Data mining (#103)

* scen

* scen2

* app

* fix

* Simplify workflow

* We can share more code in new scenarios

* rename model to rd loop

* Optimize data path

* Update rdagent/app/data_mining/model.py

* Add TODO

* Support GPU

* gpu

---------

Co-authored-by: SH-Src <suhan.c@outlook.com>

rdagent/app/data_mining/conf.py

@@ -0,0 +1,29 @@
+from pathlib import Path
+
+
+from rdagent.components.workflow.conf import BasePropSetting
+
+
+class PropSetting(BasePropSetting):
+    class Config:
+        env_prefix = "DM_"  # Use MODEL_CODER_ as prefix for environment variables
+        protected_namespaces = ()  # Add 'model_' to the protected namespaces
+
+    # 1) overriding the default
+    scen: str = "rdagent.scenarios.data_mining.experiment.model_experiment.DMModelScenario"
+    hypothesis_gen: str = "rdagent.scenarios.data_mining.proposal.model_proposal.DMModelHypothesisGen"
+    hypothesis2experiment: str = "rdagent.scenarios.data_mining.proposal.model_proposal.DMModelHypothesis2Experiment"
+    coder: str = "rdagent.scenarios.data_mining.developer.model_coder.DMModelCoSTEER"
+    runner: str = "rdagent.scenarios.data_mining.developer.model_runner.DMModelRunner"
+    summarizer: str = "rdagent.scenarios.data_mining.developer.feedback.DMModelHypothesisExperiment2Feedback"
+
+    evolving_n: int = 10
+
+    # 2) Extra config for the scenario 
+    # physionet account
+    # NOTE: You should apply the account in https://physionet.org/
+    username: str = ''
+    password: str = ''
+
+
+PROP_SETTING = PropSetting()

rdagent/app/data_mining/model.py

@@ -0,0 +1,27 @@
+import fire
+from rdagent.app.data_mining.conf import PROP_SETTING
+from rdagent.components.workflow.rd_loop import RDLoop
+from rdagent.core.exception import ModelEmptyError
+
+class ModelRDLoop(RDLoop):
+    skip_loop_error = (ModelEmptyError,)
+
+
+def main(path=None, step_n=None):
+    """
+    You can continue running session by
+
+    .. code-block:: python
+
+        dotenv run -- python rdagent/app/data_mining/model.py $LOG_PATH/__session__/1/0_propose  --step_n 1   # `step_n` is a optional paramter
+
+    """
+    if path is None:
+        model_loop = ModelRDLoop(PROP_SETTING)
+    else:
+        model_loop = ModelRDLoop.load(path)
+    model_loop.run(step_n=step_n)
+
+
+if __name__ == "__main__":
+    fire.Fire(main)