prcomp.resamples
Principal Components Analysis of Resampling Results
Performs a principal components analysis on an object of class resamples
and returns the results as an object with classes prcomp.resamples
and prcomp
.
- Keywords
- hplot
Usage
## S3 method for class 'resamples':
prcomp(x, metric = x$metrics[1], ...)## S3 method for class 'resamples':
cluster(x, metric = x$metrics[1], ...)
## S3 method for class 'prcomp.resamples':
plot(x, what = "scree", dims = max(2, ncol(x$rotation)), ...)
Arguments
- x
- For
prcomp
, an object of classresamples
and forplot.prcomp.resamples
, an object of classplot.prcomp.resamples
- metric
- a performance metric that was estimated for every resample
- what
- the type of plot:
"scree"
produces a bar chart of standard deviations,"cumulative"
produces a bar chart of the cumulative percent of variance,"loadings"
produces a scatterplot matrix of the loading values and - dims
- The number of dimensions to plot when
what = "loadings"
orwhat = "components"
- ...
- For
prcomp.resamples
, options to pass toprcomp
, forplot.prcomp.resamples
, options to pass to Lattice objects (see Details below) and, forcluster.resamples
, opti
Details
The principal components analysis treats the models as variables and the resamples are realizations of the variables. In this way, we can use PCA to "cluster" the assays and look for similarities. Most of the methods for prcomp
can be used, although custom print
and plot
methods are used.
The plot method uses lattice graphics. When what = "scree"
or what = "cumulative"
, barchart
is used.
When what = "loadings"
or what = "components"
, either xyplot
or splom
are used (the latter when dims
> 2). Options can be passed to these methods using ...
.
When what = "loadings"
or what = "components"
, the plots are put on a common scale so that later components are less likely to be over-interpreted. See Geladi et al (2003) for examples of why this can be important.
For clustering, hclust
is used to determine clusters of models based on the resampled performance values.
Value
- For
prcomp.resamples
, an object with classesprcomp.resamples
andprcomp
. This object is the same as the object produced byprcomp
, but with additional elements: metric the value for the metric
argumentcall the call - For
plot.prcomp.resamples
, a Lattice object (see Details above)
References
Geladi, P.; Manley, M.; and Lestander, T. (2003), "Scatter plotting in multivariate data analysis," J. Chemometrics, 17: 503-511
See Also
Examples
#load(url("http://caret.r-forge.r-project.org/Classification_and_Regression_Training_files/exampleModels.RData"))
resamps <- resamples(list(CART = rpartFit,
CondInfTree = ctreeFit,
MARS = earthFit))
resampPCA <- prcomp(resamps)
resampPCA
plot(resampPCA, "scree")
plot(resampPCA, "components")
plot(resampPCA, "components", dims = 2, auto.key = list(columns = 3))