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 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_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])
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
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
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])
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
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
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