|
1
|
|
|
"""!
|
|
2
|
|
|
|
|
3
|
|
|
@brief Cluster analysis algorithm: SOM-SC (Self-Organized Feature Map for Simple Clustering)
|
|
4
|
|
|
@details Based on article description:
|
|
5
|
|
|
- no reference
|
|
6
|
|
|
|
|
7
|
|
|
@authors Andrei Novikov ([email protected])
|
|
8
|
|
|
@date 2014-2017
|
|
9
|
|
|
@copyright GNU Public License
|
|
10
|
|
|
|
|
11
|
|
|
@cond GNU_PUBLIC_LICENSE
|
|
12
|
|
|
PyClustering is free software: you can redistribute it and/or modify
|
|
13
|
|
|
it under the terms of the GNU General Public License as published by
|
|
14
|
|
|
the Free Software Foundation, either version 3 of the License, or
|
|
15
|
|
|
(at your option) any later version.
|
|
16
|
|
|
|
|
17
|
|
|
PyClustering is distributed in the hope that it will be useful,
|
|
18
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
19
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
20
|
|
|
GNU General Public License for more details.
|
|
21
|
|
|
|
|
22
|
|
|
You should have received a copy of the GNU General Public License
|
|
23
|
|
|
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
24
|
|
|
@endcond
|
|
25
|
|
|
|
|
26
|
|
|
"""
|
|
27
|
|
|
|
|
28
|
|
|
|
|
29
|
|
|
from pyclustering.cluster.encoder import type_encoding;
|
|
30
|
|
|
|
|
31
|
|
|
from pyclustering.nnet.som import som;
|
|
32
|
|
|
from pyclustering.nnet.som import type_conn;
|
|
33
|
|
|
|
|
34
|
|
|
|
|
35
|
|
|
class somsc:
|
|
36
|
|
|
"""!
|
|
37
|
|
|
@brief Class represents simple clustering algorithm based on self-organized feature map.
|
|
38
|
|
|
@details This algorithm uses amount of clusters that should be allocated as a size of SOM map. Captured objects by neurons are clusters.
|
|
39
|
|
|
Algorithm is able to process data with Gaussian distribution that has spherical forms.
|
|
40
|
|
|
|
|
41
|
|
|
Example:
|
|
42
|
|
|
@code
|
|
43
|
|
|
# load list of points for cluster analysis
|
|
44
|
|
|
sample = read_sample(path);
|
|
45
|
|
|
|
|
46
|
|
|
# create instance of SOM-SC algorithm to allocated two clusters
|
|
47
|
|
|
somsc_instance = somsc(sample, 2);
|
|
48
|
|
|
|
|
49
|
|
|
# run cluster analysis and obtain results
|
|
50
|
|
|
somsc_instance.process();
|
|
51
|
|
|
somsc_instance.get_clusters();
|
|
52
|
|
|
@endcode
|
|
53
|
|
|
"""
|
|
54
|
|
|
def __init__(self, data, amount_clusters, epouch = 100, ccore = False):
|
|
55
|
|
|
|
|
56
|
|
|
self.__data_pointer = data;
|
|
57
|
|
|
self.__amount_clusters = amount_clusters;
|
|
58
|
|
|
self.__epouch = epouch;
|
|
59
|
|
|
self.__ccore = ccore;
|
|
60
|
|
|
|
|
61
|
|
|
self.__network = None;
|
|
62
|
|
|
|
|
63
|
|
|
|
|
64
|
|
|
def process(self):
|
|
65
|
|
|
"""!
|
|
66
|
|
|
@brief Performs cluster analysis by competition between neurons of SOM.
|
|
67
|
|
|
|
|
68
|
|
|
@remark Results of clustering can be obtained using corresponding get methods.
|
|
69
|
|
|
|
|
70
|
|
|
@see get_clusters()
|
|
71
|
|
|
|
|
72
|
|
|
"""
|
|
73
|
|
|
|
|
74
|
|
|
self.__network = som(1, self.__amount_clusters, type_conn.grid_four, None, self.__ccore);
|
|
75
|
|
|
self.__network.train(self.__data_pointer, self.__epouch, True);
|
|
76
|
|
|
|
|
77
|
|
|
|
|
78
|
|
|
def get_clusters(self):
|
|
79
|
|
|
"""!
|
|
80
|
|
|
@brief Returns list of allocated clusters, each cluster contains indexes of objects in list of data.
|
|
81
|
|
|
|
|
82
|
|
|
@see process()
|
|
83
|
|
|
|
|
84
|
|
|
"""
|
|
85
|
|
|
|
|
86
|
|
|
return self.__network.capture_objects;
|
|
87
|
|
|
|
|
88
|
|
|
|
|
89
|
|
|
def get_cluster_encoding(self):
|
|
90
|
|
|
"""!
|
|
91
|
|
|
@brief Returns clustering result representation type that indicate how clusters are encoded.
|
|
92
|
|
|
|
|
93
|
|
|
@return (type_encoding) Clustering result representation.
|
|
94
|
|
|
|
|
95
|
|
|
@see get_clusters()
|
|
96
|
|
|
|
|
97
|
|
|
"""
|
|
98
|
|
|
|
|
99
|
|
|
return type_encoding.CLUSTER_INDEX_LIST_SEPARATION;
|
|
100
|
|
|
|
annoviko /
pyclustering
