class TestRandomBinaryProjections(unittest.TestCase):
def setUp(self):
self.rbp = RandomBinaryProjections('testHash', 10)
self.rbp.reset(100)
def test_hash_format(self):
h = self.rbp.hash_vector(numpy.random.randn(100))
self.assertEqual(len(h), 1)
self.assertEqual(type(h[0]), type(''))
self.assertEqual(len(h[0]), 10)
for c in h[0]:
self.assertTrue(c == '1' or c == '0')
def test_hash_deterministic(self):
x = numpy.random.randn(100)
first_hash = self.rbp.hash_vector(x)[0]
for k in range(100):
self.assertEqual(first_hash, self.rbp.hash_vector(x)[0])
def test_hash_format_sparse(self):
h = self.rbp.hash_vector(scipy.sparse.rand(100, 1, density=0.1))
self.assertEqual(len(h), 1)
self.assertEqual(type(h[0]), type(''))
self.assertEqual(len(h[0]), 10)
for c in h[0]:
self.assertTrue(c == '1' or c == '0')
def test_hash_deterministic_sparse(self):
x = scipy.sparse.rand(100, 1, density=0.1)
first_hash = self.rbp.hash_vector(x)[0]
for k in range(100):
self.assertEqual(first_hash, self.rbp.hash_vector(x)[0])
def setUp(self):
logging.basicConfig(level=logging.WARNING)
numpy.random.seed(11)
# Create permutations meta-hash
self.permutations = HashPermutations('permut')
# Create binary hash as child hash
rbp = RandomBinaryProjections('rbp1', 4, rand_seed=19)
rbp_conf = {
'num_permutation': 50,
'beam_size': 10,
'num_neighbour': 100
}
# Add rbp as child hash of permutations hash
self.permutations.add_child_hash(rbp, rbp_conf)
# Create engine with meta hash and cosine distance
self.engine_perm = Engine(200,
lshashes=[self.permutations],
distance=CosineDistance())
# Create engine without permutation meta-hash
self.engine = Engine(200, lshashes=[rbp], distance=CosineDistance())
def test_hash_memory_storage_rbp(self):
hash1 = RandomBinaryProjections('testRBPHash', 10)
hash1.reset(100)
self.memory.store_hash_configuration(hash1)
hash2 = RandomBinaryProjections(None, None)
hash2.apply_config(self.memory.load_hash_configuration('testRBPHash'))
self.assertEqual(hash1.dim, hash2.dim)
self.assertEqual(hash1.hash_name, hash2.hash_name)
self.assertEqual(hash1.projection_count, hash2.projection_count)
for i in range(hash1.normals.shape[0]):
for j in range(hash1.normals.shape[1]):
self.assertEqual(hash1.normals[i, j], hash2.normals[i, j])
def test_random_binary_projections(self):
dim = 4
vector_count = 5000
vectors = numpy.random.randn(dim, vector_count)
# First get recall and precision for one 1-dim random hash
rbp = RandomBinaryProjections('rbp', 32)
nearest = NearestFilter(10 + 1)
engine = Engine(dim, lshashes=[rbp], vector_filters=[nearest])
exp = RecallPrecisionExperiment(10, vectors)
result = exp.perform_experiment([engine])
recall1 = result[0][0]
precision1 = result[0][1]
searchtime1 = result[0][2]
print('\nRecall RBP: %f, Precision RBP: %f, SearchTime RBP: %f\n' % \
(recall1, precision1, searchtime1))
def createLSHFile(inputFilename, L, K):
if os.path.isfile(inputFilename):
siftVectorFile = open(inputFilename, 'r')
# Dimension of our vector space
dimension = 2
noOfLayers = L
noOfBits = K
layers = []
for i in xrange(noOfLayers):
# Create a random binary hash with 10 bits
layers.append(RandomBinaryProjections('layer' + str(i), noOfBits))
# Create engine with pipeline configuration
engine = Engine(dimension, lshashes=layers)
outFile = open('filename_d.lsh', 'w')
storeVectors(siftVectorFile, engine, outFile)
outFile.close()
siftVectorFile.close()
else:
print 'Filename incorrect!'
def __init__(self,
dim,
lshashes=None,
distance=None,
fetch_vector_filters=None,
vector_filters=None,
storage=None):
""" Keeps the configuration. """
if lshashes is None:
lshashes = [RandomBinaryProjections('default', 10)]
self.lshashes = lshashes
if distance is None: distance = CosineDistance()
self.distance = distance
if vector_filters is None: vector_filters = [NearestFilter(10)]
self.vector_filters = vector_filters
if fetch_vector_filters is None:
fetch_vector_filters = [UniqueFilter()]
self.fetch_vector_filters = fetch_vector_filters
if storage is None: storage = MemoryStorage()
self.storage = storage
# Initialize all hashes for the data space dimension.
for lshash in self.lshashes:
lshash.reset(dim)
def example1():
# Dimension of feature space
DIM = 100
# Number of data points (dont do too much because of exact search)
POINTS = 10000
print('Creating engines')
# We want 12 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('rbpt', 20, 20)
# Create engine 1
engine_rbpt = Engine(DIM, lshashes=[rbpt], distance=CosineDistance())
# Create binary hash as child hash
rbp = RandomBinaryProjections('rbp1', 20)
# Create engine 2
engine = Engine(DIM, lshashes=[rbp], distance=CosineDistance())
# Create permutations meta-hash
permutations = HashPermutations('permut')
# Create binary hash as child hash
rbp_perm = RandomBinaryProjections('rbp_perm', 20)
rbp_conf = {'num_permutation': 50, 'beam_size': 10, 'num_neighbour': 100}
# Add rbp as child hash of permutations hash
permutations.add_child_hash(rbp_perm, rbp_conf)
# Create engine 3
engine_perm = Engine(DIM,
lshashes=[permutations],
distance=CosineDistance())
# Create permutations meta-hash
permutations2 = HashPermutationMapper('permut2')
# Create binary hash as child hash
rbp_perm2 = RandomBinaryProjections('rbp_perm2', 12)
# Add rbp as child hash of permutations hash
permutations2.add_child_hash(rbp_perm2)
# Create engine 3
engine_perm2 = Engine(DIM,
lshashes=[permutations2],
distance=CosineDistance())
print('Indexing %d random vectors of dimension %d' % (POINTS, DIM))
# First index some random vectors
matrix = numpy.zeros((POINTS, DIM))
for i in xrange(POINTS):
v = numpy.random.randn(DIM)
matrix[i] = v
engine.store_vector(v)
engine_rbpt.store_vector(v)
engine_perm.store_vector(v)
engine_perm2.store_vector(v)
print('Buckets 1 = %d' % len(engine.storage.buckets['rbp1'].keys()))
print('Buckets 2 = %d' % len(engine_rbpt.storage.buckets['rbpt'].keys()))
print('Building permuted index for HashPermutations')
# Then update permuted index
permutations.build_permuted_index()
print('Generate random data')
# Get random query vector
query = numpy.random.randn(DIM)
# Do random query on engine 1
print('\nNeighbour distances with RandomBinaryProjectionTree:')
print(' -> Candidate count is %d' % engine_rbpt.candidate_count(query))
results = engine_rbpt.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Do random query on engine 2
print('\nNeighbour distances with RandomBinaryProjections:')
print(' -> Candidate count is %d' % engine.candidate_count(query))
results = engine.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Do random query on engine 3
print('\nNeighbour distances with HashPermutations:')
print(' -> Candidate count is %d' % engine_perm.candidate_count(query))
results = engine_perm.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Do random query on engine 4
print('\nNeighbour distances with HashPermutations2:')
print(' -> Candidate count is %d' % engine_perm2.candidate_count(query))
results = engine_perm2.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Real neighbours
print('\nReal neighbour distances:')
query = query.reshape((1, DIM))
dists = CosineDistance().distance(matrix, query)
dists = dists.reshape((-1, ))
dists = sorted(dists)
print(dists[:10])
def setUp(self):
self.rbp = RandomBinaryProjections('testHash', 10)
self.rbp.reset(100)
def example2():
# Dimension of feature space
DIM = 100
# Number of data points (dont do too much because of exact search)
POINTS = 20000
##########################################################
print('Performing indexing with HashPermutations...')
t0 = time.time()
# Create permutations meta-hash
permutations = HashPermutations('permut')
# Create binary hash as child hash
rbp_perm = RandomBinaryProjections('rbp_perm', 14)
rbp_conf = {'num_permutation': 50, 'beam_size': 10, 'num_neighbour': 100}
# Add rbp as child hash of permutations hash
permutations.add_child_hash(rbp_perm, rbp_conf)
# Create engine
engine_perm = Engine(DIM,
lshashes=[permutations],
distance=CosineDistance())
# First index some random vectors
matrix = numpy.zeros((POINTS, DIM))
for i in range(POINTS):
v = numpy.random.randn(DIM)
matrix[i] = v
engine_perm.store_vector(v)
# Then update permuted index
permutations.build_permuted_index()
t1 = time.time()
print('Indexing took %f seconds' % (t1 - t0))
# Get random query vector
query = numpy.random.randn(DIM)
# Do random query on engine 3
print('\nNeighbour distances with HashPermutations:')
print(' -> Candidate count is %d' % engine_perm.candidate_count(query))
results = engine_perm.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Real neighbours
print('\nReal neighbour distances:')
query = query.reshape((DIM))
dists = CosineDistance().distance(matrix, query)
dists = dists.reshape((-1, ))
dists = sorted(dists)
print(dists[:10])
##########################################################
print('\nPerforming indexing with HashPermutationMapper...')
t0 = time.time()
# Create permutations meta-hash
permutations2 = HashPermutationMapper('permut2')
# Create binary hash as child hash
rbp_perm2 = RandomBinaryProjections('rbp_perm2', 14)
# Add rbp as child hash of permutations hash
permutations2.add_child_hash(rbp_perm2)
# Create engine
engine_perm2 = Engine(DIM,
lshashes=[permutations2],
distance=CosineDistance())
# First index some random vectors
matrix = numpy.zeros((POINTS, DIM))
for i in range(POINTS):
v = numpy.random.randn(DIM)
matrix[i] = v
engine_perm2.store_vector(v)
t1 = time.time()
print('Indexing took %f seconds' % (t1 - t0))
# Get random query vector
query = numpy.random.randn(DIM)
# Do random query on engine 4
print('\nNeighbour distances with HashPermutationMapper:')
print(' -> Candidate count is %d' % engine_perm2.candidate_count(query))
results = engine_perm2.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Real neighbours
print('\nReal neighbour distances:')
query = query.reshape((DIM))
dists = CosineDistance().distance(matrix, query)
dists = dists.reshape((-1, ))
dists = sorted(dists)
print(dists[:10])
##########################################################
print('\nPerforming indexing with multiple binary hashes...')
t0 = time.time()
hashes = []
for k in range(20):
hashes.append(RandomBinaryProjections('rbp_%d' % k, 10))
# Create engine
engine_rbps = Engine(DIM, lshashes=hashes, distance=CosineDistance())
# First index some random vectors
matrix = numpy.zeros((POINTS, DIM))
for i in range(POINTS):
v = numpy.random.randn(DIM)
matrix[i] = v
engine_rbps.store_vector(v)
t1 = time.time()
print('Indexing took %f seconds' % (t1 - t0))
# Get random query vector
query = numpy.random.randn(DIM)
# Do random query on engine 4
print('\nNeighbour distances with multiple binary hashes:')
print(' -> Candidate count is %d' % engine_rbps.candidate_count(query))
results = engine_rbps.neighbours(query)
dists = [x[2] for x in results]
print(dists)
# Real neighbours
print('\nReal neighbour distances:')
query = query.reshape((DIM))
dists = CosineDistance().distance(matrix, query)
dists = dists.reshape((-1, ))
dists = sorted(dists)
print(dists[:10])