CI checks that can be automatically repaired (#119)

* fix isort & black & toml-sort & sphinx error

* fix ci error

* fix ci error

* add comments

* Update Makefile

* change sphinx build command

* add auto-lint

* add black args

* format with black

* Auto Linting document

* fix ci error

---------

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: Young <afe.young@gmail.com>

rdagent/components/benchmark/eval_method.py

@@ -19,18 +19,17 @@ from rdagent.components.coder.factor_coder.CoSTEER.evaluators import (
 from rdagent.components.coder.factor_coder.factor import FactorFBWorkspace
 from rdagent.core.conf import RD_AGENT_SETTINGS
 from rdagent.core.developer import Developer
-
 from rdagent.core.exception import CoderException, RunnerException
 from rdagent.core.experiment import Task, Workspace
 from rdagent.core.scenario import Scenario
 from rdagent.core.utils import multiprocessing_wrapper
 
-
 EVAL_RES = Dict[
     str,
     List[Tuple[FactorEvaluator, Union[object, RunnerException]]],
 ]
 
+
 class TestCase:
     def __init__(
         self,

rdagent/components/coder/factor_coder/CoSTEER/evaluators.py

@@ -356,7 +356,9 @@ class FactorValueEvaluator(FactorEvaluator):
 
         # Check if both dataframe have the same rows count
         if gt_implementation is not None:
-            feedback_str, single_column_result = FactorRowCountEvaluator(self.scen).evaluate(implementation, gt_implementation)
+            feedback_str, single_column_result = FactorRowCountEvaluator(self.scen).evaluate(
+                implementation, gt_implementation
+            )
             conclusions.append(feedback_str)
 
             feedback_str, same_index_result = FactorIndexEvaluator(self.scen).evaluate(
@@ -364,7 +366,9 @@ class FactorValueEvaluator(FactorEvaluator):
             )
             conclusions.append(feedback_str)
 
-            feedback_str, output_format_result = FactorMissingValuesEvaluator(self.scen).evaluate(implementation, gt_implementation)
+            feedback_str, output_format_result = FactorMissingValuesEvaluator(self.scen).evaluate(
+                implementation, gt_implementation
+            )
             conclusions.append(feedback_str)
 
             feedback_str, equal_value_ratio_result = FactorEqualValueCountEvaluator(self.scen).evaluate(
@@ -464,8 +468,10 @@ class FactorFinalDecisionEvaluator(Evaluator):
             except KeyError as e:
                 attempts += 1
                 if attempts >= max_attempts:
-                    raise KeyError("Response from API is missing 'final_decision' or 'final_feedback' key after multiple attempts.") from e
-        
+                    raise KeyError(
+                        "Response from API is missing 'final_decision' or 'final_feedback' key after multiple attempts."
+                    ) from e
+
         return None, None
 
 

rdagent/components/coder/factor_coder/CoSTEER/evolving_strategy.py

@@ -68,8 +68,12 @@ class MultiProcessEvolvingStrategy(EvolvingStrategy):
         # if the number of factors to be implemented is larger than the limit, we need to select some of them
         if FACTOR_IMPLEMENT_SETTINGS.select_ratio < 1:
             # if the number of loops is equal to the select_loop, we need to select some of them
-            implementation_factors_per_round = round(FACTOR_IMPLEMENT_SETTINGS.select_ratio * len(to_be_finished_task_index) + 0.5)  # ceilling
-            implementation_factors_per_round = min(implementation_factors_per_round, len(to_be_finished_task_index))  # but not exceed the total number of tasks
+            implementation_factors_per_round = round(
+                FACTOR_IMPLEMENT_SETTINGS.select_ratio * len(to_be_finished_task_index) + 0.5
+            )  # ceilling
+            implementation_factors_per_round = min(
+                implementation_factors_per_round, len(to_be_finished_task_index)
+            )  # but not exceed the total number of tasks
 
             if FACTOR_IMPLEMENT_SETTINGS.select_method == "random":
                 to_be_finished_task_index = RandomSelect(

rdagent/components/coder/factor_coder/factor.py

@@ -10,11 +10,7 @@ import pandas as pd
 from filelock import FileLock
 
 from rdagent.components.coder.factor_coder.config import FACTOR_IMPLEMENT_SETTINGS
-from rdagent.core.exception import (
-    CodeFormatError,
-    NoOutputError,
-    CustomRuntimeError,
-)
+from rdagent.core.exception import CodeFormatError, CustomRuntimeError, NoOutputError
 from rdagent.core.experiment import Experiment, FBWorkspace, Task
 from rdagent.log import rdagent_logger as logger
 from rdagent.oai.llm_utils import md5_hash

rdagent/components/coder/model_coder/model.py

@@ -16,7 +16,14 @@ from rdagent.utils import get_module_by_module_path
 
 class ModelTask(Task):
     def __init__(
-        self, name: str, description: str, formulation: str, architecture: str, variables: Dict[str, str], hyperparameters: Dict[str, str], model_type: Optional[str] = None
+        self,
+        name: str,
+        description: str,
+        formulation: str,
+        architecture: str,
+        variables: Dict[str, str],
+        hyperparameters: Dict[str, str],
+        model_type: Optional[str] = None,
     ) -> None:
         self.name: str = name
         self.description: str = description
@@ -24,7 +31,9 @@ class ModelTask(Task):
         self.architecture: str = architecture
         self.variables: str = variables
         self.hyperparameters: str = hyperparameters
-        self.model_type: str = model_type  # Tabular for tabular model, TimesSeries for time series model, Graph for graph model 
+        self.model_type: str = (
+            model_type  # Tabular for tabular model, TimesSeries for time series model, Graph for graph model
+        )
 
     def get_task_information(self):
         return f"""name: {self.name}
@@ -107,21 +116,21 @@ class ModelFBWorkspace(FBWorkspace):
             # Initialize all parameters of `m` to `param_init_value`
             for _, param in m.named_parameters():
                 param.data.fill_(param_init_value)
-            
+
             # Execute the model
             if self.target_task.model_type == "Graph":
                 out = m(*data)
             else:
                 out = m(data)
-            
+
             execution_model_output = out.cpu().detach()
             execution_feedback_str = f"Execution successful, output tensor shape: {execution_model_output.shape}"
-            
+
             if MODEL_IMPL_SETTINGS.enable_execution_cache:
                 pickle.dump((execution_feedback_str, execution_model_output), open(cache_file_path, "wb"))
-            
+
             return execution_feedback_str, execution_model_output
-        
+
         except Exception as e:
             return f"Execution error: {e}", None
 

rdagent/components/document_reader/document_reader.py

@@ -1,16 +1,17 @@
 from __future__ import annotations
 
 from pathlib import Path
-import fitz
-from PIL import Image
 from typing import TYPE_CHECKING
 
+import fitz
 from azure.ai.formrecognizer import DocumentAnalysisClient
 from azure.core.credentials import AzureKeyCredential
 from langchain.document_loaders import PyPDFDirectoryLoader, PyPDFLoader
+from PIL import Image
 
 if TYPE_CHECKING:
     from langchain_core.documents import Document
+
 from rdagent.core.conf import RD_AGENT_SETTINGS
 
 
@@ -99,10 +100,11 @@ def load_and_process_pdfs_by_azure_document_intelligence(path: Path) -> dict[str
                 )
     return content_dict
 
+
 def extract_first_page_screenshot_from_pdf(pdf_path: Path) -> Image:
     doc = fitz.open(pdf_path)
     page = doc.load_page(0)
     pix = page.get_pixmap()
     image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
-    
-    return image
+
+    return image

rdagent/components/proposal/model_proposal.py

@@ -15,11 +15,11 @@ from rdagent.core.proposal import (
 )
 from rdagent.oai.llm_utils import APIBackend
 
-
 ModelHypothesis = Hypothesis
 
 prompt_dict = Prompts(file_path=Path(__file__).parent / "prompts.yaml")
 
+
 class ModelHypothesisGen(HypothesisGen):
     prompts: Prompts = prompt_dict
 

rdagent/components/workflow/conf.py

@@ -1,5 +1,6 @@
 from pydantic_settings import BaseSettings
 
+
 class BasePropSetting(BaseSettings):
     """
     The common part of the config for RD Loop to propose and developement
@@ -11,6 +12,7 @@ class BasePropSetting(BaseSettings):
             env_prefix = "DM_MODEL_"  # Use MODEL_CODER_ as prefix for environment variables
             protected_namespaces = ()  # Add 'model_' to the protected namespaces
     """
+
     scen: str = ""
     hypothesis_gen: str = ""
     hypothesis2experiment: str = ""

rdagent/components/workflow/rd_loop.py

@@ -4,6 +4,7 @@ It is from `rdagent/app/qlib_rd_loop/model.py` and try to replace `rdagent/app/q
 """
 
 from typing import Any
+
 from rdagent.components.workflow.conf import BasePropSetting
 from rdagent.core.developer import Developer
 from rdagent.core.proposal import (
@@ -15,11 +16,10 @@ from rdagent.core.proposal import (
 from rdagent.core.scenario import Scenario
 from rdagent.core.utils import import_class
 from rdagent.log import rdagent_logger as logger
+from rdagent.utils.workflow import LoopBase, LoopMeta
 
-from rdagent.utils.workflow import LoopMeta, LoopBase
 
 class RDLoop(LoopBase, metaclass=LoopMeta):
-
     def __init__(self, PROP_SETTING: BasePropSetting):
         scen: Scenario = import_class(PROP_SETTING.scen)()
 
@@ -62,4 +62,4 @@ class RDLoop(LoopBase, metaclass=LoopMeta):
         feedback = self.summarizer.generate_feedback(prev_out["running"], prev_out["propose"], self.trace)
         with logger.tag("ef"):  # evaluate and feedback
             logger.log_object(feedback, tag="feedback")
-        self.trace.hist.append((prev_out["propose"],prev_out["running"] , feedback))
+        self.trace.hist.append((prev_out["propose"], prev_out["running"], feedback))