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
|
# -*- coding: utf-8 -*-
"""
Nearest Centroid Classification
"""
# Author: Robert Layton <robertlayton@gmail.com>
# Olivier Grisel <olivier.grisel@ensta.org>
#
# License: BSD 3 clause
import warnings
import numpy as np
from scipy import sparse as sp
from ..base import BaseEstimator, ClassifierMixin
from ..metrics.pairwise import pairwise_distances
from ..preprocessing import LabelEncoder
from ..utils.validation import check_array, check_X_y, check_is_fitted
from ..utils.sparsefuncs import csc_median_axis_0
from ..utils.multiclass import check_classification_targets
class NearestCentroid(BaseEstimator, ClassifierMixin):
"""Nearest centroid classifier.
Each class is represented by its centroid, with test samples classified to
the class with the nearest centroid.
Read more in the :ref:`User Guide <nearest_centroid_classifier>`.
Parameters
----------
metric : string, or callable
The metric to use when calculating distance between instances in a
feature array. If metric is a string or callable, it must be one of
the options allowed by metrics.pairwise.pairwise_distances for its
metric parameter.
The centroids for the samples corresponding to each class is the point
from which the sum of the distances (according to the metric) of all
samples that belong to that particular class are minimized.
If the "manhattan" metric is provided, this centroid is the median and
for all other metrics, the centroid is now set to be the mean.
shrink_threshold : float, optional (default = None)
Threshold for shrinking centroids to remove features.
Attributes
----------
centroids_ : array-like, shape = [n_classes, n_features]
Centroid of each class
Examples
--------
>>> from sklearn.neighbors.nearest_centroid import NearestCentroid
>>> import numpy as np
>>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
>>> y = np.array([1, 1, 1, 2, 2, 2])
>>> clf = NearestCentroid()
>>> clf.fit(X, y)
NearestCentroid(metric='euclidean', shrink_threshold=None)
>>> print(clf.predict([[-0.8, -1]]))
[1]
See also
--------
sklearn.neighbors.KNeighborsClassifier: nearest neighbors classifier
Notes
-----
When used for text classification with tf-idf vectors, this classifier is
also known as the Rocchio classifier.
References
----------
Tibshirani, R., Hastie, T., Narasimhan, B., & Chu, G. (2002). Diagnosis of
multiple cancer types by shrunken centroids of gene expression. Proceedings
of the National Academy of Sciences of the United States of America,
99(10), 6567-6572. The National Academy of Sciences.
"""
def __init__(self, metric='euclidean', shrink_threshold=None):
self.metric = metric
self.shrink_threshold = shrink_threshold
def fit(self, X, y):
"""
Fit the NearestCentroid model according to the given training data.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Training vector, where n_samples is the number of samples and
n_features is the number of features.
Note that centroid shrinking cannot be used with sparse matrices.
y : array, shape = [n_samples]
Target values (integers)
"""
if self.metric == 'precomputed':
raise ValueError("Precomputed is not supported.")
# If X is sparse and the metric is "manhattan", store it in a csc
# format is easier to calculate the median.
if self.metric == 'manhattan':
X, y = check_X_y(X, y, ['csc'])
else:
X, y = check_X_y(X, y, ['csr', 'csc'])
is_X_sparse = sp.issparse(X)
if is_X_sparse and self.shrink_threshold:
raise ValueError("threshold shrinking not supported"
" for sparse input")
check_classification_targets(y)
n_samples, n_features = X.shape
le = LabelEncoder()
y_ind = le.fit_transform(y)
self.classes_ = classes = le.classes_
n_classes = classes.size
if n_classes < 2:
raise ValueError('The number of classes has to be greater than'
' one; got %d class' % (n_classes))
# Mask mapping each class to its members.
self.centroids_ = np.empty((n_classes, n_features), dtype=np.float64)
# Number of clusters in each class.
nk = np.zeros(n_classes)
for cur_class in range(n_classes):
center_mask = y_ind == cur_class
nk[cur_class] = np.sum(center_mask)
if is_X_sparse:
center_mask = np.where(center_mask)[0]
# XXX: Update other averaging methods according to the metrics.
if self.metric == "manhattan":
# NumPy does not calculate median of sparse matrices.
if not is_X_sparse:
self.centroids_[cur_class] = np.median(X[center_mask], axis=0)
else:
self.centroids_[cur_class] = csc_median_axis_0(X[center_mask])
else:
if self.metric != 'euclidean':
warnings.warn("Averaging for metrics other than "
"euclidean and manhattan not supported. "
"The average is set to be the mean."
)
self.centroids_[cur_class] = X[center_mask].mean(axis=0)
if self.shrink_threshold:
dataset_centroid_ = np.mean(X, axis=0)
# m parameter for determining deviation
m = np.sqrt((1. / nk) - (1. / n_samples))
# Calculate deviation using the standard deviation of centroids.
variance = (X - self.centroids_[y_ind]) ** 2
variance = variance.sum(axis=0)
s = np.sqrt(variance / (n_samples - n_classes))
s += np.median(s) # To deter outliers from affecting the results.
mm = m.reshape(len(m), 1) # Reshape to allow broadcasting.
ms = mm * s
deviation = ((self.centroids_ - dataset_centroid_) / ms)
# Soft thresholding: if the deviation crosses 0 during shrinking,
# it becomes zero.
signs = np.sign(deviation)
deviation = (np.abs(deviation) - self.shrink_threshold)
np.clip(deviation, 0, None, out=deviation)
deviation *= signs
# Now adjust the centroids using the deviation
msd = ms * deviation
self.centroids_ = dataset_centroid_[np.newaxis, :] + msd
return self
def predict(self, X):
"""Perform classification on an array of test vectors X.
The predicted class C for each sample in X is returned.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
C : array, shape = [n_samples]
Notes
-----
If the metric constructor parameter is "precomputed", X is assumed to
be the distance matrix between the data to be predicted and
``self.centroids_``.
"""
check_is_fitted(self, 'centroids_')
X = check_array(X, accept_sparse='csr')
return self.classes_[pairwise_distances(
X, self.centroids_, metric=self.metric).argmin(axis=1)]
|
