predict.msc: Preditcion of partition probabilites of Morse-Smale Complex...

Description Usage Arguments Value Author(s) References See Also Examples

Description

For msc.kd and msc.svm ompute probabilities for each crystal in the Morse-Smale complex for each point in X based on a kernel density estimat or and one-against all svm. For msc.lm,msc.slm and msc.slm.elnet the prediction based on the fitted regression models.

Usage

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
## S3 method for class 'msc.kd'
predict(object, newdata, addExtrema=TRUE, ...)
## S3 method for class 'msc.svm'
predict(object, newdata, ...)
## S3 method for class 'msc.lm'
predict(object, newdata, ...)
## S3 method for class 'msc.slm'
predict(object, newdata, ...)
## S3 method for class 'msc.slm.elnet'
predict(object, newdata, ...)

Arguments

object

Morse-Smale complex object.

newdata

Observations to predict, if missing the sample form the Morse-Smale complex are used.

addExtrema

Add the extrema indices of this partion (default TRUE)

...

Further arguments are ignored in these functions

Value

For Morse-Smale complex objects a (number of points) x (number of partitions) matrix with probabilities $p(C_i|x)$ of belonging to each crystal. For regression model objects the predicted function values.

Author(s)

Samuel Gerber

References

[1] Samuel Gerber and Kristin Potter The Morse-Smale Complex for Data Analysis, Journal of Statistical Software, 2012, vol. 50, no. 2, pp 1-22

[2] Samuel Gerber, Oliver Ruebel Peer-Timo Bremer, Valerio Pascucci, Ross Whitaker, Morse-Smale Regression, Journal of Computational and Graphical Statistics, 2012

[3] Samuel Gerber, Peer-Timo Bremer, Valerio Pascucci, Ross Whitaker, Visual Exploration of High Dimensional Scalar Functions, IEEE Transactions on Visualization and Computer Graphics, vol. 16, no. 6, pp 1271-1280, Nov.-Dec. 2010.

David M. Mount and Sunil Arya ANN library http://www.cs.umd.edu/~mount/ANN/

See Also

msc.nn msc.lm msc.slm

Examples

1
2
3
4
5
6
7
data(fourpeaks)
d <- fourpeaks()
#build Morse-Smale complex
ms <- msc.nn.svm(y=d[,1], x=d[, 2:3], nLevels=15, knn = 10)
#predict parttion assignments at level 15
ms$predictLevel = 13
p <- predict(ms, d[, 2:3])

msr documentation built on May 30, 2017, 4:23 a.m.