def testScale(self):
"""
Look at the scales of the unnormalised gradients.
"""
m = 100
n = 400
k = 3
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, csarray=True)
w = 0.1
eps = 0.001
learner = MaxAUCTanh(k, w)
learner.normalise = False
learner.lmbdaU = 1.0
learner.lmbdaV = 1.0
learner.rho = 1.0
learner.numAucSamples = 100
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
r = numpy.random.rand(m)
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
gi = numpy.random.rand(m)
gi /= gi.sum()
gp = numpy.random.rand(n)
gp /= gp.sum()
gq = numpy.random.rand(n)
gq /= gq.sum()
permutedRowInds = numpy.array(numpy.random.permutation(m),
numpy.uint32)
permutedColInds = numpy.array(numpy.random.permutation(n),
numpy.uint32)
maxLocalAuc = MaxLocalAUC(k, w)
normGp, normGq = maxLocalAuc.computeNormGpq(indPtr, colInds, gp, gq, m)
normDui = 0
for i in range(m):
du = learner.derivativeUi(indPtr, colInds, U, V, r, gi, gp, gq, i)
normDui += numpy.linalg.norm(du)
normDui /= float(m)
print(normDui)
normDvi = 0
for i in range(n):
dv = learner.derivativeVi(indPtr, colInds, U, V, r, gi, gp, gq, i)
normDvi += numpy.linalg.norm(dv)
normDvi /= float(n)
print(normDvi)
def testScale(self):
"""
Look at the scales of the unnormalised gradients.
"""
m = 100
n = 400
k = 3
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, csarray=True)
w = 0.1
eps = 0.001
learner = MaxAUCTanh(k, w)
learner.normalise = False
learner.lmbdaU = 1.0
learner.lmbdaV = 1.0
learner.rho = 1.0
learner.numAucSamples = 100
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
r = numpy.random.rand(m)
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
gi = numpy.random.rand(m)
gi /= gi.sum()
gp = numpy.random.rand(n)
gp /= gp.sum()
gq = numpy.random.rand(n)
gq /= gq.sum()
permutedRowInds = numpy.array(numpy.random.permutation(m), numpy.uint32)
permutedColInds = numpy.array(numpy.random.permutation(n), numpy.uint32)
maxLocalAuc = MaxLocalAUC(k, w)
normGp, normGq = maxLocalAuc.computeNormGpq(indPtr, colInds, gp, gq, m)
normDui = 0
for i in range(m):
du = learner.derivativeUi(indPtr, colInds, U, V, r, gi, gp, gq, i)
normDui += numpy.linalg.norm(du)
normDui /= float(m)
print(normDui)
normDvi = 0
for i in range(n):
dv = learner.derivativeVi(indPtr, colInds, U, V, r, gi, gp, gq, i)
normDvi += numpy.linalg.norm(dv)
normDvi /= float(n)
print(normDvi)
def testDerivativeViApprox(self):
"""
We'll test the case in which we apprormate using a large number of samples
for the AUC and see if we get close to the exact derivative
"""
m = 20
n = 30
k = 3
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, csarray=True)
for i in range(m):
X[i, 0] = 1
X[i, 1] = 0
w = 0.1
eps = 0.001
learner = MaxAUCTanh(k, w)
learner.normalise = False
learner.lmbdaU = 0
learner.lmbdaV = 0
learner.numAucSamples = n
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
gp = numpy.random.rand(n)
gp /= gp.sum()
gq = numpy.random.rand(n)
gq /= gq.sum()
permutedRowInds = numpy.array(numpy.random.permutation(m),
numpy.uint32)
permutedColInds = numpy.array(numpy.random.permutation(n),
numpy.uint32)
maxLocalAuc = MaxLocalAUC(k, w)
normGp, normGq = maxLocalAuc.computeNormGpq(indPtr, colInds, gp, gq, m)
numRuns = 100
numTests = 5
#Let's compare against using the exact derivative
for i in numpy.random.permutation(m)[0:numTests]:
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp,
gq, normGp, normGq,
permutedRowInds,
permutedColInds, i)
dv1 /= numRuns
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
dv3 = numpy.zeros(k)
for j in range(k):
eps = 10**-6
tempV = V.copy()
tempV[i, j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds, U,
tempV, gp, gq)
tempV = V.copy()
tempV[i, j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds, U,
tempV, gp, gq)
dv3[j] = (obj1 - obj2) / (2 * eps)
print(dv1, dv2, dv3)
nptst.assert_array_almost_equal(dv1, dv2, 2)
learner.lmbdaV = 0.5
learner.rho = 0.5
for i in numpy.random.permutation(m)[0:numTests]:
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp,
gq, normGp, normGq,
permutedRowInds,
permutedColInds, i)
dv1 /= numRuns
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
print(dv1, dv2)
nptst.assert_array_almost_equal(dv1, dv2, 2)
learner.numRowSamples = 10
numRuns = 1000
for i in numpy.random.permutation(m)[0:numTests]:
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp,
gq, normGp, normGq,
permutedRowInds,
permutedColInds, i)
dv1 /= numRuns
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
print(dv1, dv2)
#nptst.assert_array_almost_equal(dv1, dv2, 3)
maxLocalAuc.numRowSamples = m
maxLocalAuc.numAucSamples = 20
maxLocalAuc.lmbdaV = 0
numRuns = 1000
print("Final test")
#for i in numpy.random.permutation(m)[0:numTests]:
for i in range(m):
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp,
gq, normGp, normGq,
permutedRowInds,
permutedColInds, i)
dv1 /= numRuns
#dv1 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
print(i, dv1, dv2)
nptst.assert_array_almost_equal(dv1, dv2, 2)
def testDerivativeV(self):
m = 10
n = 20
nnzPerRow = 5
X = SparseUtils.generateSparseBinaryMatrix((m, n),
nnzPerRow,
csarray=True)
for i in range(m):
X[i, 0] = 1
X[i, 1] = 0
k = 5
u = 0.1
w = 1 - u
eps = 0.05
learner = MaxAUCTanh(k, w)
learner.normalise = False
learner.lmbdaU = 0
learner.lmbdaV = 0
learner.rho = 1.0
learner.numAucSamples = 100
numRuns = 20
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
gp = numpy.random.rand(n)
gp /= gp.sum()
gq = numpy.random.rand(n)
gq /= gq.sum()
for s in range(numRuns):
U = numpy.random.randn(m, k)
V = numpy.random.randn(n, k)
deltaV = numpy.zeros(V.shape)
for j in range(n):
deltaV[j, :] = learner.derivativeVi(indPtr, colInds, U, V, gp,
gq, j)
deltaV2 = numpy.zeros(V.shape)
eps = 0.00001
for i in range(n):
for j in range(k):
tempV = V.copy()
tempV[i, j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds,
U, tempV, gp, gq)
tempV = V.copy()
tempV[i, j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds,
U, tempV, gp, gq)
deltaV2[i, j] = (obj1 - obj2) / (2 * eps)
#deltaV2[i,:] = deltaV2[i,:]/numpy.linalg.norm(deltaV2[i,:])
#print(deltaV*100)
#print(deltaV2*100)
nptst.assert_almost_equal(deltaV, deltaV2, 3)
#Try r != 0 and rho > 0
for s in range(numRuns):
U = numpy.random.randn(m, k)
V = numpy.random.randn(n, k)
learner.rho = 0.5
deltaV = numpy.zeros(V.shape)
for j in range(n):
deltaV[j, :] = learner.derivativeVi(indPtr, colInds, U, V, gp,
gq, j)
deltaV2 = numpy.zeros(V.shape)
for i in range(n):
for j in range(k):
tempV = V.copy()
tempV[i, j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds,
U, tempV, gp, gq)
tempV = V.copy()
tempV[i, j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds,
U, tempV, gp, gq)
deltaV2[i, j] = (obj1 - obj2) / (2 * eps)
#deltaV2[i,:] = deltaV2[i,:]/numpy.linalg.norm(deltaV2[i,:])
nptst.assert_almost_equal(deltaV, deltaV2, 3)
#Try r != 0 and rho > 0
for s in range(numRuns):
U = numpy.random.randn(m, k)
V = numpy.random.randn(n, k)
learner.lmbdaV = 100
deltaV = numpy.zeros(V.shape)
for j in range(n):
deltaV[j, :] = learner.derivativeVi(indPtr, colInds, U, V, gp,
gq, j)
deltaV2 = numpy.zeros(V.shape)
for i in range(n):
for j in range(k):
tempV = V.copy()
tempV[i, j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds,
U, tempV, gp, gq)
tempV = V.copy()
tempV[i, j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds,
U, tempV, gp, gq)
deltaV2[i, j] = (obj1 - obj2) / (2 * eps)
#deltaV2[i,:] = deltaV2[i,:]/numpy.linalg.norm(deltaV2[i,:])
nptst.assert_almost_equal(deltaV, deltaV2, 3)
def testDerivativeViApprox(self):
"""
We'll test the case in which we apprormate using a large number of samples
for the AUC and see if we get close to the exact derivative
"""
m = 20
n = 30
k = 3
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, csarray=True)
for i in range(m):
X[i, 0] = 1
X[i, 1] = 0
w = 0.1
eps = 0.001
learner = MaxAUCTanh(k, w)
learner.normalise = False
learner.lmbdaU = 0
learner.lmbdaV = 0
learner.numAucSamples = n
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
gp = numpy.random.rand(n)
gp /= gp.sum()
gq = numpy.random.rand(n)
gq /= gq.sum()
permutedRowInds = numpy.array(numpy.random.permutation(m), numpy.uint32)
permutedColInds = numpy.array(numpy.random.permutation(n), numpy.uint32)
maxLocalAuc = MaxLocalAUC(k, w)
normGp, normGq = maxLocalAuc.computeNormGpq(indPtr, colInds, gp, gq, m)
numRuns = 100
numTests = 5
#Let's compare against using the exact derivative
for i in numpy.random.permutation(m)[0:numTests]:
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp, gq, normGp, normGq, permutedRowInds, permutedColInds, i)
dv1 /= numRuns
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
dv3 = numpy.zeros(k)
for j in range(k):
eps = 10**-6
tempV = V.copy()
tempV[i,j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
tempV = V.copy()
tempV[i,j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
dv3[j] = (obj1-obj2)/(2*eps)
print(dv1, dv2, dv3)
nptst.assert_array_almost_equal(dv1, dv2, 2)
learner.lmbdaV = 0.5
learner.rho = 0.5
for i in numpy.random.permutation(m)[0:numTests]:
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp, gq, normGp, normGq, permutedRowInds, permutedColInds, i)
dv1 /= numRuns
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
print(dv1, dv2)
nptst.assert_array_almost_equal(dv1, dv2, 2)
learner.numRowSamples = 10
numRuns = 1000
for i in numpy.random.permutation(m)[0:numTests]:
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp, gq, normGp, normGq, permutedRowInds, permutedColInds, i)
dv1 /= numRuns
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
print(dv1, dv2)
#nptst.assert_array_almost_equal(dv1, dv2, 3)
maxLocalAuc.numRowSamples = m
maxLocalAuc.numAucSamples = 20
maxLocalAuc.lmbdaV = 0
numRuns = 1000
print("Final test")
#for i in numpy.random.permutation(m)[0:numTests]:
for i in range(m):
U = numpy.random.rand(X.shape[0], k)
V = numpy.random.rand(X.shape[1], k)
dv1 = numpy.zeros(k)
for j in range(numRuns):
dv1 += learner.derivativeViApprox(indPtr, colInds, U, V, gp, gq, normGp, normGq, permutedRowInds, permutedColInds, i)
dv1 /= numRuns
#dv1 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
dv2 = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, i)
print(i, dv1, dv2)
nptst.assert_array_almost_equal(dv1, dv2, 2)
def testDerivativeV(self):
m = 10
n = 20
nnzPerRow = 5
X = SparseUtils.generateSparseBinaryMatrix((m, n), nnzPerRow, csarray=True)
for i in range(m):
X[i, 0] = 1
X[i, 1] = 0
k = 5
u = 0.1
w = 1-u
eps = 0.05
learner = MaxAUCTanh(k, w)
learner.normalise = False
learner.lmbdaU = 0
learner.lmbdaV = 0
learner.rho = 1.0
learner.numAucSamples = 100
numRuns = 20
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
gp = numpy.random.rand(n)
gp /= gp.sum()
gq = numpy.random.rand(n)
gq /= gq.sum()
for s in range(numRuns):
U = numpy.random.randn(m, k)
V = numpy.random.randn(n, k)
deltaV = numpy.zeros(V.shape)
for j in range(n):
deltaV[j, :] = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, j)
deltaV2 = numpy.zeros(V.shape)
eps = 0.00001
for i in range(n):
for j in range(k):
tempV = V.copy()
tempV[i,j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
tempV = V.copy()
tempV[i,j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
deltaV2[i,j] = (obj1-obj2)/(2*eps)
#deltaV2[i,:] = deltaV2[i,:]/numpy.linalg.norm(deltaV2[i,:])
#print(deltaV*100)
#print(deltaV2*100)
nptst.assert_almost_equal(deltaV, deltaV2, 3)
#Try r != 0 and rho > 0
for s in range(numRuns):
U = numpy.random.randn(m, k)
V = numpy.random.randn(n, k)
learner.rho = 0.5
deltaV = numpy.zeros(V.shape)
for j in range(n):
deltaV[j, :] = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, j)
deltaV2 = numpy.zeros(V.shape)
for i in range(n):
for j in range(k):
tempV = V.copy()
tempV[i,j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
tempV = V.copy()
tempV[i,j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
deltaV2[i,j] = (obj1-obj2)/(2*eps)
#deltaV2[i,:] = deltaV2[i,:]/numpy.linalg.norm(deltaV2[i,:])
nptst.assert_almost_equal(deltaV, deltaV2, 3)
#Try r != 0 and rho > 0
for s in range(numRuns):
U = numpy.random.randn(m, k)
V = numpy.random.randn(n, k)
learner.lmbdaV = 100
deltaV = numpy.zeros(V.shape)
for j in range(n):
deltaV[j, :] = learner.derivativeVi(indPtr, colInds, U, V, gp, gq, j)
deltaV2 = numpy.zeros(V.shape)
for i in range(n):
for j in range(k):
tempV = V.copy()
tempV[i,j] += eps
obj1 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
tempV = V.copy()
tempV[i,j] -= eps
obj2 = learner.objective(indPtr, colInds, indPtr, colInds, U, tempV, gp, gq)
deltaV2[i,j] = (obj1-obj2)/(2*eps)
#deltaV2[i,:] = deltaV2[i,:]/numpy.linalg.norm(deltaV2[i,:])
nptst.assert_almost_equal(deltaV, deltaV2, 3)