datasets/medmcqa/medmcqa_llmjudge_gen.py

opencompass/configs/datasets/Medbullets/medbullets_gen_60c8f5.py

@@ -8,14 +8,6 @@ import os
 SYSTEM_PROMPT = 'You are a helpful medical assistant.\n\n' # Where to put this?
 ZERO_SHOT_PROMPT = 'Q: {question}\n Please select the correct answer from the options above and output only the corresponding letter (A, B, C, D, or E) without any explanation or additional text.\n'
 
-# 将相对于当前文件的相对路径转换为绝对路径
-def to_abs_path(relative_path: str) -> str:
-    # 当前脚本所在目录
-    base_dir = os.path.dirname(os.path.abspath(__file__))
-    # 拼接并规范化绝对路径
-    abs_path = os.path.abspath(os.path.join(base_dir, relative_path))
-    return abs_path
-
 # Reader configuration
 reader_cfg = dict(
     input_columns=[
@@ -56,7 +48,7 @@ eval_cfg = dict(
 medbullets_dataset = dict(
     type=MedbulletsDataset,
     abbr='medbullets',
-    path=to_abs_path('data/medbullets.csv'),
+    path='opencompass/medbullets',
     prompt_mode='zero-shot',
     reader_cfg=reader_cfg,
     infer_cfg=infer_cfg,

opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen_60c8f5.py

@@ -29,15 +29,6 @@ GRADER_TEMPLATE = """
     Judging the correctness of candidates' answers:
 """.strip()
 
-
-# 将相对于当前文件的相对路径转换为绝对路径
-def to_abs_path(relative_path: str) -> str:
-    # 当前脚本所在目录
-    base_dir = os.path.dirname(os.path.abspath(__file__))
-    # 拼接并规范化绝对路径
-    abs_path = os.path.abspath(os.path.join(base_dir, relative_path))
-    return abs_path
-
 # Reader configuration
 reader_cfg = dict(
     input_columns=[
@@ -91,7 +82,7 @@ eval_cfg = dict(
         ),
         dataset_cfg=dict(
             type=MedbulletsDataset,
-            path=to_abs_path('data/medbullets.csv'),
+            path='opencompass/medbullets',
             prompt_mode='zero-shot',
             reader_cfg=reader_cfg,
         ),
@@ -104,7 +95,7 @@ eval_cfg = dict(
 medbullets_dataset = dict(
     type=MedbulletsDataset,
     abbr='medbullets',
-    path=to_abs_path('data/medbullets.csv'),
+    path='opencompass/medbullets',
     prompt_mode='zero-shot',
     reader_cfg=reader_cfg,
     infer_cfg=infer_cfg,

opencompass/datasets/Medbullets.py

@@ -5,7 +5,7 @@ from datasets import Dataset
 
 from opencompass.openicl import BaseEvaluator
 from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
-from opencompass.utils import get_logger
+from opencompass.utils import get_data_path, get_logger
 
 from .base import BaseDataset
 
@@ -39,6 +39,7 @@ class MedbulletsDataset(BaseDataset):
     @staticmethod
     def load(path: str, prompt_mode: str = 'zero-shot', **kwargs):
         # 读取 CSV 文件为 DataFrame，并将 NaN 转为空字符串
+        path = get_data_path(path)
         df = pd.read_csv(path, encoding='utf-8')
         df = df.fillna('')
 

opencompass/utils/datasets_info.py

@@ -446,6 +446,11 @@ DATASETS_MAPPING = {
         "hf_id": "",
         "local": "./data/ChemBench4K",
     },
+    "opencompass/medbullets": {
+        "ms_id": "",
+        "hf_id": "",
+        "local": "./opencompass/configs/datasets/Medbullets/data/medbullets.csv",
+    },
 
 }