Repository navigation
Expand file tree
/
Copy pathbase.py
More file actions
69 lines (58 loc) · 2.65 KB
/
Copy pathbase.py
File metadata and controls
69 lines (58 loc) · 2.65 KB
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
#
# This is part of "python-cluster". A library to group similar items together.
# Copyright (C) 2006 Michel Albert
#
# This library is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by the
# Free Software Foundation; either version 2.1 of the License, or (at your
# option) any later version.
# This library is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License
# for more details.
# You should have received a copy of the GNU Lesser General Public License
# along with this library; if not, write to the Free Software Foundation,
# Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
class BaseClusterMethod(object):
"""
The base class of all clustering methods.
:param input: a list of objects
:distance_function: a function returning the distance - or opposite of
similarity ``(distance = -similarity)`` - of two items from the input.
In other words, the closer the two items are related, the smaller this
value needs to be. With 0 meaning they are exactly the same.
.. note::
The distance function should always return the absolute distance between
two given items of the list. Say::
distance(input[1], input[4]) = distance(input[4], input[1])
This is very important for the clustering algorithm to work! Naturally,
the data returned by the distance function MUST be a comparable
datatype, so you can perform arithmetic comparisons on them (``<`` or
``>``)! The simplest examples would be floats or ints. But as long as
they are comparable, it's ok.
"""
def __init__(self, input, distance_function, progress_callback=None):
self.distance = distance_function
self._input = input # the original input
self._data = input[:] # clone the input so we can work with it
# without distroying the original data.
self.progress_callback = progress_callback
def topo(self):
"""
Returns the structure (topology) of the cluster.
See :py:meth:`~cluster.cluster.Cluster.topology` for more information.
"""
return self.data[0].topology()
@property
def data(self):
"""
Returns the data that is currently in process.
"""
return self._data
@property
def raw_data(self):
"""
Returns the raw data (data without being clustered).
"""
return self._input