/usr/share/pyshared/mlpy/_knn.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | ## This file is part of mlpy.
## k-Nearest Neighbor (kNN) based on kNN
## C-libraries developed by Stefano Merler.
## This code is written by Davide Albanese, <albanese@fbk.eu>.
## (C) 2008 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__ = ['Knn']
from numpy import *
import nncore
class Knn:
"""
k-Nearest Neighbor (KNN).
Example:
>>> import numpy as np
>>> import mlpy
>>> xtr = np.array([[1.0, 2.0, 3.1, 1.0], # first sample
... [1.0, 2.0, 3.0, 2.0], # second sample
... [1.0, 2.0, 3.1, 1.0]]) # third sample
>>> ytr = np.array([1, -1, 1]) # classes
>>> myknn = mlpy.Knn(k = 1) # initialize knn class
>>> myknn.compute(xtr, ytr) # compute knn
1
>>> myknn.predict(xtr) # predict knn model on training data
array([ 1, -1, 1])
>>> xts = np.array([4.0, 5.0, 6.0, 7.0]) # test point
>>> myknn.predict(xts) # predict knn model on test point
-1
>>> myknn.realpred # real-valued prediction
0.0
"""
def __init__(self, k, dist = 'se'):
"""
Initialize the Knn class.
:Parameters:
k : int (odd > = 1)
number of NN
dist : string ('se' = SQUARED EUCLIDEAN, 'e' = EUCLIDEAN)
adopted distance
"""
DIST = {'se': 1, # DIST_SQUARED_EUCLIDEAN
'e': 2 # DIST_EUCLIDEAN
}
self.__k = int(k)
self.__dist = DIST[dist]
self.__x = None
self.__y = None
self.__classes = None
self.realpred = None
self.__computed = False
def compute(self, x, y):
"""
Store x and y data.
:Parameters:
x : 2d ndarray float (samples x feats)
training data
y : 1d ndarray integer (-1 or 1 for binary classification)
: 1d ndarray integer (1, ..., nclasses for multiclass classificatio)
classes
:Returns:
1
:Raises:
ValueError
if not (1 <= k <= #samples)
ValueError
if there aren'e at least 2 classes
ValueError
if, in case of 2-classes problems, the lables are not 1 and -1
ValueError
if, in case of n-classes problems, the lables are not int from 1 to n
"""
self.__classes = unique(y).astype(int)
if self.__k <= 0 or self.__k >= x.shape[0]:
raise ValueError("k must be in [1, #samples)")
if self.__classes.shape[0] < 2:
raise ValueError("Number of classes must be >= 2")
elif self.__classes.shape[0] == 2:
if self.__classes[0] != -1 or self.__classes[1] != 1:
raise ValueError("For binary classification classes must be -1 and 1")
elif self.__classes.shape[0] > 2:
if not alltrue(self.__classes == arange(1, self.__classes.shape[0] + 1)):
raise ValueError("For %d-class classification classes must be 1, ..., %d"
% (self.__classes.shape[0], self.__classes.shape[0]))
self.__x = x.copy()
self.__y = y.copy()
self.__computed = True
return 1
def predict(self, p):
"""
Predict knn model on a test point(s).
:Parameters:
p : 1d or 2d ndarray float (sample(s) x feats)
test sample(s)
:Returns:
the predicted value(s) on success:
integer or 1d numpy array integer (-1 or 1) for binary classification
integer or 1d numpy array integer (1, ..., nclasses) for multiclass classification
0 on succes with non unique classification
-2 otherwise
:Raises:
StandardError
if no Knn method computed
"""
if self.__computed == False:
raise StandardError("No Knn method compute() run")
if p.ndim == 1:
pred = nncore.predictnn(self.__x, self.__y, p, self.__classes, self.__k, self.__dist)
self.realpred = 0.0
elif p.ndim == 2:
pred = empty(p.shape[0], dtype = int)
for i in range(p.shape[0]):
pred[i] = nncore.predictnn(self.__x, self.__y, p[i], self.__classes, self.__k, self.__dist)
self.realpred = zeros(p.shape[0])
return pred
|