} else {
if ( rp->score > norm->max )
norm->max = rp->score;
- if ( rp->score < norm->min && abs(rp->score) < 1e-6 )
- norm->min = rp->score; // skip zeroes
+ if ( rp->score < norm->min )
+ norm->min = rp->score;
}
}
}
static void normalize_scores(struct relevance *rel)
{
const int maxiterations = 1000;
- const double enough = 1000.0; // sets the number of decimals we are happy with
+ const double enough = 100.0; // sets the number of decimals we are happy with
const double stepchange = 0.5; // reduction of the step size when finding middle
// 0.5 sems to be magical, much better than 0.4 or 0.6
struct norm_client *norm;
for ( norm = rel->norm; norm; norm = norm->next )
{
- yaz_log(YLOG_LOG,"Normalizing client %d: scorefield=%d count=%d range=%f %f",
- norm->num, norm->scorefield, norm->count, norm->min, norm->max);
+ yaz_log(YLOG_LOG,"Normalizing client %d: scorefield=%d count=%d range=%f %f = %f",
+ norm->num, norm->scorefield, norm->count, norm->min,
+ norm->max, norm->max-norm->min);
norm->a = 1.0; // default normalizing factors, no change
norm->b = 0.0;
if ( norm->scorefield != scorefield_none &&
double chi;
char *branch = "?";
// initial guesses for the parameters
+ // Rmax = a * rmax + b # want to be 1.0
+ // Rmin = a * rmin + b # want to be 0.0
+ // Rmax - Rmin = a ( rmax - rmin ) # subtracting equations
+ // 1.0 - 0.0 = a ( rmax - rmin )
+ // a = 1 / range
+ // Rmin = a * rmin + b
+ // b = Rmin - a * rmin
+ // = 0.0 - 1/range * rmin
+ // = - rmin / range
+
if ( range < 1e-6 ) // practically zero
range = norm->max;
a = 1.0 / range;
- b = abs(norm->min);
+ b = -1.0 * norm->min / range;
+ // b = fabs(norm->min) / range;
as = a / 10;
- bs = b / 10;
+ bs = fabs(b) / 10;
chi = squaresum( norm->records, a,b);
+ yaz_log(YLOG_LOG,"Initial done: it=%d: a=%f / %f b=%f / %f chi = %f",
+ 0, a, as, b, bs, chi );
while (it++ < maxiterations) // safeguard against things not converging
{
double aplus = squaresum(norm->records, a+as, b);
branch = "step b";
}
}
- yaz_log(YLOG_LOG,"Fitting %s it=%d: a=%f %f b=%f %f chi=%f ap=%f am=%f, bp=%f bm=%f p=%f",
+ yaz_log(YLOG_LOG,"Fitting %s it=%d: a=%g %g b=%g %g chi=%g ap=%g am=%g, bp=%g bm=%g p=%g",
branch, it, a, as, b, bs, chi,
aplus, aminus, bplus, bminus, prevchi );
norm->a = a;
}
}
- yaz_log(YLOG_LOG,"Fitting done: it=%d: a=%f / %f b=%f / %f chi = %f",
+ yaz_log(YLOG_LOG,"Fitting done: it=%d: a=%g / %g b=%g / %g chi = %g",
it-1, a, as, b, bs, chi );
- yaz_log(YLOG_LOG," a: %f < %f %d",
- fabs(as)*enough, fabs(a), (fabs(as) * enough < fabs(a)) );
- yaz_log(YLOG_LOG," b: %f < %f %d",
- fabs(bs)*enough, fabs(b), (fabs(bs) * enough < fabs(b)) );
}
if ( norm->scorefield != scorefield_none )
<md-score>2.304635</md-score>
</location>
<count>1</count>
- <relevance>6645</relevance>
+ <relevance>8294</relevance>
<recid>content: title water management problems and challenges in india author dinesh kumar m medium book</recid>
</hit>
<hit>
<md-score>2.231453</md-score>
</location>
<count>1</count>
- <relevance>5215</relevance>
+ <relevance>6424</relevance>
<recid>content: title the magic of water author hochschwender ted medium book</recid>
</hit>
<hit>
<md-score>2.186368</md-score>
</location>
<count>1</count>
- <relevance>4334</relevance>
+ <relevance>5273</relevance>
<recid>content: title water author de villiers marq medium book</recid>
</hit>
<hit>
<md-score>2.186368</md-score>
</location>
<count>1</count>
- <relevance>4334</relevance>
+ <relevance>5273</relevance>
<recid>content: title water use for public water supply in michigan medium book</recid>
</hit>
<hit>
<md-score>2.114981</md-score>
</location>
<count>1</count>
- <relevance>2939</relevance>
+ <relevance>3449</relevance>
<recid>content: title report to the iucn on water demand management country study medium book</recid>
</hit>
<hit>
<md-score>2.061328</md-score>
</location>
<count>1</count>
- <relevance>1890</relevance>
+ <relevance>2078</relevance>
<recid>content: title evaluation and control of water pollution in bhavani basin medium book</recid>
</hit>
<hit>
<md-score>2.061328</md-score>
</location>
<count>1</count>
- <relevance>1890</relevance>
+ <relevance>2078</relevance>
<recid>content: title unsia water cluster medium book</recid>
</hit>
<hit>
<md-score>2.061328</md-score>
</location>
<count>1</count>
- <relevance>1890</relevance>
+ <relevance>2078</relevance>
<recid>content: title water and water supplies author thresh john clough medium book</recid>
</hit>
<hit>
<md-score>2.061328</md-score>
</location>
<count>1</count>
- <relevance>1890</relevance>
+ <relevance>2078</relevance>
<recid>content: title water author majeed abdul medium book</recid>
</hit>
<hit>
<md-score>2.061328</md-score>
</location>
<count>1</count>
- <relevance>1890</relevance>
+ <relevance>2078</relevance>
<recid>content: title water law author fisher d e medium book</recid>
</hit>
<hit>
<md-score>2.061328</md-score>
</location>
<count>1</count>
- <relevance>1890</relevance>
+ <relevance>2078</relevance>
<recid>content: title water technology management medium book</recid>
</hit>
<hit>
<md-score>2.037029</md-score>
</location>
<count>1</count>
- <relevance>1415</relevance>
+ <relevance>1457</relevance>
<recid>content: title wonderful water author glover david medium book</recid>
</hit>
<hit>
<md-score>2.016555</md-score>
</location>
<count>1</count>
- <relevance>1015</relevance>
+ <relevance>934</relevance>
<recid>content: title a primer on fresh water medium book</recid>
</hit>
<hit>
<md-score>2.016555</md-score>
</location>
<count>2</count>
- <relevance>1015</relevance>
+ <relevance>934</relevance>
<recid>content: title water quality assessment of the state water project medium book</recid>
</hit>
<hit>
<md-score>1.928196</md-score>
</location>
<count>1</count>
- <relevance>-710</relevance>
+ <relevance>-1322</relevance>
<recid>content: title district water supply plan medium book</recid>
</hit>
<hit>
<md-score>1.928196</md-score>
</location>
<count>1</count>
- <relevance>-710</relevance>
+ <relevance>-1322</relevance>
<recid>content: title proposition medium book</recid>
</hit>
<hit>
<md-score>1.928196</md-score>
</location>
<count>1</count>
- <relevance>-710</relevance>
+ <relevance>-1322</relevance>
<recid>content: title wastewater and drinking water user charge survey medium book</recid>
</hit>
<hit>
<md-score>1.928196</md-score>
</location>
<count>1</count>
- <relevance>-710</relevance>
+ <relevance>-1322</relevance>
<recid>content: title water in press medium book</recid>
</hit>
<hit>
<md-score>1.928196</md-score>
</location>
<count>1</count>
- <relevance>-710</relevance>
+ <relevance>-1322</relevance>
<recid>content: title who governs water author frey hans medium book</recid>
</hit>
</show>
\ No newline at end of file
projects / pazpar2-moved-to-github.git / commitdiff