private static Double evaluate(Collection<?> values, int quantile) {
List<Double> doubleValues = new ArrayList<>();
for (Object value : values) {
Double doubleValue = (Double) TypeUtil.parseOrCast(DataType.DOUBLE, value);
doubleValues.add(doubleValue);
}
double[] data = Doubles.toArray(doubleValues);
// The data must be (at least partially) ordered
Arrays.sort(data);
Percentile percentile = new Percentile();
percentile.setData(data);
return percentile.evaluate(quantile);
}
/**
* @return an array of values to split the numeric feature's values on when building candidate
* splits. When input size is <= MAX_NUMERIC_SPLITS + 1, it will return the averages between
* success values as split points. When larger, it will return MAX_NUMERIC_SPLITS approximate
* percentiles through the data.
*/
private static double[] chooseNumericSplitPoints(double[] values) {
if (values.length <= 1) {
return values;
}
if (values.length <= MAX_NUMERIC_SPLITS + 1) {
double[] splitPoints = new double[values.length - 1];
for (int i = 1; i < values.length; i++) {
splitPoints[i - 1] = (values[i] + values[i - 1]) / 2.0;
}
return splitPoints;
}
Percentile distribution = new Percentile();
distribution.setData(values);
double[] percentiles = new double[MAX_NUMERIC_SPLITS];
for (int i = 0; i < percentiles.length; i++) {
double p = 100.0 * ((i + 1.0) / (MAX_NUMERIC_SPLITS + 1.0));
percentiles[i] = distribution.evaluate(p);
}
return percentiles;
}
