/usr/share/pyshared/mlpy/_hcluster.py is in python-mlpy 2.2.0~dfsg1-2.1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | ## This code is written by Davide Albanese, <albanese@fbk.eu>.
## (C) 2009 Fondazione Bruno Kessler - Via Santa Croce 77, 38100 Trento, ITALY.
## This program is free software: you can redistribute it and/or modify
## it under the terms of the GNU General Public License as published by
## the Free Software Foundation, either version 3 of the License, or
## (at your option) any later version.
## This program 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 General Public License for more details.
## You should have received a copy of the GNU General Public License
## along with this program. If not, see <http://www.gnu.org/licenses/>.
from numpy import *
import hccore
__all__ = ['HCluster']
class HCluster:
"""Hierarchical Cluster.
"""
def __init__ (self, method = 'euclidean', link = 'complete'):
"""Initialize Hierarchical Cluster.
:Parameters:
method : string ('euclidean')
the distance measure to be used
link : string ('single', 'complete', 'mcquitty', 'median')
the agglomeration method to be used
Example:
>>> import numpy as np
>>> import mlpy
>>> x = np.array([[ 1. , 1.5],
... [ 1.1, 1.8],
... [ 2. , 2.8],
... [ 3.2, 3.1],
... [ 3.4, 3.2]])
>>> hc = mlpy.HCluster()
>>> hc.compute(x)
>>> hc.ia
array([-4, -1, -3, 2])
>>> hc.ib
array([-5, -2, 1, 3])
>>> hc.heights
array([ 0.2236068 , 0.31622776, 1.4560219 , 2.94108844])
>>> hc.cut(0.5)
array([0, 0, 1, 2, 2])
"""
self.METHODS = {
'euclidean': 1,
}
self.LINKS = {
'single': 1,
'complete': 2,
'mcquitty': 3,
'median': 4,
}
self.method = method
self.link = link
self.__ia = None
self.__ib = None
self.__heights = None
self.ia = None
self.ib = None
self.heights = None
self.order = None
self.computed = False
def compute(self, x):
"""Compute Hierarchical Cluster.
:Parameters:
x : ndarray
An 2-dimensional vector (sample x features).
:Returns:
self.ia : ndarray (1-dimensional vector)
merge
self.ib : ndarray (1-dimensional vector)
merge
self.heights : ndarray (1-dimensional vector)
a set of n-1 non-decreasing real values.
The clustering height: that is, the value of the
criterion associated with the clustering method
for the particular agglomeration.
Element i of merge describes the merging of clusters at step i
of the clustering. If an element j is negative, then observation
-j was merged at this stage. If j is positive then the merge was
with the cluster formed at the (earlier) stage j of the algorithm.
Thus negative entries in merge indicate agglomerations of singletons,
and positive entries indicate agglomerations of non-singletons.
"""
if x.ndim != 2:
raise ValueError("x must be 2D array")
self.__ia, self.__ib, self.__heights, self.order = \
hccore.compute(x.T, self.METHODS[self.method], self.LINKS[self.link])
self.ia = self.__ia[:-1]
self.ib = self.__ib[:-1]
self.heights = self.__heights[:-1]
self.computed = True
def cut(self, ht):
"""Cuts the tree into several groups by specifying the cut
height.
:Parameters:
ht : float
height where the tree should be cut
:Returns:
cl : ndarray (1-dimensional vector)
group memberships. Groups are in 0, ..., N-1
"""
if self.computed == False:
raise ValueError("No hierarchical clustering computed")
return hccore.cut(self.__ia, self.__ib, self.__heights, ht) - 1
|