This function 'summerize' a (big) population in a smaller groups of
individual, then simplify the trajectories by reducing their number of
points. It use reduceNbId and
reduceNbTimes. Main difference with these two function,
its applies on a Clds object.
[Clds]: object holding the
trajectories that should be simplified.
nbSenators
[integer] number of trajectories that will be
use to represent the population (i.e., number of clusters used by
k-means).
nbTimes
[numeric]: fixe the number of that the
simplified trajectories should have.
spar
[numeric]: smoothing parameter that is used if the
trajectories shall be smoothed before being simplified.
imputationMethod
[character]: Method that will be used to
impute the missing values.
Details
This function 'summerize' a (big) population in a smaller groups of
individual, then simplify the trajectories by reducing their number of
points. If 'nbSenators' is not NA, then reduceNbId is
called. If 'nbTimes' is not NA, then reduceNbTimes is
called. Note that 'nbSenators' and 'nbTimes' should not be both
missing.
If both are non-missing, reduceNbId is called first.
The results is store in the field 'senators' of the Clds object.
Value
A Clds object in which the fields
'senators', 'mySenators' and 'senatorsWeight' are now filled.
Examples
### Generating artificial data
nbLignes <- 200
trajG <- matrix(0,nbLignes,51)
for(i in 1:(nbLignes/2)){
trajG[i,] <- dnorm(0:50,runif(1,15,35),5)*rnorm(1,10,0.1)
}
for(i in (nbLignes/2+1):nbLignes){
trajG[i,] <- dnorm(0:50,runif(1,15,35),5)*rnorm(1,5,0.1)
}
myClds <- cldsWide(data.frame(1:200,trajG))
plot(myClds)
### Reducing the number of time measurement
reduceTraj(myClds,nbTimes=7)
plotSenators(myClds)
### Reducing the number of individual
reduceTraj(myClds,nbSenators=32)
plotSenators(myClds)
### Reducing both
reduceTraj(myClds,nbSenators=32,nbTimes=7)
plotSenators(myClds)