forked from scikit-learn/scikit-learn
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathunsupervised.py
214 lines (167 loc) · 7.91 KB
/
unsupervised.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
""" Unsupervised evaluation metrics. """
# Authors: Robert Layton <[email protected]>
#
# License: BSD 3 clause
import numpy as np
from ...utils import check_random_state
from ..pairwise import pairwise_distances
def silhouette_score(X, labels, metric='euclidean', sample_size=None,
random_state=None, **kwds):
"""Compute the mean Silhouette Coefficient of all samples.
The Silhouette Coefficient is calculated using the mean intra-cluster
distance (``a``) and the mean nearest-cluster distance (``b``) for each
sample. The Silhouette Coefficient for a sample is ``(b - a) / max(a,
b)``. To clarify, ``b`` is the distance between a sample and the nearest
cluster that the sample is not a part of.
Note that Silhouette Coefficent is only defined if number of labels
is 2 <= n_labels <= n_samples - 1.
This function returns the mean Silhouette Coefficient over all samples.
To obtain the values for each sample, use :func:`silhouette_samples`.
The best value is 1 and the worst value is -1. Values near 0 indicate
overlapping clusters. Negative values generally indicate that a sample has
been assigned to the wrong cluster, as a different cluster is more similar.
Parameters
----------
X : array [n_samples_a, n_samples_a] if metric == "precomputed", or, \
[n_samples_a, n_features] otherwise
Array of pairwise distances between samples, or a feature array.
labels : array, shape = [n_samples]
label values for each sample
metric : string, or callable
The metric to use when calculating distance between instances in a
feature array. If metric is a string, it must be one of the options
allowed by :func:`metrics.pairwise.pairwise_distances
<sklearn.metrics.pairwise.pairwise_distances>`. If X is the distance
array itself, use ``metric="precomputed"``.
sample_size : int or None
The size of the sample to use when computing the Silhouette
Coefficient. If ``sample_size is None``, no sampling is used.
random_state : integer or numpy.RandomState, optional
The generator used to initialize the centers. If an integer is
given, it fixes the seed. Defaults to the global numpy random
number generator.
`**kwds` : optional keyword parameters
Any further parameters are passed directly to the distance function.
If using a scipy.spatial.distance metric, the parameters are still
metric dependent. See the scipy docs for usage examples.
Returns
-------
silhouette : float
Mean Silhouette Coefficient for all samples.
References
----------
.. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the
Interpretation and Validation of Cluster Analysis". Computational
and Applied Mathematics 20: 53-65.
<http://www.sciencedirect.com/science/article/pii/0377042787901257>`_
.. [2] `Wikipedia entry on the Silhouette Coefficient
<http://en.wikipedia.org/wiki/Silhouette_(clustering)>`_
"""
n_labels = len(np.unique(labels))
n_samples = X.shape[0]
if not 2 <= n_labels <= n_samples-1:
raise ValueError("Number of labels is %d "
"but should be more than 2"
"and less than n_samples - 1" % n_labels)
if sample_size is not None:
random_state = check_random_state(random_state)
indices = random_state.permutation(X.shape[0])[:sample_size]
if metric == "precomputed":
X, labels = X[indices].T[indices].T, labels[indices]
else:
X, labels = X[indices], labels[indices]
return np.mean(silhouette_samples(X, labels, metric=metric, **kwds))
def silhouette_samples(X, labels, metric='euclidean', **kwds):
"""Compute the Silhouette Coefficient for each sample.
The Silhoeutte Coefficient is a measure of how well samples are clustered
with samples that are similar to themselves. Clustering models with a high
Silhouette Coefficient are said to be dense, where samples in the same
cluster are similar to each other, and well separated, where samples in
different clusters are not very similar to each other.
The Silhouette Coefficient is calculated using the mean intra-cluster
distance (``a``) and the mean nearest-cluster distance (``b``) for each
sample. The Silhouette Coefficient for a sample is ``(b - a) / max(a,
b)``.
Note that Silhouette Coefficent is only defined if number of labels
is 2 <= n_labels <= n_samples - 1.
This function returns the Silhouette Coefficient for each sample.
The best value is 1 and the worst value is -1. Values near 0 indicate
overlapping clusters.
Parameters
----------
X : array [n_samples_a, n_samples_a] if metric == "precomputed", or, \
[n_samples_a, n_features] otherwise
Array of pairwise distances between samples, or a feature array.
labels : array, shape = [n_samples]
label values for each sample
metric : string, or callable
The metric to use when calculating distance between instances in a
feature array. If metric is a string, it must be one of the options
allowed by :func:`sklearn.metrics.pairwise.pairwise_distances`. If X is
the distance array itself, use "precomputed" as the metric.
`**kwds` : optional keyword parameters
Any further parameters are passed directly to the distance function.
If using a ``scipy.spatial.distance`` metric, the parameters are still
metric dependent. See the scipy docs for usage examples.
Returns
-------
silhouette : array, shape = [n_samples]
Silhouette Coefficient for each samples.
References
----------
.. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the
Interpretation and Validation of Cluster Analysis". Computational
and Applied Mathematics 20: 53-65.
<http://www.sciencedirect.com/science/article/pii/0377042787901257>`_
.. [2] `Wikipedia entry on the Silhouette Coefficient
<http://en.wikipedia.org/wiki/Silhouette_(clustering)>`_
"""
distances = pairwise_distances(X, metric=metric, **kwds)
n = labels.shape[0]
A = np.array([_intra_cluster_distance(distances[i], labels, i)
for i in range(n)])
B = np.array([_nearest_cluster_distance(distances[i], labels, i)
for i in range(n)])
sil_samples = (B - A) / np.maximum(A, B)
# nan values are for clusters of size 1, and should be 0
return np.nan_to_num(sil_samples)
def _intra_cluster_distance(distances_row, labels, i):
"""Calculate the mean intra-cluster distance for sample i.
Parameters
----------
distances_row : array, shape = [n_samples]
Pairwise distance matrix between sample i and each sample.
labels : array, shape = [n_samples]
label values for each sample
i : int
Sample index being calculated. It is excluded from calculation and
used to determine the current label
Returns
-------
a : float
Mean intra-cluster distance for sample i
"""
mask = labels == labels[i]
mask[i] = False
a = np.mean(distances_row[mask])
return a
def _nearest_cluster_distance(distances_row, labels, i):
"""Calculate the mean nearest-cluster distance for sample i.
Parameters
----------
distances_row : array, shape = [n_samples]
Pairwise distance matrix between sample i and each sample.
labels : array, shape = [n_samples]
label values for each sample
i : int
Sample index being calculated. It is used to determine the current
label.
Returns
-------
b : float
Mean nearest-cluster distance for sample i
"""
label = labels[i]
b = np.min([np.mean(distances_row[labels == cur_label])
for cur_label in set(labels) if not cur_label == label])
return b