def testIteratorFunc3(self):
#Check to see if repeated calls generate new matrices
iterStartTimeStamp = time.mktime(datetime(2005,1,1).timetuple())
dataset = FlixsterDataset(iterStartTimeStamp=iterStartTimeStamp)
trainIterator = dataset.getTrainIteratorFunc()
X = next(trainIterator)
X.data += 1
trainIterator = dataset.getTrainIteratorFunc()
X2 = next(trainIterator)
nptst.assert_array_almost_equal(X.data, X2.data+1)
def testIteratorFunc2(self):
dataset = FlixsterDataset()
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 testData2(self):
#Check numbers of rows/cols of matrix
dataset = FlixsterDataset()
trainIterator = dataset.getTrainIteratorFunc()
X = trainIterator.next()
rowInds, colInds = X.nonzero()
print("Counting rows")
rowCounts = numpy.bincount(rowInds)
colCounts = numpy.bincount(colInds)
print("Done counting rows")
print((colCounts<5000).sum(), X.shape[1])