popsom: predict – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

predict

Compute Classification Labels for Given Points

Description

Compute classification labels for points in a given data frame using the underlying clustering model. If the training data is unlabeled then generated labels are used.

Usage

predict(map,points)

Arguments

`map`	An object of type 'map'.
`points`	A data frame of points to be classified.

Value

A data frame with classification results. The data frame has two columns:

Label: The assigned label to the observation at the same row in the 'points' data frame.
Confidence: A confidence value assigned to the label prediction.

Author(s)

Lutz Hamel

Examples

data(iris)

df <- subset(iris,select=-Species)
labels <- subset(iris,select=Species)

m <- map(df,labels,xdim=15,ydim=10,train=10000)

predict(m,df)

popsom

Tools for Building, Visualizing, and Evaluating Self-Organizing Maps

v5.1

GPL

Authors

Lutz Hamel [aut, cre], Benjamin Ott [aut], Gregory Breard [aut], Robert Tatoian [aut], Michael Eiger [aut], Vishakh Gopu [aut]

Initial release

2020-12-26