plot.LRCpred: Plot the predictions of logistic regression classifier

In pnnl/glmnetLRC: Lasso and Elastic-Net Logistic Regression Classification with an Arbitrary Loss Function

Description

Plot the predictions of logistic regression classifier

Usage

## S3 method for class 'LRCpred'
plot(x, pch = c(1, 2), col = c("Blue", "Red"),
  scale = 1, seed = 1, parArgs = NULL, legendArgs = NULL,
  lineArgs = NULL, textArgs = NULL, ...)

Arguments

x	an object of class LRCpred returned by predict.glmnetLRC.
pch	A vector of at most length 2 indicating the plotting symbols to be used to differentiate the two true classes. If truthCol was not specified in the call to predict.glmnetLRC, only the first element is used. This is passed to plot.
col	A vector of at most length 2 indicating the colors of the plotted points in order to differentiate the two true classes. If truthCol was not specified in the call to predict.glmnetLRC, only the first element is used. This is passed to plot.
scale	A numeric value in (0, 1] that controls scaling of the horizontal axis. A value of 1 corresponds to the standard, linear scale. Values closer to 0 symetrically 'zoom-in' the axis near 0 and 1 while 'zooming-out' the axis in the neighborhood of 0.5. Values of scale closer to 0 are useful if most of the probability predictions are piled up near 0 and 1.
seed	Single numeric value that sets the seed for the random jitter of the vertical axis of the plot.
parArgs	If desired, a list of named arguments that will be passed to par which is called prior to making the plot.
legendArgs	If desired, a list of named arguments that will be passed to legend. If truthCol was not specified in the call to predict.glmnetLRC, no legend is drawn.
lineArgs	If desired, a list of named arguments that will be passed to abline governing the vertical line that indicates the value of τ.
textArgs	If desired, a list of named arguments that will be passed to text governing the text indicating the value of τ.
...	Arguments passed to plot.default.

Value

A plot showing the predicted probabilities of the logisitic regression classifier, with a vertical bar showing the value of the probability threshold, τ.

Author(s)

Landon Sego

See Also

See glmnetLRC for an example.

pnnl/glmnetLRC documentation built on May 25, 2019, 10:22 a.m.