SPOTMisc (version 1.19.52)

prepareComparisonPlot: prepare data frame for comparisons (boxplots, violin plots)

Description

converts result from a spot run into the long format for ggplot.

Usage

prepareComparisonPlot(
  runNrMl,
  runNrDl,
  directory,
  defaultModelList = list("dl", "cvglmnet", "kknn", "ranger", "rpart", "svm", "xgboost"),
  tunedModelList = list("dl", "cvglmnet", "kknn", "ranger", "rpart", "svm", "xgboost")
)

Value

data frame with results:

x

integer representing step

y

corresponding function value at step x.

name

ml/dl model name, e.g., ranger

size

initial design size.

yInitMin

min y value before SMBO is started, based on the initial design only.

Arguments

runNrMl

run number (character) of ml models

runNrDl

run number (character) of dl models

directory

location of the (non-default, e.g., tuned) parameter file

defaultModelList

default model list. Default: list("dl", "cvglmnet", "kknn", "ranger", "rpart" , "svm", "xgboost")

tunedModelList

tuned model list. Default: list("dl", "cvglmnet", "kknn", "ranger", "rpart" , "svm", "xgboost")

Examples

# \donttest{
### These examples require an activated Python environment as described in
### Bartz-Beielstein, T., Rehbach, F., Sen, A., and Zaefferer, M.:
### Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT,
### June 2021. http://arxiv.org/abs/2105.14625.
PYTHON_RETICULATE <- FALSE
if(PYTHON_RETICULATE){
runNrMl <- list("15")
runNrDl <- list("28")
directory <- "../book/data"
prepareComparisonPlot(runNrMl,
                    runNrDl,
                    directory)
}
# }