def update(self, grid, alphas, gpi, params, *args, **kws):
gs = grid.getStorage()
# get maximum coefficient of ancestors
vi = 0.0
for _, gpp in parents(grid, gpi):
if gs.isContaining(gpp):
ix = gs.getSequenceNumber(gpp)
vi = max(vi, np.abs(alphas[ix]))
p = DataVector(gs.getDimension())
gs.getCoordinates(gpi, p)
# get joint distribution
ap = params.activeParams()
U = ap.getIndependentJointDistribution()
T = ap.getJointTransformation()
q = T.unitToProbabilistic(p.array())
# scale surplus by probability density
return np.abs(vi) * U.pdf(q)
def update(self, grid, v, gpi, params, *args, **kws):
"""
Compute ranking for variance estimation
\argmax_{i \in \A} |v_i| \sqrt{E[\varphi_i^2]}
@param grid: Grid grid
@param v: numpy array coefficients
"""
# update the quadrature operations
if not self.initialized:
self._estimationStrategy.initQuadratureStrategy(grid)
U = params.getIndependentJointDistribution()
T = params.getJointTransformation()
self.vol, self.W, self.D = self._estimationStrategy._extractPDFforMomentEstimation(U, T)
self.initialized = True
# get maximum coefficient of ancestors
vi = 0.0
gs = grid.getStorage()
for _, gpp in parents(grid, gpi):
if gs.isContaining(gpp):
ix = gs.getSequenceNumber(gpp)
vi = max(vi, np.abs(v[ix]))
# prepare data
basisi = getBasis(grid)
# compute the second moment for the current grid point
secondMoment, _ = self._estimationStrategy.computeSystemMatrixForVarianceList(gs,
[gpi], basisi,
[gpi], basisi,
self.W, self.D)
secondMoment = max(0.0, self.vol * secondMoment[0])
# update the ranking
return np.abs(vi * np.sqrt(secondMoment))