MINI MINI MANI MO
%
% Copyright (c) 2012, 2014, Oracle and/or its affiliates. All rights reserved.
%
\name{ore.predict-matrix}
\alias{ore.predict-matrix}
\alias{ore.predict,matrix-method}
\title{Oracle R Enterprise Predictions Using Distances to Rows in a Matrix}
\description{
Oracle R Enterprise method for generating predictions using rows of a
data matrix. For each row in argument \code{newdata}, the distances
to each row in argument \code{object} are computed and either those
distances or the row number from argument \code{object} with the
minimum distance is returned.
}
\usage{
\S4method{ore.predict}{matrix}(object, newdata, type = c("classes", "distances"),
method = "euclidean", p = 2, na.action = na.pass, ...)
}
\arguments{
\item{object}{A \code{\link[base]{matrix}} object with no more than
1000 rows.}
\item{newdata}{An \code{\link[OREbase:ore.frame-class]{ore.frame}}
object.}
\item{type}{A character string specifying the type of prediction to
make; either \code{"classes"} (row id) or \code{"distances"}.}
\item{method}{A character string specifying the distance measure to
use; either \code{"euclidean"}, \code{"maximum"},
\code{"manhattan"}, \code{"canberra"}, or \code{"minkowski"}. See
function \code{\link[stats]{dist}} for further explanations.}
\item{p}{The power of the Minkowski distance when argument
\code{method} is \code{"minkowski"}.}
\item{na.action}{The manner in which \code{NA} values are handled,
either \code{na.omit} or \code{na.pass}.}
\item{\dots}{Optional arguments.}
}
\value{
If argument \code{type} is \code{"classes"}, returns an
\code{\link[OREbase:ore.integer-class]{ore.integer}} object of row
number references to argument \code{object}.
If argument \code{type} is \code{"distances"}, returns an
\code{\link[OREbase:ore.frame-class]{ore.frame}} object with one
column for each row in argument \code{object}.
}
\references{
\href{http://www.oracle.com/technetwork/database/database-technologies/r/r-enterprise/documentation/index.html}{Oracle R Enterprise}
}
\author{
Oracle \email{oracle-r-enterprise@oracle.com}
}
\seealso{
\code{\link{ore.predict}},
\code{\link{ore.predict-kmeans}},
\code{\link[stats]{dist}}.
}
\examples{
groups <- cutree(hclust(dist(iris[1:4], "manhattan")), 3)
centers <- do.call(rbind, lapply(split(iris[1:4], groups), colMeans))
rownames(centers) <- sprintf("DISTANCE\%d", 1:3)
IRIS <- ore.push(iris)
IRIS$CLUSTER <- ore.predict(centers, IRIS, method = "manhattan")
IRIS <- cbind(IRIS, ore.predict(centers, IRIS, type = "distances",
method = "manhattan"))
head(IRIS)
table(IRIS$CLUSTER, IRIS$Species)
}
\keyword{multivariate}
\keyword{cluster}
OHA YOOOO