-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_species_distribution_modeling.html
466 lines (387 loc) · 41.9 KB
/
plot_species_distribution_modeling.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
<!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>Species distribution modeling — scikit-learn 0.17.1 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: '0.17.1',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true
};
</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>
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="author" title="About these documents" href="../../about.html" />
<link rel="top" title="scikit-learn 0.17.1 documentation" href="../../index.html" />
<link rel="up" title="Examples" href="../index.html" />
<link rel="next" title="Visualizing the stock market structure" href="plot_stock_market.html" />
<link rel="prev" title="Model Complexity Influence" href="plot_model_complexity_influence.html" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<script src="../../_static/js/bootstrap.min.js" type="text/javascript"></script>
<link rel="canonical" href="https://scikit-learn.org/stable/auto_examples/applications/plot_species_distribution_modeling.html" />
<script type="text/javascript">
$("div.buttonNext, div.buttonPrevious").hover(
function () {
$(this).css('background-color', '#FF9C34');
},
function () {
$(this).css('background-color', '#A7D6E2');
}
);
</script>
</head>
<body role="document">
<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">
<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 0.17 (stable)</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="../../faq.html">FAQ</a></li>
<li><a href="../../developers/contributing.html">Contributing</a></li>
<li class="divider"></li>
<li><a href="http://scikit-learn.org/dev/documentation.html">Scikit-learn 0.18 (development)</a></li>
<li><a href="http://scikit-learn.org/0.16/documentation.html">Scikit-learn 0.16</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>
<div class="search_form">
<div 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">
<!-- rellinks[1:] is an ugly hack to avoid link to module
index -->
<div class="rellink">
<a href="plot_model_complexity_influence.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
Model Complex...
</span>
<span class="hiddenrellink">
Model Complexity Influence
</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">This documentation is for scikit-learn <strong>version 0.17.1</strong> — <a href="http://scikit-learn.org/stable/support.html#documentation-resources">Other versions</a></p>
<p class="citing">If you use the software, please consider <a href="../../about.html#citing-scikit-learn">citing scikit-learn</a>.</p>
<ul>
<li><a class="reference internal" href="#">Species distribution modeling</a><ul>
<li><a class="reference internal" href="#references">References</a></li>
</ul>
</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="section" id="species-distribution-modeling">
<span id="example-applications-plot-species-distribution-modeling-py"></span><h1>Species distribution modeling<a class="headerlink" href="#species-distribution-modeling" title="Permalink to this headline">¶</a></h1>
<p>Modeling species’ geographic distributions is an important
problem in conservation biology. In this example we
model the geographic distribution of two south american
mammals given past observations and 14 environmental
variables. Since we have only positive examples (there are
no unsuccessful observations), we cast this problem as a
density estimation problem and use the <cite>OneClassSVM</cite> provided
by the package <cite>sklearn.svm</cite> as our modeling tool.
The dataset is provided by Phillips et. al. (2006).
If available, the example uses
<a class="reference external" href="http://matplotlib.sourceforge.net/basemap/doc/html/">basemap</a>
to plot the coast lines and national boundaries of South America.</p>
<p>The two species are:</p>
<blockquote>
<div><ul class="simple">
<li><a class="reference external" href="http://www.iucnredlist.org/apps/redlist/details/3038/0">“Bradypus variegatus”</a> ,
the Brown-throated Sloth.</li>
<li><a class="reference external" href="http://www.iucnredlist.org/apps/redlist/details/13408/0">“Microryzomys minutus”</a> ,
also known as the Forest Small Rice Rat, a rodent that lives in Peru,
Colombia, Ecuador, Peru, and Venezuela.</li>
</ul>
</div></blockquote>
<div class="section" id="references">
<h2>References<a class="headerlink" href="#references" title="Permalink to this headline">¶</a></h2>
<blockquote>
<div><ul class="simple">
<li><a class="reference external" href="http://www.cs.princeton.edu/~schapire/papers/ecolmod.pdf">“Maximum entropy modeling of species geographic distributions”</a>
S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,
190:231-259, 2006.</li>
</ul>
</div></blockquote>
<img alt="../../_images/plot_species_distribution_modeling_001.png" class="align-center" src="../../_images/plot_species_distribution_modeling_001.png" />
<p><strong>Script output</strong>:</p>
<div class="highlight-python"><div class="highlight"><pre>Downloading species data from http://www.cs.princeton.edu/~schapire/maxent/datasets/samples.zip to /root/scikit_learn_data
Downloading coverage data from http://www.cs.princeton.edu/~schapire/maxent/datasets/coverages.zip to /root/scikit_learn_data
- converting coverages/cld6190_ann.asc
- converting coverages/dtr6190_ann.asc
- converting coverages/ecoreg.asc
- converting coverages/frs6190_ann.asc
- converting coverages/h_dem.asc
- converting coverages/pre6190_ann.asc
- converting coverages/pre6190_l1.asc
- converting coverages/pre6190_l10.asc
- converting coverages/pre6190_l4.asc
- converting coverages/pre6190_l7.asc
- converting coverages/tmn6190_ann.asc
- converting coverages/tmp6190_ann.asc
- converting coverages/tmx6190_ann.asc
- converting coverages/vap6190_ann.asc
________________________________________________________________________________
Modeling distribution of species 'bradypus variegatus'
- fit OneClassSVM ... done.
- plot coastlines from coverage
- predict species distribution
Area under the ROC curve : 0.868380
________________________________________________________________________________
Modeling distribution of species 'microryzomys minutus'
- fit OneClassSVM ... done.
- plot coastlines from coverage
- predict species distribution
Area under the ROC curve : 0.993919
time elapsed: 36.17s
</pre></div>
</div>
<p><strong>Python source code:</strong> <a class="reference download internal" href="../../_downloads/plot_species_distribution_modeling.py"><code class="xref download docutils literal"><span class="pre">plot_species_distribution_modeling.py</span></code></a></p>
<div class="highlight-python"><div class="highlight"><pre>
<span class="c1"># Authors: Peter Prettenhofer <[email protected]></span>
<span class="c1"># Jake Vanderplas <[email protected]></span>
<span class="c1">#</span>
<span class="c1"># License: BSD 3 clause</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
<span class="kn">from</span> <span class="nn">time</span> <span class="kn">import</span> <span class="n">time</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</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">from</span> <span class="nn">sklearn.datasets.base</span> <span class="kn">import</span> <span class="n">Bunch</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">fetch_species_distributions</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets.species_distributions</span> <span class="kn">import</span> <span class="n">construct_grids</span>
<span class="kn">from</span> <span class="nn">sklearn</span> <span class="kn">import</span> <span class="n">svm</span><span class="p">,</span> <span class="n">metrics</span>
<span class="c1"># if basemap is available, we'll use it.</span>
<span class="c1"># otherwise, we'll improvise later...</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">mpl_toolkits.basemap</span> <span class="kn">import</span> <span class="n">Basemap</span>
<span class="n">basemap</span> <span class="o">=</span> <span class="bp">True</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="n">basemap</span> <span class="o">=</span> <span class="bp">False</span>
<span class="k">print</span><span class="p">(</span><span class="n">__doc__</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">create_species_bunch</span><span class="p">(</span><span class="n">species_name</span><span class="p">,</span> <span class="n">train</span><span class="p">,</span> <span class="n">test</span><span class="p">,</span> <span class="n">coverages</span><span class="p">,</span> <span class="n">xgrid</span><span class="p">,</span> <span class="n">ygrid</span><span class="p">):</span>
<span class="sd">"""Create a bunch with information about a particular organism</span>
<span class="sd"> This will use the test/train record arrays to extract the</span>
<span class="sd"> data specific to the given species name.</span>
<span class="sd"> """</span>
<span class="n">bunch</span> <span class="o">=</span> <span class="n">Bunch</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">species_name</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"_"</span><span class="p">)[:</span><span class="mi">2</span><span class="p">]))</span>
<span class="n">species_name</span> <span class="o">=</span> <span class="n">species_name</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'ascii'</span><span class="p">)</span>
<span class="n">points</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="n">test</span><span class="o">=</span><span class="n">test</span><span class="p">,</span> <span class="n">train</span><span class="o">=</span><span class="n">train</span><span class="p">)</span>
<span class="k">for</span> <span class="n">label</span><span class="p">,</span> <span class="n">pts</span> <span class="ow">in</span> <span class="n">points</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="c1"># choose points associated with the desired species</span>
<span class="n">pts</span> <span class="o">=</span> <span class="n">pts</span><span class="p">[</span><span class="n">pts</span><span class="p">[</span><span class="s1">'species'</span><span class="p">]</span> <span class="o">==</span> <span class="n">species_name</span><span class="p">]</span>
<span class="n">bunch</span><span class="p">[</span><span class="s1">'pts_</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">label</span><span class="p">]</span> <span class="o">=</span> <span class="n">pts</span>
<span class="c1"># determine coverage values for each of the training & testing points</span>
<span class="n">ix</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.searchsorted.html#numpy.searchsorted"><span class="n">np</span><span class="o">.</span><span class="n">searchsorted</span></a><span class="p">(</span><span class="n">xgrid</span><span class="p">,</span> <span class="n">pts</span><span class="p">[</span><span class="s1">'dd long'</span><span class="p">])</span>
<span class="n">iy</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.searchsorted.html#numpy.searchsorted"><span class="n">np</span><span class="o">.</span><span class="n">searchsorted</span></a><span class="p">(</span><span class="n">ygrid</span><span class="p">,</span> <span class="n">pts</span><span class="p">[</span><span class="s1">'dd lat'</span><span class="p">])</span>
<span class="n">bunch</span><span class="p">[</span><span class="s1">'cov_</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">label</span><span class="p">]</span> <span class="o">=</span> <span class="n">coverages</span><span class="p">[:,</span> <span class="o">-</span><span class="n">iy</span><span class="p">,</span> <span class="n">ix</span><span class="p">]</span><span class="o">.</span><span class="n">T</span>
<span class="k">return</span> <span class="n">bunch</span>
<span class="k">def</span> <span class="nf">plot_species_distribution</span><span class="p">(</span><span class="n">species</span><span class="o">=</span><span class="p">(</span><span class="s2">"bradypus_variegatus_0"</span><span class="p">,</span>
<span class="s2">"microryzomys_minutus_0"</span><span class="p">)):</span>
<span class="sd">"""</span>
<span class="sd"> Plot the species distribution.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">species</span><span class="p">)</span> <span class="o">></span> <span class="mi">2</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Note: when more than two species are provided,"</span>
<span class="s2">" only the first two will be used"</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="c1"># Load the compressed data</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">fetch_species_distributions</span><span class="p">()</span>
<span class="c1"># Set up the data grid</span>
<span class="n">xgrid</span><span class="p">,</span> <span class="n">ygrid</span> <span class="o">=</span> <span class="n">construct_grids</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="c1"># The grid in x,y coordinates</span>
<span class="n">X</span><span class="p">,</span> <span class="n">Y</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.meshgrid.html#numpy.meshgrid"><span class="n">np</span><span class="o">.</span><span class="n">meshgrid</span></a><span class="p">(</span><span class="n">xgrid</span><span class="p">,</span> <span class="n">ygrid</span><span class="p">[::</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="c1"># create a bunch for each species</span>
<span class="n">BV_bunch</span> <span class="o">=</span> <span class="n">create_species_bunch</span><span class="p">(</span><span class="n">species</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">data</span><span class="o">.</span><span class="n">train</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">test</span><span class="p">,</span>
<span class="n">data</span><span class="o">.</span><span class="n">coverages</span><span class="p">,</span> <span class="n">xgrid</span><span class="p">,</span> <span class="n">ygrid</span><span class="p">)</span>
<span class="n">MM_bunch</span> <span class="o">=</span> <span class="n">create_species_bunch</span><span class="p">(</span><span class="n">species</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span>
<span class="n">data</span><span class="o">.</span><span class="n">train</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">test</span><span class="p">,</span>
<span class="n">data</span><span class="o">.</span><span class="n">coverages</span><span class="p">,</span> <span class="n">xgrid</span><span class="p">,</span> <span class="n">ygrid</span><span class="p">)</span>
<span class="c1"># background points (grid coordinates) for evaluation</span>
<a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.random.seed.html#numpy.random.seed"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span></a><span class="p">(</span><span class="mi">13</span><span class="p">)</span>
<span class="n">background_points</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.c_.html#numpy.c_"><span class="n">np</span><span class="o">.</span><span class="n">c_</span></a><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">Ny</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="mi">10000</span><span class="p">),</span>
<span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">Nx</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="mi">10000</span><span class="p">)]</span><span class="o">.</span><span class="n">T</span>
<span class="c1"># We'll make use of the fact that coverages[6] has measurements at all</span>
<span class="c1"># land points. This will help us decide between land and water.</span>
<span class="n">land_reference</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">coverages</span><span class="p">[</span><span class="mi">6</span><span class="p">]</span>
<span class="c1"># Fit, predict, and plot for each species.</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">species</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">([</span><span class="n">BV_bunch</span><span class="p">,</span> <span class="n">MM_bunch</span><span class="p">]):</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"_"</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Modeling distribution of species '</span><span class="si">%s</span><span class="s2">'"</span> <span class="o">%</span> <span class="n">species</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
<span class="c1"># Standardize features</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">species</span><span class="o">.</span><span class="n">cov_train</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="n">std</span> <span class="o">=</span> <span class="n">species</span><span class="o">.</span><span class="n">cov_train</span><span class="o">.</span><span class="n">std</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">train_cover_std</span> <span class="o">=</span> <span class="p">(</span><span class="n">species</span><span class="o">.</span><span class="n">cov_train</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">/</span> <span class="n">std</span>
<span class="c1"># Fit OneClassSVM</span>
<span class="k">print</span><span class="p">(</span><span class="s2">" - fit OneClassSVM ... "</span><span class="p">,</span> <span class="n">end</span><span class="o">=</span><span class="s1">''</span><span class="p">)</span>
<span class="n">clf</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.svm.OneClassSVM.html#sklearn.svm.OneClassSVM"><span class="n">svm</span><span class="o">.</span><span class="n">OneClassSVM</span></a><span class="p">(</span><span class="n">nu</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">kernel</span><span class="o">=</span><span class="s2">"rbf"</span><span class="p">,</span> <span class="n">gamma</span><span class="o">=</span><span class="mf">0.5</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">train_cover_std</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"done."</span><span class="p">)</span>
<span class="c1"># Plot map of South America</span>
<a href="http://matplotlib.org/api/pyplot_api.html#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">2</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="k">if</span> <span class="n">basemap</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">" - plot coastlines using basemap"</span><span class="p">)</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">Basemap</span><span class="p">(</span><span class="n">projection</span><span class="o">=</span><span class="s1">'cyl'</span><span class="p">,</span> <span class="n">llcrnrlat</span><span class="o">=</span><span class="n">Y</span><span class="o">.</span><span class="n">min</span><span class="p">(),</span>
<span class="n">urcrnrlat</span><span class="o">=</span><span class="n">Y</span><span class="o">.</span><span class="n">max</span><span class="p">(),</span> <span class="n">llcrnrlon</span><span class="o">=</span><span class="n">X</span><span class="o">.</span><span class="n">min</span><span class="p">(),</span>
<span class="n">urcrnrlon</span><span class="o">=</span><span class="n">X</span><span class="o">.</span><span class="n">max</span><span class="p">(),</span> <span class="n">resolution</span><span class="o">=</span><span class="s1">'c'</span><span class="p">)</span>
<span class="n">m</span><span class="o">.</span><span class="n">drawcoastlines</span><span class="p">()</span>
<span class="n">m</span><span class="o">.</span><span class="n">drawcountries</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">" - plot coastlines from coverage"</span><span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">contour</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="n">land_reference</span><span class="p">,</span>
<span class="n">levels</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">9999</span><span class="p">],</span> <span class="n">colors</span><span class="o">=</span><span class="s2">"k"</span><span class="p">,</span>
<span class="n">linestyles</span><span class="o">=</span><span class="s2">"solid"</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.xticks"><span class="n">plt</span><span class="o">.</span><span class="n">xticks</span></a><span class="p">([])</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.yticks"><span class="n">plt</span><span class="o">.</span><span class="n">yticks</span></a><span class="p">([])</span>
<span class="k">print</span><span class="p">(</span><span class="s2">" - predict species distribution"</span><span class="p">)</span>
<span class="c1"># Predict species distribution using the training data</span>
<span class="n">Z</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.ones.html#numpy.ones"><span class="n">np</span><span class="o">.</span><span class="n">ones</span></a><span class="p">((</span><span class="n">data</span><span class="o">.</span><span class="n">Ny</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">Nx</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span>
<span class="c1"># We'll predict only for the land points.</span>
<span class="n">idx</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.where.html#numpy.where"><span class="n">np</span><span class="o">.</span><span class="n">where</span></a><span class="p">(</span><span class="n">land_reference</span> <span class="o">></span> <span class="o">-</span><span class="mi">9999</span><span class="p">)</span>
<span class="n">coverages_land</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">coverages</span><span class="p">[:,</span> <span class="n">idx</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">idx</span><span class="p">[</span><span class="mi">1</span><span class="p">]]</span><span class="o">.</span><span class="n">T</span>
<span class="n">pred</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">decision_function</span><span class="p">((</span><span class="n">coverages_land</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">/</span> <span class="n">std</span><span class="p">)[:,</span> <span class="mi">0</span><span class="p">]</span>
<span class="n">Z</span> <span class="o">*=</span> <span class="n">pred</span><span class="o">.</span><span class="n">min</span><span class="p">()</span>
<span class="n">Z</span><span class="p">[</span><span class="n">idx</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">idx</span><span class="p">[</span><span class="mi">1</span><span class="p">]]</span> <span class="o">=</span> <span class="n">pred</span>
<span class="n">levels</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.linspace.html#numpy.linspace"><span class="n">np</span><span class="o">.</span><span class="n">linspace</span></a><span class="p">(</span><span class="n">Z</span><span class="o">.</span><span class="n">min</span><span class="p">(),</span> <span class="n">Z</span><span class="o">.</span><span class="n">max</span><span class="p">(),</span> <span class="mi">25</span><span class="p">)</span>
<span class="n">Z</span><span class="p">[</span><span class="n">land_reference</span> <span class="o">==</span> <span class="o">-</span><span class="mi">9999</span><span class="p">]</span> <span class="o">=</span> <span class="o">-</span><span class="mi">9999</span>
<span class="c1"># plot contours of the prediction</span>
<a href="http://matplotlib.org/api/pyplot_api.html#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">X</span><span class="p">,</span> <span class="n">Y</span><span class="p">,</span> <span class="n">Z</span><span class="p">,</span> <span class="n">levels</span><span class="o">=</span><span class="n">levels</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">Reds</span><span class="p">)</span>
<a href="http://matplotlib.org/api/colorbar_api.html#matplotlib.colorbar"><span class="n">plt</span><span class="o">.</span><span class="n">colorbar</span></a><span class="p">(</span><span class="n">format</span><span class="o">=</span><span class="s1">'</span><span class="si">%.2f</span><span class="s1">'</span><span class="p">)</span>
<span class="c1"># scatter training/testing points</span>
<a href="http://matplotlib.org/api/pyplot_api.html#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">species</span><span class="o">.</span><span class="n">pts_train</span><span class="p">[</span><span class="s1">'dd long'</span><span class="p">],</span> <span class="n">species</span><span class="o">.</span><span class="n">pts_train</span><span class="p">[</span><span class="s1">'dd lat'</span><span class="p">],</span>
<span class="n">s</span><span class="o">=</span><span class="mi">2</span> <span class="o">**</span> <span class="mi">2</span><span class="p">,</span> <span class="n">c</span><span class="o">=</span><span class="s1">'black'</span><span class="p">,</span>
<span class="n">marker</span><span class="o">=</span><span class="s1">'^'</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'train'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#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">species</span><span class="o">.</span><span class="n">pts_test</span><span class="p">[</span><span class="s1">'dd long'</span><span class="p">],</span> <span class="n">species</span><span class="o">.</span><span class="n">pts_test</span><span class="p">[</span><span class="s1">'dd lat'</span><span class="p">],</span>
<span class="n">s</span><span class="o">=</span><span class="mi">2</span> <span class="o">**</span> <span class="mi">2</span><span class="p">,</span> <span class="n">c</span><span class="o">=</span><span class="s1">'black'</span><span class="p">,</span>
<span class="n">marker</span><span class="o">=</span><span class="s1">'x'</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'test'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/legend_api.html#matplotlib.legend"><span class="n">plt</span><span class="o">.</span><span class="n">legend</span></a><span class="p">()</span>
<a href="http://matplotlib.org/api/pyplot_api.html#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">species</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
<a href="http://matplotlib.org/api/axis_api.html#matplotlib.axis"><span class="n">plt</span><span class="o">.</span><span class="n">axis</span></a><span class="p">(</span><span class="s1">'equal'</span><span class="p">)</span>
<span class="c1"># Compute AUC with regards to background points</span>
<span class="n">pred_background</span> <span class="o">=</span> <span class="n">Z</span><span class="p">[</span><span class="n">background_points</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">background_points</span><span class="p">[</span><span class="mi">1</span><span class="p">]]</span>
<span class="n">pred_test</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">decision_function</span><span class="p">((</span><span class="n">species</span><span class="o">.</span><span class="n">cov_test</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span>
<span class="o">/</span> <span class="n">std</span><span class="p">)[:,</span> <span class="mi">0</span><span class="p">]</span>
<span class="n">scores</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.r_.html#numpy.r_"><span class="n">np</span><span class="o">.</span><span class="n">r_</span></a><span class="p">[</span><span class="n">pred_test</span><span class="p">,</span> <span class="n">pred_background</span><span class="p">]</span>
<span class="n">y</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.r_.html#numpy.r_"><span class="n">np</span><span class="o">.</span><span class="n">r_</span></a><span class="p">[</span><a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.ones.html#numpy.ones"><span class="n">np</span><span class="o">.</span><span class="n">ones</span></a><span class="p">(</span><span class="n">pred_test</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.zeros.html#numpy.zeros"><span class="n">np</span><span class="o">.</span><span class="n">zeros</span></a><span class="p">(</span><span class="n">pred_background</span><span class="o">.</span><span class="n">shape</span><span class="p">)]</span>
<span class="n">fpr</span><span class="p">,</span> <span class="n">tpr</span><span class="p">,</span> <span class="n">thresholds</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.metrics.roc_curve.html#sklearn.metrics.roc_curve"><span class="n">metrics</span><span class="o">.</span><span class="n">roc_curve</span></a><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">scores</span><span class="p">)</span>
<span class="n">roc_auc</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.metrics.auc.html#sklearn.metrics.auc"><span class="n">metrics</span><span class="o">.</span><span class="n">auc</span></a><span class="p">(</span><span class="n">fpr</span><span class="p">,</span> <span class="n">tpr</span><span class="p">)</span>
<a href="http://matplotlib.org/api/text_api.html#matplotlib.text"><span class="n">plt</span><span class="o">.</span><span class="n">text</span></a><span class="p">(</span><span class="o">-</span><span class="mi">35</span><span class="p">,</span> <span class="o">-</span><span class="mi">70</span><span class="p">,</span> <span class="s2">"AUC: </span><span class="si">%.3f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">roc_auc</span><span class="p">,</span> <span class="n">ha</span><span class="o">=</span><span class="s2">"right"</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2"> Area under the ROC curve : </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">roc_auc</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">time elapsed: </span><span class="si">%.2f</span><span class="s2">s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="n">plot_species_distribution</span><span class="p">()</span>
<a href="http://matplotlib.org/api/pyplot_api.html#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 example:</strong> 36.17 seconds
( 0 minutes 36.17 seconds)</p>
</div>
</div>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
</div>
<div class="footer">
© 2010 - 2014, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/applications/plot_species_distribution_modeling.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_model_complexity_influence.html">Previous
</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 src="http://www.google.com/jsapi" type="text/javascript"></script>
<script type="text/javascript"> google.load('search', '1',
{language : 'en'}); google.setOnLoadCallback(function() {
var customSearchControl = new
google.search.CustomSearchControl('016639176250731907682:tjtqbvtvij0');
customSearchControl.setResultSetSize(google.search.Search.FILTERED_CSE_RESULTSET);
var options = new google.search.DrawOptions();
options.setAutoComplete(true);
customSearchControl.draw('cse', options); }, true);
</script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>