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 testOverfit(self):
"""
See if we can get a zero objective on the hinge loss
"""
m = 10
n = 20
k = 5
u = 0.5
w = 1 - u
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, w, csarray=True)
eps = 0.001
k = 10
maxLocalAuc = MaxLocalAUC(k, u, eps=eps, stochastic=True)
maxLocalAuc.rate = "constant"
maxLocalAuc.maxIterations = 500
maxLocalAuc.numProcesses = 1
maxLocalAuc.loss = "hinge"
maxLocalAuc.validationUsers = 0
maxLocalAuc.lmbda = 0
print("Overfit example")
U, V, trainMeasures, testMeasures, iterations, time = maxLocalAuc.learnModel(
X, verbose=True)
self.assertAlmostEquals(trainMeasures[-1, 0], 0, 3)
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 testLearningRateSelect(self):
m = 10
n = 20
k = 5
u = 0.5
w = 1 - u
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, w, csarray=True)
eps = 0.001
maxLocalAuc = MaxLocalAUC(k, u, eps=eps, stochastic=True)
maxLocalAuc.rate = "optimal"
maxLocalAuc.maxIterations = 5
maxLocalAuc.numProcesses = 1
maxLocalAuc.learningRateSelect(X)
def testLearnModel(self):
m = 50
n = 20
k = 5
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, csarray=True)
u = 0.1
w = 1 - u
eps = 0.05
maxLocalAuc = MaxLocalAUC(k, w, alpha=5.0, eps=eps, stochastic=False)
U, V = maxLocalAuc.learnModel(X)
maxLocalAuc.stochastic = True
U, V = maxLocalAuc.learnModel(X)
#Test case where we do not have validation set
maxLocalAuc.validationUsers = 0.0
U, V = maxLocalAuc.learnModel(X)
def testModelSelectMaxNorm(self):
m = 10
n = 20
k = 5
u = 0.5
w = 1 - u
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, w, csarray=True)
os.system('taskset -p 0xffffffff %d' % os.getpid())
eps = 0.001
k = 5
maxLocalAuc = MaxLocalAUC(k, w, eps=eps, stochastic=True)
maxLocalAuc.maxIterations = 5
maxLocalAuc.recordStep = 1
maxLocalAuc.validationSize = 3
maxLocalAuc.metric = "f1"
maxLocalAuc.modelSelectNorm(X)
def profileDerivativeVjApprox(self):
k = 10
U = numpy.random.rand(self.m, k)
V = numpy.random.rand(self.n, k)
indPtr, colInds = SparseUtils.getOmegaListPtr(self.X)
gp = numpy.random.rand(self.n)
gp /= gp.sum()
gq = numpy.random.rand(self.n)
gq /= gq.sum()
j = 3
numRowSamples = 100
numAucSamples = 10
permutedRowInds = numpy.array(numpy.random.permutation(self.m),
numpy.uint32)
permutedColInds = numpy.array(numpy.random.permutation(self.n),
numpy.uint32)
maxLocalAuc = MaxLocalAUC(k, w=0.9)
normGp, normGq = maxLocalAuc.computeNormGpq(indPtr, colInds, gp, gq,
self.m)
lmbda = 0.001
normalise = True
learner = MaxLocalAUCCython()
def run():
numRuns = 1
for i in range(numRuns):
for j in range(self.n):
learner.derivativeViApprox(indPtr, colInds, U, V, gp, gq,
normGp, normGq, permutedRowInds,
permutedColInds, i)
ProfileUtils.profile('run()', 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 testParallelLearnModel(self):
numpy.random.seed(21)
m = 500
n = 200
k = 5
X = SparseUtils.generateSparseBinaryMatrix((m, n), k, csarray=True)
from wallhack.rankingexp.DatasetUtils import DatasetUtils
X, U, V = DatasetUtils.syntheticDataset1()
u = 0.1
w = 1 - u
eps = 0.05
maxLocalAuc = MaxLocalAUC(k, w, alpha=1.0, eps=eps, stochastic=True)
maxLocalAuc.maxIterations = 3
maxLocalAuc.recordStep = 1
maxLocalAuc.rate = "optimal"
maxLocalAuc.t0 = 2.0
maxLocalAuc.validationUsers = 0.0
maxLocalAuc.numProcesses = 4
os.system('taskset -p 0xffffffff %d' % os.getpid())
print(X.nnz / maxLocalAuc.numAucSamples)
U, V = maxLocalAuc.parallelLearnModel(X)
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)
def testCopy(self):
u = 0.1
eps = 0.001
k = 10
maxLocalAuc = MaxLocalAUC(k, u, alpha=5.0, eps=eps)
maxLocalAuc.copy()
def testStr(self):
k = 10
u = 0.1
eps = 0.001
maxLocalAuc = MaxLocalAUC(k, u, eps=eps)
