mhjensen
643 lines
28 KiB
HTML
643 lines
28 KiB
HTML
\
|
|
<!DOCTYPE html>
|
|
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
|
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
|
<meta name="description" content="Data Analysis and Machine Learning: Support Vector Machines">
|
|
|
|
<title>Data Analysis and Machine Learning: Support Vector Machines</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<!-- reveal.js: http://lab.hakim.se/reveal-js/ -->
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no">
|
|
|
|
<meta name="apple-mobile-web-app-capable" content="yes" />
|
|
<meta name="apple-mobile-web-app-status-bar-style" content="black-translucent" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no, minimal-ui">
|
|
|
|
<link rel="stylesheet" href="reveal.js/css/reveal.css">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/beige.css" id="theme">
|
|
<!--
|
|
<link rel="stylesheet" href="reveal.js/css/reveal.css">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/beige.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/beigesmall.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/solarized.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/serif.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/night.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/moon.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/simple.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/sky.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/darkgray.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/default.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/cbc.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/simula.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/black.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/white.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/league.css" id="theme">
|
|
-->
|
|
|
|
<!-- For syntax highlighting -->
|
|
<link rel="stylesheet" href="reveal.js/lib/css/zenburn.css">
|
|
|
|
<!-- Printing and PDF exports -->
|
|
<script>
|
|
var link = document.createElement( 'link' );
|
|
link.rel = 'stylesheet';
|
|
link.type = 'text/css';
|
|
link.href = window.location.search.match( /print-pdf/gi ) ? 'css/print/pdf.css' : 'css/print/paper.css';
|
|
document.getElementsByTagName( 'head' )[0].appendChild( link );
|
|
</script>
|
|
|
|
<style type="text/css">
|
|
hr { border: 0; width: 80%; border-bottom: 1px solid #aaa}
|
|
p.caption { width: 80%; font-size: 60%; font-style: italic; text-align: left; }
|
|
hr.figure { border: 0; width: 80%; border-bottom: 1px solid #aaa}
|
|
.reveal .alert-text-small { font-size: 80%; }
|
|
.reveal .alert-text-large { font-size: 130%; }
|
|
.reveal .alert-text-normal { font-size: 90%; }
|
|
.reveal .alert {
|
|
padding:8px 35px 8px 14px; margin-bottom:18px;
|
|
text-shadow:0 1px 0 rgba(255,255,255,0.5);
|
|
border:5px solid #bababa;
|
|
-webkit-border-radius: 14px; -moz-border-radius: 14px;
|
|
border-radius:14px;
|
|
background-position: 10px 10px;
|
|
background-repeat: no-repeat;
|
|
background-size: 38px;
|
|
padding-left: 30px; /* 55px; if icon */
|
|
}
|
|
.reveal .alert-block {padding-top:14px; padding-bottom:14px}
|
|
.reveal .alert-block > p, .alert-block > ul {margin-bottom:1em}
|
|
/*.reveal .alert li {margin-top: 1em}*/
|
|
.reveal .alert-block p+p {margin-top:5px}
|
|
/*.reveal .alert-notice { background-image: url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_notice.png); }
|
|
.reveal .alert-summary { background-image:url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_summary.png); }
|
|
.reveal .alert-warning { background-image: url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_warning.png); }
|
|
.reveal .alert-question {background-image:url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_question.png); } */
|
|
|
|
</style>
|
|
|
|
|
|
|
|
<!-- Styles for table layout of slides -->
|
|
<style type="text/css">
|
|
td.padding {
|
|
padding-top:20px;
|
|
padding-bottom:20px;
|
|
padding-right:50px;
|
|
padding-left:50px;
|
|
}
|
|
</style>
|
|
|
|
</head>
|
|
|
|
<body>
|
|
<div class="reveal">
|
|
|
|
<!-- Any section element inside the <div class="slides"> container
|
|
is displayed as a slide -->
|
|
|
|
<div class="slides">
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
TeX: {
|
|
equationNumbers: { autoNumber: "none" },
|
|
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
|
}
|
|
});
|
|
</script>
|
|
<script type="text/javascript" async
|
|
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
|
</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<section>
|
|
<!-- ------------------- main content ---------------------- -->
|
|
|
|
|
|
|
|
<center><h1 style="text-align: center;">Data Analysis and Machine Learning: Support Vector Machines</h1></center> <!-- document title -->
|
|
|
|
<p>
|
|
<!-- author(s): Morten Hjorth-Jensen -->
|
|
|
|
<center>
|
|
<b>Morten Hjorth-Jensen</b> [1, 2]
|
|
</center>
|
|
|
|
<p> <br>
|
|
<!-- institution(s) -->
|
|
|
|
<center>[1] <b>Department of Physics, University of Oslo</b></center>
|
|
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
|
<br>
|
|
<p> <br>
|
|
<center><h4>Nov 4, 2018</h4></center> <!-- date -->
|
|
<br>
|
|
<p>
|
|
|
|
<center style="font-size:80%">
|
|
<!-- copyright --> © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
|
|
</center>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec0">Support Vector Machines, overarching aims </h2>
|
|
|
|
<p>
|
|
A Support Vector Machine (SVM) is a very powerful and versatile
|
|
Machine Learning model, capable of performing linear or nonlinear
|
|
classification, regression, and even outlier detection. It is one of
|
|
the most popular models in Machine Learning, and anyone interested in
|
|
Machine Learning should have it in their toolbox. SVMs are
|
|
particularly well suited for classification of complex but small-sized or
|
|
medium-sized datasets.
|
|
|
|
<p>
|
|
The case with two well-separated classes only can be understood in an intuitive way in terms of lines in a two-dimensional space separating the two classes (see figure below).
|
|
|
|
<p>
|
|
The basic mathematics behind the SVM is however less familiar to most of us.
|
|
It relies on the definition of hyperplanes and the
|
|
definition of a <b>margin</b> which separates classes (in case of
|
|
classification problems) of variables. It is also used for regression
|
|
problems.
|
|
|
|
<p>
|
|
With SVMs we distinguish between hard margin and soft margins. The latter introduces a so-called softening parameter to be discussed below.
|
|
We distringuish also between linear and non-linear approaches. The latter are the most frequent ones since it is rather unlikely that we can separate classes easily by say straight lines.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec1">Strength and weakness </h2>
|
|
|
|
<p>
|
|
When we implement a linear support vector machine, the main parameter is the constant \( C \). Small values of \( C \) mean simple models.
|
|
These models are fast to train and also fast to predict and scale to very large data sets and work well with sparse data. Linear support vector machines make it easy to understand how a prediction is made, however it is often not easy to understand why coefficients are the way they are. These models work also well in higer dimensions.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec2">Hyperplanes and all that </h2>
|
|
|
|
<p>
|
|
The theory behind support vector machines (SVM hereafter) is based on
|
|
the mathematical description of so-called hyperplanes. Let us start
|
|
with a two-dimensional case. This will also allow us to introduce our
|
|
first SVM examples. These will be tailored to the case of two specific
|
|
classes, as displayed in the figure here.
|
|
|
|
<p>
|
|
We assume here that our data set can be well separated into two
|
|
domains, where a straight line does the job in the separating the two
|
|
classes. Here the two classes are represented by either crosses or
|
|
circles.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec3">What is a hyperplane </h2>
|
|
|
|
<p>
|
|
The aim of the SVM algorithm is to find a hyperplane in an \( n \)-dimensional space, where \( n \) is the number of features that distinctly classifies the data points.
|
|
|
|
<p>
|
|
In an \( n \)-dimensional space, a hyperplane is what we call an affine subspace of dimension of \( n-1 \).
|
|
As an example, in two dimension, a hyperplane is simply as straight line while in three dimensions it is
|
|
a two-dimensional subspace, or stated simply, a plane.
|
|
|
|
<p>
|
|
In two dimensions, with the variables \( x_1 \) and \( x_2 \), the hyperplane is defined as
|
|
<p> <br>
|
|
$$
|
|
\beta_0+\beta_1x_1+\beta_2x_2=0,
|
|
$$
|
|
<p> <br>
|
|
|
|
<p>
|
|
In an \( n \)-dimensional space we have
|
|
<p> <br>
|
|
$$
|
|
\beta_0+\beta_1x_1+\beta_2x_2+\dots +\beta_nx_n=0,
|
|
$$
|
|
<p> <br>
|
|
|
|
<p>
|
|
With \( \hat{x}=\left[x_1,x_2,\dots, x_n\right] \), if the above condition is not met and
|
|
<p> <br>
|
|
$$
|
|
\beta_0+\beta_1x_1+\beta_2x_2+\dots +\beta_nx_n < 0,
|
|
$$
|
|
<p> <br>
|
|
|
|
we say that \( \hat{x} \) lies on one of the sides of the hyperplane and if
|
|
<p> <br>
|
|
$$
|
|
\beta_0+\beta_1x_1+\beta_2x_2+\dots +\beta_nx_n>0,
|
|
$$
|
|
<p> <br>
|
|
|
|
then \( \hat{x} \) lies on the other side.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec4">The two-dimensional case </h2>
|
|
|
|
<p>
|
|
Let us try to develop our intuition about SVMs by limiting ourselves to a two-dimensional
|
|
plane. To separate the two classes of data points, there are many
|
|
possible lines (hyperplanes if you prefer a more strict naming)
|
|
that could be chosen. Our objective is to find a
|
|
plane that has the maximum margin, i.e the maximum distance between
|
|
data points of both classes. Maximizing the margin distance provides
|
|
some reinforcement so that future data points can be classified with
|
|
more confidence.
|
|
|
|
<p>
|
|
What a linear classifier attempts to accomplish is to split the
|
|
feature space into two half spaces by placing a hyperplane between the
|
|
data points. This hyperplane will be our decision boundary. All
|
|
points on one side of the plane will belong to class one and all points
|
|
on the other side of the plane will belong to the second class two.
|
|
|
|
<p>
|
|
Unfortunately there are many ways in which we can place a hyperplane
|
|
to divide the data. Below is an example of two candidate hyperplanes
|
|
for our data sample.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec5">Getting into the details </h2>
|
|
|
|
<p>
|
|
Let us define the function
|
|
<p> <br>
|
|
$$
|
|
f(x) = \beta_0+\beta_1x = 0,
|
|
$$
|
|
<p> <br>
|
|
|
|
as the function that determines the line \( L \) that separates two classes (our two features), see the figur here.
|
|
|
|
<p>
|
|
Define a vector \( \hat{\beta}:\left\{\beta_0,\beta_1\right\} \). Let us label the values of \( \hat{\beta} \) that satisfy this constraint as \( \overline{\beta} \).
|
|
|
|
<p>
|
|
Any two points \( x_1 \) and \( x_2 \) on the line \( L \) will satisfy \( \hat{\beta}(x_1-x_2)=0 \). We normalize the solution and define
|
|
<p> <br>
|
|
$$
|
|
\overline{\beta} = \frac{\hat{\beta}}{\vert\vert \hat{\beta}\vert\vert},
|
|
$$
|
|
<p> <br>
|
|
|
|
which is vector normal to the line \( L \).
|
|
|
|
<p>
|
|
The signed distance from a point \( x_0 \) on \( L \) to any point \( x \) is then
|
|
<p> <br>
|
|
$$
|
|
\overline{\beta}(x-x_0) = \frac{\beta_1 x + \beta_0}{\vert\vert \hat{\beta}\vert\vert}.
|
|
$$
|
|
<p> <br>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec6">First attempt at a minimization approach </h2>
|
|
|
|
<p>
|
|
How do we find the parameters \( \beta_0 \) and \( \beta_0 \)? What we could
|
|
do is to define a cost function which now contains the set of all
|
|
misclassified points \( M \) and attempt to minimize this function
|
|
|
|
<p> <br>
|
|
$$
|
|
C(\beta_0,\beta_1) = -\sum_{i\in M} y_i(\beta_1x_1+\beta_0).
|
|
$$
|
|
<p> <br>
|
|
|
|
<p>
|
|
We could now for example define all values \( y_i =1 \) as misclassified in case we have \( \beta_1x_i+\beta_0 < 0 \) and the opposite if we have \( y_i=-1 \). Taking the derivatives gives us
|
|
<p> <br>
|
|
$$
|
|
\frac{\partial C}{\partial \beta_0} = -\sum_{i\in M} y_i,
|
|
$$
|
|
<p> <br>
|
|
|
|
and
|
|
<p> <br>
|
|
$$
|
|
\frac{\partial C}{\partial \beta_1} = -\sum_{i\in M} y_ix_i.
|
|
$$
|
|
<p> <br>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec7">Solving the equations </h2>
|
|
|
|
<p>
|
|
We can now use the Newton-Raphson method or gradient descent to solve the equations
|
|
<p> <br>
|
|
$$
|
|
\beta_0 \leftarrow \beta_0 +\eta \frac{\partial C}{\partial \beta_0},
|
|
$$
|
|
<p> <br>
|
|
|
|
and
|
|
<p> <br>
|
|
$$
|
|
\beta_1 \leftarrow \beta_1 +\eta \frac{\partial C}{\partial \beta_1},
|
|
$$
|
|
<p> <br>
|
|
|
|
where \( \eta \) is our by now well-known learning rate.
|
|
There are however problems with this approach, although it looks pretty straightforward to implement. In case we separate our data into two distinct classes, we may up with many possible lines, as indicated in the figure and shown by running the following program. For small gaps between the entries, we may also end up needing many iterations before the solutions converge and if the data cannot be separated properly into two distinct classes, we may not experience a converge at all.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec8">A better approach </h2>
|
|
A better approach is rather to try to define a large margin between the two classes (if they are well separated from the beginning).
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec9">Examples with kernels </h2>
|
|
|
|
<p>
|
|
|
|
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
|
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">IPython.display</span> <span style="color: #8B008B; font-weight: bold">import</span> set_matplotlib_formats, display
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">pandas</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">pd</span>
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">mglearn</span>
|
|
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">cycler</span> <span style="color: #8B008B; font-weight: bold">import</span> cycler
|
|
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> LogisticRegression
|
|
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.svm</span> <span style="color: #8B008B; font-weight: bold">import</span> LinearSVC
|
|
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.datasets</span> <span style="color: #8B008B; font-weight: bold">import</span> make_blobs
|
|
|
|
|
|
X, y = make_blobs(centers=<span style="color: #B452CD">4</span>, random_state=<span style="color: #B452CD">8</span>)
|
|
y = y % <span style="color: #B452CD">2</span>
|
|
|
|
mglearn.discrete_scatter(X[:, <span style="color: #B452CD">0</span>], X[:, <span style="color: #B452CD">1</span>], y)
|
|
plt.xlabel(<span style="color: #CD5555">"Feature 0"</span>)
|
|
plt.ylabel(<span style="color: #CD5555">"Feature 1"</span>)
|
|
plt.show()
|
|
|
|
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.svm</span> <span style="color: #8B008B; font-weight: bold">import</span> LinearSVC
|
|
linear_svm = LinearSVC().fit(X, y)
|
|
|
|
mglearn.plots.plot_2d_separator(linear_svm, X)
|
|
mglearn.discrete_scatter(X[:, <span style="color: #B452CD">0</span>], X[:, <span style="color: #B452CD">1</span>], y)
|
|
plt.xlabel(<span style="color: #CD5555">"Feature 0"</span>)
|
|
plt.ylabel(<span style="color: #CD5555">"Feature 1"</span>)
|
|
</pre></div>
|
|
<p>
|
|
|
|
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
|
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #228B22"># add the squared first feature</span>
|
|
X_new = np.hstack([X, X[:, <span style="color: #B452CD">1</span>:] ** <span style="color: #B452CD">2</span>])
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">mpl_toolkits.mplot3d</span> <span style="color: #8B008B; font-weight: bold">import</span> Axes3D, axes3d
|
|
figure = plt.figure()
|
|
<span style="color: #228B22"># visualize in 3D</span>
|
|
ax = Axes3D(figure, elev=-<span style="color: #B452CD">152</span>, azim=-<span style="color: #B452CD">26</span>)
|
|
<span style="color: #228B22"># plot first all the points with y==0, then all with y == 1</span>
|
|
mask = y == <span style="color: #B452CD">0</span>
|
|
ax.scatter(X_new[mask, <span style="color: #B452CD">0</span>], X_new[mask, <span style="color: #B452CD">1</span>], X_new[mask, <span style="color: #B452CD">2</span>], c=<span style="color: #CD5555">'b'</span>,
|
|
cmap=mglearn.cm2, s=<span style="color: #B452CD">60</span>, edgecolor=<span style="color: #CD5555">'k'</span>)
|
|
ax.scatter(X_new[~mask, <span style="color: #B452CD">0</span>], X_new[~mask, <span style="color: #B452CD">1</span>], X_new[~mask, <span style="color: #B452CD">2</span>], c=<span style="color: #CD5555">'r'</span>, marker=<span style="color: #CD5555">'^'</span>,
|
|
cmap=mglearn.cm2, s=<span style="color: #B452CD">60</span>, edgecolor=<span style="color: #CD5555">'k'</span>)
|
|
ax.set_xlabel(<span style="color: #CD5555">"feature0"</span>)
|
|
ax.set_ylabel(<span style="color: #CD5555">"feature1"</span>)
|
|
ax.set_zlabel(<span style="color: #CD5555">"feature1 ** 2"</span>)
|
|
</pre></div>
|
|
<p>
|
|
|
|
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
|
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span>linear_svm_3d = LinearSVC().fit(X_new, y)
|
|
coef, intercept = linear_svm_3d.coef_.ravel(), linear_svm_3d.intercept_
|
|
|
|
<span style="color: #228B22"># show linear decision boundary</span>
|
|
figure = plt.figure()
|
|
ax = Axes3D(figure, elev=-<span style="color: #B452CD">152</span>, azim=-<span style="color: #B452CD">26</span>)
|
|
xx = np.linspace(X_new[:, <span style="color: #B452CD">0</span>].min() - <span style="color: #B452CD">2</span>, X_new[:, <span style="color: #B452CD">0</span>].max() + <span style="color: #B452CD">2</span>, <span style="color: #B452CD">50</span>)
|
|
yy = np.linspace(X_new[:, <span style="color: #B452CD">1</span>].min() - <span style="color: #B452CD">2</span>, X_new[:, <span style="color: #B452CD">1</span>].max() + <span style="color: #B452CD">2</span>, <span style="color: #B452CD">50</span>)
|
|
|
|
XX, YY = np.meshgrid(xx, yy)
|
|
ZZ = (coef[<span style="color: #B452CD">0</span>] * XX + coef[<span style="color: #B452CD">1</span>] * YY + intercept) / -coef[<span style="color: #B452CD">2</span>]
|
|
ax.plot_surface(XX, YY, ZZ, rstride=<span style="color: #B452CD">8</span>, cstride=<span style="color: #B452CD">8</span>, alpha=<span style="color: #B452CD">0.3</span>)
|
|
ax.scatter(X_new[mask, <span style="color: #B452CD">0</span>], X_new[mask, <span style="color: #B452CD">1</span>], X_new[mask, <span style="color: #B452CD">2</span>], c=<span style="color: #CD5555">'b'</span>,
|
|
cmap=mglearn.cm2, s=<span style="color: #B452CD">60</span>, edgecolor=<span style="color: #CD5555">'k'</span>)
|
|
ax.scatter(X_new[~mask, <span style="color: #B452CD">0</span>], X_new[~mask, <span style="color: #B452CD">1</span>], X_new[~mask, <span style="color: #B452CD">2</span>], c=<span style="color: #CD5555">'r'</span>, marker=<span style="color: #CD5555">'^'</span>,
|
|
cmap=mglearn.cm2, s=<span style="color: #B452CD">60</span>, edgecolor=<span style="color: #CD5555">'k'</span>)
|
|
|
|
ax.set_xlabel(<span style="color: #CD5555">"feature0"</span>)
|
|
ax.set_ylabel(<span style="color: #CD5555">"feature1"</span>)
|
|
ax.set_zlabel(<span style="color: #CD5555">"feature1 ** 2"</span>)
|
|
|
|
ZZ = YY ** <span style="color: #B452CD">2</span>
|
|
dec = linear_svm_3d.decision_function(np.c_[XX.ravel(), YY.ravel(), ZZ.ravel()])
|
|
plt.contourf(XX, YY, dec.reshape(XX.shape), levels=[dec.min(), <span style="color: #B452CD">0</span>, dec.max()],
|
|
cmap=mglearn.cm2, alpha=<span style="color: #B452CD">0.5</span>)
|
|
mglearn.discrete_scatter(X[:, <span style="color: #B452CD">0</span>], X[:, <span style="color: #B452CD">1</span>], y)
|
|
plt.xlabel(<span style="color: #CD5555">"Feature 0"</span>)
|
|
plt.ylabel(<span style="color: #CD5555">"Feature 1"</span>)
|
|
</pre></div>
|
|
<p>
|
|
|
|
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
|
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.svm</span> <span style="color: #8B008B; font-weight: bold">import</span> SVC
|
|
X, y = mglearn.tools.make_handcrafted_dataset()
|
|
svm = SVC(kernel=<span style="color: #CD5555">'rbf'</span>, C=<span style="color: #B452CD">10</span>, gamma=<span style="color: #B452CD">0.1</span>).fit(X, y)
|
|
mglearn.plots.plot_2d_separator(svm, X, eps=.<span style="color: #B452CD">5</span>)
|
|
mglearn.discrete_scatter(X[:, <span style="color: #B452CD">0</span>], X[:, <span style="color: #B452CD">1</span>], y)
|
|
<span style="color: #228B22"># plot support vectors</span>
|
|
sv = svm.support_vectors_
|
|
<span style="color: #228B22"># class labels of support vectors are given by the sign of the dual coefficients</span>
|
|
sv_labels = svm.dual_coef_.ravel() > <span style="color: #B452CD">0</span>
|
|
mglearn.discrete_scatter(sv[:, <span style="color: #B452CD">0</span>], sv[:, <span style="color: #B452CD">1</span>], sv_labels, s=<span style="color: #B452CD">15</span>, markeredgewidth=<span style="color: #B452CD">3</span>)
|
|
plt.xlabel(<span style="color: #CD5555">"Feature 0"</span>)
|
|
plt.ylabel(<span style="color: #CD5555">"Feature 1"</span>)
|
|
|
|
fig, axes = plt.subplots(<span style="color: #B452CD">3</span>, <span style="color: #B452CD">3</span>, figsize=(<span style="color: #B452CD">15</span>, <span style="color: #B452CD">10</span>))
|
|
|
|
<span style="color: #8B008B; font-weight: bold">for</span> ax, C <span style="color: #8B008B">in</span> <span style="color: #658b00">zip</span>(axes, [-<span style="color: #B452CD">1</span>, <span style="color: #B452CD">0</span>, <span style="color: #B452CD">3</span>]):
|
|
<span style="color: #8B008B; font-weight: bold">for</span> a, gamma <span style="color: #8B008B">in</span> <span style="color: #658b00">zip</span>(ax, <span style="color: #658b00">range</span>(-<span style="color: #B452CD">1</span>, <span style="color: #B452CD">2</span>)):
|
|
mglearn.plots.plot_svm(log_C=C, log_gamma=gamma, ax=a)
|
|
|
|
axes[<span style="color: #B452CD">0</span>, <span style="color: #B452CD">0</span>].legend([<span style="color: #CD5555">"class 0"</span>, <span style="color: #CD5555">"class 1"</span>, <span style="color: #CD5555">"sv class 0"</span>, <span style="color: #CD5555">"sv class 1"</span>],
|
|
ncol=<span style="color: #B452CD">4</span>, loc=(.<span style="color: #B452CD">9</span>, <span style="color: #B452CD">1.2</span>))
|
|
</pre></div>
|
|
</section>
|
|
|
|
|
|
|
|
</div> <!-- class="slides" -->
|
|
</div> <!-- class="reveal" -->
|
|
|
|
<script src="reveal.js/lib/js/head.min.js"></script>
|
|
<script src="reveal.js/js/reveal.js"></script>
|
|
|
|
<script>
|
|
// Full list of configuration options available here:
|
|
// https://github.com/hakimel/reveal.js#configuration
|
|
Reveal.initialize({
|
|
|
|
// Display navigation controls in the bottom right corner
|
|
controls: true,
|
|
|
|
// Display progress bar (below the horiz. slider)
|
|
progress: true,
|
|
|
|
// Display the page number of the current slide
|
|
slideNumber: true,
|
|
|
|
// Push each slide change to the browser history
|
|
history: false,
|
|
|
|
// Enable keyboard shortcuts for navigation
|
|
keyboard: true,
|
|
|
|
// Enable the slide overview mode
|
|
overview: true,
|
|
|
|
// Vertical centering of slides
|
|
//center: true,
|
|
center: false,
|
|
|
|
// Enables touch navigation on devices with touch input
|
|
touch: true,
|
|
|
|
// Loop the presentation
|
|
loop: false,
|
|
|
|
// Change the presentation direction to be RTL
|
|
rtl: false,
|
|
|
|
// Turns fragments on and off globally
|
|
fragments: true,
|
|
|
|
// Flags if the presentation is running in an embedded mode,
|
|
// i.e. contained within a limited portion of the screen
|
|
embedded: false,
|
|
|
|
// Number of milliseconds between automatically proceeding to the
|
|
// next slide, disabled when set to 0, this value can be overwritten
|
|
// by using a data-autoslide attribute on your slides
|
|
autoSlide: 0,
|
|
|
|
// Stop auto-sliding after user input
|
|
autoSlideStoppable: true,
|
|
|
|
// Enable slide navigation via mouse wheel
|
|
mouseWheel: false,
|
|
|
|
// Hides the address bar on mobile devices
|
|
hideAddressBar: true,
|
|
|
|
// Opens links in an iframe preview overlay
|
|
previewLinks: false,
|
|
|
|
// Transition style
|
|
transition: 'default', // default/cube/page/concave/zoom/linear/fade/none
|
|
|
|
// Transition speed
|
|
transitionSpeed: 'default', // default/fast/slow
|
|
|
|
// Transition style for full page slide backgrounds
|
|
backgroundTransition: 'default', // default/none/slide/concave/convex/zoom
|
|
|
|
// Number of slides away from the current that are visible
|
|
viewDistance: 3,
|
|
|
|
// Parallax background image
|
|
//parallaxBackgroundImage: '', // e.g. "'https://s3.amazonaws.com/hakim-static/reveal-js/reveal-parallax-1.jpg'"
|
|
|
|
// Parallax background size
|
|
//parallaxBackgroundSize: '' // CSS syntax, e.g. "2100px 900px"
|
|
|
|
theme: Reveal.getQueryHash().theme, // available themes are in reveal.js/css/theme
|
|
transition: Reveal.getQueryHash().transition || 'default', // default/cube/page/concave/zoom/linear/none
|
|
|
|
});
|
|
|
|
Reveal.initialize({
|
|
dependencies: [
|
|
// Cross-browser shim that fully implements classList - https://github.com/eligrey/classList.js/
|
|
{ src: 'reveal.js/lib/js/classList.js', condition: function() { return !document.body.classList; } },
|
|
|
|
// Interpret Markdown in <section> elements
|
|
{ src: 'reveal.js/plugin/markdown/marked.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
|
{ src: 'reveal.js/plugin/markdown/markdown.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
|
|
|
// Syntax highlight for <code> elements
|
|
{ src: 'reveal.js/plugin/highlight/highlight.js', async: true, callback: function() { hljs.initHighlightingOnLoad(); } },
|
|
|
|
// Zoom in and out with Alt+click
|
|
{ src: 'reveal.js/plugin/zoom-js/zoom.js', async: true, condition: function() { return !!document.body.classList; } },
|
|
|
|
// Speaker notes
|
|
{ src: 'reveal.js/plugin/notes/notes.js', async: true, condition: function() { return !!document.body.classList; } },
|
|
|
|
// Remote control your reveal.js presentation using a touch device
|
|
//{ src: 'reveal.js/plugin/remotes/remotes.js', async: true, condition: function() { return !!document.body.classList; } },
|
|
|
|
// MathJax
|
|
//{ src: 'reveal.js/plugin/math/math.js', async: true }
|
|
]
|
|
});
|
|
|
|
Reveal.initialize({
|
|
|
|
// The "normal" size of the presentation, aspect ratio will be preserved
|
|
// when the presentation is scaled to fit different resolutions. Can be
|
|
// specified using percentage units.
|
|
width: 1170, // original: 960,
|
|
height: 700,
|
|
|
|
// Factor of the display size that should remain empty around the content
|
|
margin: 0.1,
|
|
|
|
// Bounds for smallest/largest possible scale to apply to content
|
|
minScale: 0.2,
|
|
maxScale: 1.0
|
|
|
|
});
|
|
</script>
|
|
|
|
<!-- begin footer logo
|
|
<div style="position: absolute; bottom: 0px; left: 0; margin-left: 0px">
|
|
<img src="somelogo.png">
|
|
</div>
|
|
end footer logo -->
|
|
|
|
|
|
|
|
</body>
|
|
</html>
|