1mlpack_range_search(1) General Commands Manual mlpack_range_search(1)
2
6 mlpack_range_search - range search
7
9 mlpack_range_search [-h] [-v]
10
12 This program implements range search with a Euclidean distance metric.
13 For a given query point, a given range, and a given set of reference
14 points, the program will return all of the reference points with dis‐
15 tance to the query point in the given range. This is performed for an
16 entire set of query points. You may specify a separate set of reference
17 and query points, or only a reference set -- which is then used as both
18 the reference and query set. The given range is taken to be inclusive
19 (that is, points with a distance exactly equal to the minimum and maxi‐
20 mum of the range are included in the results).
21 For example, the following will calculate the points within the range
23 [2, 5] of each point in 'input.csv' and store the distances in 'dis‐
24 tances.csv' and the neighbors in 'neighbors.csv':
25 $ range_search --min=2 --max=5 --reference_file=input.csv --dis‐
27 tances_file=distances.csv --neighbors_file=neighbors.csv
28 The output files are organized such that line i corresponds to the
30 points found for query point i. Because sometimes 0 points may be found
31 in the given range, lines of the output files may be empty. The points
32 are not ordered in any specific manner.
33 Because the number of points returned for each query point may differ,
35 the resultant CSV-like files may not be loadable by many programs. How‐
36 ever, at this time a better way to store this non-square result is not
37 known. As a result, any output files will be written as CSVs in this
38 manner, regardless of the given extension.
39
41 --help (-h)
42 Default help info.
43 --info [string]
45 Get help on a specific module or option. Default value ''.
46 --input_model_file (-m) [string] File containing pre-trained
47 range search model. Default value ''.
48 --leaf_size (-l) [int]
50 Leaf size for tree building (used for kd-trees, vp trees, random
51 projection trees, UB trees, R trees, R* trees, X trees, Hilbert
52 R trees, R+ trees, R++ trees, and octrees). Default value
53 20.
55 --max (-U) [double]
58 Upper bound in range (if not specified, +inf will be used.
59 Default value 0.
60 --min (-L) [double]
62 Lower bound in range. Default value 0.
63 --naive (-N)
65 If true, O(n^2) naive mode is used for computation.
66 --query_file (-q) [string]
68 File containing query points (optional). Default value ''.
69 --random_basis (-R)
71 Before tree-building, project the data onto a random orthogonal
72 basis. --reference_file (-r) [string] File containing the ref‐
73 erence dataset. Default value ''.
74 --seed [int]
76 Random seed (if 0, std::time(NULL) is used). Default value 0.
77 --single_mode (-s)
79 If true, single-tree search is used (as opposed to dual-tree
80 search).
81 --tree_type (-t) [string]
83 Type of tree to use: 'kd', 'vp', 'rp', 'max-rp', ’ub', 'cover',
84 'r', 'r-star', 'x', 'ball', ’hilbert-r', 'r-plus', 'r-plus-
85 plus', 'oct'. Default value 'kd'.
86 --verbose (-v)
88 Display informational messages and the full list of parameters
89 and timers at the end of execution.
90 --version (-V)
92 Display the version of mlpack.
93
95 --distances_file (-d) [string] File to output distances into. Default
96 value ’'. --neighbors_file (-n) [string] File to output neighbors
97 into. Default value ’'. --output_model_file (-M) [string] If speci‐
98 fied, the range search model will be saved to the given file. Default
99 value ''.
100
103 For further information, including relevant papers, citations, and the‐
104 ory, For further information, including relevant papers, citations, and
105 theory, consult the documentation found at http://www.mlpack.org or
106 included with your consult the documentation found at
107 http://www.mlpack.org or included with your DISTRIBUTION OF MLPACK.
108 DISTRIBUTION OF MLPACK.
109 mlpack_range_search(1)