#generator = SyntheticDataset1(startM=5000, endM=10000, startN=1000, endN=1500, pnz=0.10, noise=0.01)
#generator = FlixsterDataset()
generator = MovieLensDataset()
iterator = CenterMatrixIterator(generator.getTrainIteratorFunc())
k = 50
for i in range(1):
X = iterator.next()
if i==0:
lastX = scipy.sparse.csc_matrix(X.shape)
print("About to compute SVD")
U, s, V = SparseUtils.svdPropack(X, k)
print("Computed SVD")
plt.figure(0)
plt.plot(numpy.arange(s.shape[0]), s)
"""
deltaX = X - lastX
deltaX.eliminate_zeros()
deltaX.prune()
print(X.nnz-lastX.nnz)
U, s, V = SparseUtils.svdPropack(deltaX, k)
plt.figure(1)
plt.plot(numpy.arange(s.shape[0]), s)
lastX = X
"""
lastX = X
else:
E = X - lastX
E.eliminate_zeros()
print(X.nnz, E.nnz)
startTime = time.time()
U3, s3, V3 = RandomisedSVD.updateSvd(X, U3, s3, V3, E, k, p)
times[i, 1] = time.time() - startTime
lastX = X
errors[i, 1] = numpy.linalg.norm(X - (U3*s3).dot(V3.T))
#Accurate method
startTime = time.time()
U4, s4, V4 = SparseUtils.svdPropack(X, k)
times[i, 2] = time.time() - startTime
errors[i, 2] = numpy.linalg.norm(X - (U4*s4).dot(V4.T))
#Final method - just use the same SVD
if i == 0:
startTime = time.time()
U5, s5, V5 = SparseUtils.svdPropack(X, k)
times[i, 3] = time.time() - startTime
errors[i, 3] = numpy.linalg.norm(X - (U5*s5).dot(V5.T))
cumtimes = numpy.cumsum(times, 0)
print(cumtimes)
