Update Book

intro.html

@@ -493,12 +493,12 @@ <h1><span class="header-section-number">Chapter 2</span> Introduction<a href="in
 Internalizing the basic concepts also empowers you to better understand and evaluate any new paper on interpretability published on <a href="https://arxiv.org/">arxiv.org</a> in the last 5 minutes since you began reading this book (I might be exaggerating the publication rate).</p>
 <p>This book starts with some (dystopian) <a href="storytime.html#storytime">short stories</a> that are not needed to understand the book, but hopefully will entertain and make you think.
 Then the book explores the concepts of <a href="interpretability.html#interpretability">machine learning interpretability</a>.
-We will discuss when interpretability is important and what different types of explanations there are.
+We will discuss when interpretability is important and the different types of explanations that exist.
 Terms used throughout the book can be looked up in the <a href="terminology.html#terminology">Terminology chapter</a>.
 Most of the models and methods explained are presented using real data examples which are described in the <a href="data.html#data">Data chapter</a>.
 One way to make machine learning interpretable is to use <a href="simple.html#simple">interpretable models</a>, such as linear models or decision trees.
 The other option is the use of <a href="agnostic.html#agnostic">model-agnostic interpretation tools</a> that can be applied to any supervised machine learning model.
-Model-agnostic methods can be divided <a href="global-methods.html#global-methods">global methods</a> that describe the average behavior of the model and <a href="local-methods.html#local-methods">local methods</a> that explain individual predictions.
+Model-agnostic methods can be divided into <a href="global-methods.html#global-methods">global methods</a> that describe the average behavior of the model, and <a href="local-methods.html#local-methods">local methods</a> that explain individual predictions.
 The Model-Agnostic Methods chapter deals with methods such as <a href="pdp.html#pdp">partial dependence plots</a> and <a href="feature-importance.html#feature-importance">feature importance</a>.
 Model-agnostic methods work by changing the input of the machine learning model and measuring changes in the prediction output.
 The book ends with an optimistic outlook on what <a href="future.html#future">the future of interpretable machine learning</a> might look like.</p>

lime.html

@@ -845,7 +845,7 @@ <h4><span class="header-section-number">9.2.2.1</span> Example<a href="lime.html
 0.1701170
 </td>
 <td style="text-align:left;">
-PSY
+is
 </td>
 <td style="text-align:right;">
 0.000000
@@ -859,7 +859,7 @@ <h4><span class="header-section-number">9.2.2.1</span> Example<a href="lime.html
 0.1701170
 </td>
 <td style="text-align:left;">
-guy
+good
 </td>
 <td style="text-align:right;">
 0.000000
@@ -873,7 +873,7 @@ <h4><span class="header-section-number">9.2.2.1</span> Example<a href="lime.html
 0.1701170
 </td>
 <td style="text-align:left;">
-good
+a
 </td>
 <td style="text-align:right;">
 0.000000