def checkPositivity(grid, alpha):
# define a full grid of maxlevel of the grid
gs = grid.getStorage()
fullGrid = Grid.createLinearGrid(gs.dim())
fullGrid.createGridGenerator().full(gs.getMaxLevel())
fullHashGridStorage = fullGrid.getStorage()
A = DataMatrix(fullHashGridStorage.size(), fullHashGridStorage.dim())
p = DataVector(gs.dim())
for i in xrange(fullHashGridStorage.size()):
fullHashGridStorage.get(i).getCoords(p)
A.setRow(i, p)
res = evalSGFunctionMulti(grid, alpha, A)
ymin, ymax, cnt = 0, -1e10, 0
for i, yi in enumerate(res.array()):
if yi < 0. and abs(yi) > 1e-13:
cnt += 1
ymin = min(ymin, yi)
ymax = max(ymax, yi)
A.getRow(i, p)
print " %s = %g" % (p, yi)
if cnt > 0:
print "warning: function is not positive"
print "%i/%i: [%g, %g]" % (cnt, fullHashGridStorage.size(), ymin, ymax)
return cnt == 0
def checkPositivity(grid, alpha):
# define a full grid of maxlevel of the grid
gs = grid.getStorage()
fullGrid = Grid.createLinearGrid(gs.dim())
fullGrid.createGridGenerator().full(gs.getMaxLevel())
fullHashGridStorage = fullGrid.getStorage()
A = DataMatrix(fullHashGridStorage.size(), fullHashGridStorage.dim())
p = DataVector(gs.dim())
for i in xrange(fullHashGridStorage.size()):
fullHashGridStorage.get(i).getCoords(p)
A.setRow(i, p)
res = evalSGFunctionMulti(grid, alpha, A)
ymin, ymax, cnt = 0, -1e10, 0
for i, yi in enumerate(res.array()):
if yi < 0. and abs(yi) > 1e-13:
cnt += 1
ymin = min(ymin, yi)
ymax = max(ymax, yi)
A.getRow(i, p)
print " %s = %g" % (p, yi)
if cnt > 0:
print "warning: function is not positive"
print "%i/%i: [%g, %g]" % (cnt, fullHashGridStorage.size(), ymin, ymax)
return cnt == 0
def testSave(self):
filename = pathlocal + '/datasets/saving.arff.gz'
testPoints = [[0.307143, 0.130137, 0.050000],
[0.365584, 0.105479, 0.050000],
[0.178571, 0.201027, 0.050000],
[0.272078, 0.145548, 0.050000],
[0.318831, 0.065411, 0.050000],
[0.190260, 0.086986, 0.050000],
[0.190260, 0.062329, 0.072500],
[0.120130, 0.068493, 0.072500],
[0.225325, 0.056164, 0.072500],
[0.213636, 0.050000, 0.072500]]
testValues = [
-1.000000, 1.000000, 1.000000, 1.000000, 1.000000, 1.000000,
-1.000000, -1.000000, -1.000000, -1.000000
]
attributes = {
"x0": "NUMERIC",
"x1": "NUMERIC",
"x2": "NUMERIC",
"class": "NUMERIC",
}
size = len(testPoints)
dim = len(testPoints[0])
point = DataVector(dim)
points = DataMatrix(size, dim)
for row in xrange(size):
for col in xrange(dim):
point[col] = testPoints[row][col]
points.setRow(row, point)
adapter = ARFFAdapter(filename)
adapter.save(points, testValues, attributes)
(points, values) = adapter.loadData().getPointsValues()
size = len(testPoints)
dim = len(testPoints[0])
testVector = DataVector(dim)
for rowIdx in xrange(size):
points.getRow(rowIdx, testVector)
for colIdx in xrange(dim):
if cvar.USING_DOUBLE_PRECISION:
self.assertEqual(testVector[colIdx],
testPoints[rowIdx][colIdx])
else:
self.assertAlmostEqual(testVector[colIdx],
testPoints[rowIdx][colIdx])
self.assertEqual(values[rowIdx], testValues[rowIdx])
os.remove(filename)
def testSave(self):
filename = pathlocal + '/datasets/saving.arff.gz'
testPoints = [[0.307143,0.130137,0.050000],
[0.365584,0.105479,0.050000],
[0.178571,0.201027,0.050000],
[0.272078,0.145548,0.050000],
[0.318831,0.065411,0.050000],
[0.190260,0.086986,0.050000],
[0.190260,0.062329,0.072500],
[0.120130,0.068493,0.072500],
[0.225325,0.056164,0.072500],
[0.213636,0.050000,0.072500]
]
testValues = [-1.000000, 1.000000, 1.000000, 1.000000, 1.000000, 1.000000, -1.000000, -1.000000, -1.000000, -1.000000]
attributes = {
"x0":"NUMERIC",
"x1":"NUMERIC",
"x2":"NUMERIC",
"class":"NUMERIC",
}
size = len(testPoints)
dim = len(testPoints[0])
point = DataVector(dim)
points = DataMatrix(size, dim)
for row in xrange(size):
for col in xrange(dim):
point[col] = testPoints[row][col]
points.setRow(row, point)
adapter = ARFFAdapter(filename)
adapter.save(points, testValues, attributes)
(points, values) = adapter.loadData().getPointsValues()
size = len(testPoints)
dim = len(testPoints[0])
testVector = DataVector(dim)
for rowIdx in xrange(size):
points.getRow(rowIdx, testVector)
for colIdx in xrange(dim):
if cvar.USING_DOUBLE_PRECISION:
self.assertEqual(testVector[colIdx], testPoints[rowIdx][colIdx])
else:
self.assertAlmostEqual(testVector[colIdx], testPoints[rowIdx][colIdx])
self.assertEqual(values[rowIdx], testValues[rowIdx])
os.remove(filename)
def computeErrors(jgrid, jalpha,
grid1, alpha1,
grid2, alpha2,
n=200):
"""
Compute some errors to estimate the quality of the
interpolation.
@param jgrid: Grid, new discretization
@param jalpha: DataVector, new surpluses
@param grid1: Grid, old discretization
@param alpha1: DataVector, old surpluses
@param grid2: Grid, old discretization
@param alpha2: DataVector, old surpluses
@return: tuple(<float>, <float>), maxdrift, l2norm
"""
jgs = jgrid.getStorage()
# create control samples
samples = DataMatrix(np.random.rand(n, jgs.getDimension()))
# evaluate the sparse grid functions
jnodalValues = evalSGFunctionMulti(jgrid, jalpha, samples)
# eval grids
nodalValues1 = evalSGFunctionMulti(grid1, alpha1, samples)
nodalValues2 = evalSGFunctionMulti(grid2, alpha2, samples)
# compute errors
p = DataVector(jgs.getDimension())
err = DataVector(n)
for i in range(n):
samples.getRow(i, p)
y = nodalValues1[i] * nodalValues2[i]
if abs(jnodalValues[i]) > 1e100:
err[i] = 0.0
else:
err[i] = abs(y - jnodalValues[i])
# get error statistics
# l2
l2norm = err.l2Norm()
# maxdrift
err.abs()
maxdrift = err.max()
return maxdrift, l2norm
def computeErrors(jgrid, jalpha,
grid1, alpha1,
grid2, alpha2,
n=200):
"""
Compute some errors to estimate the quality of the
interpolation.
@param jgrid: Grid, new discretization
@param jalpha: DataVector, new surpluses
@param grid1: Grid, old discretization
@param alpha1: DataVector, old surpluses
@param grid2: Grid, old discretization
@param alpha2: DataVector, old surpluses
@return: tuple(<float>, <float>), maxdrift, l2norm
"""
jgs = jgrid.getStorage()
# create control samples
samples = DataMatrix(np.random.rand(n, jgs.dim()))
# evaluate the sparse grid functions
jnodalValues = evalSGFunctionMulti(jgrid, jalpha, samples)
# eval grids
nodalValues1 = evalSGFunctionMulti(grid1, alpha1, samples)
nodalValues2 = evalSGFunctionMulti(grid2, alpha2, samples)
# compute errors
p = DataVector(jgs.dim())
err = DataVector(n)
for i in xrange(n):
samples.getRow(i, p)
y = nodalValues1[i] * nodalValues2[i]
if abs(jnodalValues[i]) > 1e100:
err[i] = 0.0
else:
err[i] = abs(y - jnodalValues[i])
# get error statistics
# l2
l2norm = err.l2Norm()
# maxdrift
err.abs()
maxdrift = err.max()
return maxdrift, l2norm
def computeErrors(jgrid, jalpha, grid, alpha, f, n=200):
"""
Compute some errors to estimate the quality of the
interpolation.
@param jgrid: Grid, new discretization
@param jalpha: DataVector, new surpluses
@param grid: Grid, old discretization
@param alpha: DataVector, old surpluses
@param f: function, to be interpolated
@param n: int, number of Monte Carlo estimates for error estimation
@return: tuple(<float>, <float>), maxdrift, l2norm
"""
jgs = jgrid.getStorage()
# create control samples
samples = DataMatrix(np.random.rand(n, jgs.dim()))
# evaluate the sparse grid functions
jnodalValues = evalSGFunctionMulti(jgrid, jalpha, samples)
nodalValues = evalSGFunctionMulti(grid, alpha, samples)
# compute errors
p = DataVector(jgs.dim())
err = DataVector(n)
for i in xrange(n):
samples.getRow(i, p)
y = f(p.array(), nodalValues[i])
err[i] = abs(y - jnodalValues[i])
# get error statistics
# l2
l2norm = err.l2Norm()
# maxdrift
err.abs()
maxdrift = err.max()
return maxdrift, l2norm
def computeCoefficients(jgrid, grid, alpha, f):
"""
Interpolate function f, which depends on some sparse grid function
(grid, alpha) on jgrid
@param jgrid: Grid, new discretization
@param grid: Grid, old discretization
@param alpha: DataVector, surpluses for grid
@param f: function, to be interpolated
@return: DataVector, surpluses for jgrid
"""
jgs = jgrid.getStorage()
# dehierarchization
p = DataVector(jgs.dim())
A = DataMatrix(jgs.size(), jgs.dim())
for i in xrange(jgs.size()):
jgs.get(i).getCoords(p)
A.setRow(i, p)
nodalValues = evalSGFunctionMulti(grid, alpha, A)
# apply f to all grid points
jnodalValues = DataVector(jgs.size())
for i in xrange(len(nodalValues)):
A.getRow(i, p)
# print i, p.array(), nodalValues[i], alpha.min(), alpha.max()
# if nodalValues[i] < -1e20 or nodalValues[i] > 1e20:
# from pysgpp.extensions.datadriven.uq.operations import evalSGFunction, evalSGFunctionMultiVectorized
# print alpha.min(), alpha.max()
# print evalSGFunction(grid, alpha, p)
# print evalSGFunctionMulti(grid, alpha, DataMatrix([p.array()]))
# print evalSGFunctionMultiVectorized(grid, alpha, DataMatrix([p.array()]))
# import ipdb; ipdb.set_trace()
jnodalValues[i] = f(p.array(), nodalValues[i])
jalpha = hierarchize(jgrid, jnodalValues)
return jalpha
def computeCoefficients(jgrid, grid, alpha, f):
"""
Interpolate function f, which depends on some sparse grid function
(grid, alpha) on jgrid
@param jgrid: Grid, new discretization
@param grid: Grid, old discretization
@param alpha: DataVector, surpluses for grid
@param f: function, to be interpolated
@return: DataVector, surpluses for jgrid
"""
jgs = jgrid.getStorage()
# dehierarchization
p = DataVector(jgs.dim())
A = DataMatrix(jgs.size(), jgs.dim())
for i in xrange(jgs.size()):
jgs.get(i).getCoords(p)
A.setRow(i, p)
nodalValues = evalSGFunctionMulti(grid, alpha, A)
# apply f to all grid points
jnodalValues = DataVector(jgs.size())
for i in xrange(len(nodalValues)):
A.getRow(i, p)
# print i, p.array(), nodalValues[i], alpha.min(), alpha.max()
# if nodalValues[i] < -1e20 or nodalValues[i] > 1e20:
# from pysgpp.extensions.datadriven.uq.operations import evalSGFunction, evalSGFunctionMultiVectorized
# print alpha.min(), alpha.max()
# print evalSGFunction(grid, alpha, p)
# print evalSGFunctionMulti(grid, alpha, DataMatrix([p.array()]))
# print evalSGFunctionMultiVectorized(grid, alpha, DataMatrix([p.array()]))
# import ipdb; ipdb.set_trace()
jnodalValues[i] = f(p.array(), nodalValues[i])
jalpha = hierarchize(jgrid, jnodalValues)
return jalpha
def computeErrors(jgrid, jalpha, grid, alpha, f, n=200):
"""
Compute some errors to estimate the quality of the
interpolation.
@param jgrid: Grid, new discretization
@param jalpha: DataVector, new surpluses
@param grid: Grid, old discretization
@param alpha: DataVector, old surpluses
@param f: function, to be interpolated
@param n: int, number of Monte Carlo estimates for error estimation
@return: tuple(<float>, <float>), maxdrift, l2norm
"""
jgs = jgrid.getStorage()
# create control samples
samples = DataMatrix(np.random.rand(n, jgs.dim()))
# evaluate the sparse grid functions
jnodalValues = evalSGFunctionMulti(jgrid, jalpha, samples)
nodalValues = evalSGFunctionMulti(grid, alpha, samples)
# compute errors
p = DataVector(jgs.dim())
err = DataVector(n)
for i in xrange(n):
samples.getRow(i, p)
y = f(p.array(), nodalValues[i])
err[i] = abs(y - jnodalValues[i])
# get error statistics
# l2
l2norm = err.l2Norm()
# maxdrift
err.abs()
maxdrift = err.max()
return maxdrift, l2norm
class TestWeightedRefinementOperator(unittest.TestCase):
def setUp(self):
#
# Grid
#
DIM = 2
LEVEL = 2
self.grid = Grid.createLinearGrid(DIM)
self.grid_gen = self.grid.getGenerator()
self.grid_gen.regular(LEVEL)
#
# trainData, classes, errors
#
xs = []
DELTA = 0.05
DELTA_RECI = int(1 / DELTA)
for i in range(DELTA_RECI):
for j in range(DELTA_RECI):
xs.append([DELTA * i, DELTA * j])
random.seed(1208813)
ys = [random.randint(-10, 10) for i in range(DELTA_RECI**2)]
# print xs
# print ys
self.trainData = DataMatrix(xs)
self.classes = DataVector(ys)
self.alpha = DataVector([3, 6, 7, 9, -1])
self.errors = DataVector(DELTA_RECI**2)
coord = DataVector(DIM)
opEval = createOperationEval(self.grid)
for i in range(self.trainData.getNrows()):
self.trainData.getRow(i, coord)
self.errors.__setitem__(
i, self.classes[i] - opEval.eval(self.alpha, coord))
#print "Errors:"
#print self.errors
#
# Functor
#
self.functor = WeightedErrorRefinementFunctor(self.alpha, self.grid)
self.functor.setTrainDataset(self.trainData)
self.functor.setClasses(self.classes)
self.functor.setErrors(self.errors)
def test_1(self):
storage = self.grid.getStorage()
coord = DataVector(storage.getDimension())
num_coeff = self.alpha.__len__()
values = [
self.functor.__call__(storage, i) for i in range(storage.getSize())
]
expect = []
opEval = createOperationEval(self.grid)
for i in range(num_coeff):
# print i
val = 0
single = DataVector(num_coeff)
single.__setitem__(i, self.alpha.__getitem__(i))
for j in range(self.trainData.getNrows()):
self.trainData.getRow(j, coord)
val += abs(
opEval.eval(single, coord) *
(self.errors.__getitem__(j)**2))
expect.append(val)
# print values
# print expect
# print [ values[i]/expect[i] for i in xrange(values.__len__())]
self.assertEqual(values, expect)
class TestPersistentRefinementOperator(unittest.TestCase):
def setUp(self):
#
# Grid
#
self.grid = Grid.createLinearGrid(DIM)
self.grid_gen = self.grid.createGridGenerator()
self.grid_gen.regular(LEVEL)
#
# trainData, classes, errors
#
xs = []
DELTA = 0.05
DELTA_RECI = int(1 / DELTA)
for i in xrange(DELTA_RECI):
for j in xrange(DELTA_RECI):
xs.append([DELTA * i, DELTA * j])
random.seed(1208813)
ys = [random.randint(-10, 10) for i in xrange(DELTA_RECI**2)]
# print xs
# print ys
self.trainData = DataMatrix(xs)
self.classes = DataVector(ys)
self.alpha = DataVector([3, 6, 7, 9, -1])
self.errors = DataVector(DELTA_RECI**2)
coord = DataVector(DIM)
for i in xrange(self.trainData.getNrows()):
self.trainData.getRow(i, coord)
self.errors.__setitem__(
i, self.classes[i] - self.grid.eval(self.alpha, coord))
#
# Functor
#
self.functor = PersistentErrorRefinementFunctor(self.alpha, self.grid)
self.functor.setTrainDataset(self.trainData)
self.functor.setClasses(self.classes)
self.functor.setErrors(self.errors)
self.accum = DataVector(self.alpha.__len__())
self.accum.setAll(0.0)
def test_1(self):
storage = self.grid.getStorage()
coord = DataVector(storage.dim())
num_coeff = self.alpha.__len__()
#
# First part
#
values = [
self.functor.__call__(storage, i) for i in xrange(storage.size())
]
expect = []
for j in xrange(num_coeff):
row = DataVector(DIM)
tmp_alpha = DataVector(self.alpha.__len__())
tmp_alpha.setAll(0.0)
tmp_alpha.__setitem__(j, 1.0)
current = 0
for i in xrange(self.trainData.getNrows()):
self.trainData.getRow(i, row)
current += (self.errors.__getitem__(i) *
self.grid.eval(tmp_alpha, row))**2
self.accum.__setitem__(
j,
self.accum.__getitem__(j) * (1 - BETA) +
BETA * current * abs(self.alpha.__getitem__(j)))
expect.append(self.accum.__getitem__(j))
self.assertEqual(values, expect)
#
# Second part
#
values = [
self.functor.__call__(storage, i) for i in xrange(storage.size())
]
expect = []
for j in xrange(num_coeff):
row = DataVector(DIM)
tmp_alpha = DataVector(self.alpha.__len__())
tmp_alpha.setAll(0.0)
tmp_alpha.__setitem__(j, 1.0)
current = 0
for i in xrange(self.trainData.getNrows()):
self.trainData.getRow(i, row)
current += (self.errors.__getitem__(i) *
self.grid.eval(tmp_alpha, row))**2
self.accum.__setitem__(
j,
self.accum.__getitem__(j) * (1 - BETA) +
BETA * current * abs(self.alpha.__getitem__(j)))
expect.append(self.accum.__getitem__(j))
self.assertEqual(values, expect)
class TestOnlinePredictiveRefinementDimension(unittest.TestCase):
def setUp(self):
#
# Grid
#
DIM = 2
LEVEL = 2
self.grid = Grid.createLinearGrid(DIM)
self.grid_gen = self.grid.getGenerator()
self.grid_gen.regular(LEVEL)
#
# trainData, classes, errors
#
xs = []
DELTA = 0.05
DELTA_RECI = int(1 / DELTA)
for i in range(DELTA_RECI):
for j in range(DELTA_RECI):
xs.append([DELTA * i, DELTA * j])
random.seed(1208813)
ys = [random.randint(-10, 10) for i in range(DELTA_RECI**2)]
self.trainData = DataMatrix(xs)
self.classes = DataVector(ys)
self.alpha = DataVector([3, 6, 7, 9, -1])
self.multEval = createOperationMultipleEval(self.grid, self.trainData)
opEval = createOperationEval(self.grid)
self.errors = DataVector(DELTA_RECI**2)
coord = DataVector(DIM)
for i in range(self.trainData.getNrows()):
self.trainData.getRow(i, coord)
self.errors.__setitem__(
i, abs(self.classes[i] - opEval.eval(self.alpha, coord)))
#
# OnlinePredictiveRefinementDimension
#
hash_refinement = HashRefinement()
self.strategy = OnlinePredictiveRefinementDimension(hash_refinement)
self.strategy.setTrainDataset(self.trainData)
self.strategy.setClasses(self.classes)
self.strategy.setErrors(self.errors)
def test_1(self):
storage = self.grid.getStorage()
gridSize = self.grid.getSize()
numDim = storage.getDimension()
print("######")
print("Expected result:")
print("######")
expected = {}
for j in range(gridSize):
HashGridPoint = storage.getPoint(j)
HashGridPoint.setLeaf(False)
print("Point: ", j, " (", HashGridPoint.toString(), ")")
for d in range(numDim):
#
# Get left and right child
#
leftChild = HashGridPoint(HashGridPoint)
rightChild = HashGridPoint(HashGridPoint)
storage.left_child(leftChild, d)
storage.right_child(rightChild, d)
#
# Check if point is refinable
#
if storage.isContaining(leftChild) or storage.isContaining(
rightChild):
continue
#
# Insert children temporarily
#
storage.insert(leftChild)
storage.insert(rightChild)
val1 = self.calc_indicator_value(leftChild)
val2 = self.calc_indicator_value(rightChild)
storage.deleteLast()
storage.deleteLast()
print("Dimension: ", d)
print("Left Child: ", val1)
print("Right Child: ", val2)
print("")
expected[(j, d)] = val1 + val2
print("")
for k, v in list(expected.items()):
print((k, v))
print("######")
print("Actual result:")
print("######")
actual = refinement_map({})
self.strategy.collectRefinablePoints(storage, 10, actual)
for k, v in list(actual.items()):
print((k, v))
#
# Assertions
#
for k, v in list(expected.items()):
self.assertEqual(actual[k], v)
def calc_indicator_value(self, index):
numData = self.trainData.getNrows()
numCoeff = self.grid.getSize()
seq = self.grid.getStorage().seq(index)
num = 0
denom = 0
tmp = DataVector(numCoeff)
self.multEval.multTranspose(self.errors, tmp)
num = tmp.__getitem__(seq)
num **= 2
alpha = DataVector(numCoeff)
col = DataVector(numData)
alpha.__setitem__(seq, 1.0)
self.multEval.mult(alpha, col)
col.sqr()
denom = col.sum()
if denom == 0:
print("Denominator is zero")
value = 0
else:
value = num / denom
return value
class TestWeightedRefinementOperator(unittest.TestCase):
def setUp(self):
#
# Grid
#
DIM = 2
LEVEL = 2
self.grid = Grid.createLinearGrid(DIM)
self.grid_gen = self.grid.createGridGenerator()
self.grid_gen.regular(LEVEL)
#
# trainData, classes, errors
#
xs = []
DELTA = 0.05
DELTA_RECI = int(1/DELTA)
for i in xrange(DELTA_RECI):
for j in xrange(DELTA_RECI):
xs.append([DELTA*i, DELTA*j])
random.seed(1208813)
ys = [ random.randint(-10, 10) for i in xrange(DELTA_RECI**2)]
# print xs
# print ys
self.trainData = DataMatrix(xs)
self.classes = DataVector(ys)
self.alpha = DataVector([3, 6, 7, 9, -1])
self.errors = DataVector(DELTA_RECI**2)
coord = DataVector(DIM)
for i in xrange(self.trainData.getNrows()):
self.trainData.getRow(i, coord)
self.errors.__setitem__ (i, self.classes[i] - self.grid.eval(self.alpha, coord))
#print "Errors:"
#print self.errors
#
# Functor
#
self.functor = WeightedErrorRefinementFunctor(self.alpha, self.grid)
self.functor.setTrainDataset(self.trainData)
self.functor.setClasses(self.classes)
self.functor.setErrors(self.errors)
def test_1(self):
storage = self.grid.getStorage()
coord = DataVector(storage.dim())
num_coeff = self.alpha.__len__()
values = [self.functor.__call__(storage,i) for i in xrange(storage.size())]
expect = []
for i in xrange(num_coeff):
# print i
val = 0
single = DataVector(num_coeff)
single.__setitem__(i, self.alpha.__getitem__(i))
for j in xrange(self.trainData.getNrows()):
self.trainData.getRow(j, coord)
val += abs( self.grid.eval(single, coord) * (self.errors.__getitem__(j)**2) )
expect.append(val)
# print values
# print expect
# print [ values[i]/expect[i] for i in xrange(values.__len__())]
self.assertEqual(values, expect)
class TestOnlinePredictiveRefinementDimension(unittest.TestCase):
def setUp(self):
#
# Grid
#
DIM = 2
LEVEL = 2
self.grid = Grid.createLinearGrid(DIM)
self.grid_gen = self.grid.createGridGenerator()
self.grid_gen.regular(LEVEL)
#
# trainData, classes, errors
#
xs = []
DELTA = 0.05
DELTA_RECI = int(1/DELTA)
for i in xrange(DELTA_RECI):
for j in xrange(DELTA_RECI):
xs.append([DELTA*i, DELTA*j])
random.seed(1208813)
ys = [ random.randint(-10, 10) for i in xrange(DELTA_RECI**2)]
self.trainData = DataMatrix(xs)
self.classes = DataVector(ys)
self.alpha = DataVector([3, 6, 7, 9, -1])
self.multEval = createOperationMultipleEval(self.grid, self.trainData)
self.errors = DataVector(DELTA_RECI**2)
coord = DataVector(DIM)
for i in xrange(self.trainData.getNrows()):
self.trainData.getRow(i, coord)
self.errors.__setitem__ (i, abs(self.classes[i] - self.grid.eval(self.alpha, coord)))
#
# OnlinePredictiveRefinementDimension
#
hash_refinement = HashRefinement();
self.strategy = OnlinePredictiveRefinementDimension(hash_refinement)
self.strategy.setTrainDataset(self.trainData)
self.strategy.setClasses(self.classes)
self.strategy.setErrors(self.errors)
def test_1(self):
storage = self.grid.getStorage()
gridSize = self.grid.getSize()
numDim = storage.dim()
print "######"
print "Expected result:"
print "######"
expected = {}
for j in xrange(gridSize):
HashGridIndex = storage.get(j)
HashGridIndex.setLeaf(False)
print "Point: ", j, " (", HashGridIndex.toString(), ")"
for d in xrange(numDim):
#
# Get left and right child
#
leftChild = HashGridIndex(HashGridIndex)
rightChild = HashGridIndex(HashGridIndex)
storage.left_child(leftChild, d)
storage.right_child(rightChild, d)
#
# Check if point is refinable
#
if storage.has_key(leftChild) or storage.has_key(rightChild):
continue
#
# Insert children temporarily
#
storage.insert(leftChild)
storage.insert(rightChild)
val1 = self.calc_indicator_value(leftChild)
val2 = self.calc_indicator_value(rightChild)
storage.deleteLast()
storage.deleteLast()
print "Dimension: ", d
print "Left Child: ", val1
print "Right Child: ", val2
print ""
expected[(j, d)] = val1 + val2
print ""
for k, v in expected.iteritems():
print(k, v)
print "######"
print "Actual result:"
print "######"
actual = refinement_map({})
self.strategy.collectRefinablePoints(storage, 10, actual)
for k, v in actual.iteritems():
print(k, v)
#
# Assertions
#
for k, v in expected.iteritems():
self.assertEqual(actual[k], v)
def calc_indicator_value(self, index):
numData = self.trainData.getNrows()
numCoeff = self.grid.getSize()
seq = self.grid.getStorage().seq(index)
num = 0
denom = 0
tmp = DataVector(numCoeff)
self.multEval.multTranspose(self.errors, tmp)
num = tmp.__getitem__(seq)
num **= 2
alpha = DataVector(numCoeff)
col = DataVector(numData)
alpha.__setitem__(seq, 1.0)
self.multEval.mult(alpha, col)
col.sqr()
denom = col.sum()
if denom == 0:
print "Denominator is zero"
value = 0
else:
value = num/denom
return value
