-
-
Notifications
You must be signed in to change notification settings - Fork 25.3k
/
_base.py
1235 lines (1045 loc) · 44.4 KB
/
_base.py
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
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Base and mixin classes for nearest neighbors."""
# Authors: Jake Vanderplas <vanderplas@astro.washington.edu>
# Fabian Pedregosa <fabian.pedregosa@inria.fr>
# Alexandre Gramfort <alexandre.gramfort@inria.fr>
# Sparseness support by Lars Buitinck
# Multi-output support by Arnaud Joly <a.joly@ulg.ac.be>
#
# License: BSD 3 clause (C) INRIA, University of Amsterdam
from functools import partial
import warnings
from abc import ABCMeta, abstractmethod
import numbers
import numpy as np
from scipy.sparse import csr_matrix, issparse
import joblib
from joblib import Parallel, effective_n_jobs
from ._ball_tree import BallTree
from ._kd_tree import KDTree
from ..base import BaseEstimator, MultiOutputMixin
from ..base import is_classifier
from ..metrics import pairwise_distances_chunked
from ..metrics.pairwise import PAIRWISE_DISTANCE_FUNCTIONS
from ..utils import (
check_array,
gen_even_slices,
_to_object_array,
)
from ..utils.deprecation import deprecated
from ..utils.multiclass import check_classification_targets
from ..utils.validation import check_is_fitted
from ..utils.validation import check_non_negative
from ..utils.fixes import delayed
from ..utils.fixes import parse_version
from ..exceptions import DataConversionWarning, EfficiencyWarning
VALID_METRICS = dict(
ball_tree=BallTree.valid_metrics,
kd_tree=KDTree.valid_metrics,
# The following list comes from the
# sklearn.metrics.pairwise doc string
brute=(
list(PAIRWISE_DISTANCE_FUNCTIONS.keys())
+ [
"braycurtis",
"canberra",
"chebyshev",
"correlation",
"cosine",
"dice",
"hamming",
"jaccard",
"kulsinski",
"mahalanobis",
"matching",
"minkowski",
"rogerstanimoto",
"russellrao",
"seuclidean",
"sokalmichener",
"sokalsneath",
"sqeuclidean",
"yule",
"wminkowski",
]
),
)
VALID_METRICS_SPARSE = dict(
ball_tree=[],
kd_tree=[],
brute=(PAIRWISE_DISTANCE_FUNCTIONS.keys() - {"haversine", "nan_euclidean"}),
)
def _check_weights(weights):
"""Check to make sure weights are valid"""
if weights not in (None, "uniform", "distance") and not callable(weights):
raise ValueError(
"weights not recognized: should be 'uniform', "
"'distance', or a callable function"
)
return weights
def _get_weights(dist, weights):
"""Get the weights from an array of distances and a parameter ``weights``.
Parameters
----------
dist : ndarray
The input distances.
weights : {'uniform', 'distance' or a callable}
The kind of weighting used.
Returns
-------
weights_arr : array of the same shape as ``dist``
If ``weights == 'uniform'``, then returns None.
"""
if weights in (None, "uniform"):
return None
elif weights == "distance":
# if user attempts to classify a point that was zero distance from one
# or more training points, those training points are weighted as 1.0
# and the other points as 0.0
if dist.dtype is np.dtype(object):
for point_dist_i, point_dist in enumerate(dist):
# check if point_dist is iterable
# (ex: RadiusNeighborClassifier.predict may set an element of
# dist to 1e-6 to represent an 'outlier')
if hasattr(point_dist, "__contains__") and 0.0 in point_dist:
dist[point_dist_i] = point_dist == 0.0
else:
dist[point_dist_i] = 1.0 / point_dist
else:
with np.errstate(divide="ignore"):
dist = 1.0 / dist
inf_mask = np.isinf(dist)
inf_row = np.any(inf_mask, axis=1)
dist[inf_row] = inf_mask[inf_row]
return dist
elif callable(weights):
return weights(dist)
else:
raise ValueError(
"weights not recognized: should be 'uniform', "
"'distance', or a callable function"
)
def _is_sorted_by_data(graph):
"""Return whether the graph's non-zero entries are sorted by data.
The non-zero entries are stored in graph.data and graph.indices.
For each row (or sample), the non-zero entries can be either:
- sorted by indices, as after graph.sort_indices();
- sorted by data, as after _check_precomputed(graph);
- not sorted.
Parameters
----------
graph : sparse matrix of shape (n_samples, n_samples)
Neighbors graph as given by `kneighbors_graph` or
`radius_neighbors_graph`. Matrix should be of format CSR format.
Returns
-------
res : bool
Whether input graph is sorted by data.
"""
assert graph.format == "csr"
out_of_order = graph.data[:-1] > graph.data[1:]
line_change = np.unique(graph.indptr[1:-1] - 1)
line_change = line_change[line_change < out_of_order.shape[0]]
return out_of_order.sum() == out_of_order[line_change].sum()
def _check_precomputed(X):
"""Check precomputed distance matrix.
If the precomputed distance matrix is sparse, it checks that the non-zero
entries are sorted by distances. If not, the matrix is copied and sorted.
Parameters
----------
X : {sparse matrix, array-like}, (n_samples, n_samples)
Distance matrix to other samples. X may be a sparse matrix, in which
case only non-zero elements may be considered neighbors.
Returns
-------
X : {sparse matrix, array-like}, (n_samples, n_samples)
Distance matrix to other samples. X may be a sparse matrix, in which
case only non-zero elements may be considered neighbors.
"""
if not issparse(X):
X = check_array(X)
check_non_negative(X, whom="precomputed distance matrix.")
return X
else:
graph = X
if graph.format not in ("csr", "csc", "coo", "lil"):
raise TypeError(
"Sparse matrix in {!r} format is not supported due to "
"its handling of explicit zeros".format(graph.format)
)
copied = graph.format != "csr"
graph = check_array(graph, accept_sparse="csr")
check_non_negative(graph, whom="precomputed distance matrix.")
if not _is_sorted_by_data(graph):
warnings.warn(
"Precomputed sparse input was not sorted by data.", EfficiencyWarning
)
if not copied:
graph = graph.copy()
# if each sample has the same number of provided neighbors
row_nnz = np.diff(graph.indptr)
if row_nnz.max() == row_nnz.min():
n_samples = graph.shape[0]
distances = graph.data.reshape(n_samples, -1)
order = np.argsort(distances, kind="mergesort")
order += np.arange(n_samples)[:, None] * row_nnz[0]
order = order.ravel()
graph.data = graph.data[order]
graph.indices = graph.indices[order]
else:
for start, stop in zip(graph.indptr, graph.indptr[1:]):
order = np.argsort(graph.data[start:stop], kind="mergesort")
graph.data[start:stop] = graph.data[start:stop][order]
graph.indices[start:stop] = graph.indices[start:stop][order]
return graph
def _kneighbors_from_graph(graph, n_neighbors, return_distance):
"""Decompose a nearest neighbors sparse graph into distances and indices.
Parameters
----------
graph : sparse matrix of shape (n_samples, n_samples)
Neighbors graph as given by `kneighbors_graph` or
`radius_neighbors_graph`. Matrix should be of format CSR format.
n_neighbors : int
Number of neighbors required for each sample.
return_distance : bool
Whether or not to return the distances.
Returns
-------
neigh_dist : ndarray of shape (n_samples, n_neighbors)
Distances to nearest neighbors. Only present if `return_distance=True`.
neigh_ind : ndarray of shape (n_samples, n_neighbors)
Indices of nearest neighbors.
"""
n_samples = graph.shape[0]
assert graph.format == "csr"
# number of neighbors by samples
row_nnz = np.diff(graph.indptr)
row_nnz_min = row_nnz.min()
if n_neighbors is not None and row_nnz_min < n_neighbors:
raise ValueError(
"%d neighbors per samples are required, but some samples have only"
" %d neighbors in precomputed graph matrix. Decrease number of "
"neighbors used or recompute the graph with more neighbors."
% (n_neighbors, row_nnz_min)
)
def extract(a):
# if each sample has the same number of provided neighbors
if row_nnz.max() == row_nnz_min:
return a.reshape(n_samples, -1)[:, :n_neighbors]
else:
idx = np.tile(np.arange(n_neighbors), (n_samples, 1))
idx += graph.indptr[:-1, None]
return a.take(idx, mode="clip").reshape(n_samples, n_neighbors)
if return_distance:
return extract(graph.data), extract(graph.indices)
else:
return extract(graph.indices)
def _radius_neighbors_from_graph(graph, radius, return_distance):
"""Decompose a nearest neighbors sparse graph into distances and indices.
Parameters
----------
graph : sparse matrix of shape (n_samples, n_samples)
Neighbors graph as given by `kneighbors_graph` or
`radius_neighbors_graph`. Matrix should be of format CSR format.
radius : float
Radius of neighborhoods which should be strictly positive.
return_distance : bool
Whether or not to return the distances.
Returns
-------
neigh_dist : ndarray of shape (n_samples,) of arrays
Distances to nearest neighbors. Only present if `return_distance=True`.
neigh_ind : ndarray of shape (n_samples,) of arrays
Indices of nearest neighbors.
"""
assert graph.format == "csr"
no_filter_needed = bool(graph.data.max() <= radius)
if no_filter_needed:
data, indices, indptr = graph.data, graph.indices, graph.indptr
else:
mask = graph.data <= radius
if return_distance:
data = np.compress(mask, graph.data)
indices = np.compress(mask, graph.indices)
indptr = np.concatenate(([0], np.cumsum(mask)))[graph.indptr]
indices = indices.astype(np.intp, copy=no_filter_needed)
if return_distance:
neigh_dist = _to_object_array(np.split(data, indptr[1:-1]))
neigh_ind = _to_object_array(np.split(indices, indptr[1:-1]))
if return_distance:
return neigh_dist, neigh_ind
else:
return neigh_ind
class NeighborsBase(MultiOutputMixin, BaseEstimator, metaclass=ABCMeta):
"""Base class for nearest neighbors estimators."""
@abstractmethod
def __init__(
self,
n_neighbors=None,
radius=None,
algorithm="auto",
leaf_size=30,
metric="minkowski",
p=2,
metric_params=None,
n_jobs=None,
):
self.n_neighbors = n_neighbors
self.radius = radius
self.algorithm = algorithm
self.leaf_size = leaf_size
self.metric = metric
self.metric_params = metric_params
self.p = p
self.n_jobs = n_jobs
def _check_algorithm_metric(self):
if self.algorithm not in ["auto", "brute", "kd_tree", "ball_tree"]:
raise ValueError("unrecognized algorithm: '%s'" % self.algorithm)
if self.algorithm == "auto":
if self.metric == "precomputed":
alg_check = "brute"
elif callable(self.metric) or self.metric in VALID_METRICS["ball_tree"]:
alg_check = "ball_tree"
else:
alg_check = "brute"
else:
alg_check = self.algorithm
if callable(self.metric):
if self.algorithm == "kd_tree":
# callable metric is only valid for brute force and ball_tree
raise ValueError(
"kd_tree does not support callable metric '%s'"
"Function call overhead will result"
"in very poor performance."
% self.metric
)
elif self.metric not in VALID_METRICS[alg_check]:
raise ValueError(
"Metric '%s' not valid. Use "
"sorted(sklearn.neighbors.VALID_METRICS['%s']) "
"to get valid options. "
"Metric can also be a callable function." % (self.metric, alg_check)
)
if self.metric_params is not None and "p" in self.metric_params:
if self.p is not None:
warnings.warn(
"Parameter p is found in metric_params. "
"The corresponding parameter from __init__ "
"is ignored.",
SyntaxWarning,
stacklevel=3,
)
effective_p = self.metric_params["p"]
else:
effective_p = self.p
if self.metric in ["wminkowski", "minkowski"] and effective_p < 1:
raise ValueError("p must be greater or equal to one for minkowski metric")
def _fit(self, X, y=None):
if self._get_tags()["requires_y"]:
if not isinstance(X, (KDTree, BallTree, NeighborsBase)):
X, y = self._validate_data(X, y, accept_sparse="csr", multi_output=True)
if is_classifier(self):
# Classification targets require a specific format
if y.ndim == 1 or y.ndim == 2 and y.shape[1] == 1:
if y.ndim != 1:
warnings.warn(
"A column-vector y was passed when a "
"1d array was expected. Please change "
"the shape of y to (n_samples,), for "
"example using ravel().",
DataConversionWarning,
stacklevel=2,
)
self.outputs_2d_ = False
y = y.reshape((-1, 1))
else:
self.outputs_2d_ = True
check_classification_targets(y)
self.classes_ = []
self._y = np.empty(y.shape, dtype=int)
for k in range(self._y.shape[1]):
classes, self._y[:, k] = np.unique(y[:, k], return_inverse=True)
self.classes_.append(classes)
if not self.outputs_2d_:
self.classes_ = self.classes_[0]
self._y = self._y.ravel()
else:
self._y = y
else:
if not isinstance(X, (KDTree, BallTree, NeighborsBase)):
X = self._validate_data(X, accept_sparse="csr")
self._check_algorithm_metric()
if self.metric_params is None:
self.effective_metric_params_ = {}
else:
self.effective_metric_params_ = self.metric_params.copy()
effective_p = self.effective_metric_params_.get("p", self.p)
if self.metric in ["wminkowski", "minkowski"]:
self.effective_metric_params_["p"] = effective_p
self.effective_metric_ = self.metric
# For minkowski distance, use more efficient methods where available
if self.metric == "minkowski":
p = self.effective_metric_params_.pop("p", 2)
if p < 1:
raise ValueError(
"p must be greater or equal to one for minkowski metric"
)
elif p == 1:
self.effective_metric_ = "manhattan"
elif p == 2:
self.effective_metric_ = "euclidean"
elif p == np.inf:
self.effective_metric_ = "chebyshev"
else:
self.effective_metric_params_["p"] = p
if isinstance(X, NeighborsBase):
self._fit_X = X._fit_X
self._tree = X._tree
self._fit_method = X._fit_method
self.n_samples_fit_ = X.n_samples_fit_
return self
elif isinstance(X, BallTree):
self._fit_X = X.data
self._tree = X
self._fit_method = "ball_tree"
self.n_samples_fit_ = X.data.shape[0]
return self
elif isinstance(X, KDTree):
self._fit_X = X.data
self._tree = X
self._fit_method = "kd_tree"
self.n_samples_fit_ = X.data.shape[0]
return self
if self.metric == "precomputed":
X = _check_precomputed(X)
# Precomputed matrix X must be squared
if X.shape[0] != X.shape[1]:
raise ValueError(
"Precomputed matrix must be square."
" Input is a {}x{} matrix.".format(X.shape[0], X.shape[1])
)
self.n_features_in_ = X.shape[1]
n_samples = X.shape[0]
if n_samples == 0:
raise ValueError("n_samples must be greater than 0")
if issparse(X):
if self.algorithm not in ("auto", "brute"):
warnings.warn("cannot use tree with sparse input: using brute force")
if self.effective_metric_ not in VALID_METRICS_SPARSE[
"brute"
] and not callable(self.effective_metric_):
raise ValueError(
"Metric '%s' not valid for sparse input. "
"Use sorted(sklearn.neighbors."
"VALID_METRICS_SPARSE['brute']) "
"to get valid options. "
"Metric can also be a callable function." % (self.effective_metric_)
)
self._fit_X = X.copy()
self._tree = None
self._fit_method = "brute"
self.n_samples_fit_ = X.shape[0]
return self
self._fit_method = self.algorithm
self._fit_X = X
self.n_samples_fit_ = X.shape[0]
if self._fit_method == "auto":
# A tree approach is better for small number of neighbors or small
# number of features, with KDTree generally faster when available
if (
self.metric == "precomputed"
or self._fit_X.shape[1] > 15
or (
self.n_neighbors is not None
and self.n_neighbors >= self._fit_X.shape[0] // 2
)
):
self._fit_method = "brute"
else:
if self.effective_metric_ in VALID_METRICS["kd_tree"]:
self._fit_method = "kd_tree"
elif (
callable(self.effective_metric_)
or self.effective_metric_ in VALID_METRICS["ball_tree"]
):
self._fit_method = "ball_tree"
else:
self._fit_method = "brute"
if self._fit_method == "ball_tree":
self._tree = BallTree(
X,
self.leaf_size,
metric=self.effective_metric_,
**self.effective_metric_params_,
)
elif self._fit_method == "kd_tree":
self._tree = KDTree(
X,
self.leaf_size,
metric=self.effective_metric_,
**self.effective_metric_params_,
)
elif self._fit_method == "brute":
self._tree = None
else:
raise ValueError("algorithm = '%s' not recognized" % self.algorithm)
if self.n_neighbors is not None:
if self.n_neighbors <= 0:
raise ValueError("Expected n_neighbors > 0. Got %d" % self.n_neighbors)
elif not isinstance(self.n_neighbors, numbers.Integral):
raise TypeError(
"n_neighbors does not take %s value, enter integer value"
% type(self.n_neighbors)
)
return self
def _more_tags(self):
# For cross-validation routines to split data correctly
return {"pairwise": self.metric == "precomputed"}
# TODO: Remove in 1.1
# mypy error: Decorated property not supported
@deprecated( # type: ignore
"Attribute `_pairwise` was deprecated in "
"version 0.24 and will be removed in 1.1 (renaming of 0.26)."
)
@property
def _pairwise(self):
# For cross-validation routines to split data correctly
return self.metric == "precomputed"
def _tree_query_parallel_helper(tree, *args, **kwargs):
"""Helper for the Parallel calls in KNeighborsMixin.kneighbors.
The Cython method tree.query is not directly picklable by cloudpickle
under PyPy.
"""
return tree.query(*args, **kwargs)
class KNeighborsMixin:
"""Mixin for k-neighbors searches."""
def _kneighbors_reduce_func(self, dist, start, n_neighbors, return_distance):
"""Reduce a chunk of distances to the nearest neighbors.
Callback to :func:`sklearn.metrics.pairwise.pairwise_distances_chunked`
Parameters
----------
dist : ndarray of shape (n_samples_chunk, n_samples)
The distance matrix.
start : int
The index in X which the first row of dist corresponds to.
n_neighbors : int
Number of neighbors required for each sample.
return_distance : bool
Whether or not to return the distances.
Returns
-------
dist : array of shape (n_samples_chunk, n_neighbors)
Returned only if `return_distance=True`.
neigh : array of shape (n_samples_chunk, n_neighbors)
The neighbors indices.
"""
sample_range = np.arange(dist.shape[0])[:, None]
neigh_ind = np.argpartition(dist, n_neighbors - 1, axis=1)
neigh_ind = neigh_ind[:, :n_neighbors]
# argpartition doesn't guarantee sorted order, so we sort again
neigh_ind = neigh_ind[sample_range, np.argsort(dist[sample_range, neigh_ind])]
if return_distance:
if self.effective_metric_ == "euclidean":
result = np.sqrt(dist[sample_range, neigh_ind]), neigh_ind
else:
result = dist[sample_range, neigh_ind], neigh_ind
else:
result = neigh_ind
return result
def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
"""Find the K-neighbors of a point.
Returns indices of and distances to the neighbors of each point.
Parameters
----------
X : array-like, shape (n_queries, n_features), \
or (n_queries, n_indexed) if metric == 'precomputed', \
default=None
The query point or points.
If not provided, neighbors of each indexed point are returned.
In this case, the query point is not considered its own neighbor.
n_neighbors : int, default=None
Number of neighbors required for each sample. The default is the
value passed to the constructor.
return_distance : bool, default=True
Whether or not to return the distances.
Returns
-------
neigh_dist : ndarray of shape (n_queries, n_neighbors)
Array representing the lengths to points, only present if
return_distance=True.
neigh_ind : ndarray of shape (n_queries, n_neighbors)
Indices of the nearest points in the population matrix.
Examples
--------
In the following example, we construct a NearestNeighbors
class from an array representing our data set and ask who's
the closest point to [1,1,1]
>>> samples = [[0., 0., 0.], [0., .5, 0.], [1., 1., .5]]
>>> from sklearn.neighbors import NearestNeighbors
>>> neigh = NearestNeighbors(n_neighbors=1)
>>> neigh.fit(samples)
NearestNeighbors(n_neighbors=1)
>>> print(neigh.kneighbors([[1., 1., 1.]]))
(array([[0.5]]), array([[2]]))
As you can see, it returns [[0.5]], and [[2]], which means that the
element is at distance 0.5 and is the third element of samples
(indexes start at 0). You can also query for multiple points:
>>> X = [[0., 1., 0.], [1., 0., 1.]]
>>> neigh.kneighbors(X, return_distance=False)
array([[1],
[2]]...)
"""
check_is_fitted(self)
if n_neighbors is None:
n_neighbors = self.n_neighbors
elif n_neighbors <= 0:
raise ValueError("Expected n_neighbors > 0. Got %d" % n_neighbors)
elif not isinstance(n_neighbors, numbers.Integral):
raise TypeError(
"n_neighbors does not take %s value, enter integer value"
% type(n_neighbors)
)
if X is not None:
query_is_train = False
if self.metric == "precomputed":
X = _check_precomputed(X)
else:
X = self._validate_data(X, accept_sparse="csr", reset=False)
else:
query_is_train = True
X = self._fit_X
# Include an extra neighbor to account for the sample itself being
# returned, which is removed later
n_neighbors += 1
n_samples_fit = self.n_samples_fit_
if n_neighbors > n_samples_fit:
raise ValueError(
"Expected n_neighbors <= n_samples, "
" but n_samples = %d, n_neighbors = %d" % (n_samples_fit, n_neighbors)
)
n_jobs = effective_n_jobs(self.n_jobs)
chunked_results = None
if self._fit_method == "brute" and self.metric == "precomputed" and issparse(X):
results = _kneighbors_from_graph(
X, n_neighbors=n_neighbors, return_distance=return_distance
)
elif self._fit_method == "brute":
reduce_func = partial(
self._kneighbors_reduce_func,
n_neighbors=n_neighbors,
return_distance=return_distance,
)
# for efficiency, use squared euclidean distances
if self.effective_metric_ == "euclidean":
kwds = {"squared": True}
else:
kwds = self.effective_metric_params_
chunked_results = list(
pairwise_distances_chunked(
X,
self._fit_X,
reduce_func=reduce_func,
metric=self.effective_metric_,
n_jobs=n_jobs,
**kwds,
)
)
elif self._fit_method in ["ball_tree", "kd_tree"]:
if issparse(X):
raise ValueError(
"%s does not work with sparse matrices. Densify the data, "
"or set algorithm='brute'"
% self._fit_method
)
old_joblib = parse_version(joblib.__version__) < parse_version("0.12")
if old_joblib:
# Deal with change of API in joblib
parallel_kwargs = {"backend": "threading"}
else:
parallel_kwargs = {"prefer": "threads"}
chunked_results = Parallel(n_jobs, **parallel_kwargs)(
delayed(_tree_query_parallel_helper)(
self._tree, X[s], n_neighbors, return_distance
)
for s in gen_even_slices(X.shape[0], n_jobs)
)
else:
raise ValueError("internal: _fit_method not recognized")
if chunked_results is not None:
if return_distance:
neigh_dist, neigh_ind = zip(*chunked_results)
results = np.vstack(neigh_dist), np.vstack(neigh_ind)
else:
results = np.vstack(chunked_results)
if not query_is_train:
return results
else:
# If the query data is the same as the indexed data, we would like
# to ignore the first nearest neighbor of every sample, i.e
# the sample itself.
if return_distance:
neigh_dist, neigh_ind = results
else:
neigh_ind = results
n_queries, _ = X.shape
sample_range = np.arange(n_queries)[:, None]
sample_mask = neigh_ind != sample_range
# Corner case: When the number of duplicates are more
# than the number of neighbors, the first NN will not
# be the sample, but a duplicate.
# In that case mask the first duplicate.
dup_gr_nbrs = np.all(sample_mask, axis=1)
sample_mask[:, 0][dup_gr_nbrs] = False
neigh_ind = np.reshape(neigh_ind[sample_mask], (n_queries, n_neighbors - 1))
if return_distance:
neigh_dist = np.reshape(
neigh_dist[sample_mask], (n_queries, n_neighbors - 1)
)
return neigh_dist, neigh_ind
return neigh_ind
def kneighbors_graph(self, X=None, n_neighbors=None, mode="connectivity"):
"""Compute the (weighted) graph of k-Neighbors for points in X.
Parameters
----------
X : array-like of shape (n_queries, n_features), \
or (n_queries, n_indexed) if metric == 'precomputed', \
default=None
The query point or points.
If not provided, neighbors of each indexed point are returned.
In this case, the query point is not considered its own neighbor.
For ``metric='precomputed'`` the shape should be
(n_queries, n_indexed). Otherwise the shape should be
(n_queries, n_features).
n_neighbors : int, default=None
Number of neighbors for each sample. The default is the value
passed to the constructor.
mode : {'connectivity', 'distance'}, default='connectivity'
Type of returned matrix: 'connectivity' will return the
connectivity matrix with ones and zeros, in 'distance' the
edges are distances between points, type of distance
depends on the selected metric parameter in
NearestNeighbors class.
Returns
-------
A : sparse-matrix of shape (n_queries, n_samples_fit)
`n_samples_fit` is the number of samples in the fitted data.
`A[i, j]` gives the weight of the edge connecting `i` to `j`.
The matrix is of CSR format.
See Also
--------
NearestNeighbors.radius_neighbors_graph : Compute the (weighted) graph
of Neighbors for points in X.
Examples
--------
>>> X = [[0], [3], [1]]
>>> from sklearn.neighbors import NearestNeighbors
>>> neigh = NearestNeighbors(n_neighbors=2)
>>> neigh.fit(X)
NearestNeighbors(n_neighbors=2)
>>> A = neigh.kneighbors_graph(X)
>>> A.toarray()
array([[1., 0., 1.],
[0., 1., 1.],
[1., 0., 1.]])
"""
check_is_fitted(self)
if n_neighbors is None:
n_neighbors = self.n_neighbors
# check the input only in self.kneighbors
# construct CSR matrix representation of the k-NN graph
if mode == "connectivity":
A_ind = self.kneighbors(X, n_neighbors, return_distance=False)
n_queries = A_ind.shape[0]
A_data = np.ones(n_queries * n_neighbors)
elif mode == "distance":
A_data, A_ind = self.kneighbors(X, n_neighbors, return_distance=True)
A_data = np.ravel(A_data)
else:
raise ValueError(
'Unsupported mode, must be one of "connectivity" '
'or "distance" but got "%s" instead' % mode
)
n_queries = A_ind.shape[0]
n_samples_fit = self.n_samples_fit_
n_nonzero = n_queries * n_neighbors
A_indptr = np.arange(0, n_nonzero + 1, n_neighbors)
kneighbors_graph = csr_matrix(
(A_data, A_ind.ravel(), A_indptr), shape=(n_queries, n_samples_fit)
)
return kneighbors_graph
def _tree_query_radius_parallel_helper(tree, *args, **kwargs):
"""Helper for the Parallel calls in RadiusNeighborsMixin.radius_neighbors.
The Cython method tree.query_radius is not directly picklable by
cloudpickle under PyPy.
"""
return tree.query_radius(*args, **kwargs)
class RadiusNeighborsMixin:
"""Mixin for radius-based neighbors searches."""
def _radius_neighbors_reduce_func(self, dist, start, radius, return_distance):
"""Reduce a chunk of distances to the nearest neighbors.
Callback to :func:`sklearn.metrics.pairwise.pairwise_distances_chunked`
Parameters
----------
dist : ndarray of shape (n_samples_chunk, n_samples)
The distance matrix.
start : int
The index in X which the first row of dist corresponds to.
radius : float
The radius considered when making the nearest neighbors search.
return_distance : bool
Whether or not to return the distances.
Returns
-------
dist : list of ndarray of shape (n_samples_chunk,)
Returned only if `return_distance=True`.
neigh : list of ndarray of shape (n_samples_chunk,)
The neighbors indices.
"""
neigh_ind = [np.where(d <= radius)[0] for d in dist]
if return_distance:
if self.effective_metric_ == "euclidean":
dist = [np.sqrt(d[neigh_ind[i]]) for i, d in enumerate(dist)]
else:
dist = [d[neigh_ind[i]] for i, d in enumerate(dist)]
results = dist, neigh_ind
else:
results = neigh_ind
return results
def radius_neighbors(
self, X=None, radius=None, return_distance=True, sort_results=False
):
"""Find the neighbors within a given radius of a point or points.
Return the indices and distances of each point from the dataset
lying in a ball with size ``radius`` around the points of the query
array. Points lying on the boundary are included in the results.
The result points are *not* necessarily sorted by distance to their
query point.
Parameters
----------
X : array-like of (n_samples, n_features), default=None
The query point or points.
If not provided, neighbors of each indexed point are returned.
In this case, the query point is not considered its own neighbor.
radius : float, default=None
Limiting distance of neighbors to return. The default is the value
passed to the constructor.
return_distance : bool, default=True
Whether or not to return the distances.
sort_results : bool, default=False
If True, the distances and indices will be sorted by increasing
distances before being returned. If False, the results may not
be sorted. If `return_distance=False`, setting `sort_results=True`
will result in an error.
.. versionadded:: 0.22
Returns
-------
neigh_dist : ndarray of shape (n_samples,) of arrays
Array representing the distances to each point, only present if
`return_distance=True`. The distance values are computed according
to the ``metric`` constructor parameter.
neigh_ind : ndarray of shape (n_samples,) of arrays
An array of arrays of indices of the approximate nearest points
from the population matrix that lie within a ball of size
``radius`` around the query points.