config

Classes

`ProjectPath`	Path-like object for using variable based absolute paths
`DataSourceType`	Enum for data source types.
`FeatureConfig`	Configuration for features used in the algorithm.
`DataRequests`	Individual Data Request
`DataConfig`	Configuration for data used in the algorithm.
`RewardConfig`	Configuration for the reward function used in the trading environment.
`TradeMode`	Enum for trade modes.
`PortfolioConfig`	!!! abstract "Usage Documentation"
`StockEnv`	!!! abstract "Usage Documentation"
`AgentConfig`	Configuration for the agent used in the algorithm.
`AnalysisConfig`	Configuration for the analysis of backtest results.
`BackTestConfig`	Configuration for backtesting the algorithm.
`RRConfig`	Configuration for the algorithm.

Module Contents

class config.ProjectPath(/, **data)

Bases: pydantic.BaseModel

Path-like object for using variable based absolute paths

Parameters:: data (Any)

PROJECT_ROOT: ClassVar[pathlib.Path]

OUT_DIR: ClassVar[pathlib.Path | None] = None

BACKTEST_DIR: ClassVar[pathlib.Path | None] = None

VERSION: ClassVar[str] = ''

ACTIVE_UUID: ClassVar[uuid.UUID | None] = None

path: str = None

classmethod use_cache()

classmethod cache()

classmethod validate_path(data)

Return type:: dict[str, str]

__str__()

Return type:: str

as_path()

Return type:: pathlib.Path

class config.DataSourceType

Bases: str, enum.Enum

Enum for data source types.

ALPACA = 'alpaca'

class config.FeatureConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for features used in the algorithm.

Parameters:: data (Any)

classmethod parse_features(data)

Parameters:: data (Any)

features: List[trading.src.features.generic_features.Feature] = None

fill_strategy: str = None

__repr__()

class config.DataRequests(/, **data)

Bases: pydantic.BaseModel

Individual Data Request

Parameters:: data (Any)

dataset_name: str = None

source: DataSourceType = None

endpoint: str = None

kwargs: Dict[str, Any] = None

class config.DataConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for data used in the algorithm.

Parameters:: data (Any)

start_date: str = None

end_date: str = None

time_step_unit: alpaca.data.timeframe.TimeFrameUnit = None

time_step_period: int = None

cache_path: ProjectPath = None

cache_enabled: bool = None

requests: List[DataRequests] = None

validation_split: float = None

classmethod validate_time_step_unit(value)

Validate the time_step_unit field to ensure it is a valid TimeFrameUnit.

Parameters:: value (alpaca.data.timeframe.TimeFrameUnit | str)
Return type:: alpaca.data.timeframe.TimeFrameUnit

class config.RewardConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the reward function used in the trading environment.

Parameters:: data (Any)

type: str = None

reward_scaling: float = None

kwargs: Dict[str, Any] = None

class config.TradeMode

Bases: str, enum.Enum

Enum for trade modes.

DISCRETE = 'discrete'

CONTINUOUS = 'cont'

class config.PortfolioConfig(/, **data)

Bases: pydantic.BaseModel

!!! abstract “Usage Documentation”: [Models](../concepts/models.md)

A base class for creating Pydantic models.

Parameters:: data (Any)

__class_vars__: The names of the class variables defined on the model.

__private_attributes__: Metadata about the private attributes of the model.

__signature__: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__: Whether model building is completed, or if there are still undefined fields.

__pydantic_core_schema__: The core schema of the model.

__pydantic_custom_init__: Whether the model has a custom __init__ function.

__pydantic_decorators__: Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_generic_metadata__: Metadata for generic models; contains data used for a similar purpose to __args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__: Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__: The name of the post-init method for the model, if defined.

__pydantic_root_model__: Whether the model is a [RootModel][pydantic.root_model.RootModel].

__pydantic_serializer__: The pydantic-core SchemaSerializer used to dump instances of the model.

__pydantic_validator__: The pydantic-core SchemaValidator used to validate instances of the model.

__pydantic_fields__: A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects.

__pydantic_computed_fields__: A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__: A dictionary containing extra values, if [extra][pydantic.config.ConfigDict.extra] is set to ‘allow’.

__pydantic_fields_set__: The names of fields explicitly set during instantiation.

__pydantic_private__: Values of private attributes set on the model instance.

initial_cash: int = None

maintain_history: bool = None

buy_cost_pct: float | List[float] = None

sell_cost_pct: float | List[float] = None

max_positions: int | None = None

trade_mode: TradeMode = None

trade_limit_percent: float = None

hmax: float = None

action_threshold: float = None

max_exposure: float = None

class config.StockEnv(/, **data)

Bases: pydantic.BaseModel

!!! abstract “Usage Documentation”: [Models](../concepts/models.md)

A base class for creating Pydantic models.

Parameters:: data (Any)

__class_vars__: The names of the class variables defined on the model.

__private_attributes__: Metadata about the private attributes of the model.

__signature__: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__: Whether model building is completed, or if there are still undefined fields.

__pydantic_core_schema__: The core schema of the model.

__pydantic_custom_init__: Whether the model has a custom __init__ function.

__pydantic_decorators__: Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_generic_metadata__: Metadata for generic models; contains data used for a similar purpose to __args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__: Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__: The name of the post-init method for the model, if defined.

__pydantic_root_model__: Whether the model is a [RootModel][pydantic.root_model.RootModel].

__pydantic_serializer__: The pydantic-core SchemaSerializer used to dump instances of the model.

__pydantic_validator__: The pydantic-core SchemaValidator used to validate instances of the model.

__pydantic_fields__: A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects.

__pydantic_computed_fields__: A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__: A dictionary containing extra values, if [extra][pydantic.config.ConfigDict.extra] is set to ‘allow’.

__pydantic_fields_set__: The names of fields explicitly set during instantiation.

__pydantic_private__: Values of private attributes set on the model instance.

turbulence_threshold: float | None = None

reward_config: RewardConfig = None

portfolio_config: PortfolioConfig = None

lookback_window: int = None

class config.AgentConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the agent used in the algorithm.

Parameters:: data (Any)

algo: str = None

save_path: ProjectPath = None

deterministic: bool = None

total_timesteps: int = None

kwargs: Dict[str, Any] = None

class config.AnalysisConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the analysis of backtest results.

Parameters:: data (Any)

render_plots: bool = None

save_plots: bool = None

to_csv: bool = None

tickers: List[str] | None = None

class config.BackTestConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for backtesting the algorithm.

Parameters:: data (Any)

save_results: bool = None

backtest_dir: ProjectPath = None

analysis_config: AnalysisConfig = None

classmethod validate_backtest_dir(value)

Parameters:: value (ProjectPath)
Return type:: pydantic.BaseModel

results_path: ProjectPath = None

class config.RRConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the algorithm.

Parameters:: data (Any)

name: str = None

description: str = None

version: str = None

out_dir: ProjectPath = None

agent_config: AgentConfig = None

data_config: DataConfig = None

feature_config: FeatureConfig = None

stock_env: StockEnv = None

backtest_config: BackTestConfig = None

classmethod validate_version(value)

Parameters:: value (str)
Return type:: str

classmethod validate_out_dir(value)

Parameters:: value (ProjectPath)
Return type:: pydantic.BaseModel

classmethod validate_config(value, info)

Parameters:

value (Union[ProjectPath, pydantic.BaseModel])
info (pydantic_core.core_schema.ValidationInfo)

Return type:

pydantic.BaseModel