plot.linearcl: Plot coefficients for SVM with linear kernel
In DTRlearn: Learning Algorithms for Dynamic Treatment Regimes

Description Usage Arguments Author(s) See Also Examples

The function visualize the contribution of each feature variable by plotting a selected subset of standardized coefficients from SVM with linear kernel, the coefficients are standardized dividing by the L2 norm of the subvector.

1
2
3

## S3 method for class 'linearcl'
plot(x, index = NULL, names = NULL,
ylab = "std coefficients", xlab = "", col = "gray",...)

`x`	a model with class `'linearcl'`.
`index`	is the vector of indices of variables to plot.
`names`	is the vector of names of each variables to appear in the plot. If not specified, the names would be V1-Vp.
`ylab`	The label for the y axis. Defalt is "std coefficients".
`xlab`	The label for the x axis.
`col`	color to fill the bars in the plot.
`...`	further arguments passed to or from other methods.

Ying Liu yl2802@cumc.columbia.edu http://www.columbia.edu/~yl2802/

Olearning_Single; wsvm

n=200
A=2*rbinom(n,1,0.5)-1
p=20
mu=numeric(p)
Sigma=diag(p)
X=mvrnorm(n,mu,Sigma)
R=X[,1:3]%*%c(1,1,-2)+X[,3:5]%*%c(1,1,-2)*A+rnorm(n)
model1=Olearning_Single(X,A,R)
plot(model1)

Loading required package: kernlab
Loading required package: MASS
Loading required package: glmnet
Loading required package: Matrix
Loading required package: foreach
Loaded glmnet 2.0-12

Loading required package: ggplot2

Attaching package: 'ggplot2'

The following object is masked from 'package:kernlab':

    alpha