evaluate package

Submodules

evaluate.evaluator module

class evaluate.evaluator.Evaluator(args: Namespace)

Bases: object

the evaluator to evaluate the portfolio performance

static add_args(parser: ArgumentParser) → None

add arguments to the parser

to add arguments to the parser, modify the method as follows:

@staticmethod
def add_args(parser: argparse.ArgumentParser) -> None:
    parser.add_argument(
        ...
    )

then add arguments to the parser

Parameters:

parser (argparse.ArgumentParser) – the parser to add arguments to

__init__(args: Namespace) → None

initialize the evaluator

Parameters:

args (argparse.Namespace) – the arguments

reset(initial_balance: float = None) → None

reset the evaluator

Parameters:

initial_balance (float) – the initial balance, if None, use the initial balance from the arguments. Defaults to None.

push(portfolio_value: float, portfolio_weight: Tuple[Tensor, Tensor], current_price: Tensor) → None

push the portfolio value and weight to the evaluator

Parameters:

• portfolio_value (float) – the portfolio value

• portfolio_weight (Tuple[torch.Tensor, torch.Tensor]) – the portfolio weight before and after trading

• current_price (torch.Tensor) – the current price of the considered assets

output_record_to_json(path: str) → None

output the record to a json file

Parameters:

path (str) – the path to the output file

evaluate() → None

evaluate the portfolio

Raises:

• ValueError – portfolio_value_list is empty

• ValueError – portfolio_weight_list is empty

calculate_CR() → float

evaluate the CR metric

Returns:

the CR metric

Return type:

float

calculate_SR() → float

evaluate the SR metric

Returns:

the SR metric

Return type:

float

calculate_SteR() → float

evaluate the SteR metric

Returns:

the SteR metric

Return type:

float

calculate_AT() → float

evaluate the AT metric

Returns:

the AT metric

Return type:

float

calculate_MDD() → float

evaluate the MDD metric

Returns:

the MDD metric

Return type:

float