gemseo.mlearning.linear_model_fitting.ridge_settings module#

Settings for the scikit-learn ridge algorithm.

Settings Ridge_Settings(*, fit_intercept=True, alpha=1.0, copy_X=True, max_iter=None, positive=False, random_state=None, solver=Solver.AUTO, tol=0.0001)[source]#

Bases: BaseLinearModelFitter_Settings

Settings for the scikit-learn ridge algorithm.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

  • fit_intercept (bool) --

    By default it is set to True.

  • alpha (Annotated[float, Ge(ge=0)] | ndarray) --

    By default it is set to 1.0.

  • copy_X (bool) --

    By default it is set to True.

  • max_iter (Annotated[int, Gt(gt=0)] | None)

  • positive (bool) --

    By default it is set to False.

  • random_state (int | RandomState | None)

  • solver (Solver) --

    By default it is set to "auto".

  • tol (Annotated[float, Ge(ge=0)]) --

    By default it is set to 0.0001.

Return type:

None

alpha: NonNegativeFloat | ndarray = 1.0#

The constant \(\alpha\) that multiplies the L2 term, controlling regularization strength. If an array is passed, penalties are assumed to be specific to the targets.

copy_X: bool = True#

If True, input data will be copied; else, it may be overwritten

max_iter: PositiveInt | None = None#

The maximum number of iterations for conjugate gradient solver. For "sparse_cg" and "lsqr" solvers, the default value is determined by scipy.sparse.linalg. For "sag" solver, the default value is 1000. For "lbfgs" solver, the default value is 15000.

positive: bool = False#

When set to True, forces the coefficients to be positive. Only "lbfgs" solver is supported in this case.

random_state: int | RandomState | None = None#

Used when solver == 'sag' or 'saga' to shuffle the data.

solver: Solver = Solver.AUTO#

The solver to use in the computational routines. If "auto", the solver is automatically chosen based on the type of data.

tol: NonNegativeFloat = 0.0001#

The precision of the solution is determined by tol which specifies a different convergence criterion for each solver:

  • "svd": tol has no impact.

  • "cholesky": tol has no impact.

  • "sparse_cg": norm of residuals smaller than tol.

  • "lsqr": tol is set as atol and btol of scipy.sparse.linalg.lsqr``, which control the norm of the residual vector in terms of the norms of matrix and coefficients.

  • "sag" and "saga": relative change of coef smaller than tol.

  • "lbfgs": maximum of the absolute (projected) gradient=max|residuals| smaller than tol.

Constraints:

  • ge = 0

class Solver(*values)[source]#

Bases: StrEnum

A solver type.

AUTO = 'auto'#
CHOLESKY = 'cholesky'#
LBFGS = 'lbfgs'#
LSQR = 'lsqr'#
SAG = 'sag'#
SAGE = 'saga'#
SPARSE_CG = 'sparse_cg'#
SVD = 'svd'#