feat: add timeout settings and cleanup step in data science runner (#539)

* feat: Add timeout settings and cleanup step in data science runner

* lint

rdagent/app/data_science/conf.py

@@ -30,8 +30,8 @@ class DataScienceBasePropSetting(KaggleBasePropSetting):
 
     # model_feature_selection_coder: str = "rdagent.scenarios.kaggle.developer.coder.KGModelFeatureSelectionCoder"
     # """Model Feature Selection Coder class"""
-
     # model_coder: str = "rdagent.scenarios.kaggle.developer.coder.KGModelCoSTEER"
+
     # """Model Coder class"""
 
     ## dev/runner
@@ -45,7 +45,13 @@ class DataScienceBasePropSetting(KaggleBasePropSetting):
     summarizer: str = "rdagent.scenarios.kaggle.developer.feedback.KGExperiment2Feedback"
     """Summarizer class"""
 
+    ## Workflow Related
     consecutive_errors: int = 5
 
+    debug_timeout: int = 600
+    """The timeout limit for running on debugging data"""
+    full_timeout: int = 3600
+    """The timeout limit for running on full data"""
+
 
 DS_RD_SETTING = DataScienceBasePropSetting()

rdagent/core/experiment.py

@@ -271,6 +271,9 @@ class Experiment(
         # If we implement the whole workflow, we don't have to use it, then we remove it.
         self.based_experiments: Sequence[ASpecificWSForExperiment] = based_experiments
 
+        # NOTE: Assumption
+        # - only runner will assign this variable
+        # - We will always create a new Experiment without copying previous results when we goto the next new loop.
         self.result: object = None  # The result of the experiment, can be different types in different scenarios.
         self.sub_results: dict[str, float] = (
             {}

rdagent/scenarios/data_science/dev/runner.py

@@ -16,10 +16,14 @@ class DSRunner(Developer[DSExperiment]):
     def develop(self, exp: DSExperiment) -> DSExperiment:
         ds_docker_conf = DSDockerConf()
         ds_docker_conf.extra_volumes = {f"{DS_RD_SETTING.local_data_path}/{self.scen.competition}": "/kaggle/input"}
-        ds_docker_conf.running_timeout_period = 60 * 60  # 1 hours
+        ds_docker_conf.running_timeout_period = DS_RD_SETTING.full_timeout
 
         de = DockerEnv(conf=ds_docker_conf)
 
+        stdout = exp.experiment_workspace.execute(
+            env=de, entry=f"rm submission.csv scores.csv"
+        )  # Remove previous submission and scores files generated by worklfow.
+
         # execute workflow
         stdout = exp.experiment_workspace.execute(env=de, entry="coverage run main.py")