124 lines
4.6 KiB
Python
124 lines
4.6 KiB
Python
|
"""Unsupervised nearest neighbors learner"""
|
||
|
|
|
||
|
|
from .base import NeighborsBase
|
||
|
|
from .base import KNeighborsMixin
|
||
|
|
from .base import RadiusNeighborsMixin
|
||
|
|
from .base import UnsupervisedMixin
|
||
|
|
|
||
|
|
|
||
|
|
class NearestNeighbors(NeighborsBase, KNeighborsMixin,
|
||
|
|
RadiusNeighborsMixin, UnsupervisedMixin):
|
||
|
|
"""Unsupervised learner for implementing neighbor searches.
|
||
|
|
|
||
|
|
Read more in the :ref:`User Guide <unsupervised_neighbors>`.
|
||
|
|
|
||
|
|
Parameters
|
||
|
|
----------
|
||
|
|
n_neighbors : int, optional (default = 5)
|
||
|
|
Number of neighbors to use by default for :meth:`kneighbors` queries.
|
||
|
|
|
||
|
|
radius : float, optional (default = 1.0)
|
||
|
|
Range of parameter space to use by default for :meth:`radius_neighbors`
|
||
|
|
queries.
|
||
|
|
|
||
|
|
algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional
|
||
|
|
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, optional (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 : string or callable, default 'minkowski'
|
||
|
|
metric to use for distance computation. Any metric from scikit-learn
|
||
|
|
or scipy.spatial.distance can be used.
|
||
|
|
|
||
|
|
If metric is a callable function, it is called on each
|
||
|
|
pair of instances (rows) and the resulting value recorded. The callable
|
||
|
|
should take two arrays as input and return one value indicating the
|
||
|
|
distance between them. This works for Scipy's metrics, but is less
|
||
|
|
efficient than passing the metric name as a string.
|
||
|
|
|
||
|
|
Distance matrices are not supported.
|
||
|
|
|
||
|
|
Valid values for metric are:
|
||
|
|
|
||
|
|
- from scikit-learn: ['cityblock', 'cosine', 'euclidean', 'l1', 'l2',
|
||
|
|
'manhattan']
|
||
|
|
|
||
|
|
- from scipy.spatial.distance: ['braycurtis', 'canberra', 'chebyshev',
|
||
|
|
'correlation', 'dice', 'hamming', 'jaccard', 'kulsinski',
|
||
|
|
'mahalanobis', 'matching', 'minkowski', 'rogerstanimoto',
|
||
|
|
'russellrao', 'seuclidean', 'sokalmichener', 'sokalsneath',
|
||
|
|
'sqeuclidean', 'yule']
|
||
|
|
|
||
|
|
See the documentation for scipy.spatial.distance for details on these
|
||
|
|
metrics.
|
||
|
|
|
||
|
|
p : integer, optional (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, optional (default = None)
|
||
|
|
Additional keyword arguments for the metric function.
|
||
|
|
|
||
|
|
n_jobs : int, optional (default = 1)
|
||
|
|
The number of parallel jobs to run for neighbors search.
|
||
|
|
If ``-1``, then the number of jobs is set to the number of CPU cores.
|
||
|
|
Affects only :meth:`kneighbors` and :meth:`kneighbors_graph` methods.
|
||
|
|
|
||
|
|
Examples
|
||
|
|
--------
|
||
|
|
>>> import numpy as np
|
||
|
|
>>> from sklearn.neighbors import NearestNeighbors
|
||
|
|
>>> samples = [[0, 0, 2], [1, 0, 0], [0, 0, 1]]
|
||
|
|
|
||
|
|
>>> neigh = NearestNeighbors(2, 0.4)
|
||
|
|
>>> neigh.fit(samples) #doctest: +ELLIPSIS
|
||
|
|
NearestNeighbors(...)
|
||
|
|
|
||
|
|
>>> neigh.kneighbors([[0, 0, 1.3]], 2, return_distance=False)
|
||
|
|
... #doctest: +ELLIPSIS
|
||
|
|
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
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(self, n_neighbors=5, radius=1.0,
|
||
|
|
algorithm='auto', leaf_size=30, metric='minkowski',
|
||
|
|
p=2, metric_params=None, n_jobs=1, **kwargs):
|
||
|
|
self._init_params(n_neighbors=n_neighbors,
|
||
|
|
radius=radius,
|
||
|
|
algorithm=algorithm,
|
||
|
|
leaf_size=leaf_size, metric=metric, p=p,
|
||
|
|
metric_params=metric_params, n_jobs=n_jobs, **kwargs)
|