def testModelSelect(self):
lmbda = 0.1
shape = (20, 20)
r = 20
numInds = 100
noise = 0.2
X = ExpSU.SparseUtils.generateSparseLowRank(shape, r, numInds, noise)
U, s, V = numpy.linalg.svd(X.todense())
k = 15
iterativeSoftImpute = IterativeSoftImpute(lmbda, k=None, svdAlg="propack", updateAlg="zero")
iterativeSoftImpute.numProcesses = 1
rhos = numpy.linspace(0.5, 0.001, 20)
ks = numpy.array([k], numpy.int)
folds = 3
cvInds = Sampling.randCrossValidation(folds, X.nnz)
meanTestErrors, meanTrainErrors = iterativeSoftImpute.modelSelect(X, rhos, ks, cvInds)
#Now do model selection manually
(rowInds, colInds) = X.nonzero()
trainErrors = numpy.zeros((rhos.shape[0], len(cvInds)))
testErrors = numpy.zeros((rhos.shape[0], len(cvInds)))
for i, rho in enumerate(rhos):
for j, (trainInds, testInds) in enumerate(cvInds):
trainX = scipy.sparse.csc_matrix(X.shape)
testX = scipy.sparse.csc_matrix(X.shape)
for p in trainInds:
trainX[rowInds[p], colInds[p]] = X[rowInds[p], colInds[p]]
for p in testInds:
testX[rowInds[p], colInds[p]] = X[rowInds[p], colInds[p]]
softImpute = SoftImpute(numpy.array([rho]), k=ks[0])
ZList = [softImpute.learnModel(trainX, fullMatrices=False)]
predTrainX = softImpute.predict(ZList, trainX.nonzero())[0]
predX = softImpute.predict(ZList, testX.nonzero())[0]
testErrors[i, j] = MCEvaluator.rootMeanSqError(testX, predX)
trainErrors[i, j] = MCEvaluator.rootMeanSqError(trainX, predTrainX)
meanTestErrors2 = testErrors.mean(1)
meanTrainErrors2 = trainErrors.mean(1)
nptst.assert_array_almost_equal(meanTestErrors.ravel(), meanTestErrors2, 1)
def testModelSelect2(self):
rho = 0.1
shape = (20, 20)
r = 20
numInds = 100
noise = 0.2
X = ExpSU.SparseUtils.generateSparseLowRank(shape, r, numInds, noise)
X = X.tocsc()
U, s, V = numpy.linalg.svd(X.todense())
k = 15
iterativeSoftImpute = IterativeSoftImpute(rho, k=None, svdAlg="propack", updateAlg="initial")
rhos = numpy.linspace(0.5, 0.001, 5)
ks = numpy.array([5, 10, 15], numpy.int)
folds = 3
cvInds = []
for i in range(folds):
cvInds.append((numpy.arange(X.nnz), numpy.arange(X.nnz)))
meanTestErrors, stdTestErrors = iterativeSoftImpute.modelSelect(X, rhos, ks, cvInds)
self.assertAlmostEquals(numpy.linalg.norm(stdTestErrors), 0, 3)
meanTestErrors2 = numpy.zeros((rhos.shape[0], ks.shape[0]))
#Now compute errors manually
for j, k in enumerate(ks):
iterativeSoftImpute.setK(k)
for i, rho in enumerate(rhos):
iterativeSoftImpute.setRho(rho)
ZIter = iterativeSoftImpute.learnModel(iter([X]))
indList = [X.nonzero()]
outIterator = iterativeSoftImpute.predict(ZIter, indList)
Xhat = outIterator.next()
meanTestErrors2[i, j] = MCEvaluator.rootMeanSqError(X, Xhat)
nptst.assert_array_almost_equal(meanTestErrors, meanTestErrors2, 2)
def runExperiment(self):
"""
Run the selected clustering experiments and save results
"""
if self.algoArgs.runSoftImpute:
logging.debug("Running soft impute")
for svdAlg in self.algoArgs.svdAlgs:
if svdAlg == "rsvd" or svdAlg == "rsvdUpdate" or svdAlg == "rsvdUpdate2":
resultsFileName = self.resultsDir + "ResultsSoftImpute_alg=" + svdAlg + "_p=" + str(self.algoArgs.p)+ "_q=" + str(self.algoArgs.q) + "_updateAlg=" + self.algoArgs.updateAlg + ".npz"
else:
resultsFileName = self.resultsDir + "ResultsSoftImpute_alg=" + svdAlg + "_updateAlg=" + self.algoArgs.updateAlg + ".npz"
fileLock = FileLock(resultsFileName)
if not fileLock.isLocked() and not fileLock.fileExists():
fileLock.lock()
try:
learner = IterativeSoftImpute(svdAlg=svdAlg, logStep=self.logStep, kmax=self.algoArgs.kmax, postProcess=self.algoArgs.postProcess, weighted=self.algoArgs.weighted, p=self.algoArgs.p, q=self.algoArgs.q, verbose=self.algoArgs.verbose, updateAlg=self.algoArgs.updateAlg)
if self.algoArgs.modelSelect:
trainIterator = self.getTrainIterator()
#Let's find the optimal lambda using the first matrix
X = trainIterator.next()
logging.debug("Performing model selection, taking subsample of entries of size " + str(self.sampleSize))
X = SparseUtils.submatrix(X, self.sampleSize)
cvInds = Sampling.randCrossValidation(self.algoArgs.folds, X.nnz)
meanErrors, stdErrors = learner.modelSelect(X, self.algoArgs.rhos, self.algoArgs.ks, cvInds)
logging.debug("Mean errors = " + str(meanErrors))
logging.debug("Std errors = " + str(stdErrors))
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
numpy.savez(modelSelectFileName, meanErrors, stdErrors)
logging.debug("Saved model selection grid as " + modelSelectFileName)
rho = self.algoArgs.rhos[numpy.unravel_index(numpy.argmin(meanErrors), meanErrors.shape)[0]]
k = self.algoArgs.ks[numpy.unravel_index(numpy.argmin(meanErrors), meanErrors.shape)[1]]
else:
rho = self.algoArgs.rhos[0]
k = self.algoArgs.ks[0]
learner.setK(k)
learner.setRho(rho)
logging.debug(learner)
trainIterator = self.getTrainIterator()
ZIter = learner.learnModel(trainIterator)
self.recordResults(ZIter, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runSgdMf:
logging.debug("Running SGD MF")
resultsFileName = self.resultsDir + "ResultsSgdMf.npz"
fileLock = FileLock(resultsFileName)
if not fileLock.isLocked() and not fileLock.fileExists():
fileLock.lock()
try:
learner = IterativeSGDNorm2Reg(k=self.algoArgs.ks[0], lmbda=self.algoArgs.lmbdas[0], gamma=self.algoArgs.gammas[0], eps=self.algoArgs.eps)
if self.algoArgs.modelSelect:
# Let's find optimal parameters using the first matrix
learner.modelSelect(self.getTrainIterator().next(), self.algoArgs.ks, self.algoArgs.lmbdas, self.algoArgs.gammas, self.algoArgs.folds)
trainIterator = self.getTrainIterator()
trainIterator = self.getTrainIterator()
ZIter = learner.learnModel(trainIterator)
self.recordResults(ZIter, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
logging.info("All done: see you around!")
def runExperiment(self, X):
"""
Run the selected ranking experiments and save results
"""
logging.debug("Splitting into train and test sets")
#Make sure different runs get the same train/test split
numpy.random.seed(21)
m, n = X.shape
#colProbs = (X.sum(0)+1)/float(m+1)
#colProbs = colProbs**-self.algoArgs.itemExp
#colProbs = numpy.ones(n)/float(n)
trainTestXs = Sampling.shuffleSplitRows(X, 1, self.algoArgs.testSize)
trainX, testX = trainTestXs[0]
logging.debug("Train X shape and nnz: " + str(trainX.shape) + " " + str(trainX.nnz))
logging.debug("Test X shape and nnz: " + str(testX.shape) + " " + str(testX.nnz))
#Have scipy versions of each array
trainXScipy = trainX.toScipyCsc()
testXScipy = testX.toScipyCsc()
if self.algoArgs.runSoftImpute:
logging.debug("Running soft impute")
resultsFileName = self.resultsDir + "ResultsSoftImpute.npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
modelSelectX, userInds = Sampling.sampleUsers2(trainXScipy, self.algoArgs.modelSelectSamples, prune=True)
try:
learner = IterativeSoftImpute(self.algoArgs.rhoSi, eps=self.algoArgs.epsSi, k=self.algoArgs.k, svdAlg=self.algoArgs.svdAlg, postProcess=self.algoArgs.postProcess, p=self.algoArgs.pSi, q=self.algoArgs.qSi)
learner.folds = self.algoArgs.folds
learner.metric = self.algoArgs.metric
learner.numProcesses = self.algoArgs.processes
learner.recommendSize = self.algoArgs.recommendSize
learner.validationSize = self.algoArgs.validationSize
if self.algoArgs.modelSelect:
cvInds = Sampling.randCrossValidation(self.algoArgs.folds, modelSelectX.nnz)
meanErrors, stdErrors = learner.modelSelect2(modelSelectX, self.algoArgs.rhosSi, self.algoArgs.ks, cvInds)
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
numpy.savez(modelSelectFileName, meanErrors, stdErrors)
logging.debug("Saved model selection grid as " + modelSelectFileName)
logging.debug(learner)
self.recordResults(X, trainXScipy, testXScipy, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runMaxLocalAuc:
logging.debug("Running max local AUC")
if self.algoArgs.loss != "tanh":
resultsFileName = self.resultsDir + "ResultsMaxLocalAUC_loss=" + self.algoArgs.loss + ".npz"
else:
resultsFileName = self.resultsDir + "ResultsMaxLocalAUC_loss=" + self.algoArgs.loss + "_rho=" + str(self.algoArgs.rhoMlauc) + ".npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
try:
learner = MaxLocalAUC(self.algoArgs.k, 1-self.algoArgs.u, lmbdaU=self.algoArgs.lmbdaUMlauc, lmbdaV=self.algoArgs.lmbdaVMlauc, eps=self.algoArgs.epsMlauc, stochastic=not self.algoArgs.fullGradient)
learner.alpha = self.algoArgs.alpha
learner.alphas = self.algoArgs.alphas
learner.eta = self.algoArgs.eta
learner.folds = self.algoArgs.folds
learner.initialAlg = self.algoArgs.initialAlg
learner.itemExpP = self.algoArgs.itemExpP
learner.itemExpQ = self.algoArgs.itemExpQ
learner.ks = self.algoArgs.ks
learner.lmbdas = self.algoArgs.lmbdasMlauc
learner.loss = self.algoArgs.loss
learner.maxIterations = self.algoArgs.maxIterations
learner.maxNorms = self.algoArgs.maxNorms
learner.maxNormU = self.algoArgs.maxNorm
learner.maxNormV = self.algoArgs.maxNorm
learner.metric = self.algoArgs.metric
learner.normalise = self.algoArgs.normalise
learner.numAucSamples = self.algoArgs.numAucSamples
learner.numProcesses = self.algoArgs.processes
learner.numRowSamples = self.algoArgs.numRowSamples
learner.rate = self.algoArgs.rate
learner.recommendSize = self.algoArgs.recommendSize
learner.recordStep = self.algoArgs.recordStep
learner.rho = self.algoArgs.rhoMlauc
learner.rhos = self.algoArgs.rhosMlauc
learner.startAverage = self.algoArgs.startAverage
learner.t0 = self.algoArgs.t0
learner.t0s = self.algoArgs.t0s
learner.validationSize = self.algoArgs.validationSize
learner.validationUsers = self.algoArgs.validationUsers
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
if self.algoArgs.modelSelect and not os.path.isfile(modelSelectFileName):
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
modelSelectX, userInds = Sampling.sampleUsers2(trainX, self.algoArgs.modelSelectSamples, prune=True)
#
meanMetricsLR, paramDictLR = learner.learningRateSelect(modelSelectX)
meanMetricsMS, paramDictMS = learner.modelSelectLmbda(modelSelectX)
numpy.savez(modelSelectFileName, meanMetricsLR, meanMetricsMS)
logging.debug("Saved model selection grid as " + modelSelectFileName)
elif self.algoArgs.modelSelect:
data = numpy.load(modelSelectFileName)
logging.debug("Read model selection file " + modelSelectFileName)
meanMetricsLR = data["arr_0"]
meanMetricsMS = data["arr_1"]
learner.learningRateSelect(meanMetrics=meanMetricsLR)
learner.modelSelectLmbda(meanMetrics=meanMetricsMS)
#Turn on (optionally) parallel SGD only at the final learning stage
learner.parallelSGD = self.algoArgs.parallelSGD
learner.maxIterations *= 2
logging.debug(learner)
self.recordResults(X, trainX, testX, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runWarpMf:
logging.debug("Running WARP loss MF")
resultsFileName = self.resultsDir + "ResultsWarpMf.npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
try:
learner = WarpMf(self.algoArgs.k, self.algoArgs.lmbdas[0], u=self.algoArgs.u)
learner.ks = self.algoArgs.ks
learner.numProcesses = self.algoArgs.processes
learner.recommendSize = self.algoArgs.recommendSize
learner.validationSize = self.algoArgs.validationSize
if self.algoArgs.modelSelect:
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
modelSelectX, userInds = Sampling.sampleUsers2(trainX, self.algoArgs.modelSelectSamples, prune=True)
meanAucs, stdAucs = learner.modelSelect(modelSelectX)
logging.debug("Mean local AUCs = " + str(meanAucs))
logging.debug("Std local AUCs = " + str(stdAucs))
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
numpy.savez(modelSelectFileName, meanAucs, stdAucs)
logging.debug("Saved model selection grid as " + modelSelectFileName)
logging.debug(learner)
self.recordResults(X, trainXScipy, testXScipy, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runWrMf:
logging.debug("Running Weighted Regularized Matrix Factorization")
resultsFileName = self.resultsDir + "ResultsWrMf.npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
trainXScipy = trainXScipy.tocsr()
testXScipy = testXScipy.tocsr()
try:
learner = WeightedMf(self.algoArgs.k, alpha=self.algoArgs.alphaWrMf, lmbda=self.algoArgs.lmbdasWrMf[0], maxIterations=self.algoArgs.maxIterationsWrMf)
learner.folds = self.algoArgs.folds
learner.ks = self.algoArgs.ks
learner.lmbdas = self.algoArgs.lmbdasWrMf
learner.metric = self.algoArgs.metric
learner.numProcesses = self.algoArgs.processes
learner.numRecordAucSamples = self.algoArgs.numRecordAucSamples
learner.recommendSize = self.algoArgs.recommendSize
learner.validationSize = self.algoArgs.validationSize
if self.algoArgs.modelSelect:
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
modelSelectX, userInds = Sampling.sampleUsers2(trainX, self.algoArgs.modelSelectSamples, prune=True)
meanAucs, stdAucs = learner.modelSelect(modelSelectX)
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
numpy.savez(modelSelectFileName, meanAucs, stdAucs)
logging.debug("Saved model selection grid as " + modelSelectFileName)
logging.debug(learner)
self.recordResults(X, trainXScipy, testXScipy, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runBpr:
logging.debug("Running Bayesian Personalised Recommendation")
resultsFileName = self.resultsDir + "ResultsBpr.npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
try:
#trainX = trainX.toScipyCsr()
#testX = testX.toScipyCsr()
learner = BprRecommender(self.algoArgs.k, lmbdaUser=self.algoArgs.lmbdaUserBpr, lmbdaPos=self.algoArgs.lmbdaItemBpr, lmbdaNeg=self.algoArgs.lmbdaItemBpr, gamma=self.algoArgs.gammaBpr)
learner.folds = self.algoArgs.folds
learner.gammas = self.algoArgs.gammasBpr
learner.ks = self.algoArgs.ks
learner.lmbdaItems = self.algoArgs.lmbdaItems
learner.lmbdaUsers = self.algoArgs.lmbdaUsers
learner.maxIterations = self.algoArgs.maxIterationsBpr
learner.metric = self.algoArgs.metric
#learner.numAucSamples = self.algoArgs.numAucSamples
learner.numProcesses = self.algoArgs.processes
learner.recommendSize = self.algoArgs.recommendSize
learner.recordStep = self.algoArgs.recordStep
learner.validationSize = self.algoArgs.validationSize
if self.algoArgs.modelSelect:
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
modelSelectX, userInds = Sampling.sampleUsers2(trainX, self.algoArgs.modelSelectSamples, prune=True)
meanAucs, stdAucs = learner.modelSelect(modelSelectX)
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
numpy.savez(modelSelectFileName, meanAucs, stdAucs)
logging.debug("Saved model selection grid as " + modelSelectFileName)
logging.debug(learner)
self.recordResults(X, trainX, testX, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runKnn:
logging.debug("Running kNN")
resultsFileName = self.resultsDir + "ResultsKnn.npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
try:
trainX = trainX.toScipyCsr()
testX = testX.toScipyCsr()
learner = KNNRecommender(self.algoArgs.kns[0])
learner.numProcesses = self.algoArgs.processes
logging.debug(learner)
self.recordResults(X, trainX, testX, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
if self.algoArgs.runCLiMF:
# !!!! no model selection
logging.debug("Running CLiMF")
resultsFileName = self.resultsDir + "ResultsCLiMF.npz"
fileLock = FileLock(resultsFileName)
if not (fileLock.isLocked() or fileLock.fileExists()) or self.algoArgs.overwrite:
fileLock.lock()
try:
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
modelSelectX, userInds = Sampling.sampleUsers2(trainX, self.algoArgs.modelSelectSamples, prune=True)
modelSelectX = scipy.sparse.csr_matrix(modelSelectX.toScipyCsr(), dtype=numpy.float64)
trainX = scipy.sparse.csr_matrix(trainX.toScipyCsr(), dtype=numpy.float64)
testX = testX.toScipyCsr()
learner = CLiMF(self.algoArgs.k, self.algoArgs.lmbdaCLiMF, self.algoArgs.gammaCLiMF)
learner.folds = self.algoArgs.folds
learner.gammas = self.algoArgs.gammasCLiMF
learner.ks = self.algoArgs.ks
learner.lmbdas = self.algoArgs.lmbdasCLiMF
learner.max_iters = self.algoArgs.maxIterCLiMF
learner.metric = self.algoArgs.metric
learner.numProcesses = self.algoArgs.processes
learner.numRecordAucSamples = self.algoArgs.numRecordAucSamples
learner.recommendSize = self.algoArgs.recommendSize
learner.validationSize = self.algoArgs.validationSize
learner.verbose = self.algoArgs.verbose
if self.algoArgs.modelSelect:
logging.debug("Performing model selection, taking sample size " + str(self.algoArgs.modelSelectSamples))
meanObjs, stdObjs = learner.modelSelect(modelSelectX)
modelSelectFileName = resultsFileName.replace("Results", "ModelSelect")
numpy.savez(modelSelectFileName, meanObjs, stdObjs)
logging.debug("Saved model selection grid as " + modelSelectFileName)
logging.debug(learner)
self.recordResults(X, trainX, testX, learner, resultsFileName)
finally:
fileLock.unlock()
else:
logging.debug("File is locked or already computed: " + resultsFileName)
logging.info("All done: see you around!")
