A histogram library for Java that accepts large datasets with any distribution or range with a very small memory footprint, needs no pre- or post-processing, and provides several statistical functions.

Most current version here: https://github.com/flaptor/hist4j

Hist4j has the following features:

• It adapts to any data distribution, keeping a more or less constant resolution throughout the data range by increasing the resolution where the data is more dense.
• It can process large amounts of data with a very small memory footprint.
• It doesn't need pre- or post-processing to deliver statistics about the data seen so far.

The following statistics are currently available:

• The cumulative density function for a given data point.
• The data point that splits the data set at a given percentile.

To join the project send an email to the project owners (@gmail.com) or write to the mailing list. Also you can send modifications as patches via mail.