use of uk.ac.sussex.gdsc.smlm.results.PeakResult in project GDSC-SMLM by aherbert.
the class Filter method filterSubset.
/**
* Filter the results.
*
* <p>Input PeakResults must be allocated a score for true positive, false positive, true negative
* and false negative (accessed via the object property get methods). The filter is run and
* results that pass accumulate scores for true positive and false positive, otherwise the scores
* are accumulated for true negative and false negative. The simplest scoring scheme is to mark
* valid results as tp=fn=1 and fp=tn=0 and invalid results the opposite.
*
* <p>The number of consecutive rejections are counted per frame. When the configured number of
* failures is reached all remaining results for the frame are rejected. This assumes the results
* are ordered by the frame.
*
* <p>The number of failures before each peak is stored in the origX property of the PeakResult.
*
* @param results the results
* @param failures the number of failures to allow per frame before all peaks are rejected
* @param score If not null will be populated with the fraction score [ tp, fp, tn, fn, p, n ]
* @return the filtered results
*/
public MemoryPeakResults filterSubset(MemoryPeakResults results, final int failures, double[] score) {
final MemoryPeakResults newResults = new MemoryPeakResults();
final FrameCounter counter = new FrameCounter();
newResults.copySettings(results);
setup(results);
final double[] s = new double[4];
results.forEach((PeakResultProcedure) peak -> {
counter.advanceAndReset(peak.getFrame());
final boolean isPositive;
if (counter.getCount() > failures) {
isPositive = false;
} else {
isPositive = accept(peak);
}
if (isPositive) {
peak.setOrigX(counter.getCount());
counter.reset();
newResults.add(peak);
} else {
counter.increment();
}
if (isPositive) {
s[TP] += peak.getTruePositiveScore();
s[FP] += peak.getFalsePositiveScore();
} else {
s[FN] += peak.getFalseNegativeScore();
s[TN] += peak.getTrueNegativeScore();
}
});
end();
if (score != null && score.length > 5) {
score[0] = s[TP];
score[1] = s[FP];
score[2] = s[TN];
score[3] = s[FN];
score[4] = newResults.size();
score[5] = (double) results.size() - newResults.size();
}
return newResults;
}
use of uk.ac.sussex.gdsc.smlm.results.PeakResult in project GDSC-SMLM by aherbert.
the class Filter method score.
/**
* Filter the results and return the performance score. Allows benchmarking the filter by marking
* the results as true or false.
*
* <p>Any input PeakResult with an original value that is not zero will be treated as a true
* result, all other results are false. The filter is run and the results are marked as true
* positive, false negative and false positive.
*
* @param resultsList a list of results to analyse
* @return the score
*/
public ClassificationResult score(List<MemoryPeakResults> resultsList) {
final int[] s = new int[4];
for (final MemoryPeakResults peakResults : resultsList) {
setup(peakResults);
peakResults.forEach((PeakResultProcedure) peak -> {
final boolean isTrue = peak.getOrigValue() != 0;
final boolean isPositive = accept(peak);
if (isTrue) {
if (isPositive) {
s[TP]++;
} else {
s[FN]++;
}
} else if (isPositive) {
s[FP]++;
} else {
s[TN]++;
}
});
end();
}
return new ClassificationResult(s[TP], s[FP], s[TN], s[FN]);
}
use of uk.ac.sussex.gdsc.smlm.results.PeakResult in project GDSC-SMLM by aherbert.
the class Filter method filterSubset2.
/**
* Filter the results.
*
* <p>Input PeakResults must be allocated a score for true positive, false positive, true negative
* and false negative (accessed via the object property get methods). The filter is run and
* results that pass accumulate scores for true positive and false positive, otherwise the scores
* are accumulated for true negative and false negative. The simplest scoring scheme is to mark
* valid results as tp=fn=1 and fp=tn=0 and invalid results the opposite.
*
* <p>The number of consecutive rejections are counted per frame. When the configured number of
* failures is reached all remaining results for the frame are rejected. This assumes the results
* are ordered by the frame.
*
* <p>Note that this method is to be used to score a set of results that may have been extracted
* from a larger set since the number of consecutive failures before each peak are expected to be
* stored in the origY property. Set this to zero and the results should be identical to
* {@link #filterSubset(MemoryPeakResults, int, double[])}.
*
* <p>The number of failures before each peak is stored in the origX property of the PeakResult.
*
* @param results the results
* @param failures the number of failures to allow per frame before all peaks are rejected
* @param score If not null will be populated with the fraction score [ tp, fp, tn, fn, p, n ]
* @return the filtered results
*/
public MemoryPeakResults filterSubset2(MemoryPeakResults results, final int failures, double[] score) {
final MemoryPeakResults newResults = new MemoryPeakResults();
final FrameCounter counter = new FrameCounter();
newResults.copySettings(results);
setup(results);
final double[] s = new double[4];
results.forEach((PeakResultProcedure) peak -> {
counter.advanceAndReset(peak.getFrame());
counter.increment(peak.getOrigY());
final boolean isPositive;
if (counter.getCount() > failures) {
isPositive = false;
} else {
isPositive = accept(peak);
}
if (isPositive) {
peak.setOrigX(counter.getCount());
counter.reset();
newResults.add(peak);
} else {
counter.increment();
}
if (isPositive) {
s[TP] += peak.getTruePositiveScore();
s[FP] += peak.getFalsePositiveScore();
} else {
s[FN] += peak.getFalseNegativeScore();
s[TN] += peak.getTrueNegativeScore();
}
});
end();
if (score != null && score.length > 5) {
score[0] = s[TP];
score[1] = s[FP];
score[2] = s[TN];
score[3] = s[FN];
score[4] = newResults.size();
score[5] = (double) results.size() - newResults.size();
}
return newResults;
}
use of uk.ac.sussex.gdsc.smlm.results.PeakResult in project GDSC-SMLM by aherbert.
the class ImageJImagePeakResultsTest method addPeakResults.
private static void addPeakResults(ImageJImagePeakResults results, int[] time, float[] x, float[] y, float[] value) {
final LocalList<PeakResult> list = new LocalList<>(x.length);
for (int i = 0; i < x.length; i++) {
list.add(new PeakResult(time[i], 0, 0, 0, 0, 0, 0, createParams(x[i], y[i], value[i]), null));
}
results.addAll(list);
}
Aggregations