dora.active_sampling.gp_sampler.GaussianProcess

class dora.active_sampling.gp_sampler.GaussianProcess(lower, upper, kerneldef=None, n_min=None, acq_name='var_sum', explore_priority=0.0001)

GaussianProcess Class

Inherits from the Sampler class and augments pick and update with the mechanics of the GP method

kerneldef

function -- Kernel function definition. See the 'gp' module.

n_min

int -- Number of training samples required before sampler can be trained

acq_name

str -- A string specifying the type of acquisition function used

explore_priority

float, optional -- The priority of exploration against exploitation

hyperparams

numpy.ndarray -- The hyperparameters of the Gaussian Process Inference Model

regressors

list -- List of regressor objects. See 'gp.types.RegressionParams'

y_mean

float -- Mean of the training target outputs

n_tasks

int -- Number of tasks or, equivalently, number of target outputs

See also

Sampler

Base Class

__init__(lower, upper, kerneldef=None, n_min=None, acq_name='var_sum', explore_priority=0.0001)

Initialises the GaussianProcess class

Note

Currently only supports rectangular type restrictions on the

parameter space

Parameters:

• lower (array_like) -- Lower or minimum bounds for the parameter space
• upper (array_like) -- Upper or maximum bounds for the parameter space
• kerneldef (function) -- Kernel function definition. See the 'gp' module.
• n_min (int) -- Number of training samples required before sampler can be trained
• acq_name (str) -- A string specifying the type of acquisition function used
• explore_priority (float, optional) -- The priority of exploration against exploitation

Methods

__init__(lower, upper[, kerneldef, n_min, ...])	Initialises the GaussianProcess class
get_acq_func()
get_explore_priority()
get_hyperparams()
get_kerneldef()
get_min_training_size()
get_real_data()
learn_hyperparams()	Learns the kernel hyperparameters from the data collected so far
pick([n_test, train])	Picks the next location in parameter space for the next observation
predict(Xq[, real])	Infers the mean and variance of the Gaussian process at given locations
print_kernel(kerneldef)
set_acq_name(acq_name)
set_explore_priority(explore_priority)
set_hyperparams(hyperparams)
set_kerneldef(kerneldef)
set_min_training_size(n_min)
train()	Trains the Gaussian process model
update(uid, y_true)	Updates a job with its observed value
update_regressors()	Update the regressors of the Gaussian process model
update_y_mean()	Update the mean of the target outputs