1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
|
\name{sim}
\alias{sim}
\title{
Simulate from Parameterized MVN Mixture Models
}
\description{
Simulate data from parameterized MVN mixture models.
}
\usage{
sim(modelName, parameters, n, seed = NULL, \dots)
}
\arguments{
\item{modelName}{
A character string indicating the model. The help file for
\code{\link{mclustModelNames}} describes the available models.
}
\item{parameters}{
A list with the following components:
\describe{
\item{\code{pro}}{
A vector whose \emph{k}th component is the mixing proportion for
the \emph{k}th component of the mixture model.
If missing, equal proportions are assumed.
}
\item{\code{mean}}{
The mean for each component. If there is more than one component,
this is a matrix whose kth column is the mean of the \emph{k}th
component of the mixture model.
}
\item{\code{variance}}{
A list of variance parameters for the model.
The components of this list depend on the model
specification. See the help file for \code{\link{mclustVariance}}
for details.
}
}
}
\item{n}{
An integer specifying the number of data points to be simulated.
}
\item{seed}{
An optional integer argument to \code{set.seed} for reproducible
random class assignment. By default the current seed will be used.
Reproducibility can also be achieved by calling \code{set.seed}
before calling \code{sim}.
}
\item{\dots }{
Catches unused arguments in indirect or list calls via \code{do.call}.
}
}
\value{
A matrix in which first column is the classification and the remaining
columns are the \code{n} observations simulated from the specified MVN
mixture model.
\item{Attributes:}{
\code{"modelName"} A character string indicating the variance
model used for the simulation.
}
}
\details{
This function can be used with an indirect or list call using
\code{do.call}, allowing the output of e.g. \code{mstep}, \code{em},
\code{me}, \code{Mclust} to be passed directly without the need to
specify individual parameters as arguments.
}
\seealso{
\code{\link{simE}}, \dots,
\code{\link{simVVV}},
\code{\link{Mclust}},
\code{\link{mstep}},
\code{\link{do.call}}
}
\examples{
irisBIC <- mclustBIC(iris[,-5])
irisModel <- mclustModel(iris[,-5], irisBIC)
names(irisModel)
irisSim <- sim(modelName = irisModel$modelName,
parameters = irisModel$parameters,
n = nrow(iris))
\donttest{
do.call("sim", irisModel) # alternative call
}
par(pty = "s", mfrow = c(1,2))
dimnames(irisSim) <- list(NULL, c("dummy", (dimnames(iris)[[2]])[-5]))
dimens <- c(1,2)
lim1 <- apply(iris[,dimens],2,range)
lim2 <- apply(irisSim[,dimens+1],2,range)
lims <- apply(rbind(lim1,lim2),2,range)
xlim <- lims[,1]
ylim <- lims[,2]
coordProj(iris[,-5], parameters=irisModel$parameters,
classification=map(irisModel$z),
dimens=dimens, xlim=xlim, ylim=ylim)
coordProj(iris[,-5], parameters=irisModel$parameters,
classification=map(irisModel$z), truth = irisSim[,-1],
dimens=dimens, xlim=xlim, ylim=ylim)
irisModel3 <- mclustModel(iris[,-5], irisBIC, G=3)
irisSim3 <- sim(modelName = irisModel3$modelName,
parameters = irisModel3$parameters, n = 500, seed = 1)
\donttest{
irisModel3$n <- NULL
irisSim3 <- do.call("sim",c(list(n=500,seed=1),irisModel3)) # alternative call
}
clPairs(irisSim3[,-1], cl = irisSim3[,1])
}
\keyword{cluster}
|
