-
-
Notifications
You must be signed in to change notification settings - Fork 25.1k
/
_regression.py
510 lines (410 loc) · 17.7 KB
/
_regression.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
"""Nearest Neighbor Regression."""
# 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>
# Empty radius support by Andreas Bjerre-Nielsen
#
# License: BSD 3 clause (C) INRIA, University of Amsterdam,
# University of Copenhagen
import warnings
import numpy as np
from ..base import RegressorMixin, _fit_context
from ..metrics import DistanceMetric
from ..utils._param_validation import StrOptions
from ._base import KNeighborsMixin, NeighborsBase, RadiusNeighborsMixin, _get_weights
class KNeighborsRegressor(KNeighborsMixin, RegressorMixin, NeighborsBase):
"""Regression based on k-nearest neighbors.
The target is predicted by local interpolation of the targets
associated of the nearest neighbors in the training set.
Read more in the :ref:`User Guide <regression>`.
.. versionadded:: 0.9
Parameters
----------
n_neighbors : int, default=5
Number of neighbors to use by default for :meth:`kneighbors` queries.
weights : {'uniform', 'distance'}, callable or None, default='uniform'
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'}, 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.
p : float, default=2
Power parameter for the Minkowski metric. 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 : str, DistanceMetric object or callable, default='minkowski'
Metric to use for distance computation. Default is "minkowski", which
results in the standard Euclidean distance when p = 2. See the
documentation of `scipy.spatial.distance
<https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
the metrics listed in
:class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
values.
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.
If metric is a callable function, it takes two arrays representing 1D
vectors as inputs and must return one value indicating the distance
between those vectors. This works for Scipy's metrics, but is less
efficient than passing the metric name as a string.
If metric is a DistanceMetric object, it will be passed directly to
the underlying computation routines.
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.
Doesn't affect :meth:`fit` method.
Attributes
----------
effective_metric_ : str or callable
The distance metric to use. It will be same as the `metric` parameter
or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
'minkowski' and `p` parameter set to 2.
effective_metric_params_ : dict
Additional keyword arguments for the metric function. For most metrics
will be same with `metric_params` parameter, but may also contain the
`p` parameter value if the `effective_metric_` attribute is set to
'minkowski'.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
n_samples_fit_ : int
Number of samples in the fitted data.
See Also
--------
NearestNeighbors : Unsupervised learner for implementing neighbor searches.
RadiusNeighborsRegressor : Regression based on neighbors within a fixed radius.
KNeighborsClassifier : Classifier implementing the k-nearest neighbors vote.
RadiusNeighborsClassifier : Classifier implementing
a vote among neighbors within a given radius.
Notes
-----
See :ref:`Nearest Neighbors <neighbors>` in the online documentation
for a discussion of the choice of ``algorithm`` and ``leaf_size``.
.. warning::
Regarding the Nearest Neighbors algorithms, if it is found that two
neighbors, neighbor `k+1` and `k`, have identical distances but
different labels, the results will depend on the ordering of the
training data.
https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm
Examples
--------
>>> X = [[0], [1], [2], [3]]
>>> y = [0, 0, 1, 1]
>>> from sklearn.neighbors import KNeighborsRegressor
>>> neigh = KNeighborsRegressor(n_neighbors=2)
>>> neigh.fit(X, y)
KNeighborsRegressor(...)
>>> print(neigh.predict([[1.5]]))
[0.5]
"""
_parameter_constraints: dict = {
**NeighborsBase._parameter_constraints,
"weights": [StrOptions({"uniform", "distance"}), callable, None],
}
_parameter_constraints["metric"].append(DistanceMetric)
_parameter_constraints.pop("radius")
def __init__(
self,
n_neighbors=5,
*,
weights="uniform",
algorithm="auto",
leaf_size=30,
p=2,
metric="minkowski",
metric_params=None,
n_jobs=None,
):
super().__init__(
n_neighbors=n_neighbors,
algorithm=algorithm,
leaf_size=leaf_size,
metric=metric,
p=p,
metric_params=metric_params,
n_jobs=n_jobs,
)
self.weights = weights
def _more_tags(self):
# For cross-validation routines to split data correctly
return {"pairwise": self.metric == "precomputed"}
@_fit_context(
# KNeighborsRegressor.metric is not validated yet
prefer_skip_nested_validation=False
)
def fit(self, X, y):
"""Fit the k-nearest neighbors regressor from the training dataset.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
(n_samples, n_samples) if metric='precomputed'
Training data.
y : {array-like, sparse matrix} of shape (n_samples,) or \
(n_samples, n_outputs)
Target values.
Returns
-------
self : KNeighborsRegressor
The fitted k-nearest neighbors regressor.
"""
return self._fit(X, y)
def predict(self, X):
"""Predict the target for the provided data.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_queries, n_features), \
or (n_queries, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
y : ndarray of shape (n_queries,) or (n_queries, n_outputs), dtype=int
Target values.
"""
if self.weights == "uniform":
# In that case, we do not need the distances to perform
# the weighting so we do not compute them.
neigh_ind = self.kneighbors(X, return_distance=False)
neigh_dist = None
else:
neigh_dist, neigh_ind = self.kneighbors(X)
weights = _get_weights(neigh_dist, self.weights)
_y = self._y
if _y.ndim == 1:
_y = _y.reshape((-1, 1))
if weights is None:
y_pred = np.mean(_y[neigh_ind], axis=1)
else:
y_pred = np.empty((neigh_dist.shape[0], _y.shape[1]), dtype=np.float64)
denom = np.sum(weights, axis=1)
for j in range(_y.shape[1]):
num = np.sum(_y[neigh_ind, j] * weights, axis=1)
y_pred[:, j] = num / denom
if self._y.ndim == 1:
y_pred = y_pred.ravel()
return y_pred
class RadiusNeighborsRegressor(RadiusNeighborsMixin, RegressorMixin, NeighborsBase):
"""Regression based on neighbors within a fixed radius.
The target is predicted by local interpolation of the targets
associated of the nearest neighbors in the training set.
Read more in the :ref:`User Guide <regression>`.
.. versionadded:: 0.9
Parameters
----------
radius : float, default=1.0
Range of parameter space to use by default for :meth:`radius_neighbors`
queries.
weights : {'uniform', 'distance'}, callable or None, default='uniform'
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'}, 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.
p : float, default=2
Power parameter for the Minkowski metric. 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 : str or callable, default='minkowski'
Metric to use for distance computation. Default is "minkowski", which
results in the standard Euclidean distance when p = 2. See the
documentation of `scipy.spatial.distance
<https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
the metrics listed in
:class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
values.
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.
If metric is a callable function, it takes two arrays representing 1D
vectors as inputs and must return one value indicating the distance
between those vectors. This works for Scipy's metrics, but is less
efficient than passing the metric name as a string.
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 or callable
The distance metric to use. It will be same as the `metric` parameter
or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
'minkowski' and `p` parameter set to 2.
effective_metric_params_ : dict
Additional keyword arguments for the metric function. For most metrics
will be same with `metric_params` parameter, but may also contain the
`p` parameter value if the `effective_metric_` attribute is set to
'minkowski'.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
n_samples_fit_ : int
Number of samples in the fitted data.
See Also
--------
NearestNeighbors : Unsupervised learner for implementing neighbor searches.
KNeighborsRegressor : Regression based on k-nearest neighbors.
KNeighborsClassifier : Classifier based on the k-nearest neighbors.
RadiusNeighborsClassifier : Classifier based on neighbors within a given radius.
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
Examples
--------
>>> X = [[0], [1], [2], [3]]
>>> y = [0, 0, 1, 1]
>>> from sklearn.neighbors import RadiusNeighborsRegressor
>>> neigh = RadiusNeighborsRegressor(radius=1.0)
>>> neigh.fit(X, y)
RadiusNeighborsRegressor(...)
>>> print(neigh.predict([[1.5]]))
[0.5]
"""
_parameter_constraints: dict = {
**NeighborsBase._parameter_constraints,
"weights": [StrOptions({"uniform", "distance"}), callable, None],
}
_parameter_constraints.pop("n_neighbors")
def __init__(
self,
radius=1.0,
*,
weights="uniform",
algorithm="auto",
leaf_size=30,
p=2,
metric="minkowski",
metric_params=None,
n_jobs=None,
):
super().__init__(
radius=radius,
algorithm=algorithm,
leaf_size=leaf_size,
p=p,
metric=metric,
metric_params=metric_params,
n_jobs=n_jobs,
)
self.weights = weights
@_fit_context(
# RadiusNeighborsRegressor.metric is not validated yet
prefer_skip_nested_validation=False
)
def fit(self, X, y):
"""Fit the radius neighbors regressor from the training dataset.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
(n_samples, n_samples) if metric='precomputed'
Training data.
y : {array-like, sparse matrix} of shape (n_samples,) or \
(n_samples, n_outputs)
Target values.
Returns
-------
self : RadiusNeighborsRegressor
The fitted radius neighbors regressor.
"""
return self._fit(X, y)
def predict(self, X):
"""Predict the target for the provided data.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_queries, n_features), \
or (n_queries, n_indexed) if metric == 'precomputed'
Test samples.
Returns
-------
y : ndarray of shape (n_queries,) or (n_queries, n_outputs), \
dtype=double
Target values.
"""
neigh_dist, neigh_ind = self.radius_neighbors(X)
weights = _get_weights(neigh_dist, self.weights)
_y = self._y
if _y.ndim == 1:
_y = _y.reshape((-1, 1))
empty_obs = np.full_like(_y[0], np.nan)
if weights is None:
y_pred = np.array(
[
np.mean(_y[ind, :], axis=0) if len(ind) else empty_obs
for (i, ind) in enumerate(neigh_ind)
]
)
else:
y_pred = np.array(
[
(
np.average(_y[ind, :], axis=0, weights=weights[i])
if len(ind)
else empty_obs
)
for (i, ind) in enumerate(neigh_ind)
]
)
if np.any(np.isnan(y_pred)):
empty_warning_msg = (
"One or more samples have no neighbors "
"within specified radius; predicting NaN."
)
warnings.warn(empty_warning_msg)
if self._y.ndim == 1:
y_pred = y_pred.ravel()
return y_pred