//only uses first sequence int* ghmm_bayes_hmm_fbgibbs(ghmm_bayes_hmm *bayes, ghmm_cmodel *mo, ghmm_cseq* seq, int burnIn, int seed){ #define CUR_PROC "ghmm_cmodel_fbgibbs" //XXX seed GHMM_RNG_SET (RNG, seed); int max_seq = ghmm_cseq_max_len(seq); double **alpha = ighmm_cmatrix_alloc(max_seq,mo->N); double ***pmats = ighmm_cmatrix_3d_alloc(max_seq, mo->N, mo->N); int **Q; ARRAY_CALLOC(Q, seq->seq_number); int seq_iter; for(seq_iter = 0; seq_iter < seq->seq_number; seq_iter++){ ARRAY_CALLOC(Q[seq_iter], seq->seq_len[seq_iter]); } ghmm_sample_data data; ghmm_alloc_sample_data(bayes, &data); ghmm_clear_sample_data(&data, bayes);//XXX swap parameter for(; burnIn > 0; burnIn--){ for(seq_iter = 0; seq_iter < seq->seq_number; seq_iter++){ ghmm_cmodel_fbgibbstep(mo,seq->seq[seq_iter],seq->seq_len[seq_iter], Q[seq_iter], alpha, pmats, NULL); ghmm_get_sample_data(&data, bayes, Q[seq_iter], seq->seq[seq_iter], seq->seq_len[seq_iter]); ghmm_update_model(mo, bayes, &data); ghmm_clear_sample_data(&data, bayes); } } ighmm_cmatrix_free(&alpha, max_seq); ighmm_cmatrix_3d_free(&pmats, max_seq,mo->N); return Q; STOP: return NULL; //XXX error handle #undef CUR_PROC }
ghmm_cseq *ghmm_sgenerate_extensions (ghmm_cmodel * smo, ghmm_cseq * sqd_short, int seed, int global_len, sgeneration_mode_t mode) { #define CUR_PROC "ghmm_sgenerate_extensions" ghmm_cseq *sq = NULL; int i, j, t, n, m, len = global_len, short_len, max_short_len = 0, up = 0; #ifdef bausparkasse int tilgphase = 0; #endif /* int *v_path = NULL; */ double log_p, *initial_distribution, **alpha, *scale, p, sum; /* aicj */ int class = -1; int pos; /* TEMP */ if (mode == all_viterbi || mode == viterbi_viterbi || mode == viterbi_all) { GHMM_LOG(LCONVERTED, "Error: mode not implemented yet\n"); goto STOP; } if (len <= 0) /* no global length; model should have a final state */ len = (int) GHMM_MAX_SEQ_LEN; max_short_len = ghmm_cseq_max_len (sqd_short); /*---------------alloc-------------------------------------------------*/ sq = ghmm_cseq_calloc (sqd_short->seq_number); if (!sq) { GHMM_LOG_QUEUED(LCONVERTED); goto STOP; } ARRAY_CALLOC (initial_distribution, smo->N); /* is needed in cfoba_forward() */ alpha = ighmm_cmatrix_alloc (max_short_len, smo->N); if (!alpha) { GHMM_LOG_QUEUED(LCONVERTED); goto STOP; } ARRAY_CALLOC (scale, max_short_len); ghmm_rng_init (); GHMM_RNG_SET (RNG, seed); /*---------------main loop over all seqs-------------------------------*/ for (n = 0; n < sqd_short->seq_number; n++) { ARRAY_CALLOC (sq->seq[n], len*(smo->dim)); short_len = sqd_short->seq_len[n]; if (len < short_len) { GHMM_LOG(LCONVERTED, "Error: given sequence is too long\n"); goto STOP; } ghmm_cseq_copy (sq->seq[n], sqd_short->seq[n], short_len); #ifdef GHMM_OBSOLETE sq->seq_label[n] = sqd_short->seq_label[n]; #endif /* GHMM_OBSOLETE */ /* Initial distribution */ /* 1. Viterbi-state */ #if 0 /* wieder aktivieren, wenn ghmm_cmodel_viterbi realisiert */ if (mode == viterbi_all || mode == viterbi_viterbi) { v_path = cviterbi (smo, sqd_short->seq[n], short_len, &log_p); if (v_path[short_len - 1] < 0 || v_path[short_len - 1] >= smo->N) { GHMM_LOG(LCONVERTED, "Warning:Error: from viterbi()\n"); sq->seq_len[n] = short_len; m_realloc (sq->seq[n], short_len); continue; } m_memset (initial_distribution, 0, smo->N); initial_distribution[v_path[short_len - 1]] = 1.0; /* all other 0 */ m_free (v_path); } #endif /* 2. Initial Distribution ??? Pi(i) = alpha_t(i)/P(O|lambda) */ if (mode == all_all || mode == all_viterbi) { if (short_len > 0) { if (ghmm_cmodel_forward (smo, sqd_short->seq[n], short_len, NULL /* ?? */ , alpha, scale, &log_p)) { GHMM_LOG_QUEUED(LCONVERTED); goto STOP; } sum = 0.0; for (i = 0; i < smo->N; i++) { /* alpha ist skaliert! */ initial_distribution[i] = alpha[short_len - 1][i]; sum += initial_distribution[i]; } /* nicht ok.? auf eins skalieren? */ for (i = 0; i < smo->N; i++) initial_distribution[i] /= sum; } else { for (i = 0; i < smo->N; i++) initial_distribution[i] = smo->s[i].pi; } } /* if short_len > 0: Initial state == final state from sqd_short; no output here else choose inittial state according to pi and do output */ p = GHMM_RNG_UNIFORM (RNG); sum = 0.0; for (i = 0; i < smo->N; i++) { sum += initial_distribution[i]; if (sum >= p) break; } /* error due to incorrect normalization ?? */ if (i == smo->N) { i--; while (i > 0 && initial_distribution[i] == 0.0) i--; } t = 0; pos = t * smo->dim; if (short_len == 0) { /* Output in state i */ p = GHMM_RNG_UNIFORM (RNG); sum = 0.0; for (m = 0; m < smo->M; m++) { sum += smo->s[i].c[m]; if (sum >= p) break; } /* error due to incorrect normalization ?? */ if (m == smo->M) { m--; while (m > 0 && smo->s[i].c[m] == 0.0) m--; } ghmm_cmodel_get_random_var(smo, i, m, sq->seq[n]+pos); if (smo->cos == 1) { class = 0; } else { if (!smo->class_change->get_class) { printf ("ERROR: get_class not initialized\n"); goto STOP; } /*printf("1: cos = %d, k = %d, t = %d\n",smo->cos,smo->class_change->k,t);*/ class = smo->class_change->get_class (smo, sq->seq[n], n, t); } t++; pos += smo->dim; }