UNITE Toolbox

<h1 id="unite-toolbox">UNITE Toolbox</h1>
<h3 id="unified-diagnostic-evaluation-of-scientific-models-based-on-information-theory">Unified diagnostic evaluation of scientific models based on information theory</h3>
<p>The <strong>UNITE Toolbox</strong> is a Python library for incorporating <em>Information Theory</em>
into data analysis and modeling workflows.
The toolbox collects different methods of estimating information-theoretic quantities
in one easy-to-use Python package.
Currently, UNITE includes functions to calculate entropy <em>H(X)</em>,
Kullback-Leibler divergence <MATH>D_{KL}(p||q)</MATH>, and mutual information <em>I(X; Y)</em>,
using three methods:</p>
<ul>
<li>Kernel density-based estimation (KDE)</li>
<li>Binning using histograms</li>
<li><em>k</em>-nearest neighbor-based estimation (<em>k</em>-NN)</li>
</ul>
<h2 id="darus">DaRUS</h2>
<p>This is the <em>DaRUS</em> archive for the UNITE toolbox. This archive is currently in version <em>0.1.9</em> which is the latest version as of 13.05.2024. This archive will be updated semi-regularly. Check the <a href="https://github.com/manuel-alvarez-chaves/unite_toolbox">Github repository</a> for the latest version.</p>
<h2 id="installation">Installation</h2>
<p>Although the code is still highly experimental and in very active development,
a release version is available on PyPI and can be installed using <code>pip</code>.</p>
<pre><code>pip <span class="hljs-keyword">install</span> unite_toolbox
</code></pre><p>Check the <code>pyproject.toml</code> for requirements.</p>
<p><strong>Note</strong>: <code>pip</code> will install the latest version which might not exactly match this archive.</p>
<h2 id="how-to">How-to</h2>
<p>In the <a href="https://unite-toolbox.readthedocs.io/">documentation</a> please find
<a href="https://unite-toolbox.readthedocs.io/en/latest/tutorials.html">tutorials</a> on
the general usage of the toolbox and some applications.</p>