forked from scikit-learn/scikit-learn.github.io
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathplot_kernel_approximation.html
474 lines (406 loc) · 46.9 KB
/
plot_kernel_approximation.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>Explicit feature map approximation for RBF kernels — scikit-learn 0.20.dev0 documentation</title>
<!-- htmltitle is before nature.css - we use this hack to load bootstrap first -->
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="stylesheet" href="../_static/css/bootstrap.min.css" media="screen" />
<link rel="stylesheet" href="../_static/css/bootstrap-responsive.css"/>
<link rel="stylesheet" href="../_static/nature.css" type="text/css" />
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../_static/gallery.css" type="text/css" />
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../',
VERSION: '0.20.dev0',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script type="text/javascript" src="../_static/jquery.js"></script>
<script type="text/javascript" src="../_static/underscore.js"></script>
<script type="text/javascript" src="../_static/doctools.js"></script>
<script type="text/javascript" src="../_static/js/copybutton.js"></script>
<script type="text/javascript" src="../_static/js/extra.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS_SVG"></script>
<link rel="shortcut icon" href="../_static/favicon.ico"/>
<link rel="author" title="About these documents" href="../about.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="Outlier detection on a real data set" href="applications/plot_outlier_detection_housing.html" />
<link rel="prev" title="Comparison of kernel ridge regression and SVR" href="plot_kernel_ridge_regression.html" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<script src="../_static/js/bootstrap.min.js" type="text/javascript"></script>
<script>
VERSION_SUBDIR = (function(groups) {
return groups ? groups[1] : null;
})(location.href.match(/^https?:\/\/scikit-learn.org\/([^\/]+)/));
</script>
<link rel="canonical" href="http://scikit-learn.org/stable/auto_examples/plot_kernel_approximation.html" />
<script type="text/javascript">
$("div.buttonNext, div.buttonPrevious").hover(
function () {
$(this).css('background-color', '#FF9C34');
},
function () {
$(this).css('background-color', '#A7D6E2');
}
);
function showMenu() {
var topNav = document.getElementById("scikit-navbar");
if (topNav.className === "navbar") {
topNav.className += " responsive";
} else {
topNav.className = "navbar";
}
};
</script>
</head>
<body>
<div class="header-wrapper">
<div class="header">
<p class="logo"><a href="../index.html">
<img src="../_static/scikit-learn-logo-small.png" alt="Logo"/>
</a>
</p><div class="navbar" id="scikit-navbar">
<ul>
<li><a href="../index.html">Home</a></li>
<li><a href="../install.html">Installation</a></li>
<li class="btn-li"><div class="btn-group">
<a href="../documentation.html">Documentation</a>
<a class="btn dropdown-toggle" data-toggle="dropdown">
<span class="caret"></span>
</a>
<ul class="dropdown-menu">
<li class="link-title">Scikit-learn <script>document.write(DOCUMENTATION_OPTIONS.VERSION + (VERSION_SUBDIR ? " (" + VERSION_SUBDIR + ")" : ""));</script></li>
<li><a href="../tutorial/index.html">Tutorials</a></li>
<li><a href="../user_guide.html">User guide</a></li>
<li><a href="../modules/classes.html">API</a></li>
<li><a href="../glossary.html">Glossary</a></li>
<li><a href="../faq.html">FAQ</a></li>
<li><a href="../developers/contributing.html">Contributing</a></li>
<li class="divider"></li>
<script>if (VERSION_SUBDIR != "stable") document.write('<li><a href="http://scikit-learn.org/stable/documentation.html">Stable version</a></li>')</script>
<script>if (VERSION_SUBDIR != "dev") document.write('<li><a href="http://scikit-learn.org/dev/documentation.html">Development version</a></li>')</script>
<li><a href="http://scikit-learn.org/dev/versions.html">All available versions</a></li>
<li><a href="../_downloads/scikit-learn-docs.pdf">PDF documentation</a></li>
</ul>
</div>
</li>
<li><a href="index.html">Examples</a></li>
</ul>
<a href="javascript:void(0);" onclick="showMenu()">
<div class="nav-icon">
<div class="hamburger-line"></div>
<div class="hamburger-line"></div>
<div class="hamburger-line"></div>
</div>
</a>
<div class="search_form">
<div class="gcse-search" id="cse" style="width: 100%;"></div>
</div>
</div> <!-- end navbar --></div>
</div>
<!-- GitHub "fork me" ribbon -->
<a href="https://github.com/scikit-learn/scikit-learn">
<img class="fork-me"
style="position: absolute; top: 0; right: 0; border: 0;"
src="../_static/img/forkme.png"
alt="Fork me on GitHub" />
</a>
<div class="content-wrapper">
<div class="sphinxsidebar">
<div class="sphinxsidebarwrapper">
<div class="rel">
<div class="rellink">
<a href="plot_kernel_ridge_regression.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
Comparison of...
</span>
<span class="hiddenrellink">
Comparison of kernel ridge regression and SVR
</span>
</a>
</div>
<div class="spacer">
</div>
<div class="rellink">
<a href="applications/plot_outlier_detection_housing.html"
accesskey="N">Next
<br/>
<span class="smallrellink">
Outlier detec...
</span>
<span class="hiddenrellink">
Outlier detection on a real data set
</span>
</a>
</div>
<!-- Ad a link to the 'up' page -->
<div class="spacer">
</div>
<div class="rellink">
<a href="index.html">
Up
<br/>
<span class="smallrellink">
Examples
</span>
<span class="hiddenrellink">
Examples
</span>
</a>
</div>
</div>
<p class="doc-version"><b>scikit-learn v0.20.dev0</b><br/>
<a href="http://scikit-learn.org/stable/support.html#documentation-resources">Other versions</a></p>
<p class="citing">Please <b><a href="../about.html#citing-scikit-learn" style="font-size: 110%;">cite us </a></b>if you use the software.</p>
<ul>
<li><a class="reference internal" href="#">Explicit feature map approximation for RBF kernels</a></li>
</ul>
</div>
</div>
<input type="checkbox" id="nav-trigger" class="nav-trigger" checked />
<label for="nav-trigger"></label>
<div class="content">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<div class="sphx-glr-download-link-note admonition note">
<p class="first admonition-title">Note</p>
<p class="last">Click <a class="reference internal" href="#sphx-glr-download-auto-examples-plot-kernel-approximation-py"><span class="std std-ref">here</span></a> to download the full example code or run this example in your browser via Binder</p>
</div>
<div class="sphx-glr-example-title section" id="explicit-feature-map-approximation-for-rbf-kernels">
<span id="sphx-glr-auto-examples-plot-kernel-approximation-py"></span><h1>Explicit feature map approximation for RBF kernels<a class="headerlink" href="#explicit-feature-map-approximation-for-rbf-kernels" title="Permalink to this headline">¶</a></h1>
<p>An example illustrating the approximation of the feature map
of an RBF kernel.</p>
<p>It shows how to use <a class="reference internal" href="../modules/generated/sklearn.kernel_approximation.RBFSampler.html#sklearn.kernel_approximation.RBFSampler" title="sklearn.kernel_approximation.RBFSampler"><code class="xref py py-class docutils literal"><span class="pre">RBFSampler</span></code></a> and <a class="reference internal" href="../modules/generated/sklearn.kernel_approximation.Nystroem.html#sklearn.kernel_approximation.Nystroem" title="sklearn.kernel_approximation.Nystroem"><code class="xref py py-class docutils literal"><span class="pre">Nystroem</span></code></a> to
approximate the feature map of an RBF kernel for classification with an SVM on
the digits dataset. Results using a linear SVM in the original space, a linear
SVM using the approximate mappings and using a kernelized SVM are compared.
Timings and accuracy for varying amounts of Monte Carlo samplings (in the case
of <a class="reference internal" href="../modules/generated/sklearn.kernel_approximation.RBFSampler.html#sklearn.kernel_approximation.RBFSampler" title="sklearn.kernel_approximation.RBFSampler"><code class="xref py py-class docutils literal"><span class="pre">RBFSampler</span></code></a>, which uses random Fourier features) and different sized
subsets of the training set (for <a class="reference internal" href="../modules/generated/sklearn.kernel_approximation.Nystroem.html#sklearn.kernel_approximation.Nystroem" title="sklearn.kernel_approximation.Nystroem"><code class="xref py py-class docutils literal"><span class="pre">Nystroem</span></code></a>) for the approximate mapping
are shown.</p>
<p>Please note that the dataset here is not large enough to show the benefits
of kernel approximation, as the exact SVM is still reasonably fast.</p>
<p>Sampling more dimensions clearly leads to better classification results, but
comes at a greater cost. This means there is a tradeoff between runtime and
accuracy, given by the parameter n_components. Note that solving the Linear
SVM and also the approximate kernel SVM could be greatly accelerated by using
stochastic gradient descent via <a class="reference internal" href="../modules/generated/sklearn.linear_model.SGDClassifier.html#sklearn.linear_model.SGDClassifier" title="sklearn.linear_model.SGDClassifier"><code class="xref py py-class docutils literal"><span class="pre">sklearn.linear_model.SGDClassifier</span></code></a>.
This is not easily possible for the case of the kernelized SVM.</p>
<p>The second plot visualized the decision surfaces of the RBF kernel SVM and
the linear SVM with approximate kernel maps.
The plot shows decision surfaces of the classifiers projected onto
the first two principal components of the data. This visualization should
be taken with a grain of salt since it is just an interesting slice through
the decision surface in 64 dimensions. In particular note that
a datapoint (represented as a dot) does not necessarily be classified
into the region it is lying in, since it will not lie on the plane
that the first two principal components span.</p>
<p>The usage of <a class="reference internal" href="../modules/generated/sklearn.kernel_approximation.RBFSampler.html#sklearn.kernel_approximation.RBFSampler" title="sklearn.kernel_approximation.RBFSampler"><code class="xref py py-class docutils literal"><span class="pre">RBFSampler</span></code></a> and <a class="reference internal" href="../modules/generated/sklearn.kernel_approximation.Nystroem.html#sklearn.kernel_approximation.Nystroem" title="sklearn.kernel_approximation.Nystroem"><code class="xref py py-class docutils literal"><span class="pre">Nystroem</span></code></a> is described in detail
in <a class="reference internal" href="../modules/kernel_approximation.html#kernel-approximation"><span class="std std-ref">Kernel Approximation</span></a>.</p>
<ul class="sphx-glr-horizontal">
<li><img alt="../_images/sphx_glr_plot_kernel_approximation_001.png" class="sphx-glr-multi-img first" src="../_images/sphx_glr_plot_kernel_approximation_001.png" />
</li>
<li><img alt="../_images/sphx_glr_plot_kernel_approximation_002.png" class="sphx-glr-multi-img first" src="../_images/sphx_glr_plot_kernel_approximation_002.png" />
</li>
</ul>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">print</span><span class="p">(</span><span class="vm">__doc__</span><span class="p">)</span>
<span class="c1"># Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org></span>
<span class="c1"># Andreas Mueller <[email protected]></span>
<span class="c1"># License: BSD 3 clause</span>
<span class="c1"># Standard scientific Python imports</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="kn">as</span> <span class="nn">plt</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">time</span> <span class="kn">import</span> <span class="n">time</span>
<span class="c1"># Import datasets, classifiers and performance metrics</span>
<span class="kn">from</span> <span class="nn">sklearn</span> <span class="kn">import</span> <span class="n">datasets</span><span class="p">,</span> <span class="n">svm</span><span class="p">,</span> <span class="n">pipeline</span>
<span class="kn">from</span> <span class="nn">sklearn.kernel_approximation</span> <span class="kn">import</span> <span class="p">(</span><a href="../modules/generated/sklearn.kernel_approximation.RBFSampler.html#sklearn.kernel_approximation.RBFSampler" title="View documentation for sklearn.kernel_approximation.RBFSampler"><span class="n">RBFSampler</span></a><span class="p">,</span>
<a href="../modules/generated/sklearn.kernel_approximation.Nystroem.html#sklearn.kernel_approximation.Nystroem" title="View documentation for sklearn.kernel_approximation.Nystroem"><span class="n">Nystroem</span></a><span class="p">)</span>
<span class="kn">from</span> <span class="nn">sklearn.decomposition</span> <span class="kn">import</span> <a href="../modules/generated/sklearn.decomposition.PCA.html#sklearn.decomposition.PCA" title="View documentation for sklearn.decomposition.PCA"><span class="n">PCA</span></a>
<span class="c1"># The digits dataset</span>
<span class="n">digits</span> <span class="o">=</span> <a href="../modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits" title="View documentation for sklearn.datasets.load_digits"><span class="n">datasets</span><span class="o">.</span><span class="n">load_digits</span></a><span class="p">(</span><span class="n">n_class</span><span class="o">=</span><span class="mi">9</span><span class="p">)</span>
<span class="c1"># To apply an classifier on this data, we need to flatten the image, to</span>
<span class="c1"># turn the data in a (samples, feature) matrix:</span>
<span class="n">n_samples</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">digits</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">digits</span><span class="o">.</span><span class="n">data</span> <span class="o">/</span> <span class="mf">16.</span>
<span class="n">data</span> <span class="o">-=</span> <span class="n">data</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># We learn the digits on the first half of the digits</span>
<span class="n">data_train</span><span class="p">,</span> <span class="n">targets_train</span> <span class="o">=</span> <span class="p">(</span><span class="n">data</span><span class="p">[:</span><span class="n">n_samples</span> <span class="o">//</span> <span class="mi">2</span><span class="p">],</span>
<span class="n">digits</span><span class="o">.</span><span class="n">target</span><span class="p">[:</span><span class="n">n_samples</span> <span class="o">//</span> <span class="mi">2</span><span class="p">])</span>
<span class="c1"># Now predict the value of the digit on the second half:</span>
<span class="n">data_test</span><span class="p">,</span> <span class="n">targets_test</span> <span class="o">=</span> <span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="n">n_samples</span> <span class="o">//</span> <span class="mi">2</span><span class="p">:],</span>
<span class="n">digits</span><span class="o">.</span><span class="n">target</span><span class="p">[</span><span class="n">n_samples</span> <span class="o">//</span> <span class="mi">2</span><span class="p">:])</span>
<span class="c1"># data_test = scaler.transform(data_test)</span>
<span class="c1"># Create a classifier: a support vector classifier</span>
<span class="n">kernel_svm</span> <span class="o">=</span> <a href="../modules/generated/sklearn.svm.SVC.html#sklearn.svm.SVC" title="View documentation for sklearn.svm.SVC"><span class="n">svm</span><span class="o">.</span><span class="n">SVC</span></a><span class="p">(</span><span class="n">gamma</span><span class="o">=.</span><span class="mi">2</span><span class="p">)</span>
<span class="n">linear_svm</span> <span class="o">=</span> <a href="../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">svm</span><span class="o">.</span><span class="n">LinearSVC</span></a><span class="p">()</span>
<span class="c1"># create pipeline from kernel approximation</span>
<span class="c1"># and linear svm</span>
<span class="n">feature_map_fourier</span> <span class="o">=</span> <a href="../modules/generated/sklearn.kernel_approximation.RBFSampler.html#sklearn.kernel_approximation.RBFSampler" title="View documentation for sklearn.kernel_approximation.RBFSampler"><span class="n">RBFSampler</span></a><span class="p">(</span><span class="n">gamma</span><span class="o">=.</span><span class="mi">2</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">feature_map_nystroem</span> <span class="o">=</span> <a href="../modules/generated/sklearn.kernel_approximation.Nystroem.html#sklearn.kernel_approximation.Nystroem" title="View documentation for sklearn.kernel_approximation.Nystroem"><span class="n">Nystroem</span></a><span class="p">(</span><span class="n">gamma</span><span class="o">=.</span><span class="mi">2</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">fourier_approx_svm</span> <span class="o">=</span> <a href="../modules/generated/sklearn.pipeline.Pipeline.html#sklearn.pipeline.Pipeline" title="View documentation for sklearn.pipeline.Pipeline"><span class="n">pipeline</span><span class="o">.</span><span class="n">Pipeline</span></a><span class="p">([(</span><span class="s2">"feature_map"</span><span class="p">,</span> <span class="n">feature_map_fourier</span><span class="p">),</span>
<span class="p">(</span><span class="s2">"svm"</span><span class="p">,</span> <a href="../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">svm</span><span class="o">.</span><span class="n">LinearSVC</span></a><span class="p">())])</span>
<span class="n">nystroem_approx_svm</span> <span class="o">=</span> <a href="../modules/generated/sklearn.pipeline.Pipeline.html#sklearn.pipeline.Pipeline" title="View documentation for sklearn.pipeline.Pipeline"><span class="n">pipeline</span><span class="o">.</span><span class="n">Pipeline</span></a><span class="p">([(</span><span class="s2">"feature_map"</span><span class="p">,</span> <span class="n">feature_map_nystroem</span><span class="p">),</span>
<span class="p">(</span><span class="s2">"svm"</span><span class="p">,</span> <a href="../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">svm</span><span class="o">.</span><span class="n">LinearSVC</span></a><span class="p">())])</span>
<span class="c1"># fit and predict using linear and kernel svm:</span>
<span class="n">kernel_svm_time</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">kernel_svm</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data_train</span><span class="p">,</span> <span class="n">targets_train</span><span class="p">)</span>
<span class="n">kernel_svm_score</span> <span class="o">=</span> <span class="n">kernel_svm</span><span class="o">.</span><span class="n">score</span><span class="p">(</span><span class="n">data_test</span><span class="p">,</span> <span class="n">targets_test</span><span class="p">)</span>
<span class="n">kernel_svm_time</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">kernel_svm_time</span>
<span class="n">linear_svm_time</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">linear_svm</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data_train</span><span class="p">,</span> <span class="n">targets_train</span><span class="p">)</span>
<span class="n">linear_svm_score</span> <span class="o">=</span> <span class="n">linear_svm</span><span class="o">.</span><span class="n">score</span><span class="p">(</span><span class="n">data_test</span><span class="p">,</span> <span class="n">targets_test</span><span class="p">)</span>
<span class="n">linear_svm_time</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">linear_svm_time</span>
<span class="n">sample_sizes</span> <span class="o">=</span> <span class="mi">30</span> <span class="o">*</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.arange.html#numpy.arange" title="View documentation for numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
<span class="n">fourier_scores</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">nystroem_scores</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">fourier_times</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">nystroem_times</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">D</span> <span class="ow">in</span> <span class="n">sample_sizes</span><span class="p">:</span>
<span class="n">fourier_approx_svm</span><span class="o">.</span><span class="n">set_params</span><span class="p">(</span><span class="n">feature_map__n_components</span><span class="o">=</span><span class="n">D</span><span class="p">)</span>
<span class="n">nystroem_approx_svm</span><span class="o">.</span><span class="n">set_params</span><span class="p">(</span><span class="n">feature_map__n_components</span><span class="o">=</span><span class="n">D</span><span class="p">)</span>
<span class="n">start</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">nystroem_approx_svm</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data_train</span><span class="p">,</span> <span class="n">targets_train</span><span class="p">)</span>
<span class="n">nystroem_times</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start</span><span class="p">)</span>
<span class="n">start</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">fourier_approx_svm</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data_train</span><span class="p">,</span> <span class="n">targets_train</span><span class="p">)</span>
<span class="n">fourier_times</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start</span><span class="p">)</span>
<span class="n">fourier_score</span> <span class="o">=</span> <span class="n">fourier_approx_svm</span><span class="o">.</span><span class="n">score</span><span class="p">(</span><span class="n">data_test</span><span class="p">,</span> <span class="n">targets_test</span><span class="p">)</span>
<span class="n">nystroem_score</span> <span class="o">=</span> <span class="n">nystroem_approx_svm</span><span class="o">.</span><span class="n">score</span><span class="p">(</span><span class="n">data_test</span><span class="p">,</span> <span class="n">targets_test</span><span class="p">)</span>
<span class="n">nystroem_scores</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nystroem_score</span><span class="p">)</span>
<span class="n">fourier_scores</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">fourier_score</span><span class="p">)</span>
<span class="c1"># plot the results:</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.figure.html#matplotlib.pyplot.figure" title="View documentation for matplotlib.pyplot.figure"><span class="n">plt</span><span class="o">.</span><span class="n">figure</span></a><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">8</span><span class="p">,</span> <span class="mi">8</span><span class="p">))</span>
<span class="n">accuracy</span> <span class="o">=</span> <a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplot.html#matplotlib.pyplot.subplot" title="View documentation for matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">211</span><span class="p">)</span>
<span class="c1"># second y axis for timeings</span>
<span class="n">timescale</span> <span class="o">=</span> <a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplot.html#matplotlib.pyplot.subplot" title="View documentation for matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">212</span><span class="p">)</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">sample_sizes</span><span class="p">,</span> <span class="n">nystroem_scores</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"Nystroem approx. kernel"</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">sample_sizes</span><span class="p">,</span> <span class="n">nystroem_times</span><span class="p">,</span> <span class="s1">'--'</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="s1">'Nystroem approx. kernel'</span><span class="p">)</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">sample_sizes</span><span class="p">,</span> <span class="n">fourier_scores</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"Fourier approx. kernel"</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">sample_sizes</span><span class="p">,</span> <span class="n">fourier_times</span><span class="p">,</span> <span class="s1">'--'</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="s1">'Fourier approx. kernel'</span><span class="p">)</span>
<span class="c1"># horizontal lines for exact rbf and linear kernels:</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">plot</span><span class="p">([</span><span class="n">sample_sizes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">sample_sizes</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]],</span>
<span class="p">[</span><span class="n">linear_svm_score</span><span class="p">,</span> <span class="n">linear_svm_score</span><span class="p">],</span> <span class="n">label</span><span class="o">=</span><span class="s2">"linear svm"</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">plot</span><span class="p">([</span><span class="n">sample_sizes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">sample_sizes</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]],</span>
<span class="p">[</span><span class="n">linear_svm_time</span><span class="p">,</span> <span class="n">linear_svm_time</span><span class="p">],</span> <span class="s1">'--'</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'linear svm'</span><span class="p">)</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">plot</span><span class="p">([</span><span class="n">sample_sizes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">sample_sizes</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]],</span>
<span class="p">[</span><span class="n">kernel_svm_score</span><span class="p">,</span> <span class="n">kernel_svm_score</span><span class="p">],</span> <span class="n">label</span><span class="o">=</span><span class="s2">"rbf svm"</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">plot</span><span class="p">([</span><span class="n">sample_sizes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">sample_sizes</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]],</span>
<span class="p">[</span><span class="n">kernel_svm_time</span><span class="p">,</span> <span class="n">kernel_svm_time</span><span class="p">],</span> <span class="s1">'--'</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'rbf svm'</span><span class="p">)</span>
<span class="c1"># vertical line for dataset dimensionality = 64</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">plot</span><span class="p">([</span><span class="mi">64</span><span class="p">,</span> <span class="mi">64</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.7</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">label</span><span class="o">=</span><span class="s2">"n_features"</span><span class="p">)</span>
<span class="c1"># legends and labels</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s2">"Classification accuracy"</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s2">"Training times"</span><span class="p">)</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">set_xlim</span><span class="p">(</span><span class="n">sample_sizes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">sample_sizes</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">set_xticks</span><span class="p">(())</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">set_ylim</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="n">fourier_scores</span><span class="p">),</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s2">"Sampling steps = transformed feature dimension"</span><span class="p">)</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">set_ylabel</span><span class="p">(</span><span class="s2">"Classification accuracy"</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">set_ylabel</span><span class="p">(</span><span class="s2">"Training time in seconds"</span><span class="p">)</span>
<span class="n">accuracy</span><span class="o">.</span><span class="n">legend</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s1">'best'</span><span class="p">)</span>
<span class="n">timescale</span><span class="o">.</span><span class="n">legend</span><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s1">'best'</span><span class="p">)</span>
<span class="c1"># visualize the decision surface, projected down to the first</span>
<span class="c1"># two principal components of the dataset</span>
<span class="n">pca</span> <span class="o">=</span> <a href="../modules/generated/sklearn.decomposition.PCA.html#sklearn.decomposition.PCA" title="View documentation for sklearn.decomposition.PCA"><span class="n">PCA</span></a><span class="p">(</span><span class="n">n_components</span><span class="o">=</span><span class="mi">8</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data_train</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">pca</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">data_train</span><span class="p">)</span>
<span class="c1"># Generate grid along first two principal components</span>
<span class="n">multiples</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.arange.html#numpy.arange" title="View documentation for numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="o">-</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">)</span>
<span class="c1"># steps along first component</span>
<span class="n">first</span> <span class="o">=</span> <span class="n">multiples</span><span class="p">[:,</span> <a href="https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">]</span> <span class="o">*</span> <span class="n">pca</span><span class="o">.</span><span class="n">components_</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="p">:]</span>
<span class="c1"># steps along second component</span>
<span class="n">second</span> <span class="o">=</span> <span class="n">multiples</span><span class="p">[:,</span> <a href="https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">]</span> <span class="o">*</span> <span class="n">pca</span><span class="o">.</span><span class="n">components_</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="p">:]</span>
<span class="c1"># combine</span>
<span class="n">grid</span> <span class="o">=</span> <span class="n">first</span><span class="p">[</span><a href="https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:,</span> <span class="p">:]</span> <span class="o">+</span> <span class="n">second</span><span class="p">[:,</span> <a href="https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html#numpy.newaxis" title="View documentation for numpy.newaxis"><span class="n">np</span><span class="o">.</span><span class="n">newaxis</span></a><span class="p">,</span> <span class="p">:]</span>
<span class="n">flat_grid</span> <span class="o">=</span> <span class="n">grid</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="c1"># title for the plots</span>
<span class="n">titles</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'SVC with rbf kernel'</span><span class="p">,</span>
<span class="s1">'SVC (linear kernel)</span><span class="se">\n</span><span class="s1"> with Fourier rbf feature map</span><span class="se">\n</span><span class="s1">'</span>
<span class="s1">'n_components=100'</span><span class="p">,</span>
<span class="s1">'SVC (linear kernel)</span><span class="se">\n</span><span class="s1"> with Nystroem rbf feature map</span><span class="se">\n</span><span class="s1">'</span>
<span class="s1">'n_components=100'</span><span class="p">]</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.tight_layout.html#matplotlib.pyplot.tight_layout" title="View documentation for matplotlib.pyplot.tight_layout"><span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span></a><span class="p">()</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.figure.html#matplotlib.pyplot.figure" title="View documentation for matplotlib.pyplot.figure"><span class="n">plt</span><span class="o">.</span><span class="n">figure</span></a><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">5</span><span class="p">))</span>
<span class="c1"># predict and plot</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">clf</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">((</span><span class="n">kernel_svm</span><span class="p">,</span> <span class="n">nystroem_approx_svm</span><span class="p">,</span>
<span class="n">fourier_approx_svm</span><span class="p">)):</span>
<span class="c1"># Plot the decision boundary. For that, we will assign a color to each</span>
<span class="c1"># point in the mesh [x_min, x_max]x[y_min, y_max].</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplot.html#matplotlib.pyplot.subplot" title="View documentation for matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">Z</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">flat_grid</span><span class="p">)</span>
<span class="c1"># Put the result into a color plot</span>
<span class="n">Z</span> <span class="o">=</span> <span class="n">Z</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">grid</span><span class="o">.</span><span class="n">shape</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.contourf.html#matplotlib.pyplot.contourf" title="View documentation for matplotlib.pyplot.contourf"><span class="n">plt</span><span class="o">.</span><span class="n">contourf</span></a><span class="p">(</span><span class="n">multiples</span><span class="p">,</span> <span class="n">multiples</span><span class="p">,</span> <span class="n">Z</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="n">plt</span><span class="o">.</span><span class="n">cm</span><span class="o">.</span><span class="n">Paired</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.axis.html#matplotlib.pyplot.axis" title="View documentation for matplotlib.pyplot.axis"><span class="n">plt</span><span class="o">.</span><span class="n">axis</span></a><span class="p">(</span><span class="s1">'off'</span><span class="p">)</span>
<span class="c1"># Plot also the training points</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.scatter.html#matplotlib.pyplot.scatter" title="View documentation for matplotlib.pyplot.scatter"><span class="n">plt</span><span class="o">.</span><span class="n">scatter</span></a><span class="p">(</span><span class="n">X</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">c</span><span class="o">=</span><span class="n">targets_train</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="n">plt</span><span class="o">.</span><span class="n">cm</span><span class="o">.</span><span class="n">Paired</span><span class="p">,</span>
<span class="n">edgecolors</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.title.html#matplotlib.pyplot.title" title="View documentation for matplotlib.pyplot.title"><span class="n">plt</span><span class="o">.</span><span class="n">title</span></a><span class="p">(</span><span class="n">titles</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.tight_layout.html#matplotlib.pyplot.tight_layout" title="View documentation for matplotlib.pyplot.tight_layout"><span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span></a><span class="p">()</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
</pre></div>
</div>
<p><strong>Total running time of the script:</strong> ( 0 minutes 1.092 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-kernel-approximation-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn.github.io/master?urlpath=lab/tree/notebooks/auto_examples/plot_kernel_approximation.ipynb"><img alt="https://static.mybinder.org/badge.svg" src="https://static.mybinder.org/badge.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download docutils container">
<a class="reference download internal" href="../_downloads/plot_kernel_approximation.py" download=""><code class="xref download docutils literal"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_kernel_approximation.py</span></code></a></div>
<div class="sphx-glr-download docutils container">
<a class="reference download internal" href="../_downloads/plot_kernel_approximation.ipynb" download=""><code class="xref download docutils literal"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_kernel_approximation.ipynb</span></code></a></div>
</div>
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.readthedocs.io">Gallery generated by Sphinx-Gallery</a></p>
</div>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
</div>
<div class="footer">
© 2007 - 2018, scikit-learn developers (BSD License).
<a href="../_sources/auto_examples/plot_kernel_approximation.rst.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_kernel_ridge_regression.html">Previous
</a>
</div>
<div class="buttonNext">
<a href="applications/plot_outlier_detection_housing.html">Next
</a>
</div>
</div>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-22606712-2']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
<script>
(function() {
var cx = '016639176250731907682:tjtqbvtvij0';
var gcse = document.createElement('script'); gcse.type = 'text/javascript'; gcse.async = true;
gcse.src = 'https://cse.google.com/cse.js?cx=' + cx;
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(gcse, s);
})();
</script>
</body>
</html>