def test_random_discretized_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
rdp = RandomDiscretizedProjections("rdp", 1, 0.01)
nearest = NearestFilter(10)
engine = Engine(dim, lshashes=[rdp], 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 RDP: %f, Precision RDP: %f, SearchTime RDP: %f\n" % (recall1, precision1, searchtime1))
# Then get recall and precision for one 4-dim random hash
rdp = RandomDiscretizedProjections("rdp", 2, 0.2)
engine = Engine(dim, lshashes=[rdp], vector_filters=[nearest])
result = exp.perform_experiment([engine])
recall2 = result[0][0]
precision2 = result[0][1]
searchtime2 = result[0][2]
print("\nRecall RDP: %f, Precision RDP: %f, SearchTime RDP: %f\n" % (recall2, precision2, searchtime2))
# Many things are random here, but the precision should increase
# with dimension
self.assertTrue(precision2 > precision1)
def test_random_discretized_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
rdp = RandomDiscretizedProjections('rdp', 1, 0.01)
nearest = NearestFilter(10)
engine = Engine(dim, lshashes=[rdp], 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 RDP: %f, Precision RDP: %f, SearchTime RDP: %f\n' % \
(recall1, precision1, searchtime1))
# Then get recall and precision for one 4-dim random hash
rdp = RandomDiscretizedProjections('rdp', 2, 0.2)
engine = Engine(dim, lshashes=[rdp], vector_filters=[nearest])
result = exp.perform_experiment([engine])
recall2 = result[0][0]
precision2 = result[0][1]
searchtime2 = result[0][2]
print('\nRecall RDP: %f, Precision RDP: %f, SearchTime RDP: %f\n' % \
(recall2, precision2, searchtime2))
# Many things are random here, but the precision should increase
# with dimension
self.assertTrue(precision2 > precision1)
def test_experiment_with_unibucket_1(self):
dim = 50
vector_count = 100
vectors = numpy.random.randn(dim, vector_count)
unibucket = UniBucket("testHash")
nearest = NearestFilter(10)
engine = Engine(dim, lshashes=[unibucket], vector_filters=[nearest])
exp = RecallPrecisionExperiment(10, vectors)
result = exp.perform_experiment([engine])
# Both recall and precision must be one in this case
self.assertEqual(result[0][0], 1.0)
self.assertEqual(result[0][1], 1.0)
def test_experiment_with_unibucket_1(self):
dim = 50
vector_count = 100
vectors = numpy.random.randn(dim, vector_count)
unibucket = UniBucket('testHash')
nearest = NearestFilter(10)
engine = Engine(dim, lshashes=[unibucket], vector_filters=[nearest])
exp = RecallPrecisionExperiment(10, vectors)
result = exp.perform_experiment([engine])
# Both recall and precision must be one in this case
self.assertEqual(result[0][0], 1.0)
self.assertEqual(result[0][1], 1.0)
def test_experiment_with_unibucket_3(self):
dim = 50
vector_count = 100
vectors = numpy.random.randn(dim, vector_count)
unibucket = UniBucket("testHash")
nearest = NearestFilter(5)
engine = Engine(dim, lshashes=[unibucket], vector_filters=[nearest])
exp = RecallPrecisionExperiment(10, vectors)
result = exp.perform_experiment([engine])
# In this case recall is only 0.5
# because the engine returns 5 nearest, but
# the experiment looks for 10 nearest.
self.assertEqual(result[0][0], 0.5)
self.assertEqual(result[0][1], 1.0)
def test_experiment_with_unibucket_3(self):
dim = 50
vector_count = 100
vectors = numpy.random.randn(dim, vector_count)
unibucket = UniBucket('testHash')
nearest = NearestFilter(5)
engine = Engine(dim, lshashes=[unibucket], vector_filters=[nearest])
exp = RecallPrecisionExperiment(10, vectors)
result = exp.perform_experiment([engine])
# In this case recall is only 0.5
# because the engine returns 5 nearest, but
# the experiment looks for 10 nearest.
self.assertEqual(result[0][0], 0.5)
self.assertEqual(result[0][1], 1.0)
def test_experiment_with_list_2(self):
dim = 50
vector_count = 100
vectors = []
for index in range(vector_count):
vectors.append(numpy.random.randn(dim))
unibucket = UniBucket("testHash")
nearest = NearestFilter(10)
engine = Engine(dim, lshashes=[unibucket], vector_filters=[nearest])
exp = RecallPrecisionExperiment(5, vectors)
result = exp.perform_experiment([engine])
# In this case precision is only 0.5
# because the engine returns 10 nearest, but
# the experiment only looks for 5 nearest.
self.assertEqual(result[0][0], 1.0)
self.assertEqual(result[0][1], 0.5)
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)
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 test_experiment_with_list_2(self):
dim = 50
vector_count = 100
vectors = []
for index in range(vector_count):
vectors.append(numpy.random.randn(dim))
unibucket = UniBucket('testHash')
nearest = NearestFilter(10)
engine = Engine(dim, lshashes=[unibucket], vector_filters=[nearest])
exp = RecallPrecisionExperiment(5, vectors)
result = exp.perform_experiment([engine])
# In this case precision is only 0.5
# because the engine returns 10 nearest, but
# the experiment only looks for 5 nearest.
self.assertEqual(result[0][0], 1.0)
self.assertEqual(result[0][1], 0.5)
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)
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))
