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 = MaxAUCSigmoid(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 = 200
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, 3)
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, 3)
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, 3)
logging.debug("Number of non-zero elements: " + str((trainX.nnz, testX.nnz)))
u = 0.1
w = 1-u
k2 = 64
eps = 10**-6
maxLocalAuc = MaxLocalAUC(k2, w, eps=eps, stochastic=True)
maxLocalAuc.alpha = 0.1
maxLocalAuc.alphas = 2.0**-numpy.arange(0, 5, 1)
maxLocalAuc.folds = 1
maxLocalAuc.initialAlg = "rand"
maxLocalAuc.itemExpP = 0.0
maxLocalAuc.itemExpQ = 0.0
maxLocalAuc.ks = numpy.array([k2])
maxLocalAuc.lmbdaU = 0.0
maxLocalAuc.lmbdaV = 0.0
maxLocalAuc.lmbdas = 2.0**-numpy.arange(0, 8)
maxLocalAuc.loss = "hinge"
maxLocalAuc.maxIterations = 500
maxLocalAuc.maxNorms = 2.0**numpy.arange(-2, 5, 0.5)
maxLocalAuc.metric = "f1"
maxLocalAuc.normalise = True
maxLocalAuc.numAucSamples = 10
maxLocalAuc.numProcesses = multiprocessing.cpu_count()
maxLocalAuc.numRecordAucSamples = 100
maxLocalAuc.numRowSamples = 30
maxLocalAuc.rate = "constant"
maxLocalAuc.recordStep = 10
maxLocalAuc.rho = 1.0
maxLocalAuc.t0 = 1.0
maxLocalAuc.t0s = 2.0**-numpy.arange(7, 12, 1)
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 = MaxAUCSigmoid(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 = 200
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, 3)
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, 3)
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, 3)
u = 0.1
w2 = 1-u
k = 64
eps = 10**-8
maxLocalAuc = MaxLocalAUC(k, w2, eps=eps, stochastic=True)
maxLocalAuc.maxIterations = 50
maxLocalAuc.numRowSamples = 30
maxLocalAuc.numAucSamples = 10
maxLocalAuc.initialAlg = "rand"
maxLocalAuc.recordStep = 10
maxLocalAuc.rate = "optimal"
maxLocalAuc.alpha = 1.0
maxLocalAuc.t0 = 0.1
maxLocalAuc.lmbdaU = 0.0
maxLocalAuc.lmbdaV = 1.0
maxLocalAuc.rho = 0.5
maxItems = 10
chunkSize = 1
startAverages = numpy.array([2, 5, 10, 20, 30, 40])
learningRateParams = [(4.0, 1.0), (4.0, 0.5), (4.0, 0.1), (1.0, 1.0), (1.0, 0.5), (1.0, 0.1), (0.25, 1.0), (0.25, 0.5), (0.25, 0.1)]
print(startAverages)
def computeTestObj(args):
trainX, maxLocalAuc = args
numpy.random.seed(21)
U, V, trainMeasures, testMeasures, iterations, totalTime = maxLocalAuc.learnModel(trainX, verbose=True)
return U, V, trainMeasures[-1, 0], testMeasures[-1, 0]
maxLocalAuc.recordStep = 10
maxLocalAuc.reg = False
maxLocalAuc.rho = 1.0
maxLocalAuc.startAverage = 100
maxLocalAuc.t0 = 1.0
maxLocalAuc.t0s = 2.0**-numpy.arange(1, 12, 2)
maxLocalAuc.validationSize = 5
maxLocalAuc.validationUsers = 0.0
if saveResults:
X = DatasetUtils.getDataset(dataset, nnz=100000)
print(X.shape, X.nnz)
print(maxLocalAuc)
maxLocalAuc.lmbdaU = 0.25
maxLocalAuc.lmbdaV = 0.25
meanObjs1, paramDict = maxLocalAuc.learningRateSelect(X)
maxLocalAuc.lmbdaU = 0.03125
maxLocalAuc.lmbdaV = 0.25
meanObjs2, paramDict = maxLocalAuc.learningRateSelect(X)
maxLocalAuc.lmbdaU = 0.25
maxLocalAuc.lmbdaV = 0.03125
meanObjs3, paramDict = maxLocalAuc.learningRateSelect(X)
maxLocalAuc.lmbdaU = 0.03125
maxLocalAuc.lmbdaV = 0.03125
meanObjs4, paramDict = maxLocalAuc.learningRateSelect(X)
numpy.savez(outputFile, meanObjs1, meanObjs2, meanObjs3, meanObjs4)
