int single_state_coin_toss()
{
state single_state;
model my_model;
double symbols_single_state[2]={0.5,0.5};
double trans_prob_single_state[1]={1.0};
double trans_prob_single_state_rev[1]={1.0};
int trans_id_single_state[1]={0};
sequence_t* my_output;
int silent_array[2] = {0};
my_model.model_type = 0;
/* initialise this state */
single_state.pi = 1.0;
single_state.b=symbols_single_state;
single_state.out_states=1;
single_state.out_a=trans_prob_single_state;
single_state.out_id=trans_id_single_state;
single_state.in_states=1;
single_state.in_id=trans_id_single_state;
single_state.in_a=trans_prob_single_state_rev;
single_state.fix=1;
/* initialise model */
my_model.N=1;
my_model.M=2;
my_model.s=&single_state;
my_model.prior=-1;
my_model.silent = silent_array;
fprintf(stdout,"transition matrix:\n");
model_A_print(stdout,&my_model,""," ","\n");
fprintf(stdout,"observation symbol matrix:\n");
model_B_print(stdout,&my_model,""," ","\n");
my_output=model_generate_sequences(&my_model,0,10,10,100);
sequence_print(stdout,my_output);
sequence_free(&my_output);
return 0;
}
int main(int argc, char **argv){
FILE *IN, *OUT;
seqlist_t IDs;
sequence_t *seq;
int i, keep, excl;
char *prog, *list, *f, *out, *id;
/* todo convert to uint_64 */
uint64_t n, total;
/* default values */
prog = basename(*argv);
list = NULL;
out = NULL;
OUT = stdout;
excl = keep = 0;
/* Check command line */
while ((i = getopt(argc, argv, "hl:o:x")) != -1) {
switch (i) {
case 'h':
usage(prog, EXIT_SUCCESS); break;
case 'l':
list = optarg; break;
case 'o':
out = optarg; break;
case 'x':
excl = 1; break;
default:
usage(prog, EXIT_FAILURE);
}
}
/* some files to deal with ? */
if (argc - optind < 1) { usage(prog, EXIT_FAILURE); }
/* get ids from list */
if (list != NULL) {
if ((IN = fopen(list, "r")) == NULL)
err(EXIT_FAILURE, "%s", list);
seqlist_init(&IDs);
i = seqlist_populate(&IDs, IN);
if (i == 0) errx(EXIT_FAILURE, "file: %s no identifier found", list);
if (fclose(IN) == EOF) err(EXIT_FAILURE, "%s: close failed", list);
seqlist_sort(&IDs);
}
/* open output file */
if ((out != NULL) && ((OUT = fopen(out, "w")) == NULL))
err(EXIT_FAILURE, "%s", out);
total = n = 0;
/* start filtering all argument file*/
for (i = optind; i < argc; i++) {
f = *(argv+i);
if ((IN = fopen(f, "r")) == NULL) err(EXIT_FAILURE, "%s", f);
while ((seq = sequence_parse(IN, SEQFMT_FASTA)) != NULL) {
total++;
id = seq->nam;
keep = 1;
if (list != NULL) { keep = 1 - seqlist_chk(&IDs, id); }
if (excl == 1) { keep = 1 - keep; }
if (keep == 1) { n++; sequence_print(OUT, seq, SEQFMT_FASTA); }
sequence_free(seq);
}//end while
/* check for parsing error vs EOF */
if ((feof(IN) == 0) || (total == 0)){
errx(1, "%s: unable to read sequence %d", f, total+1);
}
if (fclose(IN) == EOF) err(EXIT_FAILURE, "%s: close failed", f);
}//end for files
if ((out != NULL) && (fclose(OUT) == EOF)) err(EXIT_FAILURE, "%s", out);
if (list != NULL) seqlist_fini(&IDs);
/*display resume on stderr */
fprintf(stderr, "file %s: Extracted %"PRI_U64" from %"PRI_U64" sequences (%.2f %%)\n" ,
basename(f), n , total, (float)(n)/total*100.0);
return EXIT_SUCCESS;
}
int two_states_coin_toss()
{
model my_model;
state model_states[2];
double symbols_head_state[2]={1.0,0.0};
double trans_prob_head_state[2]={0.5,0.5};
double trans_prob_head_state_rev[2]={0.5,0.5};
int trans_id_head_state[2]={0,1};
double symbols_tail_state[2]={0.0,1.0};
double trans_prob_tail_state[2]={0.5,0.5};
double trans_prob_tail_state_rev[2]={0.5,0.5};
int trans_id_tail_state[2]={0,1};
sequence_t *my_output;
double log_p_viterbi, log_p_forward;
double **forward_alpha;
double forward_scale[10];
int *viterbi_path;
int i;
/* flags indicating whether a state is silent */
int silent_array[2] = {0,0};
my_model.model_type = 0;
/* initialise head state */
model_states[0].pi = 0.5;
model_states[0].b=symbols_head_state;
model_states[0].out_states=2;
model_states[0].out_a=trans_prob_head_state;
model_states[0].out_id=trans_id_head_state;
model_states[0].in_states=2;
model_states[0].in_id=trans_id_head_state;
model_states[0].in_a=trans_prob_head_state_rev;
model_states[0].fix=1;
/* initialise tail state */
model_states[1].pi = 0.5;
model_states[1].b=symbols_tail_state;
model_states[1].out_states=2;
model_states[1].out_id=trans_id_tail_state;
model_states[1].out_a=trans_prob_tail_state;
model_states[1].in_states=2;
model_states[1].in_id=trans_id_tail_state;
model_states[1].in_a=trans_prob_tail_state_rev;
model_states[1].fix=1;
/* initialise model */
my_model.N=2;
my_model.M=2;
my_model.s=model_states;
my_model.prior=-1;
my_model.silent = silent_array;
fprintf(stdout,"transition matrix:\n");
model_A_print(stdout,&my_model,""," ","\n");
fprintf(stdout,"observation symbol matrix:\n");
model_B_print(stdout,&my_model,""," ","\n");
my_output=model_generate_sequences(&my_model,0,10,10,100);
sequence_print(stdout,my_output);
/* try viterbi algorithm in a clear situation */
viterbi_path=viterbi(&my_model,
my_output->seq[0],
my_output->seq_len[0],
&log_p_viterbi);
if (viterbi_path==NULL)
{fprintf(stderr,"viterbi failed!"); return 1;}
fprintf(stdout,"viterbi:\n");
for(i=0;i<my_output->seq_len[0];i++){
printf(" %d, ", viterbi_path[i]);
}
printf("\n");
fprintf(stdout,
"log-p of this sequence (viterbi algorithm): %f\n",
log_p_viterbi);
/* allocate matrix for forward algorithm */
fprintf(stdout,"applying forward algorithm to the sequence...");
forward_alpha=stat_matrix_d_alloc(10,2);
if (forward_alpha==NULL)
{
fprintf(stderr,"\n could not alloc forward_alpha matrix\n");
return 1;
}
/* run foba_forward */
if (foba_forward(&my_model,
my_output->seq[0],
my_output->seq_len[0],
forward_alpha,
forward_scale,
&log_p_forward))
{
fprintf(stderr,"foba_logp failed!");
stat_matrix_d_free(&forward_alpha);
return 1;
}
/* alpha matrix */
fprintf(stdout,"Done.\nalpha matrix from forward algorithm:\n");
matrix_d_print(stdout,forward_alpha,10,2,""," ","\n");
fprintf(stdout,"log-p of this sequence (forward algorithm): %f\n",log_p_forward);
/* clean up */
sequence_free(&my_output);
free(viterbi_path);
stat_matrix_d_free(&forward_alpha);
return 0;
}
