This function estimates parameters for SVM(Gaussian Kernel) based on bayesian optimization
svm_cv_opt(data, label, gamma_range = c(10^(-3), 10^1), cost_range = c(10^(-2), 10^2), svm_kernel = "radial", degree_range = c(3L, 10L), coef0_range = c(10^(-1), 10^1), n_folds, init_points = 4, n_iter = 10, acq = "ei", kappa = 2.576, eps = 0, optkernel = list(type = "exponential", power = 2))
| data | data |
|---|---|
| label | label for classification |
| gamma_range | The range of gamma. Default is c(10 ^ (-3), 10 ^ 1) |
| cost_range | The range of C(Cost). Default is c(10 ^ (-2), 10 ^ 2) |
| svm_kernel | Kernel used in SVM. You might consider changing some of the following parameters, depending on the kernel type.
|
| degree_range | Parameter needed for kernel of type polynomial. Default is c(3L, 10L) |
| coef0_range | Parameter needed for kernels of type |
| n_folds | if a integer value k>0 is specified, a k-fold cross validation on the training data is performed to assess the quality of the model: the accuracy rate for classification and the Mean Squared Error for regression |
| init_points | Number of randomly chosen points to sample the target function before Bayesian Optimization fitting the Gaussian Process. |
| n_iter | Total number of times the Bayesian Optimization is to repeated. |
| acq | Acquisition function type to be used. Can be "ucb", "ei" or "poi".
|
| kappa | tunable parameter kappa of GP Upper Confidence Bound, to balance exploitation against exploration, increasing kappa will make the optimized hyperparameters pursuing exploration. |
| eps | tunable parameter epsilon of Expected Improvement and Probability of Improvement, to balance exploitation against exploration, increasing epsilon will make the optimized hyperparameters are more spread out across the whole range. |
| optkernel | Kernel (aka correlation function) for the underlying Gaussian Process. This parameter should be a list that specifies the type of correlation function along with the smoothness parameter. Popular choices are square exponential (default) or matern 5/2 |
The test accuracy and a list of Bayesian Optimization result is returned:
Best_Par a named vector of the best hyperparameter set found
Best_Value the value of metrics achieved by the best hyperparameter set
History a data.table of the bayesian optimization history
Pred a data.table with validation/cross-validation prediction for each round of bayesian optimization history
library(MlBayesOpt) set.seed(71) res0 <- svm_cv_opt(data = iris, label = Species, n_folds = 3, init_points = 10, n_iter = 1)#> elapsed = 0.02 Round = 1 gamma_opt = 3.3299 cost_opt = 11.7670 Value = 0.9333 #> elapsed = 0.01 Round = 2 gamma_opt = 5.5515 cost_opt = 76.1740 Value = 0.9067 #> elapsed = 0.01 Round = 3 gamma_opt = 3.2744 cost_opt = 14.1882 Value = 0.9400 #> elapsed = 0.01 Round = 4 gamma_opt = 2.1175 cost_opt = 76.6932 Value = 0.9200 #> elapsed = 0.01 Round = 5 gamma_opt = 3.1619 cost_opt = 84.2154 Value = 0.9600 #> elapsed = 0.01 Round = 6 gamma_opt = 9.4727 cost_opt = 77.6772 Value = 0.8933 #> elapsed = 0.01 Round = 7 gamma_opt = 6.6175 cost_opt = 13.3914 Value = 0.9267 #> elapsed = 0.02 Round = 8 gamma_opt = 8.8943 cost_opt = 80.5955 Value = 0.8733 #> elapsed = 0.01 Round = 9 gamma_opt = 3.3808 cost_opt = 89.6793 Value = 0.9333 #> elapsed = 0.01 Round = 10 gamma_opt = 4.3481 cost_opt = 92.6987 Value = 0.9000 #> elapsed = 0.01 Round = 11 gamma_opt = 2.9508 cost_opt = 84.8600 Value = 0.9467 #> #> Best Parameters Found: #> Round = 5 gamma_opt = 3.1619 cost_opt = 84.2154 Value = 0.9600