def testRand(self):
X = sppy.rand((10, 10), 0.1)
self.assertEquals(X.shape, (10, 10))
self.assertAlmostEqual(X.getnnz() / float(100), 0.1, 1)
X = sppy.rand(100, 0.1)
self.assertEquals(X.shape, (100, ))
self.assertAlmostEqual(X.getnnz() / float(100), 0.1, 1)
def testRand(self):
X = sppy.rand((10, 10), 0.1)
self.assertEquals(X.shape, (10, 10))
self.assertAlmostEqual(X.getnnz()/float(100), 0.1, 1)
X = sppy.rand(100, 0.1)
self.assertEquals(X.shape, (100, ))
self.assertAlmostEqual(X.getnnz()/float(100), 0.1, 1)
def testRsvd(self):
n = 100
m = 80
A = sppy.rand((m, n), 0.5)
ks = [10, 20, 30, 40]
q = 2
lastError = numpy.linalg.norm(A.toarray())
for k in ks:
U, s, V = sppy.linalg.rsvd(A, k, q)
nptst.assert_array_almost_equal(U.T.dot(U), numpy.eye(k))
nptst.assert_array_almost_equal(V.T.dot(V), numpy.eye(k))
A2 = (U*s).dot(V.T)
error = numpy.linalg.norm(A.toarray() - A2)
self.assertTrue(error <= lastError)
lastError = error
#Compare versus exact svd
U, s, V = numpy.linalg.svd(numpy.array(A.toarray()))
inds = numpy.flipud(numpy.argsort(s))[0:k*2]
U, s, V = Util.indSvd(U, s, V, inds)
Ak = (U*s).dot(V.T)
error2 = numpy.linalg.norm(A.toarray() - Ak)
self.assertTrue(error2 <= error)
def profileDot2(self):
density = 0.01
m = 10000
n = 10000
a_sppy = sppy.rand((m, n), density, storagetype='row')
a_sppy_T = sppy.csarray(a_sppy.T, storagetype="col")
ProfileUtils.profile('a_sppy.dot(a_sppy_T)', globals(), locals())
def testRsvd(self):
n = 100
m = 80
A = sppy.rand((m, n), 0.5)
ks = [10, 20, 30, 40]
q = 2
lastError = numpy.linalg.norm(A.toarray())
for k in ks:
U, s, V = sppy.linalg.rsvd(A, k, q)
nptst.assert_array_almost_equal(U.T.dot(U), numpy.eye(k))
nptst.assert_array_almost_equal(V.T.dot(V), numpy.eye(k))
A2 = (U*s).dot(V.T)
error = numpy.linalg.norm(A.toarray() - A2)
self.assertTrue(error <= lastError)
lastError = error
#Compare versus exact svd
U, s, V = numpy.linalg.svd(numpy.array(A.toarray()))
inds = numpy.flipud(numpy.argsort(s))[0:k*2]
U, s, V = Util.indSvd(U, s, V, inds)
Ak = (U*s).dot(V.T)
error2 = numpy.linalg.norm(A.toarray() - Ak)
self.assertTrue(error2 <= error)
def testWrite(self):
m = 10
n = 5
density = 0.5
A = sppy.rand((m, n), density)
sppy.io.mmwrite(tempfile.tempdir + "/test.mtx", A)
def testWrite(self):
m = 10
n = 5
density = 0.5
A = sppy.rand((m, n), density)
sppy.io.mmwrite(tempfile.tempdir + "/test.mtx", A)
def setUp(self):
numpy.set_printoptions(suppress=True, precision=3)
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
shape = (15, 15)
density = 0.5
self.A = rand(shape, density)
self.A = self.A + self.A.T
def setUp(self):
numpy.set_printoptions(suppress=True, precision=3)
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
shape = (15, 15)
density = 0.5
self.A = rand(shape, density)
self.A = self.A + self.A.T
def testNorm(self):
n = 100
m = 80
numRuns = 10
for i in range(numRuns):
A = sppy.rand((m, n), 0.5)
self.assertAlmostEquals(numpy.linalg.norm(A.toarray()), sppy.linalg.norm(A))
def testNorm(self):
n = 100
m = 80
numRuns = 10
for i in range(numRuns):
A = sppy.rand((m, n), 0.5)
self.assertAlmostEquals(numpy.linalg.norm(A.toarray()), sppy.linalg.norm(A))
def profileRowSlice(self):
numpy.random.seed(21)
m = 100000
n = 1000000
#numInds = 10000000
X = sppy.rand((m, n), density=0.001, storagetype="row")
#ProfileUtils.profile('X[0:1000, :] ', globals(), locals())
ProfileUtils.profile('X.submatrix(0, 0, 1000, n)', globals(), locals())
def testAsLinearOperatorSum(self):
n = 10
m = 5
density = 0.3
A = rand((n, m), density)
B = rand((n, m), density)
L = GeneralLinearOperator.asLinearOperator(A)
M = GeneralLinearOperator.asLinearOperator(B)
N = GeneralLinearOperator.asLinearOperatorSum(L, M)
k = 3
V = numpy.random.rand(m, k)
W = numpy.random.rand(n, k)
U = N.matmat(V)
U2 = A.dot(V) + B.dot(V)
nptst.assert_array_almost_equal(U, U2)
U = N.rmatmat(W)
U2 = A.T.dot(W) + B.T.dot(W)
nptst.assert_array_almost_equal(U, U2)
v = numpy.random.rand(m)
w = numpy.random.rand(n)
u = N.matvec(v)
u2 = A.dot(v) + B.dot(v)
nptst.assert_array_almost_equal(u, u2)
u = N.rmatvec(w)
u2 = A.T.dot(w) + B.T.dot(w)
nptst.assert_array_almost_equal(u, u2)
#See if we get an error if A, B are different shapes
B = rand((m, n), 0.1)
M = GeneralLinearOperator.asLinearOperator(B)
self.assertRaises(ValueError,
GeneralLinearOperator.asLinearOperatorSum, L, M)
def testAsLinearOperatorSum(self):
n = 10
m = 5
density = 0.3
A = rand((n, m), density)
B = rand((n, m), density)
L = GeneralLinearOperator.asLinearOperator(A)
M = GeneralLinearOperator.asLinearOperator(B)
N = GeneralLinearOperator.asLinearOperatorSum(L, M)
k = 3
V = numpy.random.rand(m, k)
W = numpy.random.rand(n, k)
U = N.matmat(V)
U2 = A.dot(V) + B.dot(V)
nptst.assert_array_almost_equal(U, U2)
U = N.rmatmat(W)
U2 = A.T.dot(W) + B.T.dot(W)
nptst.assert_array_almost_equal(U, U2)
v = numpy.random.rand(m)
w = numpy.random.rand(n)
u = N.matvec(v)
u2 = A.dot(v) + B.dot(v)
nptst.assert_array_almost_equal(u, u2)
u = N.rmatvec(w)
u2 = A.T.dot(w) + B.T.dot(w)
nptst.assert_array_almost_equal(u, u2)
#See if we get an error if A, B are different shapes
B = rand((m, n), 0.1)
M = GeneralLinearOperator.asLinearOperator(B)
self.assertRaises(ValueError, GeneralLinearOperator.asLinearOperatorSum, L, M)
def syntheticDataset1(m=500, n=200, k=8, u=0.1, sd=0, noise=5):
"""
Create a simple synthetic dataset
"""
w = 1-u
X, U, s, V, wv = SparseUtils.generateSparseBinaryMatrix((m,n), k, w, sd=sd, csarray=True, verbose=True, indsPerRow=200)
X = X + sppy.rand((m, n), noise/float(n), storagetype="row")
X[X.nonzero()] = 1
X.prune()
X = SparseUtils.pruneMatrixRows(X, minNnzRows=10)
logging.debug("Non zero elements: " + str(X.nnz) + " shape: " + str(X.shape))
U = U*s
return X, U, V
def testCenterRowsCsarray(self):
numRuns = 10
for i in range(numRuns):
density = numpy.random.rand()
m = numpy.random.randint(10, 100)
n = numpy.random.randint(10, 100)
X = sppy.rand((m,n), density)
SparseUtilsCython.centerRowsCsarray(X)
nptst.assert_array_almost_equal(X.sum(1), numpy.zeros(m))
def testPruneMatrixRows(self):
m = 30
n = 20
density = 0.5
X = sppy.rand((m, n), density)
X[X.nonzero()] = 1
newX, rowInds = SparseUtils.pruneMatrixRows(X, 10, verbose=True)
nnzRows = numpy.zeros(m)
for i in range(m):
nnzRows[i] = X.toarray()[i, :].nonzero()[0].shape[0]
if nnzRows[i] >= 10:
self.assertTrue(i in rowInds)
self.assertTrue((newX.sum(1) >= 10).all())
def testPruneMatrixRows(self):
m = 30
n = 20
density = 0.5
X = sppy.rand((m, n), density)
X[X.nonzero()] = 1
newX, rowInds = SparseUtils.pruneMatrixRows(X, 10, verbose=True)
nnzRows = numpy.zeros(m)
for i in range(m):
nnzRows[i] = X.toarray()[i, :].nonzero()[0].shape[0]
if nnzRows[i] >= 10:
self.assertTrue(i in rowInds)
self.assertTrue((newX.sum(1) >= 10).all())
def testPruneMatrixCols(self):
m = 30
n = 20
density = 0.5
X = sppy.rand((m, n), density)
X[X.nonzero()] = 1
newX, rowInds = SparseUtils.pruneMatrixCols(X, maxNnz=10, verbose=True)
nnzCols = numpy.zeros(n)
for i in range(n):
nnzCols[i] = X.toarray()[:, i].nonzero()[0].shape[0]
if nnzCols[i] <= 10:
self.assertTrue(i in rowInds)
self.assertTrue((newX.sum(0) <= 10).all())
newX, rowInds = SparseUtils.pruneMatrixCols(X, minNnz=10, verbose=True)
nnzCols = numpy.zeros(n)
for i in range(n):
nnzCols[i] = X.toarray()[:, i].nonzero()[0].shape[0]
if nnzCols[i] >= 10:
self.assertTrue(i in rowInds)
self.assertTrue((newX.sum(0) >= 10).all())
newX, rowInds = SparseUtils.pruneMatrixCols(X,
minNnz=10,
maxNnz=15,
verbose=True)
nnzCols = numpy.zeros(n)
for i in range(n):
nnzCols[i] = X.toarray()[:, i].nonzero()[0].shape[0]
if nnzCols[i] >= 10 and nnzCols[i] <= 15:
self.assertTrue(i in rowInds)
self.assertTrue(
numpy.logical_and(newX.sum(0) >= 10,
newX.sum(0) <= 15).all())
def testPruneMatrixCols(self):
m = 30
n = 20
density = 0.5
X = sppy.rand((m, n), density)
X[X.nonzero()] = 1
newX, rowInds = SparseUtils.pruneMatrixCols(X, maxNnz=10, verbose=True)
nnzCols = numpy.zeros(n)
for i in range(n):
nnzCols[i] = X.toarray()[:, i].nonzero()[0].shape[0]
if nnzCols[i] <= 10:
self.assertTrue(i in rowInds)
self.assertTrue((newX.sum(0) <= 10).all())
newX, rowInds = SparseUtils.pruneMatrixCols(X, minNnz=10, verbose=True)
nnzCols = numpy.zeros(n)
for i in range(n):
nnzCols[i] = X.toarray()[:, i].nonzero()[0].shape[0]
if nnzCols[i] >= 10:
self.assertTrue(i in rowInds)
self.assertTrue((newX.sum(0) >= 10).all())
newX, rowInds = SparseUtils.pruneMatrixCols(X, minNnz=10, maxNnz=15, verbose=True)
nnzCols = numpy.zeros(n)
for i in range(n):
nnzCols[i] = X.toarray()[:, i].nonzero()[0].shape[0]
if nnzCols[i] >= 10 and nnzCols[i] <= 15:
self.assertTrue(i in rowInds)
self.assertTrue(numpy.logical_and(newX.sum(0) >= 10, newX.sum(0) <= 15).all())
def testRead(self):
m = 10
n = 5
density = 0.5
A = sppy.rand((m, n), density)
fileName = tempfile.tempdir + "/test.mtx"
sppy.io.mmwrite(fileName, A)
B = sppy.io.mmread(fileName)
nptst.assert_array_almost_equal(A.toarray(), B.toarray(), 5)
self.assertEquals(A.dtype, B.dtype)
#Now try an integer array
A = sppy.csarray((m,n), dtype=numpy.int)
A[0, 1] = 5
A[2, 2] = -2
A[6, 3] = 1
sppy.io.mmwrite(fileName, A)
B = sppy.io.mmread(fileName)
nptst.assert_array_almost_equal(A.toarray(), B.toarray(), 5)
self.assertEquals(A.dtype, B.dtype)
def testRead(self):
m = 10
n = 5
density = 0.5
A = sppy.rand((m, n), density)
fileName = tempfile.tempdir + "/test.mtx"
sppy.io.mmwrite(fileName, A)
B = sppy.io.mmread(fileName)
nptst.assert_array_almost_equal(A.toarray(), B.toarray(), 5)
self.assertEquals(A.dtype, B.dtype)
#Now try an integer array
A = sppy.csarray((m, n), dtype=numpy.int)
A[0, 1] = 5
A[2, 2] = -2
A[6, 3] = 1
sppy.io.mmwrite(fileName, A)
B = sppy.io.mmread(fileName)
nptst.assert_array_almost_equal(A.toarray(), B.toarray(), 5)
self.assertEquals(A.dtype, B.dtype)
