From 3b8c83db3b905fe6f58d08d5e6da74d31872148c Mon Sep 17 00:00:00 2001
From: stellahsr <stellahsr@126.com>
Date: Wed, 27 Mar 2024 11:31:34 +0800
Subject: [PATCH] mv dir

---
 .../sub_swebench_dataset}/readme.md                 |   0
 .../sub_swebench_dataset}/scikit-learn-68.csv       | Bin
 .../sub_swebench_dataset}/sub_swebench.csv          | Bin
 benchmark/swe_bench/data/load_dataset.py            |   4 ++--
 benchmark/swe_bench/inference/const.py              |   4 ++--
 5 files changed, 4 insertions(+), 4 deletions(-)
 rename {sub_swebench_dataset => benchmark/sub_swebench_dataset}/readme.md (100%)
 rename {sub_swebench_dataset => benchmark/sub_swebench_dataset}/scikit-learn-68.csv (100%)
 rename {sub_swebench_dataset => benchmark/sub_swebench_dataset}/sub_swebench.csv (100%)

diff --git a/sub_swebench_dataset/readme.md b/benchmark/sub_swebench_dataset/readme.md
similarity index 100%
rename from sub_swebench_dataset/readme.md
rename to benchmark/sub_swebench_dataset/readme.md
diff --git a/sub_swebench_dataset/scikit-learn-68.csv b/benchmark/sub_swebench_dataset/scikit-learn-68.csv
similarity index 100%
rename from sub_swebench_dataset/scikit-learn-68.csv
rename to benchmark/sub_swebench_dataset/scikit-learn-68.csv
diff --git a/sub_swebench_dataset/sub_swebench.csv b/benchmark/sub_swebench_dataset/sub_swebench.csv
similarity index 100%
rename from sub_swebench_dataset/sub_swebench.csv
rename to benchmark/sub_swebench_dataset/sub_swebench.csv
diff --git a/benchmark/swe_bench/data/load_dataset.py b/benchmark/swe_bench/data/load_dataset.py
index 03a4b7df7..715d33c2f 100644
--- 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
index 57c2bbe4b..1183c1d7c 100644
--- 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.