mv dir

stellaHSR · Mar 27, 2024 · 3b8c83d · 3b8c83d
1 parent f99c7b3
commit 3b8c83d
Show file tree

Hide file tree

Showing 5 changed files with 4 additions and 4 deletions.
diff --git a/sub_swebench_dataset/readme.md → benchmark/sub_swebench_dataset/readme.md b/sub_swebench_dataset/readme.md → benchmark/sub_swebench_dataset/readme.md
diff --git a/sub_swebench_dataset/scikit-learn-68.csv → .../sub_swebench_dataset/scikit-learn-68.csv b/sub_swebench_dataset/scikit-learn-68.csv → .../sub_swebench_dataset/scikit-learn-68.csv
diff --git a/sub_swebench_dataset/sub_swebench.csv → ...ark/sub_swebench_dataset/sub_swebench.csv b/sub_swebench_dataset/sub_swebench.csv → ...ark/sub_swebench_dataset/sub_swebench.csv
diff --git a/benchmark/swe_bench/data/load_dataset.py b/benchmark/swe_bench/data/load_dataset.py
@@ -20,13 +20,13 @@ def load_oracle_dataset(dataset_name_or_path: str = "", split: str = "test", exi
     lens = np.array(list(map(len, dataset["text"])))
     dataset = dataset.select(np.argsort(lens))
 
-    if len(existing_ids) > 0:
+    if existing_ids:
         dataset = dataset.filter(
             lambda x: x["instance_id"] not in existing_ids,
             desc="Filtering out existing ids",
             load_from_cache_file=False,
         )
-    if len(SCIKIT_LEARN_IDS) > 0:
+    if SCIKIT_LEARN_IDS:
         dataset = dataset.filter(
             lambda x: x["instance_id"] in SCIKIT_LEARN_IDS,
             desc="Filtering out subset_instance_ids",

diff --git a/benchmark/swe_bench/inference/const.py b/benchmark/swe_bench/inference/const.py
@@ -5,8 +5,8 @@
 
 from metagpt.const import METAGPT_ROOT
 
-SUBSET_DATASET = METAGPT_ROOT / "sub_swebench_dataset" / "sub_swebench.csv"
-SUBSET_DATASET_SKLERARN = METAGPT_ROOT / "sub_swebench_dataset" / "scikit-learn-68.csv"
+SUBSET_DATASET = METAGPT_ROOT / "benchmark" / "swe_bench" / "sub_swebench_dataset" / "sub_swebench.csv"
+SUBSET_DATASET_SKLERARN = METAGPT_ROOT / "benchmark" / "sub_swebench_dataset" / "scikit-learn-68.csv"
 TESTBED = METAGPT_ROOT / "benchmark" / "swe_bench" / "data" / "repos"
 
 # SCIKIT_LEARN_IDS: A list of instance identifiers from 'sub_swebench.csv' within SUBSET_DATASET.