Create a rough model

Usage

sculpt_rough(
  dat,
  model_predict_fun,
  n_ice = 10,
  seed = NULL,
  verbose = 0,
  allow_par = FALSE,
  model_predict_fun_export = NULL,
  data_as_marginals = FALSE
)

Arguments

dat: Data to create the rough model from. Must be a product marginal dataset (see sample_marginals) with covariates only (i.e. without response).
model_predict_fun: Function that returns predictions given a dataset.
n_ice: Number of ICE curves to generate. Defaults to 10.
seed: (NULL) or seed for exact reproducibility.
verbose: (integer) 0 for silent run, > 0 for messages.
allow_par: (logical) Allow parallel computation? Defaults to FALSE.
model_predict_fun_export: For parallel computation only. If there is a parallel backend registered (see parallel_set()), then use this to export variables used in model_predict_fun (like model). This is passed to foreach::foreach(..., .export = model_predict_fun_export).
data_as_marginals: (logical) Use the provided data dat as already sampled dataset? Defaults to FALSE.

Value

Object of classes rough and sculpture.

Details

For parallel computation, use parallel_set() and set allow_par to TRUE. Note that parallel computation may fail if the model is too big and there is not enough memory.

Examples

df <- mtcars
df$vs <- as.factor(df$vs)
model <- rpart::rpart(
  hp ~ mpg + carb + vs,
  data = df,
  control = rpart::rpart.control(minsplit = 10)
)
model_predict <- function(x) predict(model, newdata = x)
covariates <- c("mpg", "carb", "vs")
pm <- sample_marginals(df[covariates], n = 50, seed = 5)

rs <- sculpt_rough(
  dat = pm,
  model_predict_fun = model_predict,
  n_ice = 10,
  seed = 1,
  verbose = 0
)

class(rs)
#> [1] "rough"     "sculpture" "list"     
head(predict(rs))
#>         1         2         3         4         5         6 
#>  94.25971 177.04543 136.83114 174.91686 136.83114 136.83114 

# lm model without interaction -> additive -> same predictions
model <- lm(hp ~ mpg + carb + vs, data = df)
model_predict <- function(x) predict(model, newdata = x)
covariates <- c("mpg", "carb", "vs")
pm <- sample_marginals(df[covariates], n = 50, seed = 5)

rs <- sculpt_rough(
  dat = pm,
  model_predict_fun = model_predict,
  n_ice = 10,
  seed = 1,
  verbose = 0
)

class(rs)
#> [1] "rough"     "sculpture" "list"     
head(predict(rs))
#>         1         2         3         4         5         6 
#>  94.61787 190.78181 150.66447 143.70887 126.25460 102.95408 
head(predict(model, pm))
#>         1         2         3         4         5         6 
#>  94.61787 190.78181 150.66447 143.70887 126.25460 102.95408