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
|
/**
* @file gensvm_predict.c
* @author Gertjan van den Burg
* @date August 9, 2013
* @brief Main functions for predicting class labels..
*
* @details
* This file contains functions for predicting the class labels of instances
* and a function for calculating the predictive performance (hitrate) of
* a prediction given true class labels.
*
*/
#include "gensvm_predict.h"
/**
* @brief Predict class labels of data given and output in predy
*
* @details
* The labels are predicted by mapping each instance in data to the
* simplex space using the matrix V in the given model. Next, for each
* instance the nearest simplex vertex is determined using an Euclidean
* norm. The nearest simplex vertex determines the predicted class label,
* which is recorded in predy.
*
* @param[in] testdata GenData to predict labels for
* @param[in] model GenModel with optimized V
* @param[out] predy pre-allocated vector to record predictions in
*/
void gensvm_predict_labels(struct GenData *testdata, struct GenModel *model,
long *predy)
{
long i, j, k, n, K, label;
double norm, min_dist,
*S = NULL,
*ZV = NULL;
n = testdata->n;
K = model->K;
// allocate necessary memory
S = Calloc(double, K-1);
ZV = Calloc(double, n*(K-1));
// Generate the simplex matrix
gensvm_simplex(model);
// Generate the simplex space vectors
gensvm_calculate_ZV(model, testdata, ZV);
// Calculate the distance to each of the vertices of the simplex.
// The closest vertex defines the class label
for (i=0; i<n; i++) {
label = 0;
min_dist = INFINITY;
for (j=0; j<K; j++) {
for (k=0; k<K-1; k++) {
S[k] = matrix_get(ZV, K-1, i, k) -
matrix_get(model->U, K-1, j, k);
}
norm = cblas_dnrm2(K-1, S, 1);
if (norm < min_dist) {
label = j+1;
min_dist = norm;
}
}
predy[i] = label;
}
free(ZV);
free(S);
}
/**
* @brief Calculate the predictive performance (percentage correct)
*
* @details
* The predictive performance is calculated by simply counting the number
* of correctly classified samples and dividing by the total number of
* samples, multiplying by 100.
*
* @param[in] data the GenData dataset with known labels
* @param[in] predy the predicted class labels
*
* @returns percentage correctly classified.
*/
double gensvm_prediction_perf(struct GenData *data, long *predy)
{
long i, correct = 0;
double performance;
for (i=0; i<data->n; i++)
if (data->y[i] == predy[i])
correct++;
performance = ((double) correct)/((double) data->n)* 100.0;
return performance;
}
|
