def setUp(self):
self.V = []
self.V.append((numpy.array([0]), 'data1', 0.4))
self.V.append((numpy.array([1]), 'data2', 0.9))
self.V.append((numpy.array([2]), 'data3', 1.4))
self.V.append((numpy.array([3]), 'data4', 2.1))
self.V.append((numpy.array([4]), 'data5', 0.1))
self.V.append((numpy.array([5]), 'data6', 8.7))
self.V.append((numpy.array([6]), 'data7', 3.4))
self.V.append((numpy.array([7]), 'data8', 2.8))
self.threshold_filter = DistanceThresholdFilter(1.0)
self.nearest_filter = NearestFilter(5)
self.unique = UniqueFilter()
def __init__(self, data_points, sim_threshold=0.5, num_vectors=3):
self.data_points = data_points
self.point_num = self.data_points.shape[0]
self.dimension = self.data_points.shape[1] - 1
# Create a random binary hash with . bits
self.rbp = RandomBinaryProjections('rbp', num_vectors, rand_seed=42)
self.engine = Engine(
self.dimension,
lshashes=[self.rbp],
vector_filters=[DistanceThresholdFilter(1 - sim_threshold)])
for i in range(self.point_num):
self.engine.store_vector(self.data_points[i, 1:], '%d' % i)
def setUp(self):
self.V = []
self.V.append((numpy.array([0]), 'data1', 0.4))
self.V.append((numpy.array([1]), 'data2', 0.9))
self.V.append((numpy.array([2]), 'data3', 1.4))
self.V.append((numpy.array([3]), 'data4', 2.1))
self.V.append((numpy.array([4]), 'data5', 0.1))
self.V.append((numpy.array([5]), 'data6', 8.7))
self.V.append((numpy.array([6]), 'data7', 3.4))
self.V.append((numpy.array([7]), 'data8', 2.8))
self.threshold_filter = DistanceThresholdFilter(1.0)
self.nearest_filter = NearestFilter(5)
self.unique = UniqueFilter()
def __init__(self, level, dim, proj, bico):
self.level = level
self.dim = dim
self.proj = proj
self.point_to_biconode = {}
self.rbpt = RandomBinaryProjectionTree('rbpt', proj, 1)
self.rbp = RandomBinaryProjections('rbp', proj)
self.sqdist = SquaredEuclideanDistance()
self.ann_engine = Engine(
dim,
lshashes=[self.rbp],
distance=self.sqdist,
vector_filters=[DistanceThresholdFilter(bico._getR(self.level))])
self.num_cfs = 0
self.bico = bico
self.cf = ClusteringFeature(Point(np.zeros(dim)), Point(np.zeros(dim)),
0, 0)
def __init__(self, dimension: int, number_projections: int,
threshold: float):
"""
:param dimension:
Number of dimensions of input points
:param number_projections:
Number of random projections used for finding nearest neighbors.
Trade-off: More projections result in a smaller number of false positives in candidate set
:param threshold:
Distance threshold for definition nearest: all points within this specific distance
"""
self.rbp = RandomBinaryProjections('rbp', number_projections)
self.sqdist = SquaredEuclideanDistance()
self.ann_engine = Engine(
dimension,
lshashes=[self.rbp],
distance=self.sqdist,
vector_filters=[DistanceThresholdFilter(threshold)])
class TestVectorFilters(unittest.TestCase):
def setUp(self):
self.V = []
self.V.append((numpy.array([0]), 'data1', 0.4))
self.V.append((numpy.array([1]), 'data2', 0.9))
self.V.append((numpy.array([2]), 'data3', 1.4))
self.V.append((numpy.array([3]), 'data4', 2.1))
self.V.append((numpy.array([4]), 'data5', 0.1))
self.V.append((numpy.array([5]), 'data6', 8.7))
self.V.append((numpy.array([6]), 'data7', 3.4))
self.V.append((numpy.array([7]), 'data8', 2.8))
self.threshold_filter = DistanceThresholdFilter(1.0)
self.nearest_filter = NearestFilter(5)
self.unique = UniqueFilter()
def test_thresholding(self):
result = self.threshold_filter.filter_vectors(self.V)
self.assertEqual(len(result), 3)
self.assertIn(self.V[0], result)
self.assertIn(self.V[1], result)
self.assertIn(self.V[4], result)
def test_nearest(self):
result = self.nearest_filter.filter_vectors(self.V)
self.assertEqual(len(result), 5)
self.assertIn(self.V[0], result)
self.assertIn(self.V[1], result)
self.assertIn(self.V[4], result)
self.assertIn(self.V[2], result)
self.assertIn(self.V[3], result)
def test_unique(self):
W = self.V
W.append((numpy.array([7]), 'data8', 2.8))
W.append((numpy.array([0]), 'data1', 2.8))
W.append((numpy.array([1]), 'data2', 2.8))
W.append((numpy.array([6]), 'data7', 2.8))
result = self.unique.filter_vectors(W)
self.assertEqual(len(result), 8)
class TestVectorFilters(unittest.TestCase):
def setUp(self):
self.V = []
self.V.append((numpy.array([0]), 'data1', 0.4))
self.V.append((numpy.array([1]), 'data2', 0.9))
self.V.append((numpy.array([2]), 'data3', 1.4))
self.V.append((numpy.array([3]), 'data4', 2.1))
self.V.append((numpy.array([4]), 'data5', 0.1))
self.V.append((numpy.array([5]), 'data6', 8.7))
self.V.append((numpy.array([6]), 'data7', 3.4))
self.V.append((numpy.array([7]), 'data8', 2.8))
self.threshold_filter = DistanceThresholdFilter(1.0)
self.nearest_filter = NearestFilter(5)
self.unique = UniqueFilter()
def test_thresholding(self):
result = self.threshold_filter.filter_vectors(self.V)
self.assertEqual(len(result), 3)
self.assertTrue(self.V[0] in result)
self.assertTrue(self.V[1] in result)
self.assertTrue(self.V[4] in result)
def test_nearest(self):
result = self.nearest_filter.filter_vectors(self.V)
self.assertEqual(len(result), 5)
self.assertTrue(self.V[0] in result)
self.assertTrue(self.V[1] in result)
self.assertTrue(self.V[4] in result)
self.assertTrue(self.V[2] in result)
self.assertTrue(self.V[3] in result)
def test_unique(self):
W = self.V
W.append((numpy.array([7]), 'data8', 2.8))
W.append((numpy.array([0]), 'data1', 2.8))
W.append((numpy.array([1]), 'data2', 2.8))
W.append((numpy.array([6]), 'data7', 2.8))
result = self.unique.filter_vectors(W)
self.assertEqual(len(result), 8)