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 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 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 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 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 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 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 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 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)
k2 = 8
u2 = 0.5
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("Number of non-zero elements: " + str((trainX.nnz, testX.nnz)))
k2 = 32
u2 = 0.1
w2 = 1-u2
eps = 10**-8
lmbda = 1.0
maxLocalAuc = MaxLocalAUC(k2, w2, eps=eps, lmbdaU=0.0, lmbdaV=lmbda, stochastic=True)
maxLocalAuc.alpha = 1.0
maxLocalAuc.alphas = 2.0**-numpy.arange(-5, 5, 1)
maxLocalAuc.folds = 5
maxLocalAuc.initialAlg = "rand"
maxLocalAuc.itemExpP = 1.0
maxLocalAuc.itemExpQ = 1.0
maxLocalAuc.lmbdas = numpy.linspace(0.5, 2.0, 7)
maxLocalAuc.maxIterations = 100
maxLocalAuc.metric = "f1"
maxLocalAuc.normalise = True
maxLocalAuc.numAucSamples = 10
#maxLocalAuc.numProcesses = 1
maxLocalAuc.numRecordAucSamples = 100
maxLocalAuc.numRowSamples = 30
maxLocalAuc.rate = "optimal"
maxLocalAuc.recommendSize = 5
maxLocalAuc.recordStep = 1
maxLocalAuc.rho = 1.0
maxLocalAuc.t0 = 1.0
maxLocalAuc.t0s = 2.0**-numpy.arange(-1, 6, 1)
maxLocalAuc.validationSize = 5
maxLocalAuc.validationUsers = 0
