JIDT provides a standalone, open source code Java implementation (usable in Matlab, Octave and Python) of information-theoretic measures of distributed computation in complex systems: i.e. information storage, transfer and modification.
This includes implementations for:
- both discrete and continuous-valued variables, principally for the measures transfer entropy, mutual information and active information storage;
- using various types of estimators (e.g. Kraskov-Stögbauer-Grassberger estimators, kernel estimation, linear-Gaussian).
"Full" description of any required installation is at: http://code.google.com/p/information-dynamics-toolkit/wiki/Installation
However, if you are reading this file, you've downloaded a distribution and you're halfway there!
There are no dependencies to download; unless:
a. You don't have java installed - download it from http://www.java.com/
b. You wish to build the project using the build.xml script - this requires ant: http://ant.apache.org/
c. You wish to run the JUnit test cases - this requires JUnit: http://www.junit.org/ - for how to run JUnit with our ant script see http://code.google.com/p/information-dynamics-toolkit/wiki/JUnitTestCases
Then just put the jar in a relevant location in your file structure.
a. demos/java -- basic examples on easily using the Java toolkit -- run these from the shell scripts in this directory -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/SimpleJavaExamples
b. demos/octave -- basic examples on easily using the Java toolkit from Octave or Matlab environments -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/OctaveMatlabExamples
c. demos/python -- basic examples on easily using the Java toolkit from Python -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/PythonExamples
d. demos/octave/CellularAutomata -- using the Java toolkit to plot local information dynamics profiles in cellular automata; the toolkit is run under Octave or Matlab -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/CellularAutomataDemos
e. demos/octave/SchreiberTransferEntropyExamples -- recreates the transfer entropy examples in Schreiber's original paper presenting this measure; shows the correct parameter settings to reproduce these results -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/SchreiberTeDemos
f. demos/octave/DetectingInteractionLags -- demonstration of using the transfer entropy with source-destination lags; the demo is run under Octave or Matlab -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/DetectingInteractionLags
g. demos/java/InterregionalTransfer -- higher level example using collective transfer entropy to infer effective connections between "regions" of data -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/InterregionalTransfer
h. demos/octave/NullDistributions -- investigating the correspondence between analytic and bootstrapped distributions for TE and MI under null hypotheses of no relationship; the demo is run under Octave or Matlab -- see description at https://code.google.com/p/information-dynamics-toolkit/wiki/NullDistributions
i. java/unittests -- the JUnit test cases for the Java toolkit are included in the distribution -- these case also be browsed to see simple use cases for the various calculators in the toolkit -- see description at http://code.google.com/p/information-dynamics-toolkit/wiki/JUnitTestCases
This project includes modified files from the Apache Commons Math library -- http://commons.apache.org/proper/commons-math/
This Apache 2 software is now included as a derivative work in this GPLv3 licensed JIDT project, as per: http://www.apache.org/licenses/GPL-compatibility.html
Notices and license for this software are found in the notices/commons-math directory.
Added the draft of the paper on the toolkit to the release;
Javadocs made ready for release;
Switched source->destination arguments for discrete TE calculators to be with source first in line with continuous calculators;
Renamed all discrete calculators to have Discrete suffix -- TE and conditional TE calculators also renamed to remove "Apparent" prefix and change "Complete" to "Conditional";
Kraskov estimators now using 4 nearest neighbours by default;
Unit test for Gaussian TE against ChaLearn Granger causality measurement;
Added Schreiber TE demos; Interregional transfer demos; documentation for Interaction lag demos; added examples 7 and 8 to Simple Java demos;
Added property to add noise to data for Kraskov MI;
Added derivation of Apache Commons Math code for chi square distribution, and included relevant notices in our release;
Inserted translation class for arrays between Octave and Java;
Added analytic statistical significance calculation to Gaussian calculators and discrete TE;
Corrected Kraskov algorithm 2 for conditional MI to follow equation in Wibral et al. 2014.
v0.2.0 20/4/2014 at r284
------------------------
Rearchitected (most) Transfer Entropy and Multivariate TE calculators to use an underlying conditional mutual information calculator, and have arbitrary embedding delay, source-dest delay;
this includes moving Kraskov-Grassberger Transfer Entropy calculator to use a single conditional mutual information estimator instead of two mutual information estimators;
Rearchitected (most) Active Information Storage calculators to use an underlying mutual information calculator;
Added Conditional Transfer Entropy calculators using underlying conditional mutual information calculators;
Moved mixed discrete-continuous calculators to a new "mixed" package;
bug fixes.
v0.1.4 11/9/2013 at r241
------------------------
added scripts to generate CA figures for 2013 book chapters;
added general Java demo code;
added Python demo code;
made Octave/Matlab demos and CA demos properly compatible for Matlab;
added extra Octave/Matlab general demos;
added more unit tests for MI and conditional MI calculators, including against results from Wibral's TRENTOOL;
bug fixes.
v0.1.3 13/1/2013 at r151
------------------------
existing Octave/Matlab demo code made compatible with Matlab;
several bug fixes, including using max norm by default in Kraskov calculator (instead of requiring this to be set explicitly);
more unit tests (including against results from Kraskov's own MI implementation)
