use of org.apache.commons.math.MathException in project beast-mcmc by beast-dev.
the class GammaDistribution method testQuantileCM.
private static void testQuantileCM(double y, double shape, double scale) {
long time = System.currentTimeMillis();
double value = 0;
try {
for (int i = 0; i < 1000; i++) {
value = (new org.apache.commons.math.distribution.GammaDistributionImpl(shape, scale)).inverseCumulativeProbability(y);
}
value = (new org.apache.commons.math.distribution.GammaDistributionImpl(shape, scale)).inverseCumulativeProbability(y);
} catch (MathException e) {
e.printStackTrace();
}
long elapsed = System.currentTimeMillis() - time;
System.out.println("commons.maths inverseCDF, " + y + ", for shape=" + shape + ", scale=" + scale + " : " + value + ", time=" + elapsed + "ms");
}
use of org.apache.commons.math.MathException in project beast-mcmc by beast-dev.
the class NormalPeriodPriorDistribution method calculateLogPosteriorPredictiveCDF.
public double calculateLogPosteriorPredictiveCDF(double value, boolean upperTail) {
double mean = currentParameters[0];
double sd = Math.sqrt(currentParameters[3] * (currentParameters[1] + 1) / (currentParameters[2] * currentParameters[1]));
double scaledValue = (value - mean) / sd;
double out;
if (2 * currentParameters[2] <= normalApproximationThreshold) {
TDistributionImpl tDist = new TDistributionImpl(2 * currentParameters[2]);
try {
out = upperTail ? Math.log(tDist.cumulativeProbability(-scaledValue)) : Math.log(tDist.cumulativeProbability(scaledValue));
} catch (MathException e) {
throw new RuntimeException(e.toString());
}
} else {
out = upperTail ? NormalDistribution.standardCDF(-scaledValue, true) : NormalDistribution.standardCDF(scaledValue, true);
}
return out;
}
use of org.apache.commons.math.MathException in project compiler by boalang.
the class StatisticsAggregator method finish.
/** {@inheritDoc} */
@Override
public void finish() throws IOException, InterruptedException {
if (this.isCombining()) {
String s = "";
for (final Long key : map.keySet()) s += key + ":" + map.get(key) + ";";
this.collect(s, null);
return;
}
float median = 0;
long medianPos = count / 2L;
long curPos = 0;
long prevPos = 0;
long prevKey = 0;
for (final Long key : map.keySet()) {
curPos = prevPos + map.get(key);
if (prevPos <= medianPos && medianPos < curPos) {
if (curPos % 2 == 0 && prevPos == medianPos)
median = (float) (key + prevKey) / 2.0f;
else
median = key;
break;
}
prevKey = key;
prevPos = curPos;
}
double s1 = 0;
double s2 = 0;
double s3 = 0;
double s4 = 0;
final SummaryStatistics summaryStatistics = new SummaryStatistics();
for (final Long key : map.keySet()) {
s1 += key * map.get(key);
s2 += key * key * map.get(key);
s3 += key * key * key * map.get(key);
s4 += key * key * key * key * map.get(key);
for (int i = 0; i < map.get(key); i++) summaryStatistics.addValue(key);
}
final double mean = s1 / (double) count;
final double var = s2 / (double) (count - 1) - s1 * s1 / (double) (count * (count - 1));
final double stdev = Math.sqrt(var);
final double skewness = (s3 - 3 * s1 * s2 / (double) count + s1 * s1 * s1 * 2 / (count * count)) / (count * stdev * var);
final double kurtosis = (s4 - s3 * s1 * 4 / count + s2 * s1 * s1 * 6 / (double) (count * count) - s1 * s1 * s1 * s1 * 3 / (double) (count * count * count)) / (count * var * var);
double ci = 0.0;
try {
final TDistributionImpl tDist = new TDistributionImpl(summaryStatistics.getN() - 1);
final double a = tDist.inverseCumulativeProbability(1.0 - 0.025);
ci = a * summaryStatistics.getStandardDeviation() / Math.sqrt(summaryStatistics.getN());
} catch (final MathException e) {
}
this.collect(s1 + ", " + mean + ", " + median + ", " + stdev + ", " + var + ", " + kurtosis + ", " + skewness + ", " + ci);
}
use of org.apache.commons.math.MathException in project compiler by boalang.
the class ConfidenceIntervalAggregator method finish.
/** {@inheritDoc} */
@Override
public void finish() throws IOException, InterruptedException {
if (this.isCombining()) {
String s = "";
for (final Long key : map.keySet()) s += key + ":" + map.get(key) + ";";
this.collect(s, null);
return;
}
try {
final SummaryStatistics summaryStatistics = new SummaryStatistics();
for (final Long key : map.keySet()) for (int i = 0; i < map.get(key); i++) summaryStatistics.addValue(key);
final double a = new TDistributionImpl(summaryStatistics.getN() - 1).inverseCumulativeProbability(1.0 - n / 200.0);
this.collect(a * summaryStatistics.getStandardDeviation() / Math.sqrt(summaryStatistics.getN()));
} catch (final MathException e) {
}
}
Aggregations