int
full_variances(uint32 ts,
vector_t **mean,
vector_t ***var,
uint32 n_density,
uint32 n_stream,
uint32 *veclen,
uint32 blksize,
uint32 n_in_frame,
codew_t *label)
{
uint32 *n_obs;
float64 term;
uint32 s, i, l, m, k, n_frame;
vector_t c;
E_INFO("Initializing full covariances\n");
for (s = 0; s < n_stream; s++) {
n_obs = ckd_calloc(n_density, sizeof(uint32));
n_frame = setup_obs(ts, s, n_in_frame, n_stream, veclen, blksize);
for (i = 0; i < n_frame; i++) {
k = label[i]; /* best codeword */
n_obs[k]++;
c = get_obs(i);
for (l = 0; l < veclen[s]; l++) {
for (m = 0; m < veclen[s]; m++) {
var[s][k][l][m] +=
(c[l] - mean[s][k][l])
* (c[m] - mean[s][k][m]);
}
}
}
for (k = 0; k < n_density; k++) {
term = 1.0 / (float64)n_obs[k];
for (l = 0; l < veclen[s]; l++) {
for (m = 0; m < veclen[s]; m++) {
var[s][k][l][m] *= term;
}
}
}
ckd_free(n_obs);
}
return 0;
}
float64
cluster(uint32 ts,
uint32 n_stream,
uint32 n_in_frame,
const uint32 *veclen,
vector_t **mean,
uint32 n_density,
codew_t **out_label)
{
float64 sum_sqerr, sqerr=0;
uint32 s, n_frame;
const char *meth;
*out_label = NULL;
blksize = feat_blksize();
k_means_set_get_obs(&get_obs);
for (s = 0, sum_sqerr = 0; s < n_stream; s++, sum_sqerr += sqerr) {
meth = (const char *)cmd_ln_access("-method");
n_frame = setup_obs(ts, s, n_in_frame, veclen);
if (strcmp(meth, "rkm") == 0) {
sqerr = random_kmeans(*(uint32 *)cmd_ln_access("-ntrial"),
n_frame,
veclen[s],
mean[s],
n_density,
*(float32 *)cmd_ln_access("-minratio"),
*(uint32 *)cmd_ln_access("-maxiter"),
out_label);
if (sqerr < 0) {
E_ERROR("Too few observations for kmeans\n");
return -1.0;
}
}
else if (strcmp(meth, "fnkm") == 0) {
sqerr = furthest_neighbor_kmeans(n_frame,
veclen[s],
mean[s],
n_density,
*(float32 *)cmd_ln_access("-minratio"),
*(uint32 *)cmd_ln_access("-maxiter"));
}
else {
E_ERROR("I don't know how to do method '%s'. Sorry.\n", meth);
}
}
return sum_sqerr;
}
int
variances(uint32 ts,
vector_t **mean,
vector_t **var,
uint32 n_density,
const uint32 *veclen,
uint32 n_in_frame,
uint32 n_stream,
codew_t *label)
{
uint32 *n_obs;
float64 term;
uint32 s, i, l, k, n_frame;
vector_t c;
E_INFO("Initializing variances\n");
for (s = 0; s < n_stream; s++) {
n_obs = ckd_calloc(n_density, sizeof(uint32));
n_frame = setup_obs(ts, s, n_in_frame, veclen);
for (i = 0; i < n_frame; i++) {
k = label[i]; /* best codeword */
n_obs[k]++;
c = get_obs(i);
for (l = 0; l < veclen[s]; l++) {
term = c[l] - mean[s][k][l];
term *= term;
var[s][k][l] += term;
}
}
for (k = 0; k < n_density; k++) {
term = 1.0 / (float64)n_obs[k];
for (l = 0; l < veclen[s]; l++) {
var[s][k][l] *= term;
}
}
ckd_free(n_obs);
}
return 0;
}
float64
reest_sum(uint32 ts,
vector_t **mean,
vector_t **var,
float32 **mixw,
uint32 n_density,
uint32 n_stream,
uint32 n_in_obs,
const uint32 *veclen,
uint32 n_iter,
uint32 twopassvar,
uint32 vartiethr)
{
uint32 o, i, j, k, l;
float32 *mixw_acc;
float32 *cb_acc;
vector_t **mean_acc_xx;
vector_t **var_acc_xx;
vector_t *mean_acc;
vector_t *var_acc;
float64 ol, ttt, diff, log_tot_ol = 0, p_log_tot_ol = 0;
float64 **norm, *den;
float64 log_a_den=0;
float32 mixw_norm;
vector_t obs;
uint32 n_obs;
vector_t ***n_mean_xx = NULL;
vector_t *n_mean = NULL;
float64 avg_lik=0, p_avg_lik=0;
uint32 tievar = FALSE;
E_INFO("EM reestimation of mixw/means/vars\n");
if (twopassvar) {
n_mean_xx = gauden_alloc_param(1, 1, n_density, veclen);
n_mean = n_mean_xx[0][0];
}
/* allocate mixing weight accumulators */
mixw_acc = (float32 *)ckd_calloc(n_density, sizeof(float32));
cb_acc = (float32 *)ckd_calloc(n_density, sizeof(float32));
mean_acc_xx = (vector_t **)alloc_gau_acc(1, n_density, veclen, feat_blksize());
mean_acc = mean_acc_xx[0];
var_acc_xx = (vector_t **)alloc_gau_acc(1, n_density, veclen, feat_blksize());
var_acc = var_acc_xx[0];
den = (float64 *)ckd_calloc(n_density, sizeof(float64));
norm = (float64 **)ckd_calloc_2d(n_stream, n_density, sizeof(float64));
for (j = 0; j < n_stream; j++) {
n_obs = setup_obs(ts, j, n_in_obs, veclen);
if (n_obs < vartiethr) tievar = TRUE;
for (i = 0; i < n_iter; i++) {
p_log_tot_ol = log_tot_ol;
log_tot_ol = 0;
for (k = 0; k < n_density; k++) {
/* floor variances */
for (l = 0; l < veclen[j]; l++)
if (var[j][k][l] < 1e-4) var[j][k][l] = 1e-4;
/* compute normalization factors for Gaussian
densities */
norm[j][k] = diag_norm(var[j][k], veclen[j]);
/* precompute 1/(2sigma^2) terms */
diag_eval_precomp(var[j][k], veclen[j]);
}
if (twopassvar) {
/* do a pass over the corpus to compute reestimated means */
for (o = 0; o < n_obs; o++) {
float64 mx;
obs = get_obs(o);
mx = MIN_NEG_FLOAT64;
for (k = 0; k < n_density; k++) {
/* really log(den) for the moment */
den[k] = log_diag_eval(obs, norm[j][k], mean[j][k], var[j][k], veclen[j]);
if (mx < den[k]) mx = den[k];
}
for (k = 0, ol = 0; k < n_density; k++) {
den[k] = exp(log_a_den - mx);
ol += mixw[j][k] * den[k];
}
for (k = 0; k < n_density; k++) {
ttt = mixw[j][k] * den[k] / ol;
cb_acc[k] += ttt;
for (l = 0; l < veclen[j]; l++) {
mean_acc[k][l] += obs[l] * ttt;
}
}
}
cb_acc[0] = 1.0 / cb_acc[0];
for (k = 1; k < n_density; k++) {
cb_acc[k] = 1.0 / cb_acc[k];
}
/* compute the reestimated mean value to be used in next pass */
for (k = 0; k < n_density; k++) {
for (l = 0; l < veclen[j]; l++) {
n_mean[k][l] = mean_acc[k][l] * cb_acc[k];
mean_acc[k][l] = 0;
}
cb_acc[k] = 0;
}
}
else {
n_mean = mean[j];
}
for (o = 0; o < n_obs; o++) {
float64 mx;
/* Do a pass over the data to accumulate reestimation sums
* for the remaining parameters (including means
* if not a 2-pass config) */
/* Get the next observation */
obs = get_obs(o);
mx = MIN_NEG_FLOAT64;
/* Compute the mixture density value given the
* observation and the model parameters */
for (k = 0; k < n_density; k++) {
/* really log(den) for the moment */
den[k] = log_diag_eval(obs, norm[j][k], mean[j][k], var[j][k], veclen[j]);
if (mx < den[k]) mx = den[k];
}
for (k = 0, ol = 0; k < n_density; k++) {
den[k] = exp(den[k] - mx);
ol += mixw[j][k] * den[k];
}
log_tot_ol += log(ol) + mx;
/* Compute the reestimation sum terms for each
* of the component densities */
for (k = 0; k < n_density; k++) {
ttt = mixw[j][k] * den[k] / ol;
mixw_acc[k] += ttt;
cb_acc[k] += ttt;
for (l = 0; l < veclen[j]; l++) {
/* if not doing two-pass variance computation
* n_mean <- mean above. */
diff = obs[l] - n_mean[k][l];
if (!twopassvar) {
mean_acc[k][l] += ttt * obs[l];
}
var_acc[k][l] += ttt * diff * diff;
}
}
}
avg_lik = exp(log_tot_ol / n_obs);
if (p_log_tot_ol != 0)
p_avg_lik = exp(p_log_tot_ol / n_obs);
else
p_avg_lik = 0.5 * avg_lik;
E_INFO("EM stream %u: [%u] avg_lik %e conv_ratio %e\n",
j, i, avg_lik, (avg_lik - p_avg_lik) / p_avg_lik);
/* normalize after iteration */
if (tievar) {
/* create a sum over all densities in entry 0 */
for (k = 1; k < n_density; k++) {
for (l = 0; l < veclen[j]; l++) {
var[j][0][l] += var[j][k][l];
}
cb_acc[0] += cb_acc[k];
}
/* copy entry 0 back to remaining entries */
for (k = 1; k < n_density; k++) {
for (l = 0; l < veclen[j]; l++) {
var[j][k][l] = var[j][0][l];
}
cb_acc[k] = cb_acc[0];
}
}
for (k = 0, mixw_norm = 0; k < n_density; k++) {
/* norm for per density expectations */
cb_acc[k] = 1.0 / cb_acc[k];
mixw_norm += mixw_acc[k];
}
mixw_norm = 1.0 / mixw_norm;
if (!twopassvar) {
for (k = 0; k < n_density; k++) {
mixw[j][k] = mixw_acc[k] * mixw_norm;
mixw_acc[k] = 0;
for (l = 0; l < veclen[j]; l++) {
mean[j][k][l] = mean_acc[k][l] * cb_acc[k];
mean_acc[k][l] = 0;
var[j][k][l] = var_acc[k][l] * cb_acc[k];
var_acc[k][l] = 0;
}
cb_acc[k] = 0;
}
}
else {
for (k = 0; k < n_density; k++) {
mixw[j][k] = mixw_acc[k] * mixw_norm;
mixw_acc[k] = 0;
for (l = 0; l < veclen[j]; l++) {
/* already computed in first pass */
mean[j][k][l] = n_mean[k][l];
var[j][k][l] = var_acc[k][l] * cb_acc[k];
var_acc[k][l] = 0;
}
cb_acc[k] = 0;
}
}
} /* end of EM iteration loop */
E_INFO("EM stream %u: [final] n_obs %u avg_lik %e conv_ratio %e\n",
j, n_obs, avg_lik, (avg_lik - p_avg_lik) / p_avg_lik);
} /* end of feature stream loop */
ckd_free((void *)mixw_acc);
ckd_free((void *)cb_acc);
ckd_free((void *)&mean_acc_xx[0][0][0]);
ckd_free_2d((void **)mean_acc_xx);
ckd_free((void *)&var_acc_xx[0][0][0]);
ckd_free_2d((void **)var_acc_xx);
if (n_mean_xx) {
ckd_free((void *)&n_mean_xx[0][0][0]);
ckd_free_2d((void **)n_mean);
}
ckd_free_2d((void **)norm);
ckd_free((void *)den);
return log_tot_ol;
}
/***********************************************************************//**
* @brief Generate the model map(s)
*
* This method reads the task parameters from the parfile, sets up the
* observation container, loops over all CTA observations in the container
* and generates a model map for each CTA observation.
***************************************************************************/
void ctmodel::run(void)
{
// If we're in debug mode then all output is also dumped on the screen
if (logDebug()) {
log.cout(true);
}
// Get task parameters
get_parameters();
// Setup observation container
setup_obs();
// Write parameters into logger
if (logTerse()) {
log_parameters();
log << std::endl;
}
// Write observation(s) into logger
if (logTerse()) {
log << std::endl;
if (m_obs.size() > 1) {
log.header1("Observations");
}
else {
log.header1("Observation");
}
log << m_obs << std::endl;
}
// Write header
if (logTerse()) {
log << std::endl;
if (m_obs.size() > 1) {
log.header1("Generate model maps");
}
else {
log.header1("Generate model map");
}
}
// Initialise observation counter
int n_observations = 0;
// Loop over all observations in the container
for (int i = 0; i < m_obs.size(); ++i) {
// Initialise event input and output filenames
m_infiles.push_back("");
// Get CTA observation
GCTAObservation* obs = dynamic_cast<GCTAObservation*>(m_obs[i]);
// Continue only if observation is a CTA observation
if (obs != NULL) {
// Write header for observation
if (logTerse()) {
if (obs->name().length() > 1) {
log.header3("Observation "+obs->name());
}
else {
log.header3("Observation");
}
}
// Increment number of observations
n_observations++;
// Save event file name (for possible saving)
m_infiles[i] = obs->eventfile();
// Generate model map
model_map(obs, m_obs.models());
} // endif: CTA observation found
} // endfor: looped over observations
// If more than a single observation has been handled then make sure
// that an XML file will be used for storage
if (n_observations > 1) {
m_use_xml = true;
}
// Write observation(s) into logger
if (logTerse()) {
log << std::endl;
if (m_obs.size() > 1) {
log.header1("Observations after model map generation");
}
else {
log.header1("Observation after model map generation");
}
log << m_obs << std::endl;
}
// Return
return;
}
