Function to plot gbm response variables, with the option of adding a smooth representation of the response if requested additional options in this version allow for plotting on a common scale. Note hat fitted functions are centered by subtracting their mean.
gbm.plot(gbm.object, variable.no=0, smooth=FALSE, rug=TRUE, n.plots=length(pred.names),
common.scale=TRUE, write.title=TRUE, y.label="fitted function", x.label=NULL,
show.contrib=TRUE, plot.layout=c(3, 4), ...)
a gbm object - could be one from gbm.step
the var to plot - if zero then plots all
Logical. If TRUE, a smoothed version of the fitted function is added
Logical. If TRUE, a rug of deciles is plotted
plot the first n most important preds
Logical. If TRUE, a common scale is used on the y axis
Logical. If TRUE, the plot gets a title
the default y-axis label
the default x-axis label
Logical. If TRUE, the contribution is shown on the x axis
define the default layout for graphs on the page
other arguments to pass to the plotting useful options include cex.axis, cex.lab, etc.
John R. Leathwick and Jane Elith
Elith, J., J.R. Leathwick and T. Hastie, 2009. A working guide to boosted regression trees. Journal of Animal Ecology 77: 802-81