condvis (version 0.2-2)

condtour: Conditional tour: a tour through sections in data space

Description

This function produces a tour through sections in data space defined by a path.

Usage

condtour(data, model, path, response = NULL, S = NULL, C = NULL, 
    sigma = NULL, distance = "euclidean", cex.axis = NULL, cex.lab = NULL, 
    tck = NULL, view3d = FALSE, conf = FALSE, select.colour = "blue")

Arguments

data

a data frame

model

a fitted model object, or list of fitted models

path

a path through the predictor space, i.e. a dataframe with same column names as data[, C] describing values to condition on

response

the index of the response variable in data

S

the index of the section predictor(s) in data

C

the index of the condition predictor(s) in data

sigma

parameter to choose how much data to display

distance

type of distance measure for sigma

cex.axis

scaling for axis text

cex.lab

scaling for axis labels

tck

scaling for axis ticks

view3d

if S denotes two continuous variables, should the section be visualised as a 3-D mesh

conf

show approximate confidence bounds for expected values

select.colour

colour for highlighting selected sections/conditions

Value

• An interactive graphic.

See Also

ceplot

Examples

data(powerplant)
library(e1071)
model <- svm(PE ~ ., data = powerplant)
path <- makepath(powerplant[-5], 25)
condtour(data = powerplant, model = model, path = path$path, S = "AT")

##
data(wine)
wine$Class <- as.factor(wine$Class)
library(e1071)
model5 <- list(svm(Class ~ ., data = wine))
path <- makepath(wine[-1], 50)
condtour(data = wine, model = model5, path = path$path, S = c("Hue", 
    "Flavanoids"), sigma = 3)