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 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)
wrmf = WeightedMf(k=k, maxIterations=maxIterations, alpha=1.0)
wrmf.ks = ks
wrmf.folds = folds
wrmf.lmbdas = 2.0**-numpy.arange(-1, 12, 2)
wrmf.metric = "f1"
wrmf.numProcesses = args.processes
maxLocalAuc = MaxLocalAUC(k=k, w=0.9, maxIterations=50, lmbdaU=0.1, lmbdaV=0.1, stochastic=True)
maxLocalAuc.numRowSamples = 10
maxLocalAuc.parallelSGD = True
maxLocalAuc.initialAlg = "rand"
maxLocalAuc.ks = ks
maxLocalAuc.folds = folds
maxLocalAuc.metric = "f1"
maxLocalAuc.numProcesses = args.processes
kNeighbours = 25
knn = CosineKNNRecommender(kNeighbours)
numFeatures = 200
slim = SLIM(num_selected_features=numFeatures)
learners = [("SoftImpute", softImpute), ("WRMF", wrmf), ("KNN", knn), ("MLAUC", maxLocalAuc), ("SLIM", slim)]
#Figure out the correct learner
for tempLearnerName, tempLearner in learners:
if args.alg == tempLearnerName:
learnerName = tempLearnerName
learner = tempLearner
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)]
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)
maxLocalAuc.validationSize = 3
maxLocalAuc.validationUsers = 0
newM = X.shape[0]/4
modelSelectX, userInds = Sampling.sampleUsers(X, newM)
if saveResults:
meanObjs1, stdObjs1 = maxLocalAuc.modelSelect2(X)
