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 = EuclideanDistance()
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)
print('*** engine init done ***')
def __init__(self,
dim,
lshashes=[RandomBinaryProjections('default', 10)],
distance=EuclideanDistance(),
vector_filters=[NearestFilter(10)],
storage=MemoryStorage()):
""" Keeps the configuration. """
self.lshashes = lshashes
self.distance = distance
self.vector_filters = vector_filters
self.storage = storage
# Initialize all hashes for the data space dimension.
for lshash in self.lshashes:
lshash.reset(dim)
class TestStorage(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis(host='localhost',
port=6379, db=0)
self.redis_storage = RedisStorage(self.redis_object)
def test_memory_storage(self):
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.memory.store_vector('testHash', bucket_key, x, x_data)
X = self.memory.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.memory.clean_all_buckets()
self.assertEqual(self.memory.get_bucket('testHash', bucket_key), [])
def test_redis_storage(self):
self.redis_storage.clean_all_buckets()
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.redis_storage.store_vector('testHash', bucket_key, x, x_data)
X = self.redis_storage.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.redis_storage.clean_all_buckets()
self.assertEqual(self.redis_storage.get_bucket('testHash',
bucket_key), [])
class TestStorage(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis(host='localhost', port=6379, db=0)
self.redis_storage = RedisStorage(self.redis_object)
def test_memory_storage(self):
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.memory.store_vector('testHash', bucket_key, x, x_data)
X = self.memory.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.memory.clean_all_buckets()
self.assertEqual(self.memory.get_bucket('testHash', bucket_key), [])
def test_redis_storage(self):
self.redis_storage.clean_all_buckets()
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.redis_storage.store_vector('testHash', bucket_key, x, x_data)
X = self.redis_storage.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.redis_storage.clean_all_buckets()
self.assertEqual(self.redis_storage.get_bucket('testHash', bucket_key),
[])
def __init__(self,
measure="EuclideanDistance",
data_path='data/classed_data/'):
self.res = ResnetSimilarity()
self.pbar = ProgressBar()
# Dimension of our vector space
self.dimension = 2048
self.data_path = data_path
# Create a random binary hash with 10 bits
self.rbp = RandomBinaryProjections('rbp', 10)
self.measure = measure
self.msote = MemoryStorage()
if measure == "EuclideanDistance":
self.engine = Engine(self.dimension,
lshashes=[self.rbp],
storage=self.msote,
distance=EuclideanDistance())
else:
self.engine = Engine(self.dimension,
lshashes=[self.rbp],
storage=self.msote,
distance=CosineDistance())
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis(host='localhost', port=6379, db=0)
self.redis_storage = RedisStorage(self.redis_object)
dimension = 1000
# 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)
engine = Engine(dimension,
lshashes=[permutations2],
distance=CosineDistance(),
vector_filters=[NearestFilter(5)],
storage=MemoryStorage())
i = 0
query = numpy.zeros(dimension)
f = open('features2.txt', 'r')
# Opening, reading from the file::
for next_read_line in f:
next_read_line = next_read_line.rstrip()
split_arr = next_read_line.split(" ")
split_arr = split_arr[1:]
split_arr = list(map(float, split_arr))
vector = numpy.asarray(split_arr)
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
class TestHashStorage(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis(host='localhost',
port=6379, db=0)
self.redis_storage = RedisStorage(self.redis_object)
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_hash_memory_storage_rdp(self):
hash1 = RandomDiscretizedProjections('testRDPHash', 10, 0.1)
hash1.reset(100)
self.memory.store_hash_configuration(hash1)
hash2 = RandomDiscretizedProjections(None, None, None)
hash2.apply_config(self.memory.load_hash_configuration('testRDPHash'))
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.normals.shape[0]):
for j in range(hash1.normals.shape[1]):
self.assertEqual(hash1.normals[i, j], hash2.normals[i, j])
def test_hash_memory_storage_pcabp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCABinaryProjections('testPCABPHash', 4, train_vectors)
self.memory.store_hash_configuration(hash1)
hash2 = PCABinaryProjections(None, None, None)
hash2.apply_config(self.memory.load_hash_configuration('testPCABPHash'))
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.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])
def test_hash_redis_storage_rbp(self):
hash1 = RandomBinaryProjections('testRBPHash', 10)
hash1.reset(100)
self.redis_storage.store_hash_configuration(hash1)
hash2 = RandomBinaryProjections(None, None)
hash2.apply_config(self.redis_storage.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_hash_redis_storage_rdp(self):
hash1 = RandomDiscretizedProjections('testRDPHash', 10, 0.1)
hash1.reset(100)
self.redis_storage.store_hash_configuration(hash1)
hash2 = RandomDiscretizedProjections(None, None, None)
hash2.apply_config(self.redis_storage.load_hash_configuration('testRDPHash'))
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.normals.shape[0]):
for j in range(hash1.normals.shape[1]):
self.assertEqual(hash1.normals[i, j], hash2.normals[i, j])
def test_hash_redis_storage_pcabp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCABinaryProjections('testPCABPHash', 4, train_vectors)
self.redis_storage.store_hash_configuration(hash1)
hash2 = PCABinaryProjections(None, None, None)
hash2.apply_config(self.redis_storage.load_hash_configuration('testPCABPHash'))
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.components.shape[0]):
for j in range(hash1.components.shape[1]):
self.assertEqual(hash1.components[i, j], hash2.components[i, j])
def test_hash_redis_storage_pcadp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCADiscretizedProjections('testPCADPHash', 4, train_vectors, 0.1)
self.redis_storage.store_hash_configuration(hash1)
hash2 = PCADiscretizedProjections(None, None, None, None)
hash2.apply_config(self.redis_storage.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 setUp(self):
self.storage = MemoryStorage()
super(MemoryStorageTest, self).setUp()
class TestHashStorage(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
def test_hash_memory_storage_none_config(self):
conf = self.memory.load_hash_configuration('nonexistentHash')
self.assertIsNone(conf)
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_hash_memory_storage_rdp(self):
hash1 = RandomDiscretizedProjections('testRDPHash', 10, 0.1)
hash1.reset(100)
self.memory.store_hash_configuration(hash1)
hash2 = RandomDiscretizedProjections(None, None, None)
hash2.apply_config(self.memory.load_hash_configuration('testRDPHash'))
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.normals.shape[0]):
for j in range(hash1.normals.shape[1]):
self.assertEqual(hash1.normals[i, j], hash2.normals[i, j])
def test_hash_memory_storage_pcabp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCABinaryProjections('testPCABPHash', 4, train_vectors)
self.memory.store_hash_configuration(hash1)
hash2 = PCABinaryProjections(None, None, None)
hash2.apply_config(self.memory.load_hash_configuration('testPCABPHash'))
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.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])
def test_hash_redis_storage_none_config(self):
conf = self.redis_storage.load_hash_configuration('nonexistentHash')
self.assertIsNone(conf)
def test_hash_redis_storage_rbp(self):
hash1 = RandomBinaryProjections('testRBPHash', 10)
hash1.reset(100)
self.redis_storage.store_hash_configuration(hash1)
hash2 = RandomBinaryProjections(None, None)
hash2.apply_config(self.redis_storage.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_hash_redis_storage_rdp(self):
hash1 = RandomDiscretizedProjections('testRDPHash', 10, 0.1)
hash1.reset(100)
self.redis_storage.store_hash_configuration(hash1)
hash2 = RandomDiscretizedProjections(None, None, None)
hash2.apply_config(self.redis_storage.load_hash_configuration('testRDPHash'))
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.normals.shape[0]):
for j in range(hash1.normals.shape[1]):
self.assertEqual(hash1.normals[i, j], hash2.normals[i, j])
def test_hash_redis_storage_pcabp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCABinaryProjections('testPCABPHash', 4, train_vectors)
self.redis_storage.store_hash_configuration(hash1)
hash2 = PCABinaryProjections(None, None, None)
hash2.apply_config(self.redis_storage.load_hash_configuration('testPCABPHash'))
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.components.shape[0]):
for j in range(hash1.components.shape[1]):
self.assertEqual(hash1.components[i, j], hash2.components[i, j])
def test_hash_redis_storage_pcadp(self):
train_vectors = numpy.random.randn(10, 100)
hash1 = PCADiscretizedProjections('testPCADPHash', 4, train_vectors, 0.1)
self.redis_storage.store_hash_configuration(hash1)
hash2 = PCADiscretizedProjections(None, None, None, None)
hash2.apply_config(self.redis_storage.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 setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
numpy.random.seed(16)
def memoryStorage():
return MemoryStorage()
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
numpy.random.seed(16)
class TestRandomBinaryProjectionTree(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
numpy.random.seed(16)
def test_retrieval(self):
# We want 12 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('testHash', 12, 20)
# Create engine for 100 dimensional feature space, do not forget to set
# nearest filter to 20, because default is 10
self.engine = Engine(100,
lshashes=[rbpt],
vector_filters=[NearestFilter(20)])
# First insert 200000 random vectors
for k in range(200000):
x = numpy.random.randn(100)
x_data = 'data {}'.format(k)
self.engine.store_vector(x, x_data)
# Now do random queries and check result set size
for k in range(10):
x = numpy.random.randn(100)
n = self.engine.neighbours(x)
self.assertEqual(len(n), 20)
def test_storage_memory(self):
# We want 10 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('testHash', 10, 20)
# Create engine for 100 dimensional feature space
self.engine = Engine(100,
lshashes=[rbpt],
vector_filters=[NearestFilter(20)])
# First insert 2000 random vectors
for k in range(2000):
x = numpy.random.randn(100)
x_data = 'data'
self.engine.store_vector(x, x_data)
self.memory.store_hash_configuration(rbpt)
rbpt2 = RandomBinaryProjectionTree(None, None, None)
rbpt2.apply_config(self.memory.load_hash_configuration('testHash'))
self.assertEqual(rbpt.dim, rbpt2.dim)
self.assertEqual(rbpt.hash_name, rbpt2.hash_name)
self.assertEqual(rbpt.projection_count, rbpt2.projection_count)
for i in range(rbpt.normals.shape[0]):
for j in range(rbpt.normals.shape[1]):
self.assertEqual(rbpt.normals[i, j], rbpt2.normals[i, j])
# Now do random queries and check result set size
for k in range(10):
x = numpy.random.randn(100)
keys1 = rbpt.hash_vector(x, querying=True)
keys2 = rbpt2.hash_vector(x, querying=True)
self.assertEqual(len(keys1), len(keys2))
for k in range(len(keys1)):
self.assertEqual(keys1[k], keys2[k])
def test_storage_redis(self):
# We want 10 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('testHash', 10, 20)
# Create engine for 100 dimensional feature space
self.engine = Engine(100,
lshashes=[rbpt],
vector_filters=[NearestFilter(20)])
# First insert 2000 random vectors
for k in range(2000):
x = numpy.random.randn(100)
x_data = 'data'
self.engine.store_vector(x, x_data)
self.redis_storage.store_hash_configuration(rbpt)
rbpt2 = RandomBinaryProjectionTree(None, None, None)
rbpt2.apply_config(
self.redis_storage.load_hash_configuration('testHash'))
self.assertEqual(rbpt.dim, rbpt2.dim)
self.assertEqual(rbpt.hash_name, rbpt2.hash_name)
self.assertEqual(rbpt.projection_count, rbpt2.projection_count)
for i in range(rbpt.normals.shape[0]):
for j in range(rbpt.normals.shape[1]):
self.assertEqual(rbpt.normals[i, j], rbpt2.normals[i, j])
# Now do random queries and check result set size
for k in range(10):
x = numpy.random.randn(100)
keys1 = rbpt.hash_vector(x, querying=True)
keys2 = rbpt2.hash_vector(x, querying=True)
self.assertEqual(len(keys1), len(keys2))
for k in range(len(keys1)):
self.assertEqual(keys1[k], keys2[k])
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis(host='localhost',
port=6379, db=0)
self.redis_storage = RedisStorage(self.redis_object)
class TestRandomBinaryProjectionTree(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis(host='localhost',
port=6379, db=0)
self.redis_storage = RedisStorage(self.redis_object)
def test_retrieval(self):
# We want 12 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('testHash', 12, 20)
# Create engine for 100 dimensional feature space, do not forget to set
# nearest filter to 20, because default is 10
self.engine = Engine(100, lshashes=[rbpt], vector_filters=[NearestFilter(20)])
# First insert 200000 random vectors
#print 'Indexing...'
for k in range(200000):
x = numpy.random.randn(100)
x_data = 'data'
self.engine.store_vector(x, x_data)
# Now do random queries and check result set size
#print 'Querying...'
for k in range(10):
x = numpy.random.randn(100)
n = self.engine.neighbours(x)
#print "Candidate count = %d" % self.engine.candidate_count(x)
#print "Result size = %d" % len(n)
self.assertEqual(len(n), 20)
def test_storage_memory(self):
# We want 10 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('testHash', 10, 20)
# Create engine for 100 dimensional feature space
self.engine = Engine(100, lshashes=[rbpt], vector_filters=[NearestFilter(20)])
# First insert 2000 random vectors
for k in range(2000):
x = numpy.random.randn(100)
x_data = 'data'
self.engine.store_vector(x, x_data)
self.memory.store_hash_configuration(rbpt)
rbpt2 = RandomBinaryProjectionTree(None, None, None)
rbpt2.apply_config(self.memory.load_hash_configuration('testHash'))
self.assertEqual(rbpt.dim, rbpt2.dim)
self.assertEqual(rbpt.hash_name, rbpt2.hash_name)
self.assertEqual(rbpt.projection_count, rbpt2.projection_count)
for i in range(rbpt.normals.shape[0]):
for j in range(rbpt.normals.shape[1]):
self.assertEqual(rbpt.normals[i, j], rbpt2.normals[i, j])
# Now do random queries and check result set size
for k in range(10):
x = numpy.random.randn(100)
keys1 = rbpt.hash_vector(x, querying=True)
keys2 = rbpt2.hash_vector(x, querying=True)
self.assertEqual(len(keys1), len(keys2))
for k in range(len(keys1)):
self.assertEqual(keys1[k], keys2[k])
def test_storage_redis(self):
# We want 10 projections, 20 results at least
rbpt = RandomBinaryProjectionTree('testHash', 10, 20)
# Create engine for 100 dimensional feature space
self.engine = Engine(100, lshashes=[rbpt], vector_filters=[NearestFilter(20)])
# First insert 2000 random vectors
for k in range(2000):
x = numpy.random.randn(100)
x_data = 'data'
self.engine.store_vector(x, x_data)
self.redis_storage.store_hash_configuration(rbpt)
rbpt2 = RandomBinaryProjectionTree(None, None, None)
rbpt2.apply_config(self.redis_storage.load_hash_configuration('testHash'))
self.assertEqual(rbpt.dim, rbpt2.dim)
self.assertEqual(rbpt.hash_name, rbpt2.hash_name)
self.assertEqual(rbpt.projection_count, rbpt2.projection_count)
for i in range(rbpt.normals.shape[0]):
for j in range(rbpt.normals.shape[1]):
self.assertEqual(rbpt.normals[i, j], rbpt2.normals[i, j])
# Now do random queries and check result set size
for k in range(10):
x = numpy.random.randn(100)
keys1 = rbpt.hash_vector(x, querying=True)
keys2 = rbpt2.hash_vector(x, querying=True)
self.assertEqual(len(keys1), len(keys2))
for k in range(len(keys1)):
self.assertEqual(keys1[k], keys2[k])
class TestStorage(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
def test_memory_storage(self):
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.memory.store_vector('testHash', bucket_key, x, x_data)
X = self.memory.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.memory.clean_all_buckets()
self.assertEqual(self.memory.get_bucket('testHash', bucket_key), [])
def test_redis_storage(self):
self.redis_storage.clean_all_buckets()
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.redis_storage.store_vector('testHash', bucket_key, x, x_data)
X = self.redis_storage.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.redis_storage.clean_all_buckets()
self.assertEqual(self.redis_storage.get_bucket('testHash',
bucket_key), [])
def test_redis_storage_sparse(self):
self.redis_storage.clean_all_buckets()
x = scipy.sparse.rand(100, 1, density=0.1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.redis_storage.store_vector('testHash', bucket_key, x, x_data)
X = self.redis_storage.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(type(x), type(y))
self.assertEqual(x.shape[0], y.shape[0])
self.assertEqual(x.shape[1], y.shape[1])
self.assertTrue((y - x).sum() == 0.0)
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.redis_storage.clean_all_buckets()
self.assertEqual(self.redis_storage.get_bucket('testHash',
bucket_key), [])
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
class TestStorage(unittest.TestCase):
def setUp(self):
self.memory = MemoryStorage()
self.redis_object = Redis()
self.redis_storage = RedisStorage(self.redis_object)
def test_memory_storage(self):
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.memory.store_vector('testHash', bucket_key, x, x_data)
X = self.memory.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.memory.clean_all_buckets()
self.assertEqual(self.memory.get_bucket('testHash', bucket_key), [])
def test_redis_storage(self):
self.redis_storage.clean_all_buckets()
x = numpy.random.randn(100, 1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.redis_storage.store_vector('testHash', bucket_key, x, x_data)
X = self.redis_storage.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(len(y), len(x))
self.assertEqual(type(x), type(y))
for k in range(100):
self.assertEqual(y[k], x[k])
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.redis_storage.clean_all_buckets()
self.assertEqual(self.redis_storage.get_bucket('testHash', bucket_key),
[])
def test_redis_storage_sparse(self):
self.redis_storage.clean_all_buckets()
x = scipy.sparse.rand(100, 1, density=0.1)
bucket_key = '23749283743928748'
x_data = ['one', 'two', 'three']
self.redis_storage.store_vector('testHash', bucket_key, x, x_data)
X = self.redis_storage.get_bucket('testHash', bucket_key)
self.assertEqual(len(X), 1)
y = X[0][0]
y_data = X[0][1]
self.assertEqual(type(x), type(y))
self.assertEqual(x.shape[0], y.shape[0])
self.assertEqual(x.shape[1], y.shape[1])
self.assertTrue((y - x).sum() == 0.0)
self.assertEqual(type(y_data), type(x_data))
self.assertEqual(len(y_data), len(x_data))
for k in range(3):
self.assertEqual(y_data[k], x_data[k])
self.redis_storage.clean_all_buckets()
self.assertEqual(self.redis_storage.get_bucket('testHash', bucket_key),
[])
