94 this =
this@data.selection.ASelector;
100 copy = data.selection.TimeSelector;
102 copy.Size= this.
Size;
103 copy.Seed= this.
Seed;
115 tlen = length(times);
117 if nt*tlen > this.
Size
119 num = floor(this.
Size/tlen);
120 s = RandStream.create(
" mt19937ar ",
" Seed ",this.
Seed);
122 selidx = repmat(s.randperm(tlen),1,num);
128 protraj = floor(length(selidx)/nt);
135 step = (1:protraj)+(tn-1)*protraj;
137 hlp(selidx(step)) =
true;
144 left = this.
Size - protraj * nt;
146 selsel = s.randperm(length(notsel),left);
147 sel(notsel(selsel)) =
true;
149 sel =
true(1,nt*tlen);
153 xi = []; ti = []; mui = [];
155 [x, mu] = d.getTrajectoryNr(tn);
156 idx = (1:tlen) + (tn-1)*tlen;
157 xi = [xi x(:,sel(idx))];
158 newt = times(sel(idx));
161 mui = [mui mu(:,ones(1,length(newt)))];
189 #if 0 //mtoc++: 'set.Size'
190 function
Size(value) {
192 error(" The value must be a finite positive
integer. ");
201 #if 0 //mtoc++: 'set.Seed'
202 function
Seed(value) {
204 error(" The value must be a real value. ");
TimeSelector: Approximation training data selection utilizing time information.
Base interface for any approximation training data selection algorithm.
The base class for any KerMor detailed model.
Times
Evaluation points of the model.
function registerProps(varargin)
Call this method at any class that defines DPCM observed properties.
virtual function n = getNumTrajectories()
Gets the total number of trajectories.
data.ModelData Data
The full model's data container. Defaults to an empty container.
Seed
The seed for the per-time-random selection (to enable reproduction of results)
function res = isposintscalar(value)
isposintscalar: Backwards-compatibility function for matlab versions greater than 2012a ...
Size
The (maximum) size of training samples to take.
function [ matrix xi , rowvec ti , matrix mui , fxi ] = select(models.BaseFullModel model)
Performs selection of samples adjusted to the apperances of different times.
data.ATrajectoryData TrajectoryData
The trajectory training data for the full model (only complete trajectories!)