saealib.ComparisonSurrogate#

class saealib.ComparisonSurrogate[ソース]#

ベースクラス: Surrogate

Base class for relative-fitness (comparison) surrogates.

Subclass this when train_y holds binary comparison labels {0, 1} and predictions are win-probability estimates in [0, 1].

predict_proba is the primary interface; predict delegates to it by default so that managers designed for Surrogate still work.

Methods

`__init__`
`contract`	Return the surrogate model contract.
`fit`	Fit the surrogate model.
`post_fit`	Post-fit lifecycle hook; override to inject custom processing.
`predict`	Delegate to `predict_proba`.
`predict_proba`	Return win-probability estimates.
`with_post_fit`	Return a copy of this surrogate with `fn` appended to the post-fit hook.

Method Details

ComparisonSurrogate.contract()#

Return the surrogate model contract.

abstractmethod ComparisonSurrogate.fit(train_x, train_y)#

Fit the surrogate model.

パラメータ:

train_x (np.ndarray) -- Training input data. shape: (n_samples, n_features)
train_y (np.ndarray) -- Training output data. shape: (n_samples, n_obj) For n_obj == 1, shape (n_samples,) is also accepted.

戻り値の型:

None

ComparisonSurrogate.post_fit(train_x, train_y, ctx=None)#

Post-fit lifecycle hook; override to inject custom processing.

パラメータ:

train_x (np.ndarray) -- Training input data used for this fit. shape: (n_samples, n_features)
train_y (np.ndarray) -- Training output data used for this fit. shape: (n_samples, n_obj)
ctx (OptimizationState or None, optional) -- Current optimization context.

戻り値の型:

None

ComparisonSurrogate.predict(test_x)[ソース]#

Delegate to predict_proba.

abstractmethod ComparisonSurrogate.predict_proba(test_x)[ソース]#

Return win-probability estimates.

パラメータ:: test_x (np.ndarray) -- Input data. shape: (n_samples, n_features)
戻り値:: value shape: (n_samples, 1), values in [0, 1]. std is None unless the model supports uncertainty.
戻り値の型:: SurrogatePrediction

ComparisonSurrogate.with_post_fit(fn)#

Return a copy of this surrogate with fn appended to the post-fit hook.