Newer
Older
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
/*************************************************************************/
/** File: rmse.c **/
/** Description: calculate root mean squared error of particular **/
/** clustering. **/
/** Author: Sang-Ha Lee **/
/** University of Virginia. **/
/** **/
/** Note: euclid_dist_2() and find_nearest_point() adopted from **/
/** Minebench code. **/
/** **/
/*************************************************************************/
#include <stdio.h>
#include <stdlib.h>
#include <float.h>
#include <math.h>
#ifdef _OPENMP
#include <omp.h>
#endif
#include "kmeans.h"
extern double wtime(void);
/*----< euclid_dist_2() >----------------------------------------------------*/
/* multi-dimensional spatial Euclid distance square */
__inline
float euclid_dist_2(float *pt1,
float *pt2,
int numdims)
{
int i;
float ans=0.0;
for (i=0; i<numdims; i++)
ans += (pt1[i]-pt2[i]) * (pt1[i]-pt2[i]);
return(ans);
}
/*----< find_nearest_point() >-----------------------------------------------*/
__inline
int find_nearest_point(float *pt, /* [nfeatures] */
int nfeatures,
float **pts, /* [npts][nfeatures] */
int npts)
{
int index, i;
float max_dist=FLT_MAX;
/* find the cluster center id with min distance to pt */
for (i=0; i<npts; i++) {
float dist;
dist = euclid_dist_2(pt, pts[i], nfeatures); /* no need square root */
if (dist < max_dist) {
max_dist = dist;
index = i;
}
}
return(index);
}
/*----< rms_err(): calculates RMSE of clustering >-------------------------------------*/
float rms_err (float **feature, /* [npoints][nfeatures] */
int nfeatures,
int npoints,
float **cluster_centres, /* [nclusters][nfeatures] */
int nclusters)
{
int i;
int nearest_cluster_index; /* cluster center id with min distance to pt */
float sum_euclid = 0.0; /* sum of Euclidean distance squares */
float ret; /* return value */
/* calculate and sum the sqaure of euclidean distance*/
#pragma omp parallel for \
shared(feature,cluster_centres) \
firstprivate(npoints,nfeatures,nclusters) \
private(i, nearest_cluster_index) \
schedule (static)
for (i=0; i<npoints; i++) {
nearest_cluster_index = find_nearest_point(feature[i],
nfeatures,
cluster_centres,
nclusters);
sum_euclid += euclid_dist_2(feature[i],
cluster_centres[nearest_cluster_index],
nfeatures);
}
/* divide by n, then take sqrt */
ret = sqrt(sum_euclid / npoints);
return(ret);
}