Download JAR files tagged by dimensional with all dependencies

# geokey K Dimensional Z-Order curve utils. [](https://travis-ci.org/markrileybot/geokey) [](https://coveralls.io/github/markrileybot/geokey?branch=master) [](https://maven-badges.herokuapp.com/maven-central/io.github.markrileybot/geokey) ## Building ./gradlew build ## Gradle dependency See https://search.maven.org/artifact/io.github.markrileybot/geokey/ ## Using ### Use built in keys to make geohashes ```java import org.geokey.GeoKey; // Make a geo hash key String key = new GeoKey().setLatitude(48.669).setLongitude(-4.329).toString(); // "gbsuv7ztqzpts82uzfwq5e1bp" // parse a geo hash key GeoKey gk = new GeoKey("gbsuv7ztqzpts82uzfwq5e1bp"); ``` ### Make a special purpose K-Dimensional key ```java public class GeoTimeKey extends KDKey { private static final KDKeySpec spec = new KDKeySpec.Builder() .addDim(-180, 180, 1) .addDim(-90, 90, 1) .addDim(0, 1L << 62, 1) .setAlphabet(Alphabet.GEO_TIME_HASH) .build(); public GeoTimeKey() { super(spec); } public GeoTimeKey(String s) { super(spec, s); } public GeoTimeKey(byte[] s) { super(spec, s); } public GeoTimeKey setLatitude(double latitude) { set(1, latitude); return this; } public double getLatitude() { return super.get(1); } public GeoTimeKey setLongitude(double longitude) { set(0, longitude); return this; } public double getLongitude() { return super.get(0); } public GeoTimeKey setTime(long time) { set(2, time); return this; } public long getTime() { return (long) get(2); } } ```

Class for building pace regression linear models and using them for prediction. Under regularity conditions, pace regression is provably optimal when the number of coefficients tends to infinity. It consists of a group of estimators that are either overall optimal or optimal under certain conditions. The current work of the pace regression theory, and therefore also this implementation, do not handle: - missing values - non-binary nominal attributes - the case that n - k is small where n is the number of instances and k is the number of coefficients (the threshold used in this implmentation is 20) For more information see: Wang, Y (2000). A new approach to fitting linear models in high dimensional spaces. Hamilton, New Zealand. Wang, Y., Witten, I. H.: Modeling for optimal probability prediction. In: Proceedings of the Nineteenth International Conference in Machine Learning, Sydney, Australia, 650-657, 2002.