* fix for unittest

README_ZH.md

@@ -30,7 +30,6 @@ Data-Juicer（包含[DJ-SORA](docs/DJ_SORA_ZH.md)）正在积极更新和维护
 
 欢迎提issues/PRs，以及加入我们的[Slack频道](https://join.slack.com/t/data-juicer/shared_invite/zt-23zxltg9d-Z4d3EJuhZbCLGwtnLWWUDg?spm=a2c22.12281976.0.0.7a8275bc8g7ypp) 或[钉钉群](https://qr.dingtalk.com/action/joingroup?spm=a2c22.12281976.0.0.7a8275bc8g7ypp&code=v1,k1,C0DI7CwRFrg7gJP5aMC95FUmsNuwuKJboT62BqP5DAk=&_dt_no_comment=1&origin=11) 进行讨论!
 
-
 ----
 
 ## 新消息

data_juicer/core/__init__.py

@@ -2,5 +2,4 @@
 from .data import NestedDataset
 from .executor import Executor
 from .exporter import Exporter
-from .sandbox.pipelines import SandBoxExecutor
 from .tracer import Tracer

data_juicer/core/sandbox/pipelines.py

@@ -2,12 +2,12 @@
 import os.path
 from typing import List
 
+import wandb
 import yaml
 from jsonargparse import Namespace as JsonNamespace
 from jsonargparse import namespace_to_dict
 from loguru import logger
 
-import wandb
 from data_juicer.config import init_configs, merge_config
 from data_juicer.core import Analyser
 from data_juicer.core import Executor as DjExecutor

tests/ops/filter/test_video_tagging_from_frames_filter.py

@@ -28,7 +28,7 @@ def _run_video_tagging_from_frames_filter(self,
         res_list = dataset.to_list()
         self.assertEqual(res_list, target_list)
 
-    def test_default(self):
+    def test(self):
         ds_list = [{
             'text': f'{SpecialTokens.video} 白色的小羊站在一旁讲话。旁边还有两只灰色猫咪和一只拉着灰狼的猫咪。',
             'videos': [self.vid1_path]
@@ -74,7 +74,6 @@ def test_uniform(self):
                                           frame_num=10)
         self._run_video_tagging_from_frames_filter(op, ds_list, tgt_list)
 
-
     def test_contain_any(self):
         ds_list = [{
             'text':
@@ -133,7 +132,6 @@ def test_contain_all(self):
                                           any_or_all='any')
         self._run_video_tagging_from_frames_filter(op, ds_list, tgt_list)
 
-
     def test_all(self):
         ds_list = [{
             'text':
@@ -159,7 +157,6 @@ def test_all(self):
                                           any_or_all='all')
         self._run_video_tagging_from_frames_filter(op, ds_list, tgt_list)
 
-
     def test_multi_process(self):
         # WARNING: current parallel tests only work in spawn method
         import multiprocess

tests/ops/mapper/test_video_tagging_from_frames_mapper.py

@@ -27,7 +27,7 @@ def _run_video_tagging_from_frames_mapper(self,
         res_list = dataset.to_list()
         self.assertEqual(res_list, target_list)
 
-    def test_default(self):
+    def test(self):
         ds_list = [{
             'text': f'{SpecialTokens.video} 白色的小羊站在一旁讲话。旁边还有两只灰色猫咪和一只拉着灰狼的猫咪。',
             'videos': [self.vid1_path]

tools/sandbox_starter.py

@@ -4,7 +4,7 @@
 from loguru import logger
 
 from data_juicer.config import dict_to_namespace, init_configs
-from data_juicer.core import SandBoxExecutor
+from data_juicer.core.sandbox.pipelines import SandBoxExecutor
 
 
 def prepare_side_configs(config):