def profileLearnModel(self):
#Profile full gradient descent
X, U, V = DatasetUtils.syntheticDataset1(u=0.01, m=1000, n=2000)
#X, U, V = DatasetUtils.syntheticDataset1()
#X, U, V = DatasetUtils.syntheticDataset1(u=0.2, sd=0.2)
#X = DatasetUtils.flixster()
u = 0.2
w = 1 - u
eps = 10**-6
alpha = 0.5
maxLocalAuc = MaxLocalAUC(self.k,
w,
alpha=alpha,
eps=eps,
stochastic=True)
maxLocalAuc.maxNormU = 10
maxLocalAuc.maxNormV = 10
maxLocalAuc.maxIterations = 100
maxLocalAuc.initialAlg = "rand"
maxLocalAuc.rate = "constant"
maxLocalAuc.parallelSGD = True
maxLocalAuc.numProcesses = 8
maxLocalAuc.numAucSamples = 10
maxLocalAuc.numRowSamples = 30
maxLocalAuc.scaleAlpha = False
maxLocalAuc.loss = "hinge"
maxLocalAuc.validationUsers = 0.0
print(maxLocalAuc)
ProfileUtils.profile('maxLocalAuc.learnModel(X)', globals(), locals())
def profileLearnModel2(self):
#Profile stochastic case
#X = DatasetUtils.flixster()
#X = Sampling.sampleUsers(X, 1000)
X, U, V = DatasetUtils.syntheticDataset1(u=0.001, m=10000, n=1000)
rho = 0.00
u = 0.2
w = 1 - u
eps = 10**-6
alpha = 0.5
k = self.k
maxLocalAuc = MaxLocalAUC(k, w, alpha=alpha, eps=eps, stochastic=True)
maxLocalAuc.numRowSamples = 2
maxLocalAuc.numAucSamples = 10
maxLocalAuc.maxIterations = 1
maxLocalAuc.numRecordAucSamples = 100
maxLocalAuc.recordStep = 10
maxLocalAuc.initialAlg = "rand"
maxLocalAuc.rate = "optimal"
#maxLocalAuc.parallelSGD = True
trainTestX = Sampling.shuffleSplitRows(X, maxLocalAuc.folds, 5)
trainX, testX = trainTestX[0]
def run():
U, V, trainMeasures, testMeasures, iterations, time = maxLocalAuc.learnModel(
trainX, True)
#logging.debug("Train Precision@5=" + str(MCEvaluator.precisionAtK(trainX, U, V, 5)))
#logging.debug("Train Precision@10=" + str(MCEvaluator.precisionAtK(trainX, U, V, 10)))
#logging.debug("Train Precision@20=" + str(MCEvaluator.precisionAtK(trainX, U, V, 20)))
#logging.debug("Train Precision@50=" + str(MCEvaluator.precisionAtK(trainX, U, V, 50)))
#logging.debug("Test Precision@5=" + str(MCEvaluator.precisionAtK(testX, U, V, 5)))
#logging.debug("Test Precision@10=" + str(MCEvaluator.precisionAtK(testX, U, V, 10)))
#logging.debug("Test Precision@20=" + str(MCEvaluator.precisionAtK(testX, U, V, 20)))
#logging.debug("Test Precision@50=" + str(MCEvaluator.precisionAtK(testX, U, V, 50)))
ProfileUtils.profile('run()', globals(), locals())
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)
w2 = 1-u2
eps = 10**-4
lmbda = 0.0
maxLocalAuc = MaxLocalAUC(k2, w2, eps=eps, lmbdaU=lmbda, lmbdaV=lmbda, stochastic=True)
maxLocalAuc.alpha = 0.05
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.lmbdas = numpy.linspace(0.5, 2.0, 7)
maxLocalAuc.maxIterations = 500
maxLocalAuc.metric = "f1"
maxLocalAuc.normalise = True
maxLocalAuc.numAucSamples = 10
maxLocalAuc.numProcesses = 1
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)
maxLocalAuc.validationSize = 3
maxLocalAuc.validationUsers = 0
os.system('taskset -p 0xffffffff %d' % os.getpid())
logging.debug("Starting training")
losses = [("tanh", 0.25), ("tanh", 0.5), ("tanh", 1.0), ("tanh", 2.0), ("hinge", 1), ("square", 1), ("logistic", 0.5), ("logistic", 1.0), ("logistic", 2.0), ("sigmoid", 0.5), ("sigmoid", 1.0), ("sigmoid", 2.0)]
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)
