plotMeasuredVsOOB: generates plot of response vs out-of-bag predictions across...

In juliancandia/eNetXplorer: Quantitative Exploration of Elastic Net Families for Generalized Linear Models

generates plot of response vs out-of-bag predictions across instances

Description

Given alpha, this function generates plots of response vs out-of-bag predictions across instances, which can be used to assess individual instances, examine outliers, etc. For linear regression models, it generates a response vs out-of-bag prediction scatterplot; it also displays the best linear fit and its 95% confidence level region. For categorical models, it generates a boxplot across classes showing the frequency of out-of-bag correct predictions.

Usage

plotMeasuredVsOOB(x, alpha.index=NULL, xlab=NULL, ylab=NULL, 
cex.lab=0.95, main=NULL, col.main="black", cex.main=0.85, instance.label=TRUE,
instance.label.cex=NULL, instance.label.offset=NULL, 
instance.label.added.margin=NULL, col=NULL, box.wex=NULL, box.range=NULL,
box.col=NULL, transparency=NULL, jitter=NULL, cex.pt=NULL, class.color=NULL, ...)

Arguments

x	eNetXplorer object.
alpha.index	Integer indices to select alpha values. Default is 1:length(alpha)
xlab	Custom x-axis label.
ylab	Custom y-axis label.
cex.lab	Axis label size.
main	Custom title.
col.main	Title color.
cex.main	Title size.
instance.label	Logical to display instance labels. Default is TRUE.
instance.label.cex	Size of instance labels.
instance.label.offset	Offset of instance labels.
instance.label.added.margin	(linear regression only) Margin size to accomodate instance label display.
col	(linear regression only) Symbol color.
box.wex	(categorical models only) Boxplot boxwex parameter. Default is 0.5.
box.range	(categorical models only) Boxplot range parameter. Default is 0.
box.col	(categorical models only) Boxplot col parameter. Default is white.
transparency	(categorical models only) Symbol transparency. Default is 70.
jitter	(categorical models only) Symbol jitter. Default is 0.25.
cex.pt	(categorical models only) Symbol size. Default is 1.7
class.color	(categorical models only) Vector of class colors. Default is the default palette.
...	Additional plotting parameters.

Author(s)

Julian Candia and John S. Tsang
Maintainer: Julian Candia [e-mail]

See Also

eNetXplorer, plot

Examples

data(QuickStartEx)
fit = eNetXplorer(x=QuickStartEx$predictor,y=QuickStartEx$response,
family="gaussian",n_run=20,n_perm_null=10,seed=111)
plot(x=fit,plot.type="measuredVsOOB")
plotMeasuredVsOOB(x=fit,alpha.index=2)


data(QuickStartEx)
binarized=rep("low",length(QuickStartEx$response))
binarized[QuickStartEx$response>median(QuickStartEx$response)]="high"
fit = eNetXplorer(x=QuickStartEx$predictor,y=binarized,family="binomial",n_run=20, 
n_perm_null=10,seed=111)
plot(x=fit,plot.type="measuredVsOOB")
plotMeasuredVsOOB(x=fit,alpha.index=2)

juliancandia/eNetXplorer documentation built on May 11, 2023, 1:59 a.m.