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 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)
U, V, trainMeasures, testMeasures, iterations, time = maxLocalAuc.learnModel(trainX, U=U, V=V, verbose=True)
fprTrain, tprTrain = MCEvaluator.averageRocCurve(trainX, U, V)
fprTest, tprTest = MCEvaluator.averageRocCurve(testX, U, V)
return fprTrain, tprTrain, fprTest, tprTest
if saveResults:
paramList = []
chunkSize = 1
U, V = maxLocalAuc.initUV(X)
for loss, rho in losses:
for trainX, testX in trainTestXs:
maxLocalAuc.loss = loss
maxLocalAuc.rho = rho
paramList.append((trainX, testX, maxLocalAuc.copy(), U.copy(), V.copy()))
pool = multiprocessing.Pool(maxtasksperchild=100, processes=multiprocessing.cpu_count())
resultsIterator = pool.imap(computeTestAuc, paramList, chunkSize)
#import itertools
#resultsIterator = itertools.imap(computeTestAuc, paramList)
meanFprTrains = []
meanTprTrains = []
meanFprTests = []
meanTprTests = []
for loss in losses:
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) maxLocalAuc.validationSize = 3 maxLocalAuc.validationUsers = 0
