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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
|
"""Nearest Neighbor Classification"""
# Authors: Jake Vanderplas <vanderplas@astro.washington.edu>
# Fabian Pedregosa <fabian.pedregosa@inria.fr>
# Alexandre Gramfort <alexandre.gramfort@inria.fr>
# Sparseness support by Lars Buitinck <L.J.Buitinck@uva.nl>
#
# License: BSD, (C) INRIA, University of Amsterdam
import numpy as np
from scipy import stats
from ..utils.extmath import weighted_mode
from .base import \
_check_weights, _get_weights, \
NeighborsBase, KNeighborsMixin,\
RadiusNeighborsMixin, SupervisedIntegerMixin
from ..base import ClassifierMixin
from ..utils import atleast2d_or_csr
class KNeighborsClassifier(NeighborsBase, KNeighborsMixin,
SupervisedIntegerMixin, ClassifierMixin):
"""Classifier implementing the k-nearest neighbors vote.
Parameters
----------
n_neighbors : int, optional (default = 5)
Number of neighbors to use by default for :meth:`k_neighbors` queries.
weights : str or callable
weight function used in prediction. Possible values:
- 'uniform' : uniform weights. All points in each neighborhood
are weighted equally.
- 'distance' : weight points by the inverse of their distance.
in this case, closer neighbors of a query point will have a
greater influence than neighbors which are further away.
- [callable] : a user-defined function which accepts an
array of distances, and returns an array of the same shape
containing the weights.
Uniform weights are used by default.
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:`scipy.spatial.cKDtree`
- '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 cKDTree. 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.
warn_on_equidistant : boolean, optional. Defaults to True.
Generate a warning if equidistant neighbors are discarded.
For classification or regression based on k-neighbors, if
neighbor k and neighbor k+1 have identical distances but
different labels, then the result will be dependent on the
ordering of the training data.
If the fit method is ``'kd_tree'``, no warnings will be generated.
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.
Examples
--------
>>> X = [[0], [1], [2], [3]]
>>> y = [0, 0, 1, 1]
>>> from sklearn.neighbors import KNeighborsClassifier
>>> neigh = KNeighborsClassifier(n_neighbors=2)
>>> neigh.fit(X, y) # doctest: +ELLIPSIS
KNeighborsClassifier(...)
>>> print neigh.predict([[1.5]])
[0]
See also
--------
RadiusNeighborsClassifier
KNeighborsRegressor
RadiusNeighborsRegressor
NearestNeighbors
Notes
-----
See :ref:`Nearest Neighbors <neighbors>` in the online documentation
for a discussion of the choice of ``algorithm`` and ``leaf_size``.
http://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
"""
def __init__(self, n_neighbors=5,
weights='uniform',
algorithm='auto', leaf_size=30,
warn_on_equidistant=True, p=2):
self._init_params(n_neighbors=n_neighbors,
algorithm=algorithm,
leaf_size=leaf_size,
warn_on_equidistant=warn_on_equidistant,
p=p)
self.weights = _check_weights(weights)
def predict(self, X):
"""Predict the class labels for the provided data
Parameters
----------
X: array
A 2-D array representing the test points.
Returns
-------
labels: array
List of class labels (one for each data sample).
"""
X = atleast2d_or_csr(X)
neigh_dist, neigh_ind = self.kneighbors(X)
pred_labels = self._y[neigh_ind]
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode, _ = stats.mode(pred_labels, axis=1)
else:
mode, _ = weighted_mode(pred_labels, weights, axis=1)
return mode.flatten().astype(np.int)
class RadiusNeighborsClassifier(NeighborsBase, RadiusNeighborsMixin,
SupervisedIntegerMixin, ClassifierMixin):
"""Classifier implementing a vote among neighbors within a given radius
Parameters
----------
radius : float, optional (default = 1.0)
Range of parameter space to use by default for :meth`radius_neighbors`
queries.
weights : str or callable
weight function used in prediction. Possible values:
- 'uniform' : uniform weights. All points in each neighborhood
are weighted equally.
- 'distance' : weight points by the inverse of their distance.
in this case, closer neighbors of a query point will have a
greater influence than neighbors which are further away.
- [callable] : a user-defined function which accepts an
array of distances, and returns an array of the same shape
containing the weights.
Uniform weights are used by default.
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:`scipy.spatial.cKDtree`
- '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 cKDTree. 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.
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.
outlier_label: int, optional (default = None)
Label, which is given for outlier samples (samples with no
neighbors on given radius).
If set to None, ValueError is raised, when outlier is detected.
Examples
--------
>>> X = [[0], [1], [2], [3]]
>>> y = [0, 0, 1, 1]
>>> from sklearn.neighbors import RadiusNeighborsClassifier
>>> neigh = RadiusNeighborsClassifier(radius=1.0)
>>> neigh.fit(X, y) # doctest: +ELLIPSIS
RadiusNeighborsClassifier(...)
>>> print neigh.predict([[1.5]])
[0]
See also
--------
KNeighborsClassifier
RadiusNeighborsRegressor
KNeighborsRegressor
NearestNeighbors
Notes
-----
See :ref:`Nearest Neighbors <neighbors>` in the online documentation
for a discussion of the choice of ``algorithm`` and ``leaf_size``.
http://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
"""
def __init__(self, radius=1.0, weights='uniform',
algorithm='auto', leaf_size=30, p=2, outlier_label=None):
self._init_params(radius=radius,
algorithm=algorithm,
leaf_size=leaf_size,
p=p)
self.weights = _check_weights(weights)
self.outlier_label = outlier_label
def predict(self, X):
"""Predict the class labels for the provided data
Parameters
----------
X: array
A 2-D array representing the test points.
Returns
-------
labels: array
List of class labels (one for each data sample).
"""
X = atleast2d_or_csr(X)
neigh_dist, neigh_ind = self.radius_neighbors(X)
pred_labels = [self._y[ind] for ind in neigh_ind]
if self.outlier_label:
outlier_label = np.array((self.outlier_label, ))
small_value = np.array((1e-6, ))
for i, pl in enumerate(pred_labels):
# Check that all have at least 1 neighbor
if len(pl) < 1:
pred_labels[i] = outlier_label
neigh_dist[i] = small_value
else:
for pl in pred_labels:
# Check that all have at least 1 neighbor
if len(pl) < 1:
raise ValueError('no neighbors found for a test sample, '
'you can try using larger radius, '
'give a label for outliers, '
'or consider removing them in your '
'dataset')
weights = _get_weights(neigh_dist, self.weights)
if weights is None:
mode = np.asarray([stats.mode(pl)[0] for pl in pred_labels],
dtype=np.int)
else:
mode = np.asarray([weighted_mode(pl, w)[0]
for (pl, w) in zip(pred_labels, weights)],
dtype=np.int)
return mode.flatten().astype(np.int)
|
