-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_outlier_detection_bench.html
513 lines (461 loc) · 51.7 KB
/
plot_outlier_detection_bench.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
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
<meta property="og:title" content="Evaluation of outlier detection estimators" />
<meta property="og:type" content="website" />
<meta property="og:url" content="https://scikit-learn/stable/auto_examples/miscellaneous/plot_outlier_detection_bench.html" />
<meta property="og:site_name" content="scikit-learn" />
<meta property="og:description" content="This example benchmarks outlier detection algorithms, Local Outlier Factor(LOF) and Isolation Forest(IForest), using ROC curves on classical anomaly detection datasets. The algorithm performance is..." />
<meta property="og:image" content="https://scikit-learn.org/stable/_static/scikit-learn-logo-small.png" />
<meta property="og:image:alt" content="scikit-learn" />
<meta name="description" content="This example benchmarks outlier detection algorithms, Local Outlier Factor(LOF) and Isolation Forest(IForest), using ROC curves on classical anomaly detection datasets. The algorithm performance is..." />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Evaluation of outlier detection estimators — scikit-learn 1.2.2 documentation</title>
<link rel="canonical" href="http://scikit-learn.org/stable/auto_examples/miscellaneous/plot_outlier_detection_bench.html" />
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="stylesheet" href="../../_static/css/vendor/bootstrap.min.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../_static/plot_directive.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-binder.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-dataframe.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-rendered-html.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
<script src="../../_static/js/vendor/jquery-3.6.3.slim.min.js"></script>
</head>
<body>
<nav id="navbar" class="sk-docs-navbar navbar navbar-expand-md navbar-light bg-light py-0">
<div class="container-fluid sk-docs-container px-0">
<a class="navbar-brand py-0" href="../../index.html">
<img
class="sk-brand-img"
src="../../_static/scikit-learn-logo-small.png"
alt="logo"/>
</a>
<button
id="sk-navbar-toggler"
class="navbar-toggler"
type="button"
data-toggle="collapse"
data-target="#navbarSupportedContent"
aria-controls="navbarSupportedContent"
aria-expanded="false"
aria-label="Toggle navigation"
>
<span class="navbar-toggler-icon"></span>
</button>
<div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav mr-auto">
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../install.html">Install</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../user_guide.html">User Guide</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../modules/classes.html">API</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../index.html">Examples</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://blog.scikit-learn.org/">Community</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../getting_started.html" >Getting Started</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../tutorial/index.html" >Tutorial</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../whats_new/v1.2.html" >What's new</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../glossary.html" >Glossary</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://scikit-learn.org/dev/developers/index.html" target="_blank" rel="noopener noreferrer">Development</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../faq.html" >FAQ</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../support.html" >Support</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../related_projects.html" >Related packages</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../roadmap.html" >Roadmap</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../governance.html" >Governance</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../about.html" >About us</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://github.com/scikit-learn/scikit-learn" >GitHub</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://scikit-learn.org/dev/versions.html" >Other Versions and Download</a>
</li>
<li class="nav-item dropdown nav-more-item-dropdown">
<a class="sk-nav-link nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a>
<div class="dropdown-menu" aria-labelledby="navbarDropdown">
<a class="sk-nav-dropdown-item dropdown-item" href="../../getting_started.html" >Getting Started</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../tutorial/index.html" >Tutorial</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../whats_new/v1.2.html" >What's new</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../glossary.html" >Glossary</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://scikit-learn.org/dev/developers/index.html" target="_blank" rel="noopener noreferrer">Development</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../faq.html" >FAQ</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../support.html" >Support</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../related_projects.html" >Related packages</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../roadmap.html" >Roadmap</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../governance.html" >Governance</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../about.html" >About us</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://github.com/scikit-learn/scikit-learn" >GitHub</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://scikit-learn.org/dev/versions.html" >Other Versions and Download</a>
</div>
</li>
</ul>
<div id="searchbox" role="search">
<div class="searchformwrapper">
<form class="search" action="../../search.html" method="get">
<input class="sk-search-text-input" type="text" name="q" aria-labelledby="searchlabel" />
<input class="sk-search-text-btn" type="submit" value="Go" />
</form>
</div>
</div>
</div>
</div>
</nav>
<div class="d-flex" id="sk-doc-wrapper">
<input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
<label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
<div id="sk-sidebar-wrapper" class="border-right">
<div class="sk-sidebar-toc-wrapper">
<div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
<a href="plot_estimator_representation.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Displaying estimators and complex pipelines">Prev</a><a href="index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Miscellaneous">Up</a>
<a href="plot_kernel_approximation.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Explicit feature map approximation for RBF kernels">Next</a>
</div>
<div class="alert alert-danger p-1 mb-2" role="alert">
<p class="text-center mb-0">
<strong>scikit-learn 1.2.2</strong><br/>
<a href="http://scikit-learn.org/dev/versions.html">Other versions</a>
</p>
</div>
<div class="alert alert-warning p-1 mb-2" role="alert">
<p class="text-center mb-0">
Please <a class="font-weight-bold" href="../../about.html#citing-scikit-learn"><string>cite us</string></a> if you use the software.
</p>
</div>
<div class="sk-sidebar-toc">
<ul>
<li><a class="reference internal" href="#">Evaluation of outlier detection estimators</a><ul>
<li><a class="reference internal" href="#define-a-data-preprocessing-function">Define a data preprocessing function</a></li>
<li><a class="reference internal" href="#define-an-outlier-prediction-function">Define an outlier prediction function</a></li>
<li><a class="reference internal" href="#plot-and-interpret-results">Plot and interpret results</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div>
<div id="sk-page-content-wrapper">
<div class="sk-page-content container-fluid body px-md-3" role="main">
<div class="sphx-glr-download-link-note admonition note">
<p class="admonition-title">Note</p>
<p>Click <a class="reference internal" href="#sphx-glr-download-auto-examples-miscellaneous-plot-outlier-detection-bench-py"><span class="std std-ref">here</span></a>
to download the full example code or to run this example in your browser via Binder</p>
</div>
<section class="sphx-glr-example-title" id="evaluation-of-outlier-detection-estimators">
<span id="sphx-glr-auto-examples-miscellaneous-plot-outlier-detection-bench-py"></span><h1>Evaluation of outlier detection estimators<a class="headerlink" href="#evaluation-of-outlier-detection-estimators" title="Permalink to this heading">¶</a></h1>
<p>This example benchmarks outlier detection algorithms, <a class="reference internal" href="../../modules/outlier_detection.html#local-outlier-factor"><span class="std std-ref">Local Outlier Factor</span></a>
(LOF) and <a class="reference internal" href="../../modules/outlier_detection.html#isolation-forest"><span class="std std-ref">Isolation Forest</span></a> (IForest), using ROC curves on
classical anomaly detection datasets. The algorithm performance
is assessed in an outlier detection context:</p>
<p>1. The algorithms are trained on the whole dataset which is assumed to
contain outliers.</p>
<p>2. The ROC curve from <a class="reference internal" href="../../modules/generated/sklearn.metrics.RocCurveDisplay.html#sklearn.metrics.RocCurveDisplay" title="sklearn.metrics.RocCurveDisplay"><code class="xref py py-class docutils literal notranslate"><span class="pre">RocCurveDisplay</span></code></a> is computed
on the same dataset using the knowledge of the labels.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Author: Pharuj Rajborirug <[email protected]></span>
<span class="c1"># License: BSD 3 clause</span>
<span class="nb">print</span><span class="p">(</span><span class="vm">__doc__</span><span class="p">)</span>
</pre></div>
</div>
<section id="define-a-data-preprocessing-function">
<h2>Define a data preprocessing function<a class="headerlink" href="#define-a-data-preprocessing-function" title="Permalink to this heading">¶</a></h2>
<p>The example uses real-world datasets available in
<a class="reference internal" href="../../modules/classes.html#module-sklearn.datasets" title="sklearn.datasets"><code class="xref py py-class docutils literal notranslate"><span class="pre">sklearn.datasets</span></code></a> and the sample size of some datasets is reduced
to speed up computation. After the data preprocessing, the datasets’ targets
will have two classes, 0 representing inliers and 1 representing outliers.
The <code class="docutils literal notranslate"><span class="pre">preprocess_dataset</span></code> function returns data and target.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.datasets.fetch_kddcup99.html#sklearn.datasets.fetch_kddcup99" title="sklearn.datasets.fetch_kddcup99" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_kddcup99</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.datasets.fetch_covtype.html#sklearn.datasets.fetch_covtype" title="sklearn.datasets.fetch_covtype" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_covtype</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.datasets.fetch_openml.html#sklearn.datasets.fetch_openml" title="sklearn.datasets.fetch_openml" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_openml</span></a>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.preprocessing.LabelBinarizer.html#sklearn.preprocessing.LabelBinarizer" title="sklearn.preprocessing.LabelBinarizer" class="sphx-glr-backref-module-sklearn-preprocessing sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">LabelBinarizer</span></a>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="n">rng</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/random/legacy.html#numpy.random.RandomState" title="numpy.random.RandomState" class="sphx-glr-backref-module-numpy-random sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">RandomState</span></a><span class="p">(</span><span class="mi">42</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">preprocess_dataset</span><span class="p">(</span><span class="n">dataset_name</span><span class="p">):</span>
<span class="c1"># loading and vectorization</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Loading </span><span class="si">{</span><span class="n">dataset_name</span><span class="si">}</span><span class="s2"> data"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">dataset_name</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"http"</span><span class="p">,</span> <span class="s2">"smtp"</span><span class="p">,</span> <span class="s2">"SA"</span><span class="p">,</span> <span class="s2">"SF"</span><span class="p">]:</span>
<span class="n">dataset</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.fetch_kddcup99.html#sklearn.datasets.fetch_kddcup99" title="sklearn.datasets.fetch_kddcup99" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_kddcup99</span></a><span class="p">(</span><span class="n">subset</span><span class="o">=</span><span class="n">dataset_name</span><span class="p">,</span> <span class="n">percent10</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="n">rng</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">data</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">target</span>
<span class="n">lb</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.preprocessing.LabelBinarizer.html#sklearn.preprocessing.LabelBinarizer" title="sklearn.preprocessing.LabelBinarizer" class="sphx-glr-backref-module-sklearn-preprocessing sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">LabelBinarizer</span></a><span class="p">()</span>
<span class="k">if</span> <span class="n">dataset_name</span> <span class="o">==</span> <span class="s2">"SF"</span><span class="p">:</span>
<span class="n">idx</span> <span class="o">=</span> <span class="n">rng</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">int</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="mf">0.1</span><span class="p">),</span> <span class="n">replace</span><span class="o">=</span><span class="kc">False</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">idx</span><span class="p">]</span> <span class="c1"># reduce the sample size</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="n">x1</span> <span class="o">=</span> <span class="n">lb</span><span class="o">.</span><span class="n">fit_transform</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="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">str</span><span class="p">))</span>
<span class="n">X</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.c_.html#numpy.c_" title="numpy.c_" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">c_</span></a><span class="p">[</span><span class="n">X</span><span class="p">[:,</span> <span class="p">:</span><span class="mi">1</span><span class="p">],</span> <span class="n">x1</span><span class="p">,</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">:]]</span>
<span class="k">elif</span> <span class="n">dataset_name</span> <span class="o">==</span> <span class="s2">"SA"</span><span class="p">:</span>
<span class="n">idx</span> <span class="o">=</span> <span class="n">rng</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">int</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="mf">0.1</span><span class="p">),</span> <span class="n">replace</span><span class="o">=</span><span class="kc">False</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">idx</span><span class="p">]</span> <span class="c1"># reduce the sample size</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="n">x1</span> <span class="o">=</span> <span class="n">lb</span><span class="o">.</span><span class="n">fit_transform</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="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">str</span><span class="p">))</span>
<span class="n">x2</span> <span class="o">=</span> <span class="n">lb</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">X</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">str</span><span class="p">))</span>
<span class="n">x3</span> <span class="o">=</span> <span class="n">lb</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">X</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">str</span><span class="p">))</span>
<span class="n">X</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.c_.html#numpy.c_" title="numpy.c_" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">c_</span></a><span class="p">[</span><span class="n">X</span><span class="p">[:,</span> <span class="p">:</span><span class="mi">1</span><span class="p">],</span> <span class="n">x1</span><span class="p">,</span> <span class="n">x2</span><span class="p">,</span> <span class="n">x3</span><span class="p">,</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">4</span><span class="p">:]]</span>
<span class="n">y</span> <span class="o">=</span> <span class="p">(</span><span class="n">y</span> <span class="o">!=</span> <span class="sa">b</span><span class="s2">"normal."</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="k">if</span> <span class="n">dataset_name</span> <span class="o">==</span> <span class="s2">"forestcover"</span><span class="p">:</span>
<span class="n">dataset</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.fetch_covtype.html#sklearn.datasets.fetch_covtype" title="sklearn.datasets.fetch_covtype" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_covtype</span></a><span class="p">()</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">data</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">target</span>
<span class="n">idx</span> <span class="o">=</span> <span class="n">rng</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">int</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="mf">0.1</span><span class="p">),</span> <span class="n">replace</span><span class="o">=</span><span class="kc">False</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">idx</span><span class="p">]</span> <span class="c1"># reduce the sample size</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="c1"># inliers are those with attribute 2</span>
<span class="c1"># outliers are those with attribute 4</span>
<span class="n">s</span> <span class="o">=</span> <span class="p">(</span><span class="n">y</span> <span class="o">==</span> <span class="mi">2</span><span class="p">)</span> <span class="o">+</span> <span class="p">(</span><span class="n">y</span> <span class="o">==</span> <span class="mi">4</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">s</span><span class="p">,</span> <span class="p">:]</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="p">[</span><span class="n">s</span><span class="p">]</span>
<span class="n">y</span> <span class="o">=</span> <span class="p">(</span><span class="n">y</span> <span class="o">!=</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="k">if</span> <span class="n">dataset_name</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"glass"</span><span class="p">,</span> <span class="s2">"wdbc"</span><span class="p">,</span> <span class="s2">"cardiotocography"</span><span class="p">]:</span>
<span class="n">dataset</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.fetch_openml.html#sklearn.datasets.fetch_openml" title="sklearn.datasets.fetch_openml" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_openml</span></a><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="n">dataset_name</span><span class="p">,</span> <span class="n">version</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">as_frame</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">parser</span><span class="o">=</span><span class="s2">"pandas"</span>
<span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">data</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">target</span>
<span class="k">if</span> <span class="n">dataset_name</span> <span class="o">==</span> <span class="s2">"glass"</span><span class="p">:</span>
<span class="n">s</span> <span class="o">=</span> <span class="n">y</span> <span class="o">==</span> <span class="s2">"tableware"</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="k">if</span> <span class="n">dataset_name</span> <span class="o">==</span> <span class="s2">"wdbc"</span><span class="p">:</span>
<span class="n">s</span> <span class="o">=</span> <span class="n">y</span> <span class="o">==</span> <span class="s2">"2"</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="n">X_mal</span><span class="p">,</span> <span class="n">y_mal</span> <span class="o">=</span> <span class="n">X</span><span class="p">[</span><span class="n">s</span><span class="p">],</span> <span class="n">y</span><span class="p">[</span><span class="n">s</span><span class="p">]</span>
<span class="n">X_ben</span><span class="p">,</span> <span class="n">y_ben</span> <span class="o">=</span> <span class="n">X</span><span class="p">[</span><span class="o">~</span><span class="n">s</span><span class="p">],</span> <span class="n">y</span><span class="p">[</span><span class="o">~</span><span class="n">s</span><span class="p">]</span>
<span class="c1"># downsampled to 39 points (9.8% outliers)</span>
<span class="n">idx</span> <span class="o">=</span> <span class="n">rng</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">y_mal</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="mi">39</span><span class="p">,</span> <span class="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="n">X_mal2</span> <span class="o">=</span> <span class="n">X_mal</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="n">y_mal2</span> <span class="o">=</span> <span class="n">y_mal</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="n">X</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.concatenate.html#numpy.concatenate" title="numpy.concatenate" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">concatenate</span></a><span class="p">((</span><span class="n">X_ben</span><span class="p">,</span> <span class="n">X_mal2</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="n">y</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.concatenate.html#numpy.concatenate" title="numpy.concatenate" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">concatenate</span></a><span class="p">((</span><span class="n">y_ben</span><span class="p">,</span> <span class="n">y_mal2</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="k">if</span> <span class="n">dataset_name</span> <span class="o">==</span> <span class="s2">"cardiotocography"</span><span class="p">:</span>
<span class="n">s</span> <span class="o">=</span> <span class="n">y</span> <span class="o">==</span> <span class="s2">"3"</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="c1"># 0 represents inliers, and 1 represents outliers</span>
<span class="n">y</span> <span class="o">=</span> <a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.html#pandas.Series" title="pandas.Series" class="sphx-glr-backref-module-pandas sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">pd</span><span class="o">.</span><span class="n">Series</span></a><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"category"</span><span class="p">)</span>
<span class="k">return</span> <span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="define-an-outlier-prediction-function">
<h2>Define an outlier prediction function<a class="headerlink" href="#define-an-outlier-prediction-function" title="Permalink to this heading">¶</a></h2>
<p>There is no particular reason to choose algorithms
<a class="reference internal" href="../../modules/generated/sklearn.neighbors.LocalOutlierFactor.html#sklearn.neighbors.LocalOutlierFactor" title="sklearn.neighbors.LocalOutlierFactor"><code class="xref py py-class docutils literal notranslate"><span class="pre">LocalOutlierFactor</span></code></a> and
<a class="reference internal" href="../../modules/generated/sklearn.ensemble.IsolationForest.html#sklearn.ensemble.IsolationForest" title="sklearn.ensemble.IsolationForest"><code class="xref py py-class docutils literal notranslate"><span class="pre">IsolationForest</span></code></a>. The goal is to show that
different algorithm performs well on different datasets. The following
<code class="docutils literal notranslate"><span class="pre">compute_prediction</span></code> function returns average outlier score of X.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.neighbors</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.neighbors.LocalOutlierFactor.html#sklearn.neighbors.LocalOutlierFactor" title="sklearn.neighbors.LocalOutlierFactor" class="sphx-glr-backref-module-sklearn-neighbors sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">LocalOutlierFactor</span></a>
<span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.ensemble.IsolationForest.html#sklearn.ensemble.IsolationForest" title="sklearn.ensemble.IsolationForest" class="sphx-glr-backref-module-sklearn-ensemble sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">IsolationForest</span></a>
<span class="k">def</span> <span class="nf">compute_prediction</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">model_name</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Computing </span><span class="si">{</span><span class="n">model_name</span><span class="si">}</span><span class="s2"> prediction..."</span><span class="p">)</span>
<span class="k">if</span> <span class="n">model_name</span> <span class="o">==</span> <span class="s2">"LOF"</span><span class="p">:</span>
<span class="n">clf</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.neighbors.LocalOutlierFactor.html#sklearn.neighbors.LocalOutlierFactor" title="sklearn.neighbors.LocalOutlierFactor" class="sphx-glr-backref-module-sklearn-neighbors sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">LocalOutlierFactor</span></a><span class="p">(</span><span class="n">n_neighbors</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">contamination</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">)</span>
<span class="n">clf</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">negative_outlier_factor_</span>
<span class="k">if</span> <span class="n">model_name</span> <span class="o">==</span> <span class="s2">"IForest"</span><span class="p">:</span>
<span class="n">clf</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.ensemble.IsolationForest.html#sklearn.ensemble.IsolationForest" title="sklearn.ensemble.IsolationForest" class="sphx-glr-backref-module-sklearn-ensemble sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">IsolationForest</span></a><span class="p">(</span><span class="n">random_state</span><span class="o">=</span><span class="n">rng</span><span class="p">,</span> <span class="n">contamination</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">)</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X</span><span class="p">)</span><span class="o">.</span><span class="n">decision_function</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>
<span class="k">return</span> <span class="n">y_pred</span>
</pre></div>
</div>
</section>
<section id="plot-and-interpret-results">
<h2>Plot and interpret results<a class="headerlink" href="#plot-and-interpret-results" title="Permalink to this heading">¶</a></h2>
<p>The algorithm performance relates to how good the true positive rate (TPR)
is at low value of the false positive rate (FPR). The best algorithms
have the curve on the top-left of the plot and the area under curve (AUC)
close to 1. The diagonal dashed line represents a random classification
of outliers and inliers.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">math</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
<span class="kn">from</span> <span class="nn">sklearn.metrics</span> <span class="kn">import</span> <span class="n">RocCurveDisplay</span>
<span class="n">datasets_name</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">"http"</span><span class="p">,</span>
<span class="s2">"smtp"</span><span class="p">,</span>
<span class="s2">"SA"</span><span class="p">,</span>
<span class="s2">"SF"</span><span class="p">,</span>
<span class="s2">"forestcover"</span><span class="p">,</span>
<span class="s2">"glass"</span><span class="p">,</span>
<span class="s2">"wdbc"</span><span class="p">,</span>
<span class="s2">"cardiotocography"</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">models_name</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">"LOF"</span><span class="p">,</span>
<span class="s2">"IForest"</span><span class="p">,</span>
<span class="p">]</span>
<span class="c1"># plotting parameters</span>
<span class="n">cols</span> <span class="o">=</span> <span class="mi">2</span>
<span class="n">linewidth</span> <span class="o">=</span> <span class="mi">1</span>
<span class="n">pos_label</span> <span class="o">=</span> <span class="mi">0</span> <span class="c1"># mean 0 belongs to positive class</span>
<span class="n">rows</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/math.html#math.ceil" title="math.ceil" class="sphx-glr-backref-module-math sphx-glr-backref-type-py-function"><span class="n">math</span><span class="o">.</span><span class="n">ceil</span></a><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">datasets_name</span><span class="p">)</span> <span class="o">/</span> <span class="n">cols</span><span class="p">)</span>
<span class="n">fig</span><span class="p">,</span> <span class="n">axs</span> <span class="o">=</span> <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.subplots.html#matplotlib.pyplot.subplots" title="matplotlib.pyplot.subplots" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">subplots</span></a><span class="p">(</span><span class="n">rows</span><span class="p">,</span> <span class="n">cols</span><span class="p">,</span> <span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="n">rows</span> <span class="o">*</span> <span class="mi">3</span><span class="p">))</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">dataset_name</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">datasets_name</span><span class="p">):</span>
<span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span> <span class="o">=</span> <span class="n">preprocess_dataset</span><span class="p">(</span><span class="n">dataset_name</span><span class="o">=</span><span class="n">dataset_name</span><span class="p">)</span>
<span class="k">for</span> <span class="n">model_name</span> <span class="ow">in</span> <span class="n">models_name</span><span class="p">:</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">compute_prediction</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">model_name</span><span class="o">=</span><span class="n">model_name</span><span class="p">)</span>
<span class="n">display</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.metrics.RocCurveDisplay.html#sklearn.metrics.RocCurveDisplay.from_predictions" title="sklearn.metrics.RocCurveDisplay.from_predictions" class="sphx-glr-backref-module-sklearn-metrics-RocCurveDisplay sphx-glr-backref-type-py-method"><span class="n">RocCurveDisplay</span><span class="o">.</span><span class="n">from_predictions</span></a><span class="p">(</span>
<span class="n">y</span><span class="p">,</span>
<span class="n">y_pred</span><span class="p">,</span>
<span class="n">pos_label</span><span class="o">=</span><span class="n">pos_label</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="n">model_name</span><span class="p">,</span>
<span class="n">linewidth</span><span class="o">=</span><span class="n">linewidth</span><span class="p">,</span>
<span class="n">ax</span><span class="o">=</span><span class="n">axs</span><span class="p">[</span><span class="n">i</span> <span class="o">//</span> <span class="n">cols</span><span class="p">,</span> <span class="n">i</span> <span class="o">%</span> <span class="n">cols</span><span class="p">],</span>
<span class="p">)</span>
<span class="n">axs</span><span class="p">[</span><span class="n">i</span> <span class="o">//</span> <span class="n">cols</span><span class="p">,</span> <span class="n">i</span> <span class="o">%</span> <span class="n">cols</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">linewidth</span><span class="o">=</span><span class="n">linewidth</span><span class="p">,</span> <span class="n">linestyle</span><span class="o">=</span><span class="s2">":"</span><span class="p">)</span>
<span class="n">axs</span><span class="p">[</span><span class="n">i</span> <span class="o">//</span> <span class="n">cols</span><span class="p">,</span> <span class="n">i</span> <span class="o">%</span> <span class="n">cols</span><span class="p">]</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="n">dataset_name</span><span class="p">)</span>
<span class="n">axs</span><span class="p">[</span><span class="n">i</span> <span class="o">//</span> <span class="n">cols</span><span class="p">,</span> <span class="n">i</span> <span class="o">%</span> <span class="n">cols</span><span class="p">]</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s2">"False Positive Rate"</span><span class="p">)</span>
<span class="n">axs</span><span class="p">[</span><span class="n">i</span> <span class="o">//</span> <span class="n">cols</span><span class="p">,</span> <span class="n">i</span> <span class="o">%</span> <span class="n">cols</span><span class="p">]</span><span class="o">.</span><span class="n">set_ylabel</span><span class="p">(</span><span class="s2">"True Positive Rate"</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.tight_layout.html#matplotlib.pyplot.tight_layout" title="matplotlib.pyplot.tight_layout" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span></a><span class="p">(</span><span class="n">pad</span><span class="o">=</span><span class="mf">2.0</span><span class="p">)</span> <span class="c1"># spacing between subplots</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="matplotlib.pyplot.show" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
</pre></div>
</div>
<img src="../../_images/sphx_glr_plot_outlier_detection_bench_001.png" srcset="../../_images/sphx_glr_plot_outlier_detection_bench_001.png" alt="http, smtp, SA, SF, forestcover, glass, wdbc, cardiotocography" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Loading http data
Computing LOF prediction...
Computing IForest prediction...
Loading smtp data
Computing LOF prediction...
Computing IForest prediction...
Loading SA data
Computing LOF prediction...
Computing IForest prediction...
Loading SF data
Computing LOF prediction...
Computing IForest prediction...
Loading forestcover data
Computing LOF prediction...
Computing IForest prediction...
Loading glass data
Computing LOF prediction...
Computing IForest prediction...
Loading wdbc data
Computing LOF prediction...
Computing IForest prediction...
Loading cardiotocography data
Computing LOF prediction...
Computing IForest prediction...
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 46.233 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-miscellaneous-plot-outlier-detection-bench-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.2.X?urlpath=lab/tree/notebooks/auto_examples/miscellaneous/plot_outlier_detection_bench.ipynb"><img alt="Launch binder" src="../../_images/binder_badge_logo23.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b7e32fe54d613dce0d3c376377af061d/plot_outlier_detection_bench.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_outlier_detection_bench.py</span></code></a></p>
</div>
<div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eacb6a63c887dafcff02b3cee64854ef/plot_outlier_detection_bench.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_outlier_detection_bench.ipynb</span></code></a></p>
</div>
</div>
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.github.io">Gallery generated by Sphinx-Gallery</a></p>
</section>
</section>
</div>
<div class="container">
<footer class="sk-content-footer">
© 2007 - 2023, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/miscellaneous/plot_outlier_detection_bench.rst.txt" rel="nofollow">Show this page source</a>
</footer>
</div>
</div>
</div>
<script src="../../_static/js/vendor/bootstrap.min.js"></script>
<script>
window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date;
ga('create', 'UA-22606712-2', 'auto');
ga('set', 'anonymizeIp', true);
ga('send', 'pageview');
</script>
<script async src='https://www.google-analytics.com/analytics.js'></script>
<script defer data-domain="scikit-learn.org" src="https://views.scientific-python.org/js/script.js">
</script>
<script>
$(document).ready(function() {
/* Add a [>>>] button on the top-right corner of code samples to hide
* the >>> and ... prompts and the output and thus make the code
* copyable. */
var div = $('.highlight-python .highlight,' +
'.highlight-python3 .highlight,' +
'.highlight-pycon .highlight,' +
'.highlight-default .highlight')
var pre = div.find('pre');
// get the styles from the current theme
pre.parent().parent().css('position', 'relative');
var hide_text = 'Hide prompts and outputs';
var show_text = 'Show prompts and outputs';
// create and add the button to all the code blocks that contain >>>
div.each(function(index) {
var jthis = $(this);
if (jthis.find('.gp').length > 0) {
var button = $('<span class="copybutton">>>></span>');
button.attr('title', hide_text);
button.data('hidden', 'false');
jthis.prepend(button);
}
// tracebacks (.gt) contain bare text elements that need to be
// wrapped in a span to work with .nextUntil() (see later)
jthis.find('pre:has(.gt)').contents().filter(function() {
return ((this.nodeType == 3) && (this.data.trim().length > 0));
}).wrap('<span>');
});
// define the behavior of the button when it's clicked
$('.copybutton').click(function(e){
e.preventDefault();
var button = $(this);
if (button.data('hidden') === 'false') {
// hide the code output
button.parent().find('.go, .gp, .gt').hide();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
button.css('text-decoration', 'line-through');
button.attr('title', show_text);
button.data('hidden', 'true');
} else {
// show the code output
button.parent().find('.go, .gp, .gt').show();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
button.css('text-decoration', 'none');
button.attr('title', hide_text);
button.data('hidden', 'false');
}
});
/*** Add permalink buttons next to glossary terms ***/
$('dl.glossary > dt[id]').append(function() {
return ('<a class="headerlink" href="#' +
this.getAttribute('id') +
'" title="Permalink to this term">¶</a>');
});
});
</script>
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>