k-meansクラスタ分析

nag_mv_kmeans_cluster_analysis (g03efc) Example Program Data

U 20 5 5 3 10

77.3 13.0  9.7 1.5 6.4
82.5 10.0  7.5 1.5 6.5
66.9 20.6 12.5 2.3 7.0
47.2 33.8 19.0 2.8 5.8
65.3 20.5 14.2 1.9 6.9
83.3 10.0  6.7 2.2 7.0
81.6 12.7  5.7 2.9 6.7
47.8 36.5 15.7 2.3 7.2
48.6 37.1 14.3 2.1 7.2
61.6 25.5 12.9 1.9 7.3
58.6 26.5 14.9 2.4 6.7
69.3 22.3  8.4 4.0 7.0
61.8 30.8  7.4 2.7 6.4
67.7 25.3  7.0 4.8 7.3
57.2 31.2 11.6 2.4 6.5
67.2 22.7 10.1 3.3 6.2
59.2 31.2  9.6 2.4 6.0
80.2 13.2  6.6 2.0 5.8
82.2 11.1  6.7 2.2 7.2
69.7 20.7  9.6 3.1 5.9

82.5 10.0  7.5 1.5 6.5
47.8 36.5 15.7 2.3 7.2
67.2 22.7 10.1 3.3 6.2

1 1 1 1 1

nag_mv_kmeans_cluster_analysis (g03efc) Example Program Results


The cluster each point belongs to
      1      1      3      2      3      1      1      2      2      3
      3      3      3      3      3      3      3      1      1      3


The number of points in each cluster
      6      3     11

The within-cluster sum of weights of each cluster
      6.00      3.00     11.00

The within-cluster sum of squares of each cluster

       46.5717       20.3800      468.8964

The final cluster centres
                  1       2       3       4       5
     1      81.1833 11.6667  7.1500  2.0500  6.6000
     2      47.8667 35.8000 16.3333  2.4000  6.7333
     3      64.0455 25.2091 10.7455  2.8364  6.6545

/* nag_mv_kmeans_cluster_analysis (g03efc) Example Program.
 *
 * CLL6I261D/CLL6I261DL Version.
 *
 * Copyright 2017 Numerical Algorithms Group.
 *
 * Mark 26.1, 2017.
 *
 */

#include <nag.h>
#include <stdio.h>
#include <nag_stdlib.h>
#include <nagg03.h>

#define CMEANS(I, J) cmeans[(I) *tdcmeans + J]
#define X(I, J)      x[(I) *tdx + J]
int main(void)
{
  Integer exit_status = 0, i, *inc = 0, *isx = 0, j, k, m, maxit, n, *nic = 0,
         nvar;
  Integer tdcmeans, tdx;
  NagError fail;
  char weight[2];
  double *cmeans = 0, *css = 0, *csw = 0, *wt = 0, *wtptr, *x = 0;

  INIT_FAIL(fail);

  printf("nag_mv_kmeans_cluster_analysis (g03efc) Example Program Results"
         "\n\n");

  /* Skip heading in the data file */
  scanf("%*[^\n]");

  scanf("%1s", weight);
  scanf("%ld", &n);
  scanf("%ld", &m);
  scanf("%ld", &nvar);
  scanf("%ld", &k);
  scanf("%ld", &maxit);

  if (n >= 2 && nvar >= 1 && m >= nvar && k >= 2) {
    if (!(cmeans = nAG_ALLOC((k) * (nvar), double)) ||
        !(css = nAG_ALLOC(k, double)) ||
        !(csw = nAG_ALLOC(k, double)) ||
        !(wt = nAG_ALLOC(n, double)) ||
        !(x = nAG_ALLOC((n) * (m), double)) ||
        !(inc = nAG_ALLOC(n, Integer)) ||
        !(isx = nAG_ALLOC(m, Integer)) || !(nic = nAG_ALLOC(k, Integer)))
    {
      printf("Allocation failure\n");
      exit_status = -1;
      goto END;
    }
    tdx = m;
    tdcmeans = nvar;
  }
  else {
    printf("Invalid n or nvar or m or k.\n");
    exit_status = 1;
    return exit_status;
  }
  if (*weight == 'W') {
    for (i = 0; i < n; ++i) {
      for (j = 0; j < m; ++j)
        scanf("%lf", &X(i, j));
      scanf("%lf", &wt[i]);
    }
    wtptr = wt;
  }
  else {
    for (i = 0; i < n; ++i) {
      for (j = 0; j < m; ++j)
        scanf("%lf", &X(i, j));
    }
    wtptr = 0;
  }
  for (i = 0; i < k; ++i) {
    for (j = 0; j < nvar; ++j)
      scanf("%lf", &CMEANS(i, j));
  }
  for (j = 0; j < m; ++j)
    scanf("%ld", &isx[j]);

  /* nag_mv_kmeans_cluster_analysis (g03efc).
   * K-means
   */
  nag_mv_kmeans_cluster_analysis(n, m, x, tdx, isx, nvar, k, cmeans,
                                 tdcmeans, wtptr, inc, nic, css, csw, maxit,
                                 &fail);
  if (fail.code != NE_NOERROR) {
    printf("Error from nag_mv_kmeans_cluster_analysis (g03efc).\n%s\n",
           fail.message);
    exit_status = 1;
    goto END;
  }

  printf("\nThe cluster each point belongs to\n");
  for (i = 0; i < n; ++i)
    printf(" %6ld%s", inc[i], (i + 1) % 10 ? "" : "\n");

  printf("\n\nThe number of points in each cluster\n");
  for (i = 0; i < k; ++i)
    printf(" %6ld", nic[i]);

  printf("\n\nThe within-cluster sum of weights of each cluster\n");
  for (i = 0; i < k; ++i)
    printf(" %9.2f", csw[i]);

  printf("\n\nThe within-cluster sum of squares of each cluster\n\n");
  for (i = 0; i < k; ++i)
    printf(" %13.4f", css[i]);

  printf("\n\nThe final cluster centres\n");
  printf("                  1       2       3       4       5\n");
  for (i = 0; i < k; ++i) {
    printf(" %5ld     ", i + 1);
    for (j = 0; j < nvar; ++j)
      printf("%8.4f", CMEANS(i, j));
    printf("\n");
  }
END:
  nAG_FREE(cmeans);
  nAG_FREE(css);
  nAG_FREE(csw);
  nAG_FREE(wt);
  nAG_FREE(x);
  nAG_FREE(inc);
  nAG_FREE(isx);
  nAG_FREE(nic);
  return exit_status;
}