def test_hash_memory_storage_pcadp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCADiscretizedProjections('testPCADPHash', 4, train_vectors, 0.1)
self.memory.store_hash_configuration(hash1)
hash2 = PCADiscretizedProjections(None, None, None, None)
hash2.apply_config(self.memory.load_hash_configuration('testPCADPHash'))
self.assertEqual(hash1.dim, hash2.dim)
self.assertEqual(hash1.hash_name, hash2.hash_name)
self.assertEqual(hash1.bin_width, hash2.bin_width)
self.assertEqual(hash1.projection_count, hash2.projection_count)
for i in range(hash1.components.shape[0]):
for j in range(hash1.components.shape[1]):
self.assertEqual(hash1.components[i, j], hash2.components[i, j])
def test_hash_memory_storage_pcadp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCADiscretizedProjections('testPCADPHash', 4, train_vectors, 0.1)
self.memory.store_hash_configuration(hash1)
hash2 = PCADiscretizedProjections(None, None, None, None)
hash2.apply_config(self.memory.load_hash_configuration('testPCADPHash'))
self.assertEqual(hash1.dim, hash2.dim)
self.assertEqual(hash1.hash_name, hash2.hash_name)
self.assertEqual(hash1.bin_width, hash2.bin_width)
self.assertEqual(hash1.projection_count, hash2.projection_count)
for i in range(hash1.components.shape[0]):
for j in range(hash1.components.shape[1]):
self.assertEqual(hash1.components[i, j], hash2.components[i, j])
class TestPCADiscretizedProjections(unittest.TestCase):
def setUp(self):
self.vectors = numpy.random.randn(10, 100)
self.pdp = PCADiscretizedProjections('pdp', 4, self.vectors, 0.1)
def test_hash_format(self):
h = self.pdp.hash_vector(numpy.random.randn(10))
self.assertEqual(len(h), 1)
self.assertEqual(type(h[0]), type(''))
def test_hash_deterministic(self):
x = numpy.random.randn(10)
first_hash = self.pdp.hash_vector(x)[0]
for k in range(100):
self.assertEqual(first_hash, self.pdp.hash_vector(x)[0])
def test_hash_format_sparse(self):
h = self.pdp.hash_vector(scipy.sparse.rand(10, 1, density=0.6))
self.assertEqual(len(h), 1)
self.assertEqual(type(h[0]), type(''))
def test_hash_deterministic_sparse(self):
x = scipy.sparse.rand(10, 1, density=0.6)
first_hash = self.pdp.hash_vector(x)[0]
for k in range(100):
self.assertEqual(first_hash, self.pdp.hash_vector(x)[0])
class TestPCADiscretizedProjections(unittest.TestCase):
def setUp(self):
self.vectors = numpy.random.randn(10, 100)
self.pdp = PCADiscretizedProjections('pdp', 4, self.vectors, 0.1)
def test_hash_format(self):
h = self.pdp.hash_vector(numpy.random.randn(10))
self.assertEqual(len(h), 1)
self.assertEqual(type(h[0]), type(''))
def test_hash_deterministic(self):
x = numpy.random.randn(10)
first_hash = self.pdp.hash_vector(x)[0]
for k in range(100):
self.assertEqual(first_hash, self.pdp.hash_vector(x)[0])
def test_hash_format_sparse(self):
h = self.pdp.hash_vector(scipy.sparse.rand(10, 1, density=0.6))
self.assertEqual(len(h), 1)
self.assertEqual(type(h[0]), type(''))
def test_hash_deterministic_sparse(self):
x = scipy.sparse.rand(10, 1, density=0.6)
first_hash = self.pdp.hash_vector(x)[0]
for k in range(100):
self.assertEqual(first_hash, self.pdp.hash_vector(x)[0])
def setUp(self):
self.vectors = numpy.random.randn(10, 100)
self.pdp = PCADiscretizedProjections('pdp', 4, self.vectors, 0.1)
def setUp(self):
self.vectors = numpy.random.randn(10, 100)
self.pdp = PCADiscretizedProjections('pdp', 4, self.vectors, 0.1)
