/usr/share/pyshared/mlpy/_kmeans.py is in python-mlpy 2.2.0~dfsg1-2.
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 | """
k-means algorithm.
"""
## This code is written by Davide Albanese, <albanese@fbk.eu>
## (C) 2010 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/>.
__all__= ['Kmeans']
import numpy as np
import kmeanscore
class Kmeans(object):
"""k-means algorithm.
"""
def __init__(self, k, init="std", seed=0):
"""Initialization.
:Parameters:
k : int (>1)
number of clusters
init : string ('std', 'plus')
initialization algorithm
* 'std' : randomly selected
* 'plus' : k-means++ algorithm
seed : int (>=0)
random seed
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]])
>>> kmeans = mlpy.Kmeans(k=3, init="plus", seed=0)
>>> kmeans.compute(x)
array([1, 1, 2, 0, 0], dtype=int32)
>>> kmeans.means
array([[ 3.3 , 3.15],
[ 1.05, 1.65],
[ 2. , 2.8 ]])
>>> kmeans.steps
2
"""
self.INIT = {
'std': 0,
'plus': 1,
}
self.__k = k
self.__init = init
self.__seed = seed
self.means = None
self.steps = None
def compute(self, x):
"""Compute Kmeans.
:Parameters:
x : ndarray
an 2-dimensional vector (number of points x dimensions)
:Returns:
cls : ndarray (1-dimensional vector)
cluster membership. Clusters are in 0, ..., k-1
:Attributes:
Kmeans.means : 2d ndarray float (k x dim)
means
Kmeans.steps : int
number of steps
"""
cls, self.means, self.steps = kmeanscore.kmeans(
x, self.__k, self.INIT[self.__init], self.__seed)
return cls
|