void hca_displaytopics(char *stem, char *resstem, int topword,
enum ScoreType scoretype, int pmicount, int fullreport) {
int w,k;
uint32_t *termindk = NULL;
uint32_t *indk = NULL;
int Nk_tot = 0;
double (*termtscore)(int) = NULL;
double (*tscore)(int) = NULL;
double sparsityword = 0;
double sparsitydoc = 0;
double underused = 0;
uint32_t *top1cnt = NULL;
FILE *fp;
float *tpmi = NULL;
char *topfile;
char *repfile;
uint32_t *psort;
FILE *rp = NULL;
float *gtvec = globalprop();
//#define XTRA // prints model topic probs after observed
#ifdef XTRA
double *gtavec = calloc(ddN.T,sizeof(gtavec[0]));
#endif
float *gpvec = calloc(ddN.W,sizeof(gpvec[0]));
float *pvec = calloc(ddN.W,sizeof(pvec[0]));
#ifdef KL
float *dfvec = calloc(ddN.W,sizeof(dfvec[0]));
#endif
double *ngalpha = NULL;
T_stats_t *termstats;
#ifdef XTRA
get_probs(gtavec);
#endif
if ( pmicount>topword )
pmicount = topword;
if ( scoretype == ST_idf ) {
tscore = idfscore;
} else if ( scoretype == ST_phirat ) {
tscore = phiratioscore;
} else if ( scoretype == ST_phi ) {
tscore = phiscore;
} else if ( scoretype == ST_count ) {
tscore = countscore;
} else if ( scoretype == ST_cost ) {
tscore = costscore;
} else if ( scoretype == ST_Q ) {
tscore = Qscore;
lowerQ = 1.0/ddN.T;
}
if ( ddS.TwT==NULL && ddP.phi==NULL && scoretype == ST_phirat )
yap_quit("Cannot use '-orat' option with this model/settings.\n");
if ( ddP.PYalpha==H_NG ) {
/*
* provide an estimate of alpha
*/
ngalpha = dvec(ddN.T);
get_probs(ngalpha);
for (k=0; k<ddN.T; k++) {
ddP.alphapr[k] = ngalpha[k];
}
}
/*
* returns null if no relevant data file
*/
termstats = tstats_init(ddS.z, ddD.NdTcum, ddN.T, ddN.DT, stem);
if ( termstats ) {
if ( scoretype == ST_idf ) {
termtscore = termidfscore;
} else
termtscore = termcountscore;
}
/*
* first collect counts of each word/term,
* and build gpvec (mean word probs)
*/
build_NwK();
if ( termstats )
build_termNwK(termstats);
{
/*
* gpvec[] is normalised NwK[]
*/
double tot = 0;
for (w=0; w<ddN.W; w++)
tot += gpvec[w] = NwK[w]+0.1;
for (w=0; w<ddN.W; w++)
gpvec[w] /= tot;
}
if ( ddS.Nwt ) {
for (k=0; k<ddN.T; k++) {
Nk_tot += ddS.NWt[k];
}
}
psort = sorttops(gtvec, ddN.T);
top1cnt = hca_top1cnt();
if ( !top1cnt )
yap_quit("Cannot allocate top1cnt in hca_displaytopics()\n");
if ( pmicount ) {
tpmi = malloc(sizeof(*tpmi)*(ddN.T+1));
if ( !tpmi )
yap_quit("Cannot allocate tpmi in hca_displaytopics()\n");
}
indk = malloc(sizeof(*indk)*ddN.W);
if ( !indk )
yap_quit("Cannot allocate indk in hca_displaytopics()\n");
if ( termstats ) {
termindk = malloc(sizeof(*indk)*termstats->K);
if ( !termindk )
yap_quit("Cannot allocate termindk in hca_displaytopics()\n");
}
data_df(stem);
#ifdef KL
for (w=0; w<ddN.W; w++)
dfvec[w] = ddD.df[w];
#endif
/*
* two passes through,
* first to build the top words and dump to file
*/
repfile = yap_makename(resstem,".topset");
topfile = yap_makename(resstem,".toplst");
fp = fopen(topfile,"w");
if ( !fp )
yap_sysquit("Cannot open file '%s' for write\n", topfile);
yap_message("\n");
for (k=0; k<ddN.T; k++) {
int cnt, termcnt = 0;
tscorek = k;
/*
* build sorted word list
*/
cnt = buildindk(k, indk);
topk(topword, cnt, indk, tscore);
if ( cnt==0 )
continue;
if ( termstats ) {
termcnt = buildtermindk(k, termindk, termstats);
topk(topword, termcnt, termindk, termtscore);
}
/*
* dump words to file
*/
fprintf(fp,"%d: ", k);
for (w=0; w<topword && w<cnt; w++) {
fprintf(fp," %d", (int)indk[w]);
}
if ( termstats ) {
for (w=0; w<topword && w<termcnt; w++) {
fprintf(fp," %d", (int)termstats->Kmin+termindk[w]);
}
}
fprintf(fp, "\n");
}
if ( ddP.PYbeta && (ddP.phi==NULL || ddP.betapr) ) {
int cnt;
/*
* dump root words
*/
tscorek = -1;
cnt = buildindk(-1, indk);
topk(topword, cnt, indk, (ddP.phi==NULL)?countscore:phiscore);
fprintf(fp,"-1:");
for (w=0; w<topword && w<cnt; w++) {
fprintf(fp," %d", (int)indk[w]);
}
fprintf(fp, "\n");
}
fclose(fp);
if ( verbose>1 ) yap_message("\n");
if ( pmicount ) {
/*
* compute PMI
*/
char *toppmifile;
char *pmifile;
double *tp;
tp = dvec(ddN.T);
pmifile=yap_makename(stem,".pmi");
toppmifile=yap_makename(resstem,".toppmi");
get_probs(tp);
report_pmi(topfile, pmifile, toppmifile, ddN.T, ddN.W, 1,
pmicount, tp, tpmi);
free(toppmifile);
free(pmifile);
free(tp);
}
/*
* now report words and diagnostics
*/
//ttop_open(topfile);
if ( fullreport ) {
rp = fopen(repfile,"w");
if ( !rp )
yap_sysquit("Cannot open file '%s' for write\n", repfile);
fprintf(rp, "#topic index rank prop word-sparse doc-sparse eff-words eff-docs docs-bound top-one "
"dist-unif dist-unigrm");
if ( PCTL_BURSTY() )
fprintf(rp, " burst-concent");
if ( ddN.tokens )
fprintf(rp, " ave-length");
fprintf(rp, " coher");
if ( pmicount )
fprintf(rp, " pmi");
fprintf(rp, "\n#word topic index rank");
if ( ddS.Nwt )
fprintf(rp, " count");
fprintf(rp, " prop cumm df coher\n");
}
for (k=0; k<ddN.T; k++) {
int cnt, termcnt = 0;
int kk = psort[k];
uint32_t **dfmtx;
if ( ddP.phi==NULL && ddS.NWt[kk]==0 )
continue;
/*
* grab word prob vec for later use
*/
if ( ddS.Nwt ) {
int w;
for (w=0; w<ddN.W; w++)
pvec[w] = wordprob(w,kk);
} else if ( ddP.phi )
fv_copy(pvec, ddP.phi[kk], ddN.W);
else if ( ddS.phi )
fv_copy(pvec, ddS.phi[kk], ddN.W);
/*
* rebuild word list
*/
tscorek = kk;
cnt = buildindk(kk, indk);
topk(topword, cnt, indk, tscore);
if ( topword<cnt )
cnt = topword;
assert(cnt>0);
if ( termstats ) {
termcnt = buildtermindk(kk, termindk, termstats);
topk(topword, termcnt, termindk, termtscore);
if ( topword<termcnt )
termcnt = topword;
}
/*
* df stats for topic returned as matrix
*/
dfmtx = hca_dfmtx(indk, cnt, kk);
if ( ddS.Nwt && (ddS.NWt[kk]*ddN.T*100<Nk_tot || ddS.NWt[kk]<5 ))
underused++;
/*
* print stats for topic
* Mallet: tokens, doc_ent, ave-word-len, coher.,
* uni-dist, corp-dist, eff-no-words
*/
yap_message("Topic %d/%d", kk, k);
{
/*
* compute diagnostics
*/
double prop = gtvec[kk];
float *dprop = docprop(kk);
double spw = 0;
double spd = ((double)nonzero_Ndt(kk))/((double)ddN.DT);
#ifdef KL
double ew = fv_kl(dfvec,pvec,ddN.W);
#else
double ew = exp(fv_entropy(pvec,ddN.W));
#endif
double ud = fv_helldistunif(pvec,ddN.W);
double pd = fv_helldist(pvec,gpvec,ddN.W);
double sl = fv_avestrlen(pvec,ddN.tokens,ddN.W);
double co = coherence(dfmtx, cnt);
double ed = dprop?exp(fv_entropy(dprop,ddN.DT)):ddN.DT;
#define MALLET_EW
#ifdef MALLET_EW
double ewp = dprop?(1.0/fv_expprob(pvec,ddN.W)):ddN.W;
#endif
double da = dprop?fv_bound(dprop,ddN.DT,1.0/sqrt((double)ddN.T)):0;
sparsitydoc += spd;
yap_message((ddN.T>200)?" p=%.3lf%%":" p=%.2lf%%",100*prop);
#ifdef XTRA
yap_message((ddN.T>200)?"/%.3lf%%":"/%.2lf%%",100*gtavec[kk]);
#endif
if ( ddS.Nwt ) {
spw = ((double)nonzero_Nwt(kk))/((double)ddN.W);
sparsityword += spw;
yap_message(" ws=%.1lf%%", 100*(1-spw));
}
yap_message(" ds=%.1lf%%", 100*(1-spd) );
#ifdef KL
yap_message(" ew=%lf", ew);
#else
yap_message(" ew=%.0lf", ew);
#endif
#ifdef MALLET_EW
yap_message(" ewp=%.1lf", ewp);
#endif
yap_message(" ed=%.1lf", ed);
yap_message(" da=%.0lf", da+0.1);
yap_message(" t1=%u", top1cnt[kk]);
yap_message(" ud=%.3lf", ud);
yap_message(" pd=%.3lf", pd);
if ( PCTL_BURSTY() )
yap_message(" bd=%.3lf", ddP.bdk[kk]);
if ( ddP.NGbeta ) {
/*
* approx. as sqrt(var(lambda_k)/lambda-normaliser
*/
double ngvar = sqrt(ddP.NGalpha[kk])
* (ngalpha[kk]/ddP.NGalpha[kk]);
yap_message(" ng=%.4lf,%.4lf",
ngalpha[kk], ngvar/ngalpha[kk]);
if ( ddS.sparse )
yap_message(",%.4f", 1-((float)ddS.sparseD[kk])/ddN.DTused);
if ( verbose>2 )
yap_message(" ngl=%.4lf,%.4lf, nga=%.4lf,%.4lf",
ddP.NGalpha[kk]/ddP.NGbeta[kk],
sqrt(ddP.NGalpha[kk]/ddP.NGbeta[kk]/ddP.NGbeta[kk]),
ddP.NGalpha[kk], ddP.NGbeta[kk]);
}
if ( ddN.tokens )
yap_message(" sl=%.2lf", sl);
yap_message(" co=%.3lf%%", co);
if ( pmicount )
yap_message(" pmi=%.3f", tpmi[kk]);
if ( fullreport ) {
fprintf(rp,"topic %d %d", kk, k);
fprintf(rp," %.6lf", prop);
if ( ddS.Nwt ) {
fprintf(rp," %.6lf", (1-spw));
} else {
fprintf(rp," 0");
}
fprintf(rp," %.6lf", (1-spd) );
#ifdef KL
yap_message(" %lf", ew);
#else
fprintf(rp," %.2lf", ew);
#endif
#ifdef MALLET_EW
fprintf(rp," %.2lf", ewp);
#endif
fprintf(rp," %.2lf", ed);
fprintf(rp," %.0lf", da+0.1);
fprintf(rp," %u", top1cnt[kk]);
fprintf(rp," %.6lf", ud);
fprintf(rp," %.6lf", pd);
if ( PCTL_BURSTY() )
fprintf(rp," %.3lf", ddP.bdk[kk]);
fprintf(rp," %.4lf", (ddN.tokens)?sl:0);
fprintf(rp," %.6lf", co);
if ( pmicount )
fprintf(rp," %.4f", tpmi[kk]);
fprintf(rp,"\n");
}
if ( dprop) free(dprop);
}
if ( verbose>1 ) {
double pcumm = 0;
/*
* print top words:
* Mallet: rank, count, prob, cumm, docs, coh
*/
yap_message("\ntopic %d/%d", kk, k);
yap_message(" words=");
for (w=0; w<cnt; w++) {
if ( w>0 ) yap_message(",");
if ( ddN.tokens )
yap_message("%s", ddN.tokens[indk[w]]);
else
yap_message("%d", indk[w]);
if ( verbose>2 ) {
if ( scoretype == ST_count )
yap_message("(%d)", (int)(tscore(indk[w])+0.2));
else
yap_message("(%6lf)", tscore(indk[w]));
}
if ( fullreport ) {
fprintf(rp, "word %d %d %d", kk, indk[w], w);
if ( ddS.Nwt )
fprintf(rp, " %d", ddS.Nwt[indk[w]][kk]);
pcumm += pvec[indk[w]];
fprintf(rp, " %.6f %.6f", pvec[indk[w]], pcumm);
fprintf(rp, " %d", dfmtx[w][w]);
fprintf(rp, " %.6f", coherence_word(dfmtx, cnt, w));
if ( ddN.tokens )
fprintf(rp, " %s", ddN.tokens[indk[w]]);
fprintf(rp, "\n");
}
}
if ( termstats ) {
yap_message(" terms=");
for (w=0; w<termcnt; w++) {
if ( w>0 ) yap_message(",");
if ( ddN.tokens )
yap_message("%s", termstats->tokens[termindk[w]]);
else
yap_message("%d", termstats->Kmin+termindk[w]);
if ( verbose>2 ) {
if ( scoretype == ST_count )
yap_message("(%d)", (int)(termtscore(termindk[w])+0.2));
else
yap_message("(%6lf)", termtscore(termindk[w]));
}
if ( fullreport ) {
fprintf(rp, "term %d %d %d", kk, termindk[w], w);
fprintf(rp, " %d", termstats->Nkt[termindk[w]][kk]);
fprintf(rp, " %s", termstats->tokens[termindk[w]]);
fprintf(rp, "\n");
}
}
}
}
yap_message("\n");
free(dfmtx[0]); free(dfmtx);
}
if ( verbose>1 && ddP.PYbeta ) {
int cnt;
double pcumm = 0;
/*
* print root words
*/
tscorek = -1;
cnt = buildindk(-1,indk);
/* this case gives bad results */
// if ( scoretype == ST_phirat ) topk(topword, cnt, indk, phiratioscore);
topk(topword, cnt, indk, (ddP.phi==NULL)?countscore:phiscore);
/*
* cannot build df mtx for root because
* it is latent w.r.t. topics
*/
yap_message("Topic root words=");
if ( fullreport ) {
int w;
if ( ddP.phi && ddP.PYbeta!=H_PDP ) {
for (w=0; w<ddN.W; w++)
pvec[w] = ddS.phi[ddN.T][w];
} else {
for (w=0; w<ddN.W; w++)
pvec[w] = betabasewordprob(w);
}
#ifdef KL
double ew = fv_kl(dfvec,pvec,ddN.W);
#else
double ew = exp(fv_entropy(pvec,ddN.W));
#endif
double ud = fv_helldistunif(pvec,ddN.W);
double pd = fv_helldist(pvec,gpvec,ddN.W);
fprintf(rp,"topic -1 -1 0 0");
fprintf(rp," %.4lf", ew);
fprintf(rp," %.6lf", ud);
fprintf(rp," %.6lf", pd);
fprintf(rp,"\n");
}
for (w=0; w<topword && w<cnt; w++) {
if ( w>0 ) yap_message(",");
if ( ddN.tokens )
yap_message("%s", ddN.tokens[indk[w]]);
else
yap_message("%d", indk[w]);
if ( verbose>2 && !ddP.phi )
yap_message("(%6lf)", countscore(indk[w]));
if ( fullreport ) {
fprintf(rp, "word %d %d %d", -1, indk[w], w);
if ( ddS.TwT )
fprintf(rp, " %d", ddS.TwT[w]);
pcumm += pvec[indk[w]];
fprintf(rp, " %.6f %.6f", pvec[indk[w]], pcumm);
fprintf(rp, " 0 0");
if ( ddN.tokens )
fprintf(rp, " %s", ddN.tokens[indk[w]]);
fprintf(rp, "\n");
}
}
yap_message("\nTopical words=");
topk(topword, cnt, indk, phiinvratioscore);
for (w=0; w<topword && w<cnt; w++) {
if ( w>0 ) yap_message(",");
if ( ddN.tokens )
yap_message("%s", ddN.tokens[indk[w]]);
else
yap_message("%d", indk[w]);
}
yap_message("\n");
}
yap_message("\n");
if ( rp )
fclose(rp);
if ( ddS.Nwt )
yap_message("Average topicXword sparsity = %.2lf%%\n",
100*(1-sparsityword/ddN.T) );
yap_message("Average docXtopic sparsity = %.2lf%%\n"
"Underused topics = %.1lf%%\n",
100*(1-sparsitydoc/ddN.T),
100.0*underused/(double)ddN.T);
if ( ddS.sparse && ddP.PYalpha==H_NG ) {
double avesp = 0;
// correct_docsp();
for (k=0; k<ddN.T; k++) {
avesp += gtvec[k];
}
// check gtvec[] sums to 1
assert(fabs(avesp-1.0)<0.00001);
avesp = 0;
for (k=0; k<ddN.T; k++) {
avesp += gtvec[k]*((float)ddS.sparseD[k])/ddN.DTused;
assert(ddS.sparseD[k]<=ddN.DTused);
}
assert(avesp<=1.0);
assert(avesp>0.0);
yap_message("IBP sparsity = %.2lf%%\n", 100*(1-avesp));
}
if ( pmicount )
yap_message("Average PMI = %.3f\n", tpmi[ddN.T]);
/*
* print
*/
if ( 1 ) {
float **cmtx = hca_topmtx();
int t1, t2;
int m1, m2;
float mval;
char *corfile = yap_makename(resstem,".topcor");
fp = fopen(corfile,"w");
if ( !fp )
yap_sysquit("Cannot open file '%s' for write\n", corfile);
/*
* print file
*/
for (t1=0; t1<ddN.T; t1++) {
for (t2=0; t2<t1; t2++)
if ( cmtx[t1][t2]>1.0e-7 )
fprintf(fp, "%d %d %0.6f\n", t1, t2, cmtx[t1][t2]);
}
fclose(fp);
free(corfile);
/*
* display maximum
*/
m1 = 1; m2 = 0;
mval = cmtx[1][0];
for (t1=0; t1<ddN.T; t1++) {
for (t2=0; t2<t1; t2++) {
if ( mval<cmtx[t1][t2] ) {
mval = cmtx[t1][t2];
m1 = t1;
m2 = t2;
}
}
}
yap_message("Maximum correlated topics (%d,%d) = %f\n", m1, m2, mval);
free(cmtx[0]); free(cmtx);
}
/*
* print burstiness report
*/
if ( PCTL_BURSTY() ) {
int tottbl = 0;
int totmlttbl = 0;
int totmlt = 0;
int i;
for (i=0; i<ddN.NT; i++) {
if ( Z_issetr(ddS.z[i]) ) {
if ( M_multi(i) )
totmlttbl++;
tottbl++;
}
if ( M_multi(i) )
totmlt++;
}
yap_message("Burst report: multis=%.2lf%%, tables=%.2lf%%, tbls-in-multis=%.2lf%%\n",
100.0*((double)ddM.dim_multiind)/ddN.N,
100.0*((double)tottbl)/ddN.NT,
100.0*((double)totmlttbl)/totmlt);
}
yap_message("\n");
free(topfile);
if ( repfile ) free(repfile);
if ( top1cnt ) free(top1cnt);
free(indk);
free(psort);
if ( ngalpha )
free(ngalpha);
if ( pmicount )
free(tpmi);
if ( NwK ) {
free(NwK);
NwK = NULL;
}
#ifdef KL
free(dfvec);
#endif
free(pvec);
free(gtvec);
free(gpvec);
tstats_free(termstats);
}
void hca_displaytopics(char *stem, char *resstem, int topword,
enum ScoreType scoretype, int pmicount, int fullreport) {
int w,k;
uint32_t *indk = NULL;
int Nk_tot = 0;
double (*tscore)(int) = NULL;
double sparsityword = 0;
double sparsitydoc = 0;
double underused = 0;
uint32_t *top1cnt = NULL;
FILE *fp;
float *tpmi = NULL;
char *topfile;
char *repfile;
uint32_t *psort;
FILE *rp = NULL;
float *gtvec = globalprop();
float *gpvec = calloc(ddN.W,sizeof(gpvec[0]));
float *pvec = calloc(ddN.W,sizeof(pvec[0]));
if ( pmicount>topword )
pmicount = topword;
if ( scoretype == ST_idf ) {
tscore = idfscore;
} else if ( scoretype == ST_phi ) {
tscore = phiscore;
} else if ( scoretype == ST_count ) {
tscore = countscore;
} else if ( scoretype == ST_cost ) {
tscore = costscore;
} else if ( scoretype == ST_Q ) {
tscore = Qscore;
lowerQ = 1.0/ddN.T;
}
/*
* first collect counts of each word/term,
* and build gpvec (mean word probs)
*/
build_NwK();
{
/*
* gpvec[] is normalised NwK[]
*/
double tot = 0;
for (w=0; w<ddN.W; w++)
tot += gpvec[w] = NwK[w]+0.1;
for (w=0; w<ddN.W; w++)
gpvec[w] /= tot;
}
if ( ddS.Nwt ) {
for (k=0; k<ddN.T; k++) {
Nk_tot += ddS.NWt[k];
}
}
psort = sorttops(gtvec, ddN.T);
top1cnt = hca_top1cnt();
if ( !top1cnt )
yap_quit("Cannot allocate top1cnt in hca_displaytopics()\n");
if ( pmicount ) {
tpmi = malloc(sizeof(*tpmi)*(ddN.T+1));
if ( !tpmi )
yap_quit("Cannot allocate tpmi in hca_displaytopics()\n");
}
indk = malloc(sizeof(*indk)*ddN.W);
if ( !indk )
yap_quit("Cannot allocate indk in hca_displaytopics()\n");
/*
* two passes through,
* first to build the top words and dump to file
*/
repfile = yap_makename(resstem,".topset");
topfile = yap_makename(resstem,".toplst");
fp = fopen(topfile,"w");
if ( !fp )
yap_sysquit("Cannot open file '%s' for write\n", topfile);
yap_message("\n");
for (k=0; k<ddN.T; k++) {
int cnt;
tscorek = k;
/*
* build sorted word list
*/
cnt = buildindk(k, indk);
topk(topword, cnt, indk, tscore);
if ( cnt==0 )
continue;
/*
* dump words to file
*/
fprintf(fp,"%d: ", k);
for (w=0; w<topword && w<cnt; w++) {
fprintf(fp," %d", (int)indk[w]);
}
fprintf(fp, "\n");
}
if ( ddP.PYbeta && (ddP.phi==NULL || ddP.betapr) ) {
int cnt;
/*
* dump root words
*/
tscorek = -1;
cnt = buildindk(-1, indk);
topk(topword, cnt, indk, (ddP.phi==NULL)?countscore:phiscore);
fprintf(fp,"-1:");
for (w=0; w<topword && w<cnt; w++) {
fprintf(fp," %d", (int)indk[w]);
}
fprintf(fp, "\n");
}
fclose(fp);
if ( verbose>1 ) yap_message("\n");
if ( pmicount ) {
/*
* compute PMI
*/
char *toppmifile;
char *pmifile;
double *tp;
tp = dvec(ddN.T);
pmifile=yap_makename(stem,".pmi");
toppmifile=yap_makename(resstem,".toppmi");
get_probs(tp);
report_pmi(topfile, pmifile, toppmifile, ddN.T, ddN.W, 1,
pmicount, tp, tpmi);
free(toppmifile);
free(pmifile);
free(tp);
}
/*
* now report words and diagnostics
*/
//ttop_open(topfile);
if ( fullreport ) {
rp = fopen(repfile,"w");
if ( !rp )
yap_sysquit("Cannot open file '%s' for write\n", repfile);
fprintf(rp, "#topic index rank prop word-sparse doc-sparse eff-words eff-docs docs-bound top-one "
"dist-unif dist-unigrm");
if ( PCTL_BURSTY() )
fprintf(rp, " burst-concent");
if ( ddN.tokens )
fprintf(rp, " ave-length");
fprintf(rp, " coher");
if ( pmicount )
fprintf(rp, " pmi");
fprintf(rp, "\n#word topic index rank");
if ( ddS.Nwt )
fprintf(rp, " count");
fprintf(rp, " prop cumm df coher\n");
}
for (k=0; k<ddN.T; k++) {
int cnt;
int kk = psort[k];
uint32_t **dfmtx;
if ( ddP.phi==NULL && ddS.NWt[kk]==0 )
continue;
/*
* grab word prob vec for later use
*/
if ( ddS.Nwt ) {
int w;
for (w=0; w<ddN.W; w++)
pvec[w] = wordprob(w,kk);
} else if ( ddP.phi )
fv_copy(pvec, ddP.phi[kk], ddN.W);
else if ( ddS.phi )
fv_copy(pvec, ddS.phi[kk], ddN.W);
/*
* rebuild word list
*/
tscorek = kk;
cnt = buildindk(kk, indk);
topk(topword, cnt, indk, tscore);
if ( topword<cnt )
cnt = topword;
assert(cnt>0);
/*
* df stats for topic returned as matrix
*/
dfmtx = hca_dfmtx(indk, cnt, kk);
if ( ddS.Nwt && (ddS.NWt[kk]*ddN.T*100<Nk_tot || ddS.NWt[kk]<5 ))
underused++;
/*
* print stats for topic
* Mallet: tokens, doc_ent, ave-word-len, coher.,
* uni-dist, corp-dist, eff-no-words
*/
yap_message("Topic %d/%d", kk, k);
{
/*
* compute diagnostics
*/
double prop = gtvec[kk];
float *dprop = docprop(kk);
double spw = 0;
double spd = ((double)nonzero_Ndt(kk))/((double)ddN.DT);
double ew = exp(fv_entropy(pvec,ddN.W));
double ud = fv_helldistunif(pvec,ddN.W);
double pd = fv_helldist(pvec,gpvec,ddN.W);
double sl = fv_avestrlen(pvec,ddN.tokens,ddN.W);
double co = coherence(dfmtx, cnt);
double ed = dprop?exp(fv_entropy(dprop,ddN.DT)):ddN.DT;
double da = dprop?fv_bound(dprop,ddN.DT,1.0/sqrt((double)ddN.T)):0;
sparsitydoc += spd;
yap_message((ddN.T>200)?" p=%.3lf%%":" p=%.2lf%%",100*prop);
if ( ddS.Nwt ) {
spw = ((double)nonzero_Nwt(kk))/((double)ddN.W);
sparsityword += spw;
yap_message(" ws=%.1lf%%", 100*(1-spw));
}
yap_message(" ds=%.1lf%%", 100*(1-spd) );
yap_message(" ew=%.0lf", ew);
yap_message(" ed=%.1lf", ed);
yap_message(" da=%.0lf", da+0.1);
yap_message(" t1=%u", top1cnt[kk]);
yap_message(" ud=%.3lf", ud);
yap_message(" pd=%.3lf", pd);
if ( PCTL_BURSTY() )
yap_message(" bd=%.3lf", ddP.bdk[kk]);
if ( ddN.tokens )
yap_message(" sl=%.2lf", sl);
yap_message(" co=%.3lf%%", co);
if ( pmicount )
yap_message(" pmi=%.3f", tpmi[kk]);
if ( fullreport ) {
fprintf(rp,"topic %d %d", kk, k);
fprintf(rp," %.6lf", prop);
if ( ddS.Nwt ) {
fprintf(rp," %.6lf", (1-spw));
} else {
fprintf(rp," 0");
}
fprintf(rp," %.6lf", (1-spd) );
fprintf(rp," %.2lf", ew);
fprintf(rp," %.2lf", ed);
fprintf(rp," %.0lf", da+0.1);
fprintf(rp," %u", top1cnt[kk]);
fprintf(rp," %.6lf", ud);
fprintf(rp," %.6lf", pd);
if ( PCTL_BURSTY() )
fprintf(rp," %.3lf", ddP.bdk[kk]);
fprintf(rp," %.4lf", (ddN.tokens)?sl:0);
fprintf(rp," %.6lf", co);
if ( pmicount )
fprintf(rp," %.4f", tpmi[kk]);
fprintf(rp,"\n");
}
if ( dprop) free(dprop);
}
if ( verbose>1 ) {
double pcumm = 0;
/*
* print top words:
* Mallet: rank, count, prob, cumm, docs, coh
*/
yap_message("\ntopic %d/%d", kk, k);
yap_message(" words=");
for (w=0; w<cnt; w++) {
if ( w>0 ) yap_message(",");
if ( ddN.tokens )
yap_message("%s", ddN.tokens[indk[w]]);
else
yap_message("%d", indk[w]);
if ( verbose>2 )
yap_message("(%6lf)", tscore(indk[w]));
if ( fullreport ) {
fprintf(rp, "word %d %d %d", kk, indk[w], w);
if ( ddS.Nwt )
fprintf(rp, " %d", ddS.Nwt[indk[w]][kk]);
pcumm += pvec[indk[w]];
fprintf(rp, " %.6f %.6f", pvec[indk[w]], pcumm);
fprintf(rp, " %d", dfmtx[w][w]);
fprintf(rp, " %.6f", coherence_word(dfmtx, cnt, w));
if ( ddN.tokens )
fprintf(rp, " %s", ddN.tokens[indk[w]]);
fprintf(rp, "\n");
}
}
}
yap_message("\n");
free(dfmtx[0]); free(dfmtx);
}
if ( verbose>1 && ddP.PYbeta && (ddP.phi==NULL || ddP.betapr) ) {
int cnt;
double pcumm = 0;
/*
* print root words
*/
tscorek = -1;
cnt = buildindk(-1,indk);
topk(topword, cnt, indk, (ddP.phi==NULL)?countscore:phiscore);
/*
* cannot build df mtx for root because
* it is latent w.r.t. topics
*/
yap_message("Topic root words=");
if ( fullreport ) {
int w;
for (w=0; w<ddN.W; w++)
pvec[w] = betabasewordprob(w);
double ew = exp(fv_entropy(pvec,ddN.W));
double ud = fv_helldistunif(pvec,ddN.W);
double pd = fv_helldist(pvec,gpvec,ddN.W);
fprintf(rp,"topic -1 -1 0 0");
fprintf(rp," %.4lf", ew);
fprintf(rp," %.6lf", ud);
fprintf(rp," %.6lf", pd);
fprintf(rp,"\n");
}
for (w=0; w<topword && w<cnt; w++) {
if ( w>0 ) yap_message(",");
if ( ddN.tokens )
yap_message("%s", ddN.tokens[indk[w]]);
else
yap_message("%d", indk[w]);
if ( verbose>2 )
yap_message("(%6lf)", countscore(indk[w]));
if ( fullreport ) {
fprintf(rp, "word %d %d %d", -1, indk[w], w);
if ( ddS.TwT )
fprintf(rp, " %d", ddS.TwT[w]);
pcumm += pvec[indk[w]];
fprintf(rp, " %.6f %.6f", pvec[indk[w]], pcumm);
fprintf(rp, " 0 0");
if ( ddN.tokens )
fprintf(rp, " %s", ddN.tokens[indk[w]]);
fprintf(rp, "\n");
}
}
yap_message("\n");
}
yap_message("\n");
if ( rp )
fclose(rp);
if ( ddS.Nwt )
yap_message("Average topicXword sparsity = %.2lf%%\n",
100*(1-sparsityword/ddN.T) );
yap_message("Average docXtopic sparsity = %.2lf%%\n"
"Underused topics = %.1lf%%\n",
100*(1-sparsitydoc/ddN.T),
100.0*underused/(double)ddN.T);
if ( pmicount )
yap_message("Average PMI = %.3f\n", tpmi[ddN.T]);
/*
* print
*/
if ( 1 ) {
float **cmtx = hca_topmtx();
int t1, t2;
int m1, m2;
float mval;
char *corfile = yap_makename(resstem,".topcor");
fp = fopen(corfile,"w");
if ( !fp )
yap_sysquit("Cannot open file '%s' for write\n", corfile);
/*
* print file
*/
for (t1=0; t1<ddN.T; t1++) {
for (t2=0; t2<t1; t2++)
if ( cmtx[t1][t2]>1.0e-3 )
fprintf(fp, "%d %d %0.6f\n", t1, t2, cmtx[t1][t2]);
}
fclose(fp);
free(corfile);
/*
* display maximum
*/
m1 = 1; m2 = 0;
mval = cmtx[1][0];
for (t1=0; t1<ddN.T; t1++) {
for (t2=0; t2<t1; t2++) {
if ( mval<cmtx[t1][t2] ) {
mval = cmtx[t1][t2];
m1 = t1;
m2 = t2;
}
}
}
yap_message("Maximum correlated topics (%d,%d) = %f\n", m1, m2, mval);
free(cmtx[0]); free(cmtx);
}
/*
* print burstiness report
*/
if ( PCTL_BURSTY() ) {
int tottbl = 0;
int totmlttbl = 0;
int totmlt = 0;
int i;
for (i=0; i<ddN.NT; i++) {
if ( Z_issetr(ddS.z[i]) ) {
if ( M_multi(i) )
totmlttbl++;
tottbl++;
}
if ( M_multi(i) )
totmlt++;
}
yap_message("Burst report: multis=%.2lf%%, tables=%.2lf%%, tbls-in-multis=%.2lf%%\n",
100.0*((double)ddM.dim_multiind)/ddN.N,
100.0*((double)tottbl)/ddN.NT,
100.0*((double)totmlttbl)/totmlt);
}
yap_message("\n");
free(topfile);
if ( repfile ) free(repfile);
if ( top1cnt ) free(top1cnt);
free(indk);
free(psort);
if ( pmicount )
free(tpmi);
if ( NwK ) {
free(NwK);
NwK = NULL;
}
free(pvec);
free(gtvec);
free(gpvec);
}
