protected void searchMedian(Instances instances) {
medians = new double[instances.numAttributes()];
imputations = new int[instances.numAttributes()];
for (int j = 0; j < instances.numAttributes(); ++j) {
int numPresentValues = 0;
if (instances.attribute(j).isNumeric()) {
double[] values = new double[instances.numInstances()];
for (int i = 0; i < instances.numInstances(); ++i) {
Instance current = instances.get(i);
if (Utils.isMissingValue(current.value(j)) == false) {
values[numPresentValues] = current.value(j);
numPresentValues += 1;
}
}
if (numPresentValues > 0) {
double[] goodValues = Arrays.copyOf(values, numPresentValues);
Median median = new Median();
medians[j] = median.evaluate(goodValues);
}
}
}
for (int j = 0; j < instances.numAttributes(); ++j) {
if (instances.attribute(j).isNumeric()) {
Conversion.log(
"OK",
"Impute Numeric",
"Attribute " + instances.attribute(j) + " - Median: " + medians[j]);
}
}
}
private Map<String, Double> getSampleMedian(Set<String> samp, List<String> bad) {
Map<String, Double> sampleMedian = new LinkedHashMap<>();
for (String s : samp) {
List<Double> list = new LinkedList<>();
for (Map.Entry<String, Map<String, Sample>> entry : samples.entrySet()) {
if (!bad.contains(entry.getKey())) {
list.add(entry.getValue().get(s).getNorm1());
}
}
sampleMedian.put(s, median.evaluate(toDoubleArray(list)));
}
return sampleMedian;
}
private double getMedDepth(double[] depth, Set<String> samp) {
int i = 0;
for (Map.Entry<String, Map<String, Sample>> entry : samples.entrySet()) {
Map<String, Sample> sampleMap = entry.getValue();
for (Map.Entry<String, Sample> sampleEntry : sampleMap.entrySet()) {
Sample sample = sampleEntry.getValue();
double norm1 = Precision.round((sample.getCov() * factor.get(sample.getSample())), 2);
sample.setNorm1(norm1);
depth[i++] = norm1;
samp.add(sample.getSample());
}
}
return median.evaluate(depth);
}
/**
* Main method, makes the statistics calculation according to the algorithm print result to the
* Standart output
*/
public void doWork() {
double[] depth = new double[samples.size()];
Set<String> samp = new HashSet<>();
double medDepth = getMedDepth(depth, samp);
List<String> bad = new LinkedList<>();
List<Double> gooddepth = new LinkedList<>();
splitQualitySamples(samp, medDepth, bad, gooddepth);
medDepth = median.evaluate(toDoubleArray(gooddepth));
Map<String, Double> factor2 = new LinkedHashMap<>();
setFactor2(medDepth, bad, factor2);
Map<String, Double> sampleMedian = getSampleMedian(samp, bad);
setNorm(medDepth, bad, factor2, sampleMedian);
printResult(bad);
}
public static Double median(double[] values) {
Median medianCalculator = new Median();
return medianCalculator.evaluate(values);
}
