fitPath: Constructs tours of data space based on fits.

In condvis2: Interactive Conditional Visualization for Supervised and Unsupervised Models in Shiny

Constructs tours of data space based on fits.

Description

Constructs tours of data space based on fits.

Usage

lofPath(
  data,
  fits,
  length = 10,
  reorder = TRUE,
  conditionvars = NULL,
  predictArgs = NULL,
  response = NULL,
  ...
)

diffitsPath(
  data,
  fits,
  length = 10,
  reorder = TRUE,
  conditionvars = NULL,
  predictArgs = NULL,
  ...
)

hiresponsePath(
  data,
  response = NULL,
  length = 10,
  reorder = TRUE,
  conditionvars = NULL,
  ...
)

loresponsePath(
  data,
  response = NULL,
  length = 10,
  reorder = TRUE,
  conditionvars = NULL,
  ...
)

Arguments

data	A dataframe
fits	A model fit or list of fits
length	Path length, defaults to 10
reorder	If TRUE (default) uses DendSer to reorder the path dser
conditionvars	A vector of variable names. The returned tour is for this subset of variables.
predictArgs	Extra inputs to CVpredict
response	The name of the response variable
...	ignored

Value

A dataframe with the path

Functions

• lofPath(): Constructs a tour of data space showing biggest absolute residuals from fits.

• diffitsPath(): Constructs a tour of data space showing biggest differences in fits.

• hiresponsePath(): Constructs a tour of data space showing high (numeric) response values

• loresponsePath(): Constructs a tour of data space showing low (numeric) response values

Examples

fit1 <- lm(mpg ~ wt+hp+am, data=mtcars)
fit2 <- lm(mpg ~ wt, data=mtcars)
lofPath(mtcars,fit1, response="mpg")
diffitsPath(mtcars,list(fit1,fit2))

condvis2 documentation built on Sept. 14, 2022, 5:06 p.m.