Source code for cann.engine.calibration_config

from __future__ import annotations

import ast
from dataclasses import dataclass
from typing import Any, Dict, Literal, Tuple

import numpy as np




@dataclass
class CalibrationConfig:
    """
    Settings for the calibration optimization process.

        Key fields include ``max_iter``, ``pop_size``, ``strategy``, and inference ``batch_size``.
    """

    optimizer: Literal["de"] = "de"
    strategy: str = "best1bin"
    max_iter: int = 2000
    pop_size: int = 10
    tol: float = 0.01
    mutation: float | Tuple[float, float] = (0.5, 1.0)
    recombination: float = 0.7
    init: Literal["latinhypercube", "random"] = "latinhypercube"
    polish: bool = True
    batch_size: int = 32768
    weight_atm: float = 1.0
    seed: int | None = 42



    @classmethod
    def from_dict(cls, cfg: dict) -> CalibrationConfig:
        """
        Create a CalibrationConfig instance from a dictionary.

        Args:
            cfg (dict): Dictionary containing configuration parameters.

        Returns:
            CalibrationConfig: Parsed calibration configuration.

        Notes:
            If ``mutation`` is provided as a string (e.g. from YAML), it is parsed via
            :func:`ast.literal_eval` when possible.
        """
        if "mutation" in cfg:
            mutation = cfg["mutation"]
            if isinstance(mutation, str):
                try:
                    mutation = ast.literal_eval(mutation)
                except (ValueError, SyntaxError):
                    pass
            if isinstance(mutation, list):
                mutation = tuple(mutation)
            cfg["mutation"] = mutation
        return cls(**cfg)






@dataclass
class CalibrationResult:
    """
    Result of the calibration optimization process after optimization.

        Fields include ``optimal_parameters``, ``final_loss``, convergence diagnostics, and
        optional optimizer diagnostics.
    """

    optimal_parameters: np.ndarray
    final_loss: float
    num_iterations: int
    num_function_evals: int
    runtime_seconds: float
    converged: bool
    diagnostics: Dict[str, Any]