_unsupervised.py
4.25 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
"""Unsupervised nearest neighbors learner"""
from ._base import NeighborsBase
from ._base import KNeighborsMixin
from ._base import RadiusNeighborsMixin
from ._base import UnsupervisedMixin
from ..utils.validation import _deprecate_positional_args
class NearestNeighbors(KNeighborsMixin, RadiusNeighborsMixin,
UnsupervisedMixin, NeighborsBase):
"""Unsupervised learner for implementing neighbor searches.
Read more in the :ref:`User Guide <unsupervised_neighbors>`.
.. versionadded:: 0.9
Parameters
----------
n_neighbors : int, default=5
Number of neighbors to use by default for :meth:`kneighbors` queries.
radius : float, default=1.0
Range of parameter space to use by default for :meth:`radius_neighbors`
queries.
algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
Algorithm used to compute the nearest neighbors:
- 'ball_tree' will use :class:`BallTree`
- 'kd_tree' will use :class:`KDTree`
- 'brute' will use a brute-force search.
- 'auto' will attempt to decide the most appropriate algorithm
based on the values passed to :meth:`fit` method.
Note: fitting on sparse input will override the setting of
this parameter, using brute force.
leaf_size : int, default=30
Leaf size passed to BallTree or KDTree. This can affect the
speed of the construction and query, as well as the memory
required to store the tree. The optimal value depends on the
nature of the problem.
metric : str or callable, default='minkowski'
the distance metric to use for the tree. The default metric is
minkowski, and with p=2 is equivalent to the standard Euclidean
metric. See the documentation of :class:`DistanceMetric` for a
list of available metrics.
If metric is "precomputed", X is assumed to be a distance matrix and
must be square during fit. X may be a :term:`sparse graph`,
in which case only "nonzero" elements may be considered neighbors.
p : int, default=2
Parameter for the Minkowski metric from
sklearn.metrics.pairwise.pairwise_distances. When p = 1, this is
equivalent to using manhattan_distance (l1), and euclidean_distance
(l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
metric_params : dict, default=None
Additional keyword arguments for the metric function.
n_jobs : int, default=None
The number of parallel jobs to run for neighbors search.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See :term:`Glossary <n_jobs>`
for more details.
Attributes
----------
effective_metric_ : str
Metric used to compute distances to neighbors.
effective_metric_params_ : dict
Parameters for the metric used to compute distances to neighbors.
Examples
--------
>>> import numpy as np
>>> from sklearn.neighbors import NearestNeighbors
>>> samples = [[0, 0, 2], [1, 0, 0], [0, 0, 1]]
>>> neigh = NearestNeighbors(n_neighbors=2, radius=0.4)
>>> neigh.fit(samples)
NearestNeighbors(...)
>>> neigh.kneighbors([[0, 0, 1.3]], 2, return_distance=False)
array([[2, 0]]...)
>>> nbrs = neigh.radius_neighbors([[0, 0, 1.3]], 0.4, return_distance=False)
>>> np.asarray(nbrs[0][0])
array(2)
See also
--------
KNeighborsClassifier
RadiusNeighborsClassifier
KNeighborsRegressor
RadiusNeighborsRegressor
BallTree
Notes
-----
See :ref:`Nearest Neighbors <neighbors>` in the online documentation
for a discussion of the choice of ``algorithm`` and ``leaf_size``.
https://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
"""
@_deprecate_positional_args
def __init__(self, *, n_neighbors=5, radius=1.0,
algorithm='auto', leaf_size=30, metric='minkowski',
p=2, metric_params=None, n_jobs=None):
super().__init__(
n_neighbors=n_neighbors,
radius=radius,
algorithm=algorithm,
leaf_size=leaf_size, metric=metric, p=p,
metric_params=metric_params, n_jobs=n_jobs)