Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
os.remove(index_name)
index = nmslib.init(
space_type,
space_param,
method_name,
nmslib.DataType.DENSE_VECTOR,
nmslib.DistType.FLOAT)
start = time.time()
if fast:
data = read_data_fast('sample_dataset.txt')
print('data.shape', data.shape)
positions = nmslib.addDataPointBatch(index, np.arange(len(data), dtype=np.int32), data)
else:
for id, data in enumerate(read_data('sample_dataset.txt')):
pos = nmslib.addDataPoint(index, id, data)
if id != pos:
print('id %s != pos %s' % (id, pos))
sys.exit(1)
end = time.time()
print('added data in %s secs' % (end - start))
print('Let\'s print a few data entries')
print('We have added %d data points' % nmslib.getDataPointQty(index))
print("Distance between points (0,0) " + str(nmslib.getDistance(index, 0, 0)));
print("Distance between points (1,1) " + str(nmslib.getDistance(index, 1, 1)));
print("Distance between points (0,1) " + str(nmslib.getDistance(index, 0, 1)));
print("Distance between points (1,0) " + str(nmslib.getDistance(index, 1, 0)));
for i in range(0,min(MAX_PRINT_QTY,nmslib.getDataPointQty(index))):
print(nmslib.getDataPoint(index, i))
]
QUERY_STRS = ["abc", "def", "ghik"]
space_type = 'leven'
space_param = []
method_name = 'small_world_rand'
index_name = method_name + '.index'
index = nmslib.init(
space_type,
space_param,
method_name,
nmslib.DataType.OBJECT_AS_STRING,
nmslib.DistType.INT)
for id, data in enumerate(DATA_STRS):
nmslib.addDataPoint(index, id, data)
print('Let\'s print a few data entries')
print('We have added %d data points' % nmslib.getDataPointQty(index))
for i in range(0,min(MAX_PRINT_QTY,nmslib.getDataPointQty(index))):
print(nmslib.getDataPoint(index,i))
print('Let\'s invoke the index-build process')
index_param = ['NN=17', 'efConstruction=50', 'indexThreadQty=4']
query_time_param = ['efSearch=50']
nmslib.loadIndex(index, index_name)
print("The index %s is loaded" % index_name)
method_name = 'small_world_rand'
index_name = method_name + '.index'
index = nmslib.init(
space_type,
space_param,
method_name,
nmslib.DataType.OBJECT_AS_STRING,
nmslib.DistType.INT)
if batch:
print('DATA_STRS', DATA_STRS)
positions = nmslib.addDataPointBatch(index, np.arange(len(DATA_STRS), dtype=np.int32), DATA_STRS)
else:
for id, data in enumerate(DATA_STRS):
nmslib.addDataPoint(index, id, data)
print('Let\'s print a few data entries')
print('We have added %d data points' % nmslib.getDataPointQty(index))
print("Distance between points (0,0) " + str(nmslib.getDistance(index, 0, 0)));
print("Distance between points (1,1) " + str(nmslib.getDistance(index, 1, 1)));
print("Distance between points (0,1) " + str(nmslib.getDistance(index, 0, 1)));
print("Distance between points (1,0) " + str(nmslib.getDistance(index, 1, 0)));
for i in range(0,min(MAX_PRINT_QTY,nmslib.getDataPointQty(index))):
print(nmslib.getDataPoint(index,i))
print('Let\'s invoke the index-build process')
index_param = ['NN=17', 'efConstruction=50', 'indexThreadQty=4']
query_time_param = ['efSearch=50']
def test_sparse_vector_fresh():
space_type = 'cosinesimil_sparse_fast'
space_param = []
method_name = 'small_world_rand'
index_name = method_name + '_sparse.index'
if os.path.isfile(index_name):
os.remove(index_name)
index = nmslib.init(
space_type,
space_param,
method_name,
nmslib.DataType.SPARSE_VECTOR,
nmslib.DistType.FLOAT)
for id, data in enumerate(read_sparse_data('sample_sparse_dataset.txt')):
nmslib.addDataPoint(index, id, data)
print('We have added %d data points' % nmslib.getDataPointQty(index))
for i in range(0,min(MAX_PRINT_QTY,nmslib.getDataPointQty(index))):
print(nmslib.getDataPoint(index,i))
print('Let\'s invoke the index-build process')
index_param = ['NN=17', 'efConstruction=50', 'indexThreadQty=4']
query_time_param = ['efSearch=50']
nmslib.createIndex(index, index_param)
print('The index is created')
nmslib.setQueryTimeParams(index,query_time_param)
def test_vector_loaded():
space_type = 'cosinesimil'
space_param = []
method_name = 'small_world_rand'
index_name = method_name + '.index'
index = nmslib.init(
space_type,
space_param,
method_name,
nmslib.DataType.DENSE_VECTOR,
nmslib.DistType.FLOAT)
for id, data in enumerate(read_data('sample_dataset.txt')):
pos = nmslib.addDataPoint(index, id, data)
if id != pos:
print('id %s != pos %s' % (id, pos))
sys.exit(1)
print('Let\'s print a few data entries')
print('We have added %d data points' % nmslib.getDataPointQty(index))
for i in range(0,min(MAX_PRINT_QTY,nmslib.getDataPointQty(index))):
print(nmslib.getDataPoint(index,i))
print('Let\'s invoke the index-build process')
query_time_param = ['efSearch=50']
nmslib.loadIndex(index, index_name)
if batch:
with TimeIt('batch add'):
positions = nmslib.addDataPointBatch(index, np.arange(len(dataset), dtype=np.int32), data_matrix)
print('positions', positions)
else:
d = []
q = []
with TimeIt('preparing'):
for data in dataset:
d.append([[i, v] for i, v in enumerate(data) if v > 0])
for data in queryset:
q.append([[i, v] for i, v in enumerate(data) if v > 0])
with TimeIt('adding points'):
for id, data in enumerate(d):
nmslib.addDataPoint(index, id, data)
print('Let\'s invoke the index-build process')
index_param = ['NN=17', 'efConstruction=50', 'indexThreadQty=4']
query_time_param = ['efSearch=50']
with TimeIt('building index'):
nmslib.createIndex(index, index_param)
print('The index is created')
nmslib.setQueryTimeParams(index,query_time_param)
print('Query time parameters are set')
print("Results for the freshly created index:")
def test_add_points(self):
self.assertEqual(0, nmslib.addDataPoint(self.index, 1000, "string1"))
self.assertEqual(1, nmslib.addDataPoint(self.index, 1001, "string2"))