// TODO Update with Java 8
private static boolean isPositive(DataBlock q) {
for (int i = 0; i < q.getLength(); ++i) {
if (q.get(i) < State.ZERO) {
return false;
}
}
return true;
}
/**
* @param t
* @param state
*/
@Override
public void save(final int t, final MState state) {
m_var.save(t, state);
m_fdata.save(t, state);
DataBlock diag = state.F.diagonal();
for (int i = 0; i < state.E.getLength(); ++i) {
double r = diag.get(i);
if (r != 0) {
addStd(state.E.get(i), r);
}
}
}
private int check(DataBlock z) {
int idx = -1;
for (int i = 0; i < z.getLength(); ++i) {
if (z.get(i) != 0) {
if (idx != -1) {
return -1;
} else {
idx = i;
}
}
}
return idx;
}
@Override
public void save(final int t, final AugmentedPredictionErrors pe) {
DataBlock U = pe.getTransformedPredictionErrors();
Matrix L = pe.getCholeskyFactor();
DataBlock D = L.diagonal();
Matrix E = pe.E();
int nvars = E.getColumnsCount();
n += nvars;
LogSign sld = D.sumLog();
det += sld.value;
Q.subMatrix(0, nd, nd + 1, nd + 1 + nvars).copy(E.subMatrix());
Q.row(nd).range(nd + 1, nd + 1 + nvars).copy(U);
ec.tstoolkit.maths.matrices.ElementaryTransformations.fastGivensTriangularize(Q.subMatrix());
}
double[] scomponent() {
DisturbanceSmoother smoother = new DisturbanceSmoother();
smoother.setSsf(ssf);
smoother.process(ssfdata);
SmoothingResults sstates = smoother.calcSmoothedStates();
double[] cmp = new double[ssfdata.getCount()];
DataBlock z = new DataBlock(ssf.getStateDim());
DataBlock zc = z.drop(2, 0);
for (int i = 0; i < cmp.length; ++i) {
zc.copy(S.row(i));
cmp[i] = sstates.zcomponent(i, z);
}
return cmp;
}
/**
* @param z
* @return
*/
public double[] zvariance(DataBlock z) {
if (m_P == null) {
return null;
}
if (m_r != z.getLength()) {
return null;
}
int iz = check(z);
double[] var = new double[m_n - m_start];
if (iz >= 0) {
return componentVar(iz);
} else {
for (int i = 0; i < m_n - m_start; ++i) {
var[i] = SymmetricMatrix.quadraticForm(m_P.matrix(i), z) * m_ser2;
}
}
return var;
}
/**
* @param z
* @return
*/
public double[] zcomponent(DataBlock z) {
int iz = check(z);
if (iz >= 0) {
return component(iz);
}
if (m_a == null) {
return null;
}
if (m_r != z.getLength()) {
return null;
}
int n = m_n - m_start;
double[] c = new double[n];
for (int i = 0; i < n; ++i) {
c[i] = m_a.block(i).dot(z);
}
return c;
}
/**
* @param s
* @param domain
* @return
*/
@Override
public TsData process(TsData s, TsDomain domain) {
TsDomain rdomain = domain == null ? s.getDomain() : domain;
TsData out = new TsData(rdomain);
PeriodIterator pin = new PeriodIterator(s, domain);
PeriodIterator pout = new PeriodIterator(out);
int p = 0;
while (pin.hasMoreElements()) {
DataBlock bin = pin.nextElement().data;
DataBlock bout = pout.nextElement().data;
int nf = 0, len = bin.getLength();
if (filters[p] != null) {
nf = filters[p].getUpperBound();
}
if (filters[p] != null && 2 * nf < len && (nf < 9 || len >= 20)) {
filters[p].filter(bin, bout.drop(nf, nf));
endPointsProcessors[p].process(bin, bout);
} else {
bout.set(bin.sum() / len);
}
++p;
}
return out;
}
@Override
public void XS(int pos, DataBlock x, DataBlock xs) {
xs.set(0, std() * x.get(0));
}
@Override
public void addSU(int pos, DataBlock x, DataBlock u) {
x.add(0, std() * u.get(0));
}
// time-varying trading days
// @Test
public void demoTD() {
TsData s = Data.X;
CompositeResults rslts = TramoSeatsProcessingFactory.process(s, TramoSeatsSpecification.RSA5);
PreprocessingModel regarima = rslts.get("preprocessing", PreprocessingModel.class);
SeatsResults seats = rslts.get("decomposition", SeatsResults.class);
assertTrue(seats != null && regarima != null);
if (regarima.isMultiplicative()) {
s = s.log();
}
int[] calPos =
regarima.description.getRegressionVariablePositions(ComponentType.CalendarEffect);
UcarimaModel ucm = seats.getUcarimaModel();
// compute the full decomposition...
SsfUcarima stoch = new SsfUcarima(ucm);
ExtendedSsfData xdata = new ExtendedSsfData(new SsfData(s, null));
xdata.setForecastsCount(s.getFrequency().intValue());
Matrix x =
regarima
.description
.buildRegressionVariables()
.all()
.matrix(new TsDomain(s.getStart(), xdata.getCount()));
RegSsf xssf = new RegSsf(stoch, x.subMatrix());
Filter filter = new Filter();
filter.setInitializer(new DiffuseSquareRootInitializer());
filter.setSsf(xssf);
DiffuseFilteringResults fr = new DiffuseFilteringResults(true);
fr.getVarianceFilter().setSavingP(true);
fr.getFilteredData().setSavingA(true);
filter.process(xdata, fr);
Smoother smoother = new Smoother();
smoother.setSsf(xssf);
smoother.setCalcVar(true);
SmoothingResults sm = new SmoothingResults();
smoother.process(xdata, fr, sm);
Smoother lsmoother = new Smoother();
lsmoother.setSsf(stoch);
lsmoother.setCalcVar(true);
SmoothingResults lsm = new SmoothingResults();
ExtendedSsfData xldata =
new ExtendedSsfData(new SsfData(regarima.linearizedSeries(false), null));
xldata.setForecastsCount(s.getFrequency().intValue());
lsmoother.process(xldata, lsm);
int spos = stoch.cmpPos(1);
DataBlock Z = new DataBlock(xssf.getStateDim());
double[] v = new double[xdata.getCount()];
double[] c = new double[xdata.getCount()];
double[] svar = sm.componentVar(spos);
double[] slvar = lsm.componentVar(spos);
int start = regarima.description.getRegressionVariablesStartingPosition();
for (int i = 0; i < v.length; ++i) {
Z.set(spos, 1);
for (int j = 0; j < calPos.length; ++j) {
Z.set(stoch.getStateDim() + calPos[j], x.get(i, calPos[j]));
}
v[i] = sm.zvariance(i, Z);
Z.set(spos, 0);
c[i] = sm.zvariance(i, Z);
System.out.print(svar[i]);
System.out.print('\t');
System.out.print(slvar[i]);
System.out.print('\t');
System.out.print(c[i]);
System.out.print('\t');
System.out.println(v[i]);
}
System.out.println(sm.P(50));
System.out.println(sm.P(svar.length - 1));
System.out.println(regarima.estimation.getLikelihood().getBVar());
}