SPOTMisc (version 1.19.52)

getMlConfig: get ml config for keras on census

Description

get ml config for keras on census

Usage

getMlConfig(
  target,
  model,
  data,
  task.type,
  nobs,
  nfactors,
  nnumericals,
  cardinality,
  data.seed,
  prop
)

Value

cfg (list)

Arguments

target

character "age" or "income_class"

model

character model name, e.g., "dl"

data

data, e.g., from getDataCensus

task.type

"classif" (character)

nobs

number of observations (numerical), max 229285. Default: 1e4

nfactors

(character), e.g., "high"

nnumericals

(character), e.g., "high"

cardinality

(character), e.g., "high"

data.seed

(numerical) seed

prop

(numerical) split proportion (train, vals,test)

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){
target <- "age"
task.type <- "classif"
nobs <- 1e2
nfactors <- "high"
nnumericals <- "high"
cardinality <- "high"
data.seed <- 1
cachedir <- "oml.cache"
model <- "ranger"

dfCensus <- getDataCensus(
task.type = task.type,
nobs = nobs,
nfactors = nfactors,
nnumericals = nnumericals,
cardinality = cardinality,
data.seed = data.seed,
cachedir = cachedir,
target = target)

cfg <- getMlConfig(
target = target,
model = model,
data = dfCensus,
task.type = task.type,
nobs = nobs,
nfactors = nfactors,
nnumericals = nnumericals,
cardinality = cardinality,
data.seed = data.seed,
prop= 2/3)
}
# }