update documentation

docs/_modules/index.html

@@ -111,6 +111,9 @@
   <h1>All modules for which code is available</h1>
 <ul><li><a href="robo/acquisition_functions/base_acquisition.html">robo.acquisition_functions.base_acquisition</a></li>
 <li><a href="robo/acquisition_functions/ei.html">robo.acquisition_functions.ei</a></li>
+<li><a href="robo/acquisition_functions/information_gain.html">robo.acquisition_functions.information_gain</a></li>
+<li><a href="robo/acquisition_functions/information_gain_mc.html">robo.acquisition_functions.information_gain_mc</a></li>
+<li><a href="robo/acquisition_functions/information_gain_per_unit_cost.html">robo.acquisition_functions.information_gain_per_unit_cost</a></li>
 <li><a href="robo/acquisition_functions/integrated_acquisition.html">robo.acquisition_functions.integrated_acquisition</a></li>
 <li><a href="robo/acquisition_functions/lcb.html">robo.acquisition_functions.lcb</a></li>
 <li><a href="robo/acquisition_functions/log_ei.html">robo.acquisition_functions.log_ei</a></li>

docs/_sources/installation.rst.txt

@@ -22,7 +22,7 @@ Additionally RoBO has some optional dependencies that are only needed for specif
 * `sgmcmc <https://github.com/stokasto/sgmcmc>`_
 * `hpolib2 <https://github.com/automl/HPOlib2>`_
 
-**Note**: RoBO works only with Python3. Python2 is not support anymore.
+**Note**: RoBO works only with Python3. Python2 is not supported anymore.
 
 -------------------
 Manual Installation
@@ -34,10 +34,11 @@ RoBO uses the Gaussian processes library `george <https://github.com/dfm/george>
 
      sudo apt-get install libeigen3-dev swig
 
-then change into the new directory:
+Download RoBO and then change into the new directory:
 
 .. code:: bash
 
+	git clone https://github.com/automl/RoBO
 	cd RoBO/
 
 Before you install RoBO you have to install the required dependencies

docs/apis.html

@@ -231,6 +231,90 @@ <h3>Acquisition:<a class="headerlink" href="#acquisition" title="Permalink to th
 
 </dd></dl>
 
+<dl class="class">
+<dt id="robo.acquisition_functions.information_gain.InformationGain">
+<em class="property">class </em><code class="descclassname">robo.acquisition_functions.information_gain.</code><code class="descname">InformationGain</code><span class="sig-paren">(</span><em>model</em>, <em>lower</em>, <em>upper</em>, <em>Nb=50</em>, <em>Np=400</em>, <em>sampling_acquisition=None</em>, <em>sampling_acquisition_kw={‘par’: 0.0}</em>, <em>rng=None</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/acquisition_functions/information_gain.html#InformationGain"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.acquisition_functions.information_gain.InformationGain" title="Permalink to this definition">¶</a></dt>
+<dd><dl class="method">
+<dt id="robo.acquisition_functions.information_gain.InformationGain.compute">
+<code class="descname">compute</code><span class="sig-paren">(</span><em>X_test</em>, <em>derivative=False</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/acquisition_functions/information_gain.html#InformationGain.compute"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.acquisition_functions.information_gain.InformationGain.compute" title="Permalink to this definition">¶</a></dt>
+<dd><p>Computes the information gain of X and its derivatives</p>
+<table class="docutils field-list" frame="void" rules="none">
+<col class="field-name" />
+<col class="field-body" />
+<tbody valign="top">
+<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><p class="first"><strong>X_test: np.ndarray(N, D), The input point where the acquisition_functions function</strong></p>
+<blockquote>
+<div><p>should be evaluate.</p>
+</div></blockquote>
+<p><strong>derivative: Boolean</strong></p>
+<blockquote>
+<div><p>If is set to true also the derivative of the acquisition_functions
+function at X is returned
+Not tested!</p>
+</div></blockquote>
+</td>
+</tr>
+<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">np.ndarray(N,)</p>
+<blockquote>
+<div><p>Relative change of entropy of pmin</p>
+</div></blockquote>
+<p>np.ndarray(N,D)</p>
+<blockquote class="last">
+<div><p>Derivatives with respect to X
+(only if derivative=True)</p>
+</div></blockquote>
+</td>
+</tr>
+</tbody>
+</table>
+</dd></dl>
+
+</dd></dl>
+
+<dl class="class">
+<dt id="robo.acquisition_functions.information_gain_mc.InformationGainMC">
+<em class="property">class </em><code class="descclassname">robo.acquisition_functions.information_gain_mc.</code><code class="descname">InformationGainMC</code><span class="sig-paren">(</span><em>model</em>, <em>lower</em>, <em>upper</em>, <em>Nb=50</em>, <em>Nf=500</em>, <em>sampling_acquisition=None</em>, <em>sampling_acquisition_kw={‘par’: 0.0}</em>, <em>Np=50</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/acquisition_functions/information_gain_mc.html#InformationGainMC"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.acquisition_functions.information_gain_mc.InformationGainMC" title="Permalink to this definition">¶</a></dt>
+<dd></dd></dl>
+
+<dl class="class">
+<dt id="robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost">
+<em class="property">class </em><code class="descclassname">robo.acquisition_functions.information_gain_per_unit_cost.</code><code class="descname">InformationGainPerUnitCost</code><span class="sig-paren">(</span><em>model</em>, <em>cost_model</em>, <em>lower</em>, <em>upper</em>, <em>is_env_variable</em>, <em>n_representer=50</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/acquisition_functions/information_gain_per_unit_cost.html#InformationGainPerUnitCost"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost" title="Permalink to this definition">¶</a></dt>
+<dd><dl class="method">
+<dt id="robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost.compute">
+<code class="descname">compute</code><span class="sig-paren">(</span><em>X</em>, <em>derivative=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/acquisition_functions/information_gain_per_unit_cost.html#InformationGainPerUnitCost.compute"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost.compute" title="Permalink to this definition">¶</a></dt>
+<dd><p>Computes the acquisition_functions value for a single point.</p>
+<table class="docutils field-list" frame="void" rules="none">
+<col class="field-name" />
+<col class="field-body" />
+<tbody valign="top">
+<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><p class="first"><strong>X</strong> : (1, D) numpy array</p>
+<blockquote>
+<div><p>The input point for which the acquisition_functions functions is computed.</p>
+</div></blockquote>
+<p><strong>derivative</strong> : bool, optional</p>
+<blockquote>
+<div><p>If it is equal to True also the derivatives with respect to X is
+computed.</p>
+</div></blockquote>
+</td>
+</tr>
+<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">acquisition_value: numpy array</p>
+<blockquote>
+<div><p>The acquisition_functions value computed for X.</p>
+</div></blockquote>
+<p><strong>grad</strong> : numpy array</p>
+<blockquote class="last">
+<div><p>The computed gradient of the acquisition_functions function at X. Only
+returned if derivative==True</p>
+</div></blockquote>
+</td>
+</tr>
+</tbody>
+</table>
+</dd></dl>
+
+</dd></dl>
+
 <dl class="class">
 <dt id="robo.acquisition_functions.integrated_acquisition.IntegratedAcquisition">
 <em class="property">class </em><code class="descclassname">robo.acquisition_functions.integrated_acquisition.</code><code class="descname">IntegratedAcquisition</code><span class="sig-paren">(</span><em>model</em>, <em>acquisition_func</em>, <em>X_lower</em>, <em>X_upper</em>, <em>cost_model=None</em>, <em>is_dngo=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/acquisition_functions/integrated_acquisition.html#IntegratedAcquisition"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.acquisition_functions.integrated_acquisition.IntegratedAcquisition" title="Permalink to this definition">¶</a></dt>
@@ -752,7 +836,7 @@ <h3>Maximizers:<a class="headerlink" href="#maximizers" title="Permalink to this
 
 <dl class="class">
 <dt id="robo.maximizers.scipy_optimizer.SciPyOptimizer">
-<em class="property">class </em><code class="descclassname">robo.maximizers.scipy_optimizer.</code><code class="descname">SciPyOptimizer</code><span class="sig-paren">(</span><em>objective_function</em>, <em>X_lower</em>, <em>X_upper</em>, <em>n_restarts=10</em>, <em>verbosity=False</em>, <em>rng=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/maximizers/scipy_optimizer.html#SciPyOptimizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.maximizers.scipy_optimizer.SciPyOptimizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">robo.maximizers.scipy_optimizer.</code><code class="descname">SciPyOptimizer</code><span class="sig-paren">(</span><em>objective_function</em>, <em>lower</em>, <em>upper</em>, <em>n_restarts=10</em>, <em>verbosity=True</em>, <em>rng=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/maximizers/scipy_optimizer.html#SciPyOptimizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.maximizers.scipy_optimizer.SciPyOptimizer" title="Permalink to this definition">¶</a></dt>
 <dd><dl class="method">
 <dt id="robo.maximizers.scipy_optimizer.SciPyOptimizer.maximize">
 <code class="descname">maximize</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/robo/maximizers/scipy_optimizer.html#SciPyOptimizer.maximize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#robo.maximizers.scipy_optimizer.SciPyOptimizer.maximize" title="Permalink to this definition">¶</a></dt>

docs/genindex.html

@@ -169,6 +169,10 @@ <h2 id="C">C</h2>
 
       <ul>
         <li><a href="apis.html#robo.acquisition_functions.ei.EI.compute">(robo.acquisition_functions.ei.EI method)</a>
+</li>
+        <li><a href="apis.html#robo.acquisition_functions.information_gain.InformationGain.compute">(robo.acquisition_functions.information_gain.InformationGain method)</a>
+</li>
+        <li><a href="apis.html#robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost.compute">(robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost method)</a>
 </li>
         <li><a href="apis.html#robo.acquisition_functions.integrated_acquisition.IntegratedAcquisition.compute">(robo.acquisition_functions.integrated_acquisition.IntegratedAcquisition method)</a>
 </li>
@@ -257,6 +261,14 @@ <h2 id="H">H</h2>
 <h2 id="I">I</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="apis.html#robo.acquisition_functions.information_gain.InformationGain">InformationGain (class in robo.acquisition_functions.information_gain)</a>
+</li>
+      <li><a href="apis.html#robo.acquisition_functions.information_gain_mc.InformationGainMC">InformationGainMC (class in robo.acquisition_functions.information_gain_mc)</a>
+</li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="apis.html#robo.acquisition_functions.information_gain_per_unit_cost.InformationGainPerUnitCost">InformationGainPerUnitCost (class in robo.acquisition_functions.information_gain_per_unit_cost)</a>
+</li>
       <li><a href="apis.html#robo.acquisition_functions.integrated_acquisition.IntegratedAcquisition">IntegratedAcquisition (class in robo.acquisition_functions.integrated_acquisition)</a>
 </li>
   </ul></td>

docs/installation.html

@@ -142,15 +142,16 @@ <h2>Dependencies<a class="headerlink" href="#dependencies" title="Permalink to t
 <li><a class="reference external" href="https://github.com/stokasto/sgmcmc">sgmcmc</a></li>
 <li><a class="reference external" href="https://github.com/automl/HPOlib2">hpolib2</a></li>
 </ul>
-<p><strong>Note</strong>: RoBO works only with Python3. Python2 is not support anymore.</p>
+<p><strong>Note</strong>: RoBO works only with Python3. Python2 is not supported anymore.</p>
 <div class="section" id="manual-installation">
 <h3>Manual Installation<a class="headerlink" href="#manual-installation" title="Permalink to this headline">¶</a></h3>
 <p>RoBO uses the Gaussian processes library <a class="reference external" href="https://github.com/dfm/george">george</a>  and the random forests library <a class="reference external" href="https://github.com/automl/random_forest_run">pyrfr</a>. In order to use this library make sure the libeigen and swig are installed:</p>
 <div class="code bash highlight-default"><div class="highlight"><pre><span></span><span class="n">sudo</span> <span class="n">apt</span><span class="o">-</span><span class="n">get</span> <span class="n">install</span> <span class="n">libeigen3</span><span class="o">-</span><span class="n">dev</span> <span class="n">swig</span>
 </pre></div>
 </div>
-<p>then change into the new directory:</p>
-<div class="code bash highlight-default"><div class="highlight"><pre><span></span><span class="n">cd</span> <span class="n">RoBO</span><span class="o">/</span>
+<p>Download RoBO and then change into the new directory:</p>
+<div class="code bash highlight-default"><div class="highlight"><pre><span></span><span class="n">git</span> <span class="n">clone</span> <span class="n">https</span><span class="p">:</span><span class="o">//</span><span class="n">github</span><span class="o">.</span><span class="n">com</span><span class="o">/</span><span class="n">automl</span><span class="o">/</span><span class="n">RoBO</span>
+<span class="n">cd</span> <span class="n">RoBO</span><span class="o">/</span>
 </pre></div>
 </div>
 <p>Before you install RoBO you have to install the required dependencies</p>