New MonteCarloShapleyBatch function added

Author: simon.grah

README.md

@@ -72,6 +72,10 @@ If the dimension exceeds about 15, then you may need approximation algorithms to
 mc_shap = MonteCarloShapley(x=x, fc=fc, ref=reference, n_iter=1000)
 ```
 
+If your reward function `fc` can handle data set of inputs, the batch version of Monte Carlo algorithm is more efficient as it calls `fc` only once:
+```python
+mc_shap_batch = MonteCarloShapleyBatch(x=x, fc=fc, ref=reference, n_iter=1000)
+```
 
 * Projected Stochastic Gradient Descent algorithm:
 

docs/_data/sidebars/home_sidebar.yml

@@ -11,19 +11,19 @@ entries:
       url: /
     - output: web,pdf
       title: Callback
-      url: /inspector
+      url: inspector.html
     - output: web,pdf
       title: Monte Carlo Shapley
-      url: /monte_carlo_shapley
+      url: monte_carlo_shapley.html
     - output: web,pdf
       title: Plots
-      url: /plots
+      url: plots.html
     - output: web,pdf
       title: Projected Stochastic Gradient Shapley
-      url: /sgd_shapley
+      url: sgd_shapley.html
     - output: web,pdf
       title: Shapley Value
-      url: /shapley_values
+      url: shapley_values.html
     output: web
     title: shapkit
   output: web

docs/index.html

@@ -2,11 +2,13 @@
 
 title: Shapkit
 
+
 keywords: fastai
 sidebar: home_sidebar
 
 summary: "Interpret machine learning predictions using agnostic local feature importance based on Shapley Values. Documentation: https://thalesgroup.github.io/shapkit/"
 description: "Interpret machine learning predictions using agnostic local feature importance based on Shapley Values. Documentation: https://thalesgroup.github.io/shapkit/"
+nb_path: "nbs/index.ipynb"
 ---
 <!--
 
@@ -121,6 +123,9 @@ <h2 id="How-to-use">How to use<a class="anchor-link" href="#How-to-use"> </a></h
 </ul>
 <div class="highlight"><pre><span></span><span class="n">mc_shap</span> <span class="o">=</span> <span class="n">MonteCarloShapley</span><span class="p">(</span><span class="n">x</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">fc</span><span class="o">=</span><span class="n">fc</span><span class="p">,</span> <span class="n">ref</span><span class="o">=</span><span class="n">reference</span><span class="p">,</span> <span class="n">n_iter</span><span class="o">=</span><span class="mi">1000</span><span class="p">)</span>
 </pre></div>
+<p>If your reward function <code>fc</code> can handle data set of inputs, the batch version of Monte Carlo algorithm is more efficient as it calls <code>fc</code> only once:</p>
+<div class="highlight"><pre><span></span><span class="n">mc_shap_batch</span> <span class="o">=</span> <span class="n">MonteCarloShapleyBatch</span><span class="p">(</span><span class="n">x</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">fc</span><span class="o">=</span><span class="n">fc</span><span class="p">,</span> <span class="n">ref</span><span class="o">=</span><span class="n">reference</span><span class="p">,</span> <span class="n">n_iter</span><span class="o">=</span><span class="mi">1000</span><span class="p">)</span>
+</pre></div>
 <ul>
 <li>Projected Stochastic Gradient Descent algorithm:</li>
 </ul>

docs/inspector.html

@@ -2,11 +2,13 @@
 
 title: Callback
 
+
 keywords: fastai
 sidebar: home_sidebar
 
 summary: "A closure called to update metrics after each iteration."
 description: "A closure called to update metrics after each iteration."
+nb_path: "nbs/inspector.ipynb"
 ---
 <!--
 
@@ -45,13 +47,6 @@
 
 <div class="cell border-box-sizing code_cell rendered">
 
-</div>
-    {% endraw %}
-
-    {% raw %}
-    
-<div class="cell border-box-sizing code_cell rendered">
-
 <div class="output_wrapper">
 <div class="output">
 
@@ -70,6 +65,13 @@ <h4 id="inspector" class="doc_header"><code>inspector</code><a href="https://git
 </div>
 </div>
 
+</div>
+    {% endraw %}
+
+    {% raw %}
+    
+<div class="cell border-box-sizing code_cell rendered">
+
 </div>
     {% endraw %}