def run(): dataset = NetflixDataset(maxIter=30) trainIterator = dataset.getTrainIteratorFunc() for trainX in trainIterator: print(trainX.shape)
def testIteratorFunc2(self): dataset = NetflixDataset() trainIterator = dataset.getTrainIteratorFunc() testIterator = dataset.getTestIteratorFunc() for trainX in trainIterator: testX = testIterator.next() print(trainX.shape, trainX.nnz, testX.nnz) self.assertEquals(trainX.shape, testX.shape)
def profileSvd3(self): dataset = NetflixDataset() iterator = dataset.getTrainIteratorFunc() X = iterator.next() #L = LinOperatorUtils.parallelSparseOp(X) L = GeneralLinearOperator.asLinearOperator(X) k = 50 U, s, V = RandomisedSVD.svd(L, k) print(s) print("All done")
def testIteratorFunc(self): iterStartTimeStamp = time.mktime(datetime(2005,12,31).timetuple()) dataset = NetflixDataset(iterStartTimeStamp=iterStartTimeStamp) #iterator = dataset.getTrainIteratorFunc() trainIterator = dataset.getTrainIteratorFunc() testIterator = dataset.getTestIteratorFunc() trainX = trainIterator.next() testX = testIterator.next() self.assertEquals(trainX.shape, testX.shape) self.assertEquals(trainX.nnz + testX.nnz, dataset.numRatings) try: trainIterator.next() self.fail() except StopIteration: pass