Skip to content

Axing a mda.

Source: R/mda.R
axe-mda.Rd

mda and fda objects are created from the mda package, leveraged to carry out mixture discriminant analysis and flexible discriminat analysis, respectively.

Usage

# S3 method for mda
axe_call(x, verbose = FALSE, ...)

# S3 method for fda
axe_call(x, verbose = FALSE, ...)

# S3 method for mda
axe_env(x, verbose = FALSE, ...)

# S3 method for fda
axe_env(x, verbose = FALSE, ...)

# S3 method for mda
axe_fitted(x, verbose = FALSE, ...)

# S3 method for fda
axe_fitted(x, verbose = FALSE, ...)

Arguments

x

A model object.

verbose

Print information each time an axe method is executed. Notes how much memory is released and what functions are disabled. Default is FALSE.

...

Any additional arguments related to axing.

Value

Axed mda object.

Examples

library(mda)
#> Loading required package: class
#> Loaded mda 0.5-4
#> 
#> Attaching package: ‘mda’
#> The following object is masked from ‘package:parsnip’:
#> 
#>     mars

mtcars$cyl <- as.factor(mtcars$cyl)

fit <- mda(cyl ~ ., data = mtcars)
out <- butcher(fit, verbose = TRUE)
#> ✔ Memory released: 10.18 kB
#> ✖ Disabled: `print()`, `summary()`, and `update()`

fit2 <- fda(cyl ~ ., data = mtcars)
out2 <- butcher(fit2, verbose = TRUE)
#> ✔ Memory released: 29.82 kB
#> ✖ Disabled: `print()`, `summary()`, and `update()`

# Another mda object
data(glass)
wrapped_mda <- function(fit_fn) {
  some_junk_in_environment <- runif(1e6)
  fit <- fit_fn(Type ~ ., data = glass)
  return(fit)
}

lobstr::obj_size(wrapped_mda(mda))
#> 8.16 MB
lobstr::obj_size(butcher(wrapped_mda(mda)))
#> 29.60 kB

lobstr::obj_size(wrapped_mda(fda))
#> 8.10 MB
lobstr::obj_size(butcher(wrapped_mda(fda)))
#> 15.05 kB