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 __init__(self):
numpy.random.seed(21)
#Create a low rank matrix
m = 1000
n = 500
self.k = 8
#self.X = SparseUtils.generateSparseBinaryMatrix((m, n), self.k, csarray=True)
self.X, U, V = DatasetUtils.syntheticDataset1(u=0.2, sd=0.2)
def computeRProfile(self):
X, U, V = DatasetUtils.syntheticDataset1(m=1000, n=20000)
w = 0.9
indsPerRow = 50
numRuns = 1000
def run():
for i in range(numRuns):
SparseUtilsCython.computeR(U, V, w, indsPerRow)
ProfileUtils.profile('run()', globals(), locals())
def profileRestrictOmega(self):
X, U, V = DatasetUtils.syntheticDataset1(u=0.01, m=1000, n=2000)
m, n = X.shape
indPtr, colInds = SparseUtils.getOmegaListPtr(X)
colIndsSubset = numpy.random.choice(n, 500, replace=False)
def run():
for i in range(100):
newIndPtr, newColInds = restrictOmega(indPtr, colInds,
colIndsSubset)
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)
import numpy
import logging
import sys
import argparse
from wallhack.rankingexp.RankingExpHelper import RankingExpHelper
from wallhack.rankingexp.DatasetUtils import DatasetUtils
from sandbox.util.Util import Util
Util.setupScript()
#Create a low rank matrix
X, U, V = DatasetUtils.syntheticDataset1(u=0.2, sd=0.2)
m, n = X.shape
u = 0.1
w = 1-u
# Arguments related to the dataset
dataArgs = argparse.Namespace()
# Arguments related to the algorithm
defaultAlgoArgs = argparse.Namespace()
defaultAlgoArgs.u = 5/float(n)
#defaultAlgoArgs.validationUsers = 0.0
defaultAlgoArgs.ks = numpy.array([8])
# data args parser #
dataParser = argparse.ArgumentParser(description="", add_help=False)
dataParser.add_argument("-h", "--help", action="store_true", help="show this help message and exit")
devNull, remainingArgs = dataParser.parse_known_args(namespace=dataArgs)
if dataArgs.help:
helpParser = argparse.ArgumentParser(description="", add_help=False, parents=[dataParser, RankingExpHelper.newAlgoParser(defaultAlgoArgs)])
