Learn R Programming

⚠️There's a newer version (2.11.14) of this package.Take me there.

SPOT (version 2.5.18)

Sequential Parameter Optimization Toolbox

Description

A set of tools for model-based optimization and tuning of algorithms (hyperparameter tuning respectively hyperparameter optimization). It includes surrogate models, optimizers, and design of experiment approaches. The main interface is spot, which uses sequentially updated surrogate models for the purpose of efficient optimization. The main goal is to ease the burden of objective function evaluations, when a single evaluation requires a significant amount of resources.

Copy Link

Version

Install

install.packages('SPOT')

Monthly Downloads

201

Version

2.5.18

License

GPL (>= 2)

Maintainer

Thomas Bartz-Beielstein

Last Published

January 3rd, 2022

Functions in SPOT (2.5.18)

Build Kriging Model

ranger Interface

Tree Regression Interface

checkLowerSmallerThanUpper

Check That Lower is smaller than Upper

checkTypesOfInput

Check Input Types

Evaluate DACE fit

Fix model parameters DACE

Linear Model Interface

Normalized LHD Design

designUniformRandom

Uniform Design Generator

Build LOESS Model

buildGaussianProcess

Gaussian Process Model Interface

buildEnsembleStack

Ensemble: Stacking

Objective function - Cyclone Simulation: Barth/Muschelknautz

funShiftedSphere

funShiftedSphere

Check for NAs in x lower and upper

Sobol and Levitan Test Function

Correlation: Noisy Gauss

calculationBarthMuschelknautz

Cyclone Simulation: Barth/Muschelknautz

calculationMothes

Cyclone Simulation: Mothes

Descent RSM model

Latin Hypercube Design Generator

corrnoisykriging

Correlation: Noisy Kriging

infillExpectedImprovement

infillExpectedImprovement

infillGetFullPrediction

infillGetFullPrediction

checkFunEvalsDesignSize

Check funEvals Setting against designSize

plotPCAvariance

plotPCAvariance

plotSingleDimFunction

plotSingleDimFunction

Expected Improvement Infill Criterion

getNatDesignFromCoded

Get natural parameter values from coded +-1 representation

normalizeMatrix2

Normalize design 2

Correlation: Kriging

checkInputDimensionsionalityCorrect

Check Dimensions of spotInputs

Correlation: Lin

duplicateAndReplicateHandling

duplicateAndReplicateHandling

predict.ensembleStack

Predict Stacked Ensemble

Wrapper for Maximum Likelihood Estimation

predict.kriging

Predict Kriging Model

objectiveFunctionEvaluation

objectiveFunctionEvaluation Objective Function Evaluation

print.spotBOModel

Print method for BO model

print.spotLOESS

Print method for loess model

repairNonNumeric

Repair Non-numeric Values

print.spotLassoModel

Print method for lasso model

spotAlgEsDominantReco

spotAlgEsDominantReco

Interface SANN to SPOT

Optimal Computing Budget Allocation

Satterthwaite Function

spotAlgEsGetSuccessRate

get Success Rate

print.spotGaussianProcessModel

Print method for Gaussian Process Model

spotAlgEsInterRecoBeSw02

spotAlgEsInterRecoBeSw02

Minimization by GENetic Optimization Using Derivatives

Minimization by L-BFGS-B

Bayesian Optimization Model Interface

S-Ring Simulation Data Obtained With SPOT

Lasso Model Interface

spotAlgEsInitParentPop

Initialize Parent Population

spotAlgEsMarriage

spotAlgEsInterReco

spotAlgEsInterReco

spotAlgEsSelection

spotAlgEsSelection

checkInputTypesInControl

Check input types in the spotControl list.

wrapSystem_parseMatrixToString

wrapSystem_parseMatrixToString

spotAlgEsStratMutation

spotAlgEsStratMutation

checkLowerNotEqualsUpper

Check That Lower and Upper are not Equal

wrapFunctionParallel

Parallelized Function Evaluation Wrapper

wrapSystemCommand

wrapSystemCommand

predict.spotLOESS

Predict loess model

S-Ring Simulation Data

S-Ring Simulation Data

daceStartParameters

Start parameter setup DACE

Gas Sensor Data

predict.spotLassoModel

Prediction method for lasso model

Build Response Surface Model

predict.spotRanger

Predictor for spotExtraTrees

predict.spotRandomForest

Prediction method for random forest

buildRandomForest

Random Forest Interface

Correlation: Cubic

Correlation: Exp

Correlation: Expg

Correlation: Gauss

expectedImprovement

Expected Improvement

print.spotRandomForest

Print method for random forest

Ishigami Test Function

funBaBSimHospital

Optimization of the BaBSim.Hospital Simulator

print.spotRanger

Print method for random forest

getCorrelationMatrix

getCorrelationMatrix

selectN. Select n Design Points

Evolution Strategy Implementation

initialInputCheck

initialInputCheck. Initial Input Check of Spot Configuration

normalizeMatrix

Normalize design

maxNearestNeighbourDistance

maxNearestNeighbourDistance

spotFillControlList

spotFillControlList

Minimization by Latin Hypercube Sampling

Interpolated plot

optimNLOPTR. Minimization by NLOPT

Surface plot of a function

spotPlotSeverity

spotPlotSeverity

prepareBestObjectiveVal

Preprocess y Values to Plot Best Objective Value

predict.spotBOModel

Prediction method for bayesian optimization model

predict.spotGaussianProcessModel

Prediction method for Gaussian Process Model

Print Function DACE Kriging

Surface plot of a model

Sequential Parameter Optimization Toolbox

predict.cvModel

predict.cvModel

print.spotLinearModel

Print method for linear model

print.spotTreeModel

Print method for rpart tree models

Print method for RSM model

checkVerbosityLevels

Check correct verbosity levels

Transform coded values to natural values

Correlation: Spherical

DACE objective function

Correlation: Spline

spotAlgEsIndividualInitial

Individual Initialization

Termination hps

spotAlgEsObjMutation

spotAlgEsObjMutation

spotAlgEsMarriageWithReplace

Marriage with replace

Prepare DACE fit

funGoldsteinPrice

Goldstein-Price Test Function

Parallel execution of code, dependent on the operating system

Regression: Regpoly0

S-Ring Simulation Data Obtained With SPOT

spotAlgEsTermination

funOptimLecture

funOptimLecture

S-Ring Simulation Data

thetaNuggetGradient

thetaNuggetGradient

Minimization by Differential Evolution

linearAdaptedSE

linearAdaptedSE

krigingLikelihood

Calculate negative log-likelihood

Evolution Strategy

plot.spotTreeModel

Plot rpart tree model

Plot Best Objective Value

predict.spotLinearModel

Prediction method for linear model

predictKrigingReinterpolation

Predict Kriging Model (Re-interpolating)

predict.spotTreeModel

Prediction method for rpart tree models

predict.spotRSM

Predict RSM model

Regression: Regpoly1

Regression: Regpoly2

simulationSpectral

simulationSpectral

simulateFunction

simulateFunction

simulate.kriging

Kriging Simulation

simulationDecompose

Kriging Simulation: Decomposition

Backslash operator.

Sequential Parameter Optimization Main Loop

Function Evaluation Wrapper

buildKrigingDACE

Build DACE model