plot.haldensify: Plot Method for HAL Conditional Density Estimates

Description Usage Arguments Value Examples

View source: R/plots.R

Description

Plot Method for HAL Conditional Density Estimates

Usage

1
2
## S3 method for class 'haldensify'
plot(x, ..., type = c("risk", "density"))

Arguments

x

Object of class haldensify, containing conditional density estimates, as produced by haldensify.

...

Additional arguments to be passed plot, currently ignored.

type

A character indicating the type of plot to be produced. Options include visualizing the empirical risks of the conditional density estimators across a grid of values of the regularization parameter and a plot of the estimated conditional density (based on the estimator selected by cross-validation). The latter has yet to be implemented.

Value

Object of class ggplot containing a plot of the desired type.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
# simulate data: W ~ U[-4, 4] and A|W ~ N(mu = W, sd = 0.5)
n_train <- 50
w <- runif(n_train, -4, 4)
a <- rnorm(n_train, w, 0.5)
# learn relationship A|W using HAL-based density estimation procedure
haldensify_fit <- haldensify(
  A = a, W = w, n_bins = 3,
  lambda_seq = exp(seq(-1, -10, length = 50)),
  # the following arguments are passed to hal9001::fit_hal()
  max_degree = 3, reduce_basis = 0.1
)
plot(haldensify_fit)

haldensify documentation built on Feb. 10, 2022, 1:07 a.m.