def testPostProcess(self):
lmbda = 0.0
eps = 0.1
k = 20
matrixIterator = iter(self.matrixList)
iterativeSoftImpute = IterativeSoftImpute(lmbda, k=k, eps=eps, svdAlg="rsvd", postProcess=True)
ZList = iterativeSoftImpute.learnModel(matrixIterator)
for i, Z in enumerate(ZList):
U, s, V = Z
Xhat = (U*s).dot(V.T)
nptst.assert_array_almost_equal(Xhat, numpy.array(self.matrixList[i].todense()))
#Try case with iterativeSoftImpute.postProcessSamples < X.nnz
matrixIterator = iter(self.matrixList)
iterativeSoftImpute.postProcessSamples = int(self.matrixList[0].nnz/2)
ZList = iterativeSoftImpute.learnModel(matrixIterator)
for i, Z in enumerate(ZList):
U, s, V = Z
Xhat = (U*s).dot(V.T)
nptst.assert_array_almost_equal(Xhat, self.matrixList[i].todense(), 2)
#Try for larger lambda
iterativeSoftImpute.setRho(0.2)
ZList = iterativeSoftImpute.learnModel(matrixIterator)
for i, Z in enumerate(ZList):
U, s, V = Z
Xhat = (U*s).dot(V.T)
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!")