docs: Updated documentation for all the major scenarios. (#190)

* Fixed some bugs introduced during refactoring. * update data_agent_fin_doc * Updated documentation for the four major scenarios * feat: remove pdfs and enable online pdf readings (#183) * remove pdfs and enable online pdf readings * update doc format * use url as key * feat: add entry for rdagent. (#187) * Add entries * update entry for rdagent * lint * fix typo * docs: Demo links (#188) add demo links * fix: Fix a fail href in readme (#189) * fix a ci bug * doc * feat: remove pdfs and enable online pdf readings (#183) * remove pdfs and enable online pdf readings * update doc format * use url as key * feat: add entry for rdagent. (#187) * Add entries * update entry for rdagent * lint * fix typo * doc * Updated documentation for med_model scenarios. * fix a ci bug --------- Co-authored-by: Xu Yang <peteryang@vip.qq.com> Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> Co-authored-by: XianBW <36835909+XianBW@users.noreply.github.com> Co-authored-by: SH-Src <suhan.c@outlook.com>
2026-08-06 11:37:44 +00:00 · 2024-08-09 13:27:33 +08:00
parent 05a3b67aa8
commit a75c19b17c
8 changed files with 301 additions and 136 deletions
@@ -1,20 +1,38 @@
 from pathlib import Path

+from pydantic_settings import BaseSettings
+
 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
+        env_prefix = "DM_"
+        """Use `DM_` 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"
+    """Scenario class for data mining model"""
+
    hypothesis_gen: str = "rdagent.scenarios.data_mining.proposal.model_proposal.DMModelHypothesisGen"
+    """Hypothesis generation class"""
+
    hypothesis2experiment: str = "rdagent.scenarios.data_mining.proposal.model_proposal.DMModelHypothesis2Experiment"
+    """Hypothesis to experiment class"""
+
    coder: str = "rdagent.scenarios.data_mining.developer.model_coder.DMModelCoSTEER"
+    """Coder class"""
+
    runner: str = "rdagent.scenarios.data_mining.developer.model_runner.DMModelRunner"
+    """Runner class"""
+
    summarizer: str = "rdagent.scenarios.data_mining.developer.feedback.DMModelHypothesisExperiment2Feedback"
+    """Summarizer class"""
+
+    evolving_n: int = 10
+    """Number of evolutions"""

    evolving_n: int = 10

@@ -22,7 +40,10 @@ class PropSetting(BasePropSetting):
    # physionet account
    # NOTE: You should apply the account in https://physionet.org/
    username: str = ""
+    """Physionet account username"""
+
    password: str = ""
+    """Physionet account password"""


 PROP_SETTING = PropSetting()
@@ -1,45 +1,79 @@
+from pydantic_settings import BaseSettings
+
 from rdagent.components.workflow.conf import BasePropSetting


 class ModelBasePropSetting(BasePropSetting):
    class Config:
-        env_prefix = "QLIB_MODEL_"  # Use MODEL_CODER_ as prefix for environment variables
-        protected_namespaces = ()  # Add 'model_' to the protected namespaces
+        env_prefix = "QLIB_MODEL_"
+        """Use `QLIB_MODEL_` as prefix for environment variables"""
+        protected_namespaces = ()
+        """Add 'model_' to the protected namespaces"""

+    # 1) override base settings
    scen: str = "rdagent.scenarios.qlib.experiment.model_experiment.QlibModelScenario"
+    """Scenario class for Qlib Model"""
+
    hypothesis_gen: str = "rdagent.scenarios.qlib.proposal.model_proposal.QlibModelHypothesisGen"
+    """Hypothesis generation class"""
+
    hypothesis2experiment: str = "rdagent.scenarios.qlib.proposal.model_proposal.QlibModelHypothesis2Experiment"
+    """Hypothesis to experiment class"""
+
    coder: str = "rdagent.scenarios.qlib.developer.model_coder.QlibModelCoSTEER"
+    """Coder class"""
+
    runner: str = "rdagent.scenarios.qlib.developer.model_runner.QlibModelRunner"
+    """Runner class"""
+
    summarizer: str = "rdagent.scenarios.qlib.developer.feedback.QlibModelHypothesisExperiment2Feedback"
+    """Summarizer class"""

    evolving_n: int = 10
+    """Number of evolutions"""


 class FactorBasePropSetting(BasePropSetting):
    class Config:
-        env_prefix = "QLIB_FACTOR_"  # Use MODEL_CODER_ as prefix for environment variables
-        protected_namespaces = ()  # Add 'model_' to the protected namespaces
+        env_prefix = "QLIB_FACTOR_"
+        """Use `QLIB_FACTOR_` as prefix for environment variables"""
+        protected_namespaces = ()
+        """Add 'factor_' to the protected namespaces"""

    # 1) override base settings
-    # TODO: model part is not finished yet
    scen: str = "rdagent.scenarios.qlib.experiment.factor_experiment.QlibFactorScenario"
+    """Scenario class for Qlib Factor"""
+
    hypothesis_gen: str = "rdagent.scenarios.qlib.proposal.factor_proposal.QlibFactorHypothesisGen"
+    """Hypothesis generation class"""
+
    hypothesis2experiment: str = "rdagent.scenarios.qlib.proposal.factor_proposal.QlibFactorHypothesis2Experiment"
+    """Hypothesis to experiment class"""
+
    coder: str = "rdagent.scenarios.qlib.developer.factor_coder.QlibFactorCoSTEER"
+    """Coder class"""
+
    runner: str = "rdagent.scenarios.qlib.developer.factor_runner.QlibFactorRunner"
+    """Runner class"""
+
    summarizer: str = "rdagent.scenarios.qlib.developer.feedback.QlibFactorHypothesisExperiment2Feedback"
+    """Summarizer class"""

    evolving_n: int = 10
-
-    # 2) sub task specific:
-    report_result_json_file_path: str = "git_ignore_folder/report_list.json"
-    max_factors_per_exp: int = 10000
+    """Number of evolutions"""


 class FactorFromReportPropSetting(FactorBasePropSetting):
-    # Override the scen attribute
+    # 1) override the scen attribute
    scen: str = "rdagent.scenarios.qlib.experiment.factor_from_report_experiment.QlibFactorFromReportScenario"
+    """Scenario class for Qlib Factor from Report"""
+
+    # 2) sub task specific:
+    report_result_json_file_path: str = "git_ignore_folder/report_list.json"
+    """Path to the JSON file listing research reports for factor extraction"""
+
+    max_factors_per_exp: int = 10000
+    """Maximum number of factors implemented per experiment"""


 FACTOR_PROP_SETTING = FactorBasePropSetting()
@@ -8,19 +8,23 @@ SELECT_METHOD = Literal["random", "scheduler"]

 class FactorImplementSettings(BaseSettings):
    class Config:
-        env_prefix = "FACTOR_CODER_"  # Use FACTOR_CODER_ as prefix for environment variables
+        env_prefix = "FACTOR_CODER_"
+        """Use `FACTOR_CODER_` as prefix for environment variables"""

    coder_use_cache: bool = False
-    data_folder: str = str(
-        (Path().cwd() / "git_ignore_folder" / "factor_implementation_source_data").absolute(),
-    )
-    data_folder_debug: str = str(
-        (Path().cwd() / "git_ignore_folder" / "factor_implementation_source_data_debug").absolute(),
-    )
-    cache_location: str = str(
-        (Path().cwd() / "git_ignore_folder" / "factor_implementation_execution_cache").absolute(),
-    )
-    enable_execution_cache: bool = True  # whether to enable the execution cache
+    """Indicates whether to use cache for the coder"""
+
+    data_folder: str = "git_ignore_folder/factor_implementation_source_data"
+    """Path to the folder containing financial data (default is fundamental data in Qlib)"""
+
+    data_folder_debug: str = "git_ignore_folder/factor_implementation_source_data_debug"
+    """Path to the folder containing partial financial data (for debugging)"""
+
+    cache_location: str = "git_ignore_folder/factor_implementation_execution_cache"
+    """Path to the cache location"""
+
+    enable_execution_cache: bool = True
+    """Indicates whether to enable the execution cache"""

    # TODO: the factor implement specific settings should not appear in this settings
    # Evolving should have a method specific settings
@@ -36,17 +40,26 @@ class FactorImplementSettings(BaseSettings):
    v2_error_summary: bool = False
    v2_knowledge_sampler: float = 1.0

-    file_based_execution_timeout: int = 120  # seconds for each factor implementation execution
+    file_based_execution_timeout: int = 120
+    """Timeout in seconds for each factor implementation execution"""
+
+    select_method: str = "random"
+    """Method for the selection of factors implementation"""

-    select_method: SELECT_METHOD = "random"
    select_threshold: int = 10
+    """Threshold for the number of factor selections"""

    max_loop: int = 10
+    """Maximum number of task implementation loops"""

    knowledge_base_path: Union[str, None] = None
+    """Path to the knowledge base"""
+
    new_knowledge_base_path: Union[str, None] = None
+    """Path to the new knowledge base"""

    python_bin: str = "python"
+    """Path to the Python binary"""


 FACTOR_IMPLEMENT_SETTINGS = FactorImplementSettings()