Package de.lmu.ifi.dbs.elki.utilities.datastructures.histogram

Classes for computing histograms This package contains two families of histograms.

See: Description

Interface Summary

Interface	Description
Histogram	Abstract API for histograms.
Histogram.Iter	Array iterator.
ObjHistogram.BucketFactory<T>	Function to make new buckets.

Class Summary

Class	Description
AbstractObjDynamicHistogram<T>	A dynamic histogram can dynamically adapt the number of bins to the data fed into the histogram.
AbstractStaticHistogram	Abstract base class for histograms.
DoubleDynamicHistogram	A flexible histogram storing double, that can dynamically adapt the number of bins to the data fed into the histogram.
DoubleHistogram	Histogram class storing double values.
ObjHistogram<T>	Histogram class storing double values.

Package de.lmu.ifi.dbs.elki.utilities.datastructures.histogram Description

Classes for computing histograms

This package contains two families of histograms. Static histograms have a fixed initial number of bins. When encountering values outside of their range, they will grow similar to an ArrayList by adding additional bins.

"Dynamic" histograms are more useful when you do not know the value range of the data: they start by collecting a number of sample data, then use this to estimate the initial histogram range. If they grow to twice their initial size they will downsample, to keep the histogram size in the bounds n to 2n-1, which effectively limits the memory use and histogram complexity.