def test_1D_Refinement(self):
""" Refine a point in a 2D grid in one direction"""
# get point ((2,1), (2,3)) (top right) that will be refined
point_to_refine_idx = None
point = None
for i in xrange(17):
point = self.grid_storage.get(i)
if point.getLevel(0) == 2 and point.getIndex(0) == 1 \
and point.getLevel(1) == 2 and point.getIndex(1) == 3:
point_to_refine_idx = i
point_to_refine = point
break
self.assertNotEqual(point_to_refine_idx, None,
'Point ((2,1), (2,3)) was not found')
# refine the point in x1-direction
dim = 0
hash_refinement = HashRefinement()
hash_refinement.refineGridpoint1D(self.grid_storage, point_to_refine_idx,
dim)
# check number of grid points
self.assertEqual(self.grid.getSize(), 19,
'Number of grid points doesn\'t match')
# check if new points are in the grid
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.left_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x1 left child was not found')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.right_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x1 right child was not found')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.left_child(child, 1)
self.assertFalse(self.grid_storage.has_key(child),
'Left x2 left child is present, though should not be')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.right_child(child, 1)
self.assertFalse(self.grid_storage.has_key(child),
'Left x2 right child is present, though should not be')
# refine the point in x2-direction
dim = 1
hash_refinement.refineGridpoint1D(self.grid_storage, point_to_refine_idx,
dim)
# check number of grid points
self.assertEqual(self.grid.getSize(), 21,
'Number of grid points doesn\'t match')
# check if new points are in the grid
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.left_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x2 left child was not found')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.right_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x2 right child was not found')
def testFreeRefine(self):
"""Tests surplus based refine for Hash-Storage"""
from pysgpp import GridStorage, HashGenerator
from pysgpp import SurplusRefinementFunctor, HashRefinement, DataVector
s = GridStorage(2)
g = HashGenerator()
g.regular(s, 1)
d = DataVector(1)
d[0] = 1.0
f = SurplusRefinementFunctor(d)
r = HashRefinement()
r.free_refine(s, f)
self.failUnlessEqual(s.size(), 5)
def testFreeRefine(self):
"""Tests surplus based refine for Hash-Storage"""
from pysgpp import GridStorage, HashGenerator
from pysgpp import SurplusRefinementFunctor, HashRefinement, DataVector
s = GridStorage(2)
g = HashGenerator()
g.regular(s, 1)
d = DataVector(1)
d[0] = 1.0
f = SurplusRefinementFunctor(d)
r = HashRefinement()
r.free_refine(s, f)
self.failUnlessEqual(s.size(), 5)
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_1D_Refinement(self):
""" Refine a point in a 2D grid in one direction"""
# get point ((2,1), (2,3)) (top right) that will be refined
point_to_refine_idx = None
point = None
for i in xrange(17):
point = self.grid_storage.get(i)
if point.getLevel(0) == 2 and point.getIndex(0) == 1 \
and point.getLevel(1) == 2 and point.getIndex(1) == 3:
point_to_refine_idx = i
point_to_refine = point
break
self.assertNotEqual(point_to_refine_idx, None,
'Point ((2,1), (2,3)) was not found')
# refine the point in x1-direction
dim = 0
hash_refinement = HashRefinement()
hash_refinement.refineGridpoint1D(self.grid_storage,
point_to_refine_idx, dim)
# check number of grid points
self.assertEqual(self.grid.getSize(), 19,
'Number of grid points doesn\'t match')
# check if new points are in the grid
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.left_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x1 left child was not found')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.right_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x1 right child was not found')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.left_child(child, 1)
self.assertFalse(
self.grid_storage.has_key(child),
'Left x2 left child is present, though should not be')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.right_child(child, 1)
self.assertFalse(
self.grid_storage.has_key(child),
'Left x2 right child is present, though should not be')
# refine the point in x2-direction
dim = 1
hash_refinement.refineGridpoint1D(self.grid_storage,
point_to_refine_idx, dim)
# check number of grid points
self.assertEqual(self.grid.getSize(), 21,
'Number of grid points doesn\'t match')
# check if new points are in the grid
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.left_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x2 left child was not found')
child = point_to_refine.__class__(point_to_refine)
self.grid_storage.right_child(child, dim)
self.assertTrue(self.grid_storage.has_key(child),
'Left x2 right child was not found')
def test_ANOVA_Refinement_Volume(self):
"""Dimensionally adaptive refinement using volume as local error
indicator
"""
# point ((3,7), (1,1)) (middle most right) gets larger surplus coefficient
alpha = DataVector(self.grid.getSize())
point_to_refine = None
for i in range(17):
point = self.grid_storage.getPoint(i)
if point.getLevel(0) == 3 and point.getIndex(0) == 7 \
and point.getLevel(1) == 1 and point.getIndex(1) == 1:
point_to_refine = point
alpha[i] = 2.0
else:
alpha[i] = 1.0
# refine one point
functor = SurplusVolumeRefinementFunctor(alpha, 1, 0.0)
hash_refinement = HashRefinement()
refinement_strategy = ANOVAHashRefinement()
refinement_strategy.free_refine(self.grid_storage, functor)
# check if only the children along x1 direction were inserted
self.assertEqual(
self.grid.getSize(), 19,
'Number of grid points doesn\'t match: %d != %d' %
(self.grid.getSize(), 19))
child = point_to_refine.__class__(point_to_refine)
child.getLeftChild(0)
self.assertTrue(self.grid_storage.isContaining(child),
'Left x1 left child was not found')
child = point_to_refine.__class__(point_to_refine)
child.getRightChild(0)
self.assertTrue(self.grid_storage.isContaining(child),
'Left x1 right child was not found')
child = point_to_refine.__class__(point_to_refine)
child.getLeftChild(1)
self.assertFalse(
self.grid_storage.isContaining(child),
'Left x2 left child is present, though should not be')
child = point_to_refine.__class__(point_to_refine)
child.getRightChild(1)
self.assertFalse(
self.grid_storage.isContaining(child),
'Left x2 right child is present, though should not be')
def test_freeRefineSubspaceIsotropic(self):
"""Refine the isotropic middle subspace"""
alpha = DataVector(self.grid.getSize())
alpha.setAll(1.0)
for i in [13, 14, 15, 16]:
alpha[i] = 2.
#refinement stuff
refinement = HashRefinement()
decorator = SubspaceRefinement(refinement)
# refine a single grid point each time
functor = SurplusRefinementFunctor(alpha, 1)
decorator.free_refine(self.HashGridStorage, functor)
for i in range(self.grid.getSize()):
HashGridPoint = self.HashGridStorage.getPoint(i)
self.assertEqual(self.grid.getSize(), 33)
for i in range(self.grid.getSize()):
HashGridPoint = self.HashGridStorage.getPoint(i)
levelIndex = eval(HashGridPoint.toString())
self.assertFalse(levelIndex[0] == 4 or levelIndex[2] == 4)
def test_freeRefineSubspaceIsotropic(self):
"""Refine the isotropic middle subspace"""
alpha = DataVector(self.grid.getSize())
alpha.setAll(1.0)
alpha[12] = 2.
#refinement stuff
refinement = HashRefinement()
decorator = GSGRefinement(refinement)
# refine a single grid point each time
functor = SurplusRefinementFunctor(alpha, 1)
decorator.freeRefineSubspace(self.HashGridStorage, functor)
for i in xrange(self.grid.getSize()):
HashGridIndex = self.HashGridStorage.get(i)
print i, HashGridIndex.toString()
self.assertEqual(self.grid.getSize(), 15)
for i in xrange(self.grid.getSize()):
HashGridIndex = self.HashGridStorage.get(i)
levelIndex = eval(HashGridIndex.toString())
self.assertFalse(levelIndex[0] == 4 or levelIndex[2] >= 3)
def test_freeRefineSubspaceAnisotropic(self):
"""Refine Anisotropic subspace (x2)"""
alpha = DataVector(self.grid.getSize())
alpha.setAll(1.0)
for i in [9, 10, 11, 12]:
alpha[i] = 2.
#refinement stuff
refinement = HashRefinement()
decorator = SubspaceRefinement(refinement)
# refine a single grid point each time
functor = SurplusRefinementFunctor(alpha, 1)
decorator.free_refine(self.HashGridStorage, functor)
for i in xrange(self.grid.getSize()):
HashGridIndex = self.HashGridStorage.get(i)
print i, HashGridIndex.toString()
self.assertEqual(self.grid.getSize(), 33)
for i in xrange(self.grid.getSize()):
HashGridIndex = self.HashGridStorage.get(i)
levelIndex = eval(HashGridIndex.toString())
self.assertFalse(levelIndex[0] == 4)
def test_manual(self):
print "#" * 20
result = {(1, 0): 5, (2, 0): 25}
#
# Grid
#
DIM = 1
LEVEL = 2
self.grid = Grid.createLinearGrid(DIM)
self.grid_gen = self.grid.createGridGenerator()
self.grid_gen.regular(LEVEL)
#
# trainData, classes, errors
#
xs = [[0.1], [0.4], [0.6], [0.8]]
errs = [1, 2, 3, 4]
self.trainData = DataMatrix(xs)
self.errors = DataVector(errs)
self.multEval = createOperationMultipleEval(self.grid, self.trainData)
self.dim = DIM
self.storage = self.grid.getStorage()
self.gridSize = self.grid.getSize()
#
# OnlinePredictiveRefinementDimension
#
print "OnlineRefinementDim"
hash_refinement = HashRefinement()
online = OnlinePredictiveRefinementDimension(hash_refinement)
online.setTrainDataset(self.trainData)
online.setErrors(self.errors)
online_result = refinement_map({})
online.collectRefinablePoints(self.grid.getStorage(), 10,
online_result)
for k, v in online_result.iteritems():
print k, v
for k, v in online_result.iteritems():
self.assertAlmostEqual(online_result[k], result[k])
#
# Naive
#
print
print "Naive"
naive_result = self.naive_calc()
for k, v in naive_result.iteritems():
print k, v
for k, v in naive_result.iteritems():
self.assertAlmostEqual(naive_result[k], result[k])
def __testANOVAS(self, suffix):
# from bin.controller.InfoToScreen import InfoToScreen
builder = LearnerBuilder()
builder = builder.buildRegressor()
learner = builder.withTrainingDataFromCSVFile('refinement_strategy_%s.csv.gz'%suffix)\
.withGrid().withLevel(3)\
.withBorder(Types.BorderTypes.NONE)\
.withSpecification().withIdentityOperator().withAdaptThreshold(0.001)\
.withAdaptRate(1.0)\
.withLambda(0.0001)\
.withCGSolver().withImax(500)\
.withStopPolicy().withAdaptiveItarationLimit(5)\
.andGetResult()
learner.specification.setBOperator(
createOperationMultipleEval(
learner.grid,
learner.dataContainer.getPoints(DataContainer.TRAIN_CATEGORY)))
while True: #repeat until policy says "stop"
learner.notifyEventControllers(LearnerEvents.LEARNING_STEP_STARTED)
#learning step
learner.alpha = learner.doLearningIteration(learner.dataContainer)
learner.knowledge.update(learner.alpha)
#compress grid
if learner.iteration == 0:
generator = learner.grid.getGenerator()
functor = self.coarsening_functor(
learner.alpha, generator.getNumberOfRemovablePoints(),
learner.specification.getAdaptThreshold())
generator.coarsen(functor, learner.alpha)
self.plotGrid(learner, suffix)
storage = learner.grid.getStorage()
self.plot_grid_historgram(suffix, learner, storage)
formatter = GridImageFormatter()
formatter.serializeToFile(
learner.grid,
"%s%d_projections_anova.png" % (suffix, learner.iteration))
#calculate avg. error for training and test data and avg. for refine alpha
learner.updateResults(learner.alpha, learner.dataContainer)
learner.notifyEventControllers(
LearnerEvents.LEARNING_STEP_COMPLETE)
p_val = learner.trainAccuracy[-1] + learner.specification.getL(
) * np.sum(learner.alpha.array()**2)
print("ANOVA %s iteration %d: %d grid points, %1.9f MSE, p* = %1.10f" \
% (suffix, learner.iteration, storage.getSize(), learner.trainAccuracy[-1], p_val))
learner.iteration += 1
if learner.iteration == 5:
pass
if (learner.stopPolicy.isTrainingComplete(learner)): break
#refine grid
learner.notifyEventControllers(LearnerEvents.REFINING_GRID)
learner.grid.getStorage().recalcLeafProperty()
refinable_poits = learner.grid.getGenerator(
).getNumberOfRefinablePoints()
pointsNum = learner.specification.getNumOfPointsToRefine(
refinable_poits)
# learner.grid.getGenerator().refine( SurplusRefinementFunctor(learner.errors, int(pointsNum), learner.specification.getAdaptThreshold()) )
refiner = HashRefinement()
functor = self.refinement_functor(
learner.alpha, int(pointsNum),
learner.specification.getAdaptThreshold())
anova_refinement = ANOVARefinement(refiner)
anova_refinement.free_refine(learner.grid.getStorage(), functor)
#formatter = GridFormatter()
#formatter.serializeToFile(learner.grid, "grid_anova_%s.txt"%suffix)
del learner
print "(1, 0): 4.04"
print "#" * 10
d = 2
l = 2
xs = [[0.1, 0.9], [0.9, 0.2], [0.3, 0.5], [0.3, 0.0], [0.9, 0.0]]
errs = [-2, -0.1, -0.2, -0.2, -1.8]
grid = Grid.createLinearGrid(d)
grid_gen = grid.createGridGenerator()
grid_gen.regular(l)
trainData = DataMatrix(xs)
errors = DataVector(errs)
multEval = createOperationMultipleEval(grid, trainData)
dim = d
storage = grid.getStorage()
gridSize = grid.getSize()
hash_refinement = HashRefinement()
online = OnlinePredictiveRefinementDimension(hash_refinement)
online.setTrainDataset(trainData)
online.setErrors(errors)
online_result = refinement_map({})
online.collectRefinablePoints(storage, 10, online_result)
for k, v in online_result.iteritems():
print k, v
def general_test(self, d, l, num):
# print "#"*20
# print
xs = [self.get_random_x(d) for i in xrange(num)]
dupl = True
while dupl:
dupl_tmp = False
for x in xs:
for y in xs:
if x == y:
dupl = True
break
if dupl:
break
dupl = dupl_tmp
xs = [self.get_random_x(d) for i in xrange(num)]
errs = [self.get_random_err() for i in xrange(num)]
self.grid = Grid.createLinearGrid(d)
self.grid_gen = self.grid.createGridGenerator()
self.grid_gen.regular(l)
self.trainData = DataMatrix(xs)
self.errors = DataVector(errs)
self.multEval = createOperationMultipleEval(self.grid, self.trainData)
self.dim = d
self.storage = self.grid.getStorage()
self.gridSize = self.grid.getSize()
#
# OnlinePredictiveRefinementDimension
#
# print "OnlineRefinementDim"
hash_refinement = HashRefinement();
online = OnlinePredictiveRefinementDimension(hash_refinement)
online.setTrainDataset(self.trainData)
online.setErrors(self.errors)
online_result = refinement_map({})
online.collectRefinablePoints(self.storage, 5, online_result)
# for k,v in online_result.iteritems():
# print k, v
#
# Naive
#
# print
# print "Naive"
naive_result = self.naive_calc()
# for k,v in naive_result.iteritems():
# print k, v
#
# OnlinePredictiveRefinementDimensionOld
#
hash_refinement = HashRefinement();
online_old = OnlinePredictiveRefinementDimensionOld(hash_refinement)
#
# Assertions
#
for k,v in online_result.iteritems():
if abs(online_result[k] - naive_result[k]) >= 0.1:
#print "Error in:", k
#print online_result[k]
#print naive_result[k]
#print naive_result
#print "Datapoints"
#print xs
#print "Errors"
#print errs
#print "All values:"
#print "Key: Online result, naive result"
#for k,v in online_result.iteritems():
# print("{} ({}): {}, {}".format(k, self.storage.get(k[0]).toString(), v, naive_result[k]))
self.assertTrue(False)
# self.assertAlmostEqual(online_result[k], naive_result[k])
del self.grid
del self.grid_gen
del self.trainData
del self.errors
del self.multEval
del self.storage