int genrmt(char *infile, char *outfile)
{
int i,j;
FILE *fp;
double x,t0,t1;
char *cbuf,*fext;
/* open file */
switch(seqmode) {
case SEQ_MOLPHY: fext=fext_molphy; break;
case SEQ_PAML: fext=fext_paml; break;
case SEQ_PAUP: fext=fext_paup; break;
case SEQ_PUZZLE: fext=fext_puzzle; break;
case SEQ_PHYML: fext=fext_phyml; break;
case SEQ_MT:
default: fext=fext_mt; break;
}
if(infile) {
fp=openfp(infile,fext,"r",&cbuf);
printf("\n# reading %s",cbuf);
} else {
fp=STDIN;
printf("\n# reading from stdin");
}
/* read file */
mm=nn=0;
switch(seqmode) {
case SEQ_MOLPHY:
datmat = fread_mat_lls(fp, &mm, &nn); break;
case SEQ_PAML:
datmat = fread_mat_lfh(fp, &mm, &nn); break;
case SEQ_PAUP:
datmat = fread_mat_paup(fp, &mm, &nn); break;
case SEQ_PUZZLE:
datmat = fread_mat_puzzle(fp, &mm, &nn); break;
case SEQ_PHYML:
datmat = fread_mat_phyml(fp, &mm, &nn); break;
case SEQ_MT:
default:
datmat = fread_mat(fp, &mm, &nn); break;
}
if(infile) {fclose(fp); FREE(cbuf);}
printf("\n# M:%d N:%d",mm,nn);
/* allocating buffers */
datvec=new_vec(mm);
bn=new_ivec(kk); rr1=new_vec(kk);
/* calculate the log-likelihoods */
for(i=0;i<mm;i++) {
x=0; for(j=0;j<nn;j++) x+=datmat[i][j];
datvec[i]=x;
}
/* calculate scales */
for(i=0;i<kk;i++) {
bn[i]=(int)(rr[i]*nn); /* sample size for bootstrap */
rr1[i]=(double)bn[i]/nn; /* recalculate rr for integer adjustment */
}
/* open out file */
if(outfile) {
/* vt ascii write to file */
fp=openfp(outfile,fext_vt,"w",&cbuf);
printf("\n# writing %s",cbuf);
fwrite_vec(fp,datvec,mm);
fclose(fp); FREE(cbuf);
/* rmt binary write to file */
fp=openfp(outfile,fext_rmt,"wb",&cbuf);
printf("\n# writing %s",cbuf);
fwrite_bvec(fp,datvec,mm);
fwrite_bvec(fp,rr1,kk);
fwrite_bivec(fp,bb,kk);
fwrite_bi(fp,kk);
} else {
/* rmt ascii write to stdout */
printf("\n# writing to stdout");
printf("\n# OBS:\n"); write_vec(datvec,mm);
printf("\n# R:\n"); write_vec(rr1,kk);
printf("\n# B:\n"); write_ivec(bb,kk);
printf("\n# RMAT:\n");
printf("%d\n",kk);
}
/* generating the replicates by resampling*/
for(i=j=0;i<kk;i++) j+=bb[i];
printf("\n# start generating total %d replicates for %d items",j,mm);
fflush(STDOUT);
t0=get_time();
for(i=0;i<kk;i++) {
repmat=new_lmat(mm,bb[i]);
scaleboot(datmat,repmat,mm,nn,bn[i],bb[i]);
if(outfile) {
fwrite_bmat(fp,repmat,mm,bb[i]);
putdot();
} else {
printf("\n## RMAT[%d]:\n",i); write_mat(repmat,mm,bb[i]);
}
free_lmat(repmat,mm);
}
t1=get_time();
printf("\n# time elapsed for bootstrap t=%g sec",t1-t0);
if(outfile) {
fclose(fp); FREE(cbuf);
}
/* freeing buffers */
free_vec(bn); free_vec(rr1); free_vec(datvec); free_mat(datmat);
return 0;
}
/*==========================================
* main
*========================================== */
int main(int argc, char* argv[])
{
int T; // number of topics
int W; // number of unique words
int D; // number of docs
int N; // number of words in corpus
int i, iter, seed;
int *w, *d, *z, *order;
double **Nwt, **Ndt, *Nt;
double alpha, beta;
if (argc == 1) {
fprintf(stderr, "usage: %s T iter seed\n", argv[0]);
exit(-1);
}
T = atoi(argv[1]);
assert(T>0);
iter = atoi(argv[2]);
assert(iter>0);
seed = atoi(argv[3]);
assert(seed>0);
N = countN("docword.txt");
w = ivec(N);
d = ivec(N);
z = ivec(N);
read_dw("docword.txt", d, w, &D, &W);
Nwt = dmat(W,T);
Ndt = dmat(D,T);
Nt = dvec(T);
alpha = 0.05 * N / (D * T);
beta = 0.01;
printf("seed = %d\n", seed);
printf("N = %d\n", N);
printf("W = %d\n", W);
printf("D = %d\n", D);
printf("T = %d\n", T);
printf("iter = %d\n", iter);
printf("alpha = %f\n", alpha);
printf("beta = %f\n", beta);
srand48(seed);
randomassignment_d(N,T,w,d,z,Nwt,Ndt,Nt);
order = randperm(N);
add_smooth_d(D,T,Ndt,alpha);
add_smooth_d(W,T,Nwt,beta);
add_smooth1d( T,Nt, W*beta);
for (i = 0; i < iter; i++) {
sample_chain_d(N,W,T,w,d,z,Nwt,Ndt,Nt,order);
printf("iter %d \n", i);
}
printf("In-Sample Perplexity = %.2f\n",pplex_d(N,W,T,w,d,Nwt,Ndt));
add_smooth_d(D,T,Ndt,-alpha);
add_smooth_d(W,T,Nwt,-beta);
add_smooth1d( T,Nt, -W*beta);
write_sparse_d(W,T,Nwt,"Nwt.txt");
write_sparse_d(D,T,Ndt,"Ndt.txt");
write_ivec(N,z,"z.txt");
return 0;
}
