physbo package

Subpackages

• physbo.blm package
  • Subpackages
    • physbo.blm.basis package
    • physbo.blm.core package
    • physbo.blm.inf package
    • physbo.blm.lik package
    • physbo.blm.prior package
  • Module contents
    • Model
    • Predictor
• physbo.gp package
  • Subpackages
    • physbo.gp.core package
    • physbo.gp.cov package
    • physbo.gp.inf package
    • physbo.gp.lik package
    • physbo.gp.mean package
  • Module contents
    • Model
    • Predictor
    • Prior
    • SFS
• physbo.misc package
  • Submodules
    • physbo.misc.permutation_importance module
  • Module contents
    • deprecated_warning()
    • set_config()
• physbo.opt package
  • Module contents
    • Adam
• physbo.search package
  • Subpackages
    • physbo.search.discrete package
    • physbo.search.discrete_multi package
    • physbo.search.optimize package
    • physbo.search.range package
    • physbo.search.range_multi package
  • Submodules
    • physbo.search.pareto module
    • physbo.search.score module
    • physbo.search.score_multi module
    • physbo.search.utility module
  • Module contents

Submodules

• physbo.predictor module
  • BasePredictor
    • BasePredictor.delete_stats()
    • BasePredictor.fit()
    • BasePredictor.get_basis()
    • BasePredictor.get_permutation_importance()
    • BasePredictor.get_post_fcov()
    • BasePredictor.get_post_fmean()
    • BasePredictor.get_post_params()
    • BasePredictor.get_post_params_samples()
    • BasePredictor.get_post_samples()
    • BasePredictor.get_predict_samples()
    • BasePredictor.load()
    • BasePredictor.prepare()
    • BasePredictor.save()
    • BasePredictor.update()

Module contents

class physbo.Variable(X=None, t=None, Z=None)

ベースクラス: object

Variable class

Variable class represents a set of pairs of input (X) and output (t).

X: ndarray

Points in the search space. N x d dimensional array, where N is the number of points and d is the dimension of the search space.

Z: ndarray

Random basis representation of the search candidates for each objective. k x N x n dimensional array, where k is the number of objectives, N is the number of points, and n is the dimension of the random basis.

add(X=None, t=None, Z=None)

Adding variables of X, t, Z.

パラメータ:

• X (numpy array) -- N x d dimensional matrix. Each row of X denotes the d-dimensional feature vector of each search candidate.

• t (numpy array) -- N dimensional array (single-objective) or N x k dimensional matrix (multi-objective). The negative energy of each search candidate (value of the objective function to be optimized).

• Z

check_shape()

delete(num_row)

Deleting variables of X, t, Z whose indexes are specified by num_row.

パラメータ:

num_row (numpy array) -- Index array to be deleted.

get_subset(index)

Getting subset of variables as a new Variable.

パラメータ:

index (int or array of int) -- Index of selected action.

戻り値:

variable

戻り値の型:

physbo.Variable

load(file_name)

Loading variables X, t, Z from the file.

パラメータ:

file_name (str) -- A file name for loading variables X, t, Z using numpy.load.

save(file_name)

Saving variables X, t, Z to the file.

パラメータ:

file_name (str) -- A file name for saving variables X, t, Z using numpy.savez_compressed.

t: ndarray

Values of the objective functions to be maximized for each point. N x k dimensional array, where N is the number of points and k is the number of objectives.