Brute Force

1
cdef class Index

1
def trained(self)

1
def build(dataset, metric="sqeuclidean", metric_arg=2.0, resources=None)

1
>>> import cupy as cp
2
>>> from cuvs.neighbors import brute_force
3
>>> n_samples = 50000
4
>>> n_features = 50
5
>>> n_queries = 1000
6
>>> k = 10
7
>>> dataset = cp.random.random_sample((n_samples, n_features),
8
...                                   dtype=cp.float32)
9
>>> index = brute_force.build(dataset, metric="cosine")
10
>>> distances, neighbors = brute_force.search(index, dataset, k)
11
>>> distances = cp.asarray(distances)
12
>>> neighbors = cp.asarray(neighbors)

1
def search(Index index, queries, k, neighbors=None, distances=None, resources=None, prefilter=None)

1
>>> # Example without pre-filter
2
>>> import cupy as cp
3
>>> from cuvs.neighbors import brute_force
4
>>> n_samples = 50000
5
>>> n_features = 50
6
>>> n_queries = 1000
7
>>> dataset = cp.random.random_sample((n_samples, n_features),
8
...                                   dtype=cp.float32)
9
>>> # Build index
10
>>> index = brute_force.build(dataset, metric="sqeuclidean")
11
>>> # Search using the built index
12
>>> queries = cp.random.random_sample((n_queries, n_features),
13
...                                   dtype=cp.float32)
14
>>> k = 10
15
>>> # Using a pooling allocator reduces overhead of temporary array
16
>>> # creation during search. This is useful if multiple searches
17
>>> # are performed with same query size.
18
>>> distances, neighbors = brute_force.search(index, queries, k)
19
>>> neighbors = cp.asarray(neighbors)
20
>>> distances = cp.asarray(distances)

1
>>> # Example with pre-filter
2
>>> import numpy as np
3
>>> import cupy as cp
4
>>> from cuvs.neighbors import brute_force, filters
5
>>> n_samples = 50000
6
>>> n_features = 50
7
>>> n_queries = 1000
8
>>> dataset = cp.random.random_sample((n_samples, n_features),
9
...                                   dtype=cp.float32)
10
>>> # Build index
11
>>> index = brute_force.build(dataset, metric="sqeuclidean")
12
>>> # Search using the built index
13
>>> queries = cp.random.random_sample((n_queries, n_features),
14
...                                   dtype=cp.float32)
15
>>> # Build filters
16
>>> n_bitmap = np.ceil(n_samples * n_queries / 32).astype(int)
17
>>> # Create your own bitmap as the filter by replacing the random one.
18
>>> bitmap = cp.random.randint(1, 100, size=(n_bitmap,), dtype=cp.uint32)
19
>>> bitmap_prefilter = filters.from_bitmap(bitmap)
20
>>>
21
>>> # or Build bitset prefilter:
22
>>> # n_bitset = np.ceil(n_samples * 1 / 32).astype(int)
23
>>> # # Create your own bitset as the filter by replacing the random one.
24
>>> # bitset = cp.random.randint(1, 100, size=(n_bitset,), dtype=cp.uint32)
25
>>> # bitset_prefilter = filters.from_bitset(bitset)
26
>>>
27
>>> k = 10
28
>>> # Using a pooling allocator reduces overhead of temporary array
29
>>> # creation during search. This is useful if multiple searches
30
>>> # are performed with same query size.
31
>>> distances, neighbors = brute_force.search(index, queries, k,
32
...                                           prefilter=bitmap_prefilter)
33
>>> neighbors = cp.asarray(neighbors)
34
>>> distances = cp.asarray(distances)

1
def save(filename, Index index, bool include_dataset=True, resources=None)

1
>>> import cupy as cp
2
>>> from cuvs.neighbors import brute_force
3
>>> n_samples = 50000
4
>>> n_features = 50
5
>>> dataset = cp.random.random_sample((n_samples, n_features),
6
...                                   dtype=cp.float32)
7
>>> # Build index
8
>>> index = brute_force.build(dataset)
9
>>> # Serialize and deserialize the brute_force index built
10
>>> brute_force.save("my_index.bin", index)
11
>>> index_loaded = brute_force.load("my_index.bin")

1
def load(filename, resources=None)

1
>>> import cupy as cp
2
>>> from cuvs.neighbors import brute_force
3
>>> n_samples = 50000
4
>>> n_features = 50
5
>>> dataset = cp.random.random_sample((n_samples, n_features),
6
...                                   dtype=cp.float32)
7
>>> # Build index
8
>>> index = brute_force.build(dataset)
9
>>> # Serialize and deserialize the brute_force index built
10
>>> brute_force.save("my_index.bin", index)
11
>>> index_loaded = brute_force.load("my_index.bin")