-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_missing_values.html
404 lines (344 loc) · 37.1 KB
/
plot_missing_values.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
<!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>Imputing missing values before building an estimator — scikit-learn 0.21.3 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: '0.21.3',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script type="text/javascript" src="../../_static/jquery.js"></script>
<script type="text/javascript" src="../../_static/underscore.js"></script>
<script type="text/javascript" src="../../_static/doctools.js"></script>
<script type="text/javascript" src="../../_static/js/copybutton.js"></script>
<script type="text/javascript" src="../../_static/js/extra.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS_SVG"></script>
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="author" title="About these documents" href="../../about.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Partial Dependence Plots" href="../inspection/plot_partial_dependence.html" />
<link rel="prev" title="Imputing missing values with variants of IterativeImputer" href="plot_iterative_imputer_variants_comparison.html" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<script src="../../_static/js/bootstrap.min.js" type="text/javascript"></script>
<script>
VERSION_SUBDIR = (function(groups) {
return groups ? groups[1] : null;
})(location.href.match(/^https?:\/\/scikit-learn.org\/([^\/]+)/));
</script>
<link rel="canonical" href="https://scikit-learn.org/stable/auto_examples/impute/plot_missing_values.html" />
<script type="text/javascript">
$("div.buttonNext, div.buttonPrevious").hover(
function () {
$(this).css('background-color', '#FF9C34');
},
function () {
$(this).css('background-color', '#A7D6E2');
}
);
function showMenu() {
var topNav = document.getElementById("scikit-navbar");
if (topNav.className === "navbar") {
topNav.className += " responsive";
} else {
topNav.className = "navbar";
}
};
</script>
</head>
<body>
<div class="header-wrapper">
<div class="header">
<p class="logo"><a href="../../index.html">
<img src="../../_static/scikit-learn-logo-small.png" alt="Logo"/>
</a>
</p><div class="navbar" id="scikit-navbar">
<ul>
<li><a href="../../index.html">Home</a></li>
<li><a href="../../install.html">Installation</a></li>
<li class="btn-li"><div class="btn-group">
<a href="../../documentation.html">Documentation</a>
<a class="btn dropdown-toggle" data-toggle="dropdown">
<span class="caret"></span>
</a>
<ul class="dropdown-menu">
<li class="link-title">Scikit-learn <script>document.write(DOCUMENTATION_OPTIONS.VERSION + (VERSION_SUBDIR ? " (" + VERSION_SUBDIR + ")" : ""));</script></li>
<li><a href="../../tutorial/index.html">Tutorials</a></li>
<li><a href="../../user_guide.html">User guide</a></li>
<li><a href="../../modules/classes.html">API</a></li>
<li><a href="../../glossary.html">Glossary</a></li>
<li><a href="../../faq.html">FAQ</a></li>
<li><a href="../../developers/index.html">Development</a></li>
<li><a href="../../roadmap.html">Roadmap</a></li>
<li><a href="../../about.html">About us</a></li>
<li class="divider"></li>
<script>if (VERSION_SUBDIR != "stable") document.write('<li><a href="http://scikit-learn.org/stable/documentation.html">Stable version</a></li>')</script>
<script>if (VERSION_SUBDIR != "dev") document.write('<li><a href="http://scikit-learn.org/dev/documentation.html">Development version</a></li>')</script>
<li><a href="http://scikit-learn.org/dev/versions.html">All available versions</a></li>
<li><a href="../../_downloads/scikit-learn-docs.pdf">PDF documentation</a></li>
</ul>
</div>
</li>
<li><a href="../index.html">Examples</a></li>
</ul>
<a href="javascript:void(0);" onclick="showMenu()">
<div class="nav-icon">
<div class="hamburger-line"></div>
<div class="hamburger-line"></div>
<div class="hamburger-line"></div>
</div>
</a>
<div class="search_form">
<div class="gcse-search" id="cse" style="width: 100%;"></div>
</div>
</div> <!-- end navbar --></div>
</div>
<!-- GitHub "fork me" ribbon -->
<a href="https://github.com/scikit-learn/scikit-learn">
<img class="fork-me"
style="position: absolute; top: 0; right: 0; border: 0;"
src="../../_static/img/forkme.png"
alt="Fork me on GitHub" />
</a>
<div class="content-wrapper">
<div class="sphinxsidebar">
<div class="sphinxsidebarwrapper">
<div class="rel">
<div class="rellink">
<a href="plot_iterative_imputer_variants_comparison.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
Imputing miss...
</span>
<span class="hiddenrellink">
Imputing missing values with variants of IterativeImputer
</span>
</a>
</div>
<div class="spacer">
</div>
<div class="rellink">
<a href="../inspection/plot_partial_dependence.html"
accesskey="N">Next
<br/>
<span class="smallrellink">
Partial Depen...
</span>
<span class="hiddenrellink">
Partial Dependence Plots
</span>
</a>
</div>
<!-- Ad a link to the 'up' page -->
<div class="spacer">
</div>
<div class="rellink">
<a href="../index.html">
Up
<br/>
<span class="smallrellink">
Examples
</span>
<span class="hiddenrellink">
Examples
</span>
</a>
</div>
</div>
<p class="doc-version"><b>scikit-learn v0.21.3</b><br/>
<a href="http://scikit-learn.org/dev/versions.html">Other versions</a></p>
<p class="citing">Please <b><a href="../../about.html#citing-scikit-learn" style="font-size: 110%;">cite us </a></b>if you use the software.</p>
<ul>
<li><a class="reference internal" href="#">Imputing missing values before building an estimator</a></li>
</ul>
</div>
</div>
<input type="checkbox" id="nav-trigger" class="nav-trigger" checked />
<label for="nav-trigger"></label>
<div class="content">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<div class="sphx-glr-download-link-note admonition note">
<p class="first admonition-title">Note</p>
<p class="last">Click <a class="reference internal" href="#sphx-glr-download-auto-examples-impute-plot-missing-values-py"><span class="std std-ref">here</span></a> to download the full example code</p>
</div>
<div class="sphx-glr-example-title section" id="imputing-missing-values-before-building-an-estimator">
<span id="sphx-glr-auto-examples-impute-plot-missing-values-py"></span><h1>Imputing missing values before building an estimator<a class="headerlink" href="#imputing-missing-values-before-building-an-estimator" title="Permalink to this headline">¶</a></h1>
<p>Missing values can be replaced by the mean, the median or the most frequent
value using the basic <a class="reference internal" href="../../modules/generated/sklearn.impute.SimpleImputer.html#sklearn.impute.SimpleImputer" title="sklearn.impute.SimpleImputer"><code class="xref py py-class docutils literal"><span class="pre">sklearn.impute.SimpleImputer</span></code></a>.
The median is a more robust estimator for data with high magnitude variables
which could dominate results (otherwise known as a ‘long tail’).</p>
<p>Another option is the <a class="reference internal" href="../../modules/generated/sklearn.impute.IterativeImputer.html#sklearn.impute.IterativeImputer" title="sklearn.impute.IterativeImputer"><code class="xref py py-class docutils literal"><span class="pre">sklearn.impute.IterativeImputer</span></code></a>. This uses
round-robin linear regression, treating every variable as an output in
turn. The version implemented assumes Gaussian (output) variables. If your
features are obviously non-Normal, consider transforming them to look more
Normal so as to potentially improve performance.</p>
<p>In addition of using an imputing method, we can also keep an indication of the
missing information using <a class="reference internal" href="../../modules/generated/sklearn.impute.MissingIndicator.html#sklearn.impute.MissingIndicator" title="sklearn.impute.MissingIndicator"><code class="xref py py-func docutils literal"><span class="pre">sklearn.impute.MissingIndicator</span></code></a> which might
carry some information.</p>
<img alt="../../_images/sphx_glr_plot_missing_values_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_plot_missing_values_001.png" />
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">print</span><span class="p">(</span><span class="vm">__doc__</span><span class="p">)</span>
<span class="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="c1"># To use the experimental IterativeImputer, we need to explicitly ask for it:</span>
<span class="kn">from</span> <span class="nn">sklearn.experimental</span> <span class="kn">import</span> <span class="n">enable_iterative_imputer</span> <span class="c1"># noqa</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.datasets.load_diabetes.html#sklearn.datasets.load_diabetes" title="View documentation for sklearn.datasets.load_diabetes"><span class="n">load_diabetes</span></a>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.datasets.load_boston.html#sklearn.datasets.load_boston" title="View documentation for sklearn.datasets.load_boston"><span class="n">load_boston</span></a>
<span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.ensemble.RandomForestRegressor.html#sklearn.ensemble.RandomForestRegressor" title="View documentation for sklearn.ensemble.RandomForestRegressor"><span class="n">RandomForestRegressor</span></a>
<span class="kn">from</span> <span class="nn">sklearn.pipeline</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.pipeline.make_pipeline.html#sklearn.pipeline.make_pipeline" title="View documentation for sklearn.pipeline.make_pipeline"><span class="n">make_pipeline</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.pipeline.make_union.html#sklearn.pipeline.make_union" title="View documentation for sklearn.pipeline.make_union"><span class="n">make_union</span></a>
<span class="kn">from</span> <span class="nn">sklearn.impute</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.impute.SimpleImputer.html#sklearn.impute.SimpleImputer" title="View documentation for sklearn.impute.SimpleImputer"><span class="n">SimpleImputer</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.impute.IterativeImputer.html#sklearn.impute.IterativeImputer" title="View documentation for sklearn.impute.IterativeImputer"><span class="n">IterativeImputer</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.impute.MissingIndicator.html#sklearn.impute.MissingIndicator" title="View documentation for sklearn.impute.MissingIndicator"><span class="n">MissingIndicator</span></a>
<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.model_selection.cross_val_score.html#sklearn.model_selection.cross_val_score" title="View documentation for sklearn.model_selection.cross_val_score"><span class="n">cross_val_score</span></a>
<span class="n">rng</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">RandomState</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">N_SPLITS</span> <span class="o">=</span> <span class="mi">5</span>
<span class="n">REGRESSOR</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.ensemble.RandomForestRegressor.html#sklearn.ensemble.RandomForestRegressor" title="View documentation for sklearn.ensemble.RandomForestRegressor"><span class="n">RandomForestRegressor</span></a><span class="p">(</span><span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">n_estimators</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">get_scores_for_imputer</span><span class="p">(</span><span class="n">imputer</span><span class="p">,</span> <span class="n">X_missing</span><span class="p">,</span> <span class="n">y_missing</span><span class="p">):</span>
<span class="n">estimator</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.pipeline.make_pipeline.html#sklearn.pipeline.make_pipeline" title="View documentation for sklearn.pipeline.make_pipeline"><span class="n">make_pipeline</span></a><span class="p">(</span>
<a href="../../modules/generated/sklearn.pipeline.make_union.html#sklearn.pipeline.make_union" title="View documentation for sklearn.pipeline.make_union"><span class="n">make_union</span></a><span class="p">(</span><span class="n">imputer</span><span class="p">,</span> <a href="../../modules/generated/sklearn.impute.MissingIndicator.html#sklearn.impute.MissingIndicator" title="View documentation for sklearn.impute.MissingIndicator"><span class="n">MissingIndicator</span></a><span class="p">(</span><span class="n">missing_values</span><span class="o">=</span><span class="mi">0</span><span class="p">)),</span>
<span class="n">REGRESSOR</span><span class="p">)</span>
<span class="n">impute_scores</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.model_selection.cross_val_score.html#sklearn.model_selection.cross_val_score" title="View documentation for sklearn.model_selection.cross_val_score"><span class="n">cross_val_score</span></a><span class="p">(</span><span class="n">estimator</span><span class="p">,</span> <span class="n">X_missing</span><span class="p">,</span> <span class="n">y_missing</span><span class="p">,</span>
<span class="n">scoring</span><span class="o">=</span><span class="s1">'neg_mean_squared_error'</span><span class="p">,</span>
<span class="n">cv</span><span class="o">=</span><span class="n">N_SPLITS</span><span class="p">)</span>
<span class="k">return</span> <span class="n">impute_scores</span>
<span class="k">def</span> <span class="nf">get_results</span><span class="p">(</span><span class="n">dataset</span><span class="p">):</span>
<span class="n">X_full</span><span class="p">,</span> <span class="n">y_full</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">dataset</span><span class="o">.</span><span class="n">target</span>
<span class="n">n_samples</span> <span class="o">=</span> <span class="n">X_full</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="n">n_features</span> <span class="o">=</span> <span class="n">X_full</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="c1"># Estimate the score on the entire dataset, with no missing values</span>
<span class="n">full_scores</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.model_selection.cross_val_score.html#sklearn.model_selection.cross_val_score" title="View documentation for sklearn.model_selection.cross_val_score"><span class="n">cross_val_score</span></a><span class="p">(</span><span class="n">REGRESSOR</span><span class="p">,</span> <span class="n">X_full</span><span class="p">,</span> <span class="n">y_full</span><span class="p">,</span>
<span class="n">scoring</span><span class="o">=</span><span class="s1">'neg_mean_squared_error'</span><span class="p">,</span>
<span class="n">cv</span><span class="o">=</span><span class="n">N_SPLITS</span><span class="p">)</span>
<span class="c1"># Add missing values in 75% of the lines</span>
<span class="n">missing_rate</span> <span class="o">=</span> <span class="mf">0.75</span>
<span class="n">n_missing_samples</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.floor.html#numpy.floor" title="View documentation for numpy.floor"><span class="n">np</span><span class="o">.</span><span class="n">floor</span></a><span class="p">(</span><span class="n">n_samples</span> <span class="o">*</span> <span class="n">missing_rate</span><span class="p">))</span>
<span class="n">missing_samples</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.hstack.html#numpy.hstack" title="View documentation for numpy.hstack"><span class="n">np</span><span class="o">.</span><span class="n">hstack</span></a><span class="p">((</span><a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.zeros.html#numpy.zeros" title="View documentation for numpy.zeros"><span class="n">np</span><span class="o">.</span><span class="n">zeros</span></a><span class="p">(</span><span class="n">n_samples</span> <span class="o">-</span> <span class="n">n_missing_samples</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">bool</span><span class="p">),</span>
<a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.ones.html#numpy.ones" title="View documentation for numpy.ones"><span class="n">np</span><span class="o">.</span><span class="n">ones</span></a><span class="p">(</span><span class="n">n_missing_samples</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">bool</span><span class="p">)))</span>
<span class="n">rng</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">missing_samples</span><span class="p">)</span>
<span class="n">missing_features</span> <span class="o">=</span> <span class="n">rng</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">n_features</span><span class="p">,</span> <span class="n">n_missing_samples</span><span class="p">)</span>
<span class="n">X_missing</span> <span class="o">=</span> <span class="n">X_full</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">X_missing</span><span class="p">[</span><a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.where.html#numpy.where" title="View documentation for numpy.where"><span class="n">np</span><span class="o">.</span><span class="n">where</span></a><span class="p">(</span><span class="n">missing_samples</span><span class="p">)[</span><span class="mi">0</span><span class="p">],</span> <span class="n">missing_features</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">y_missing</span> <span class="o">=</span> <span class="n">y_full</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="c1"># Estimate the score after replacing missing values by 0</span>
<span class="n">imputer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.impute.SimpleImputer.html#sklearn.impute.SimpleImputer" title="View documentation for sklearn.impute.SimpleImputer"><span class="n">SimpleImputer</span></a><span class="p">(</span><span class="n">missing_values</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">strategy</span><span class="o">=</span><span class="s1">'constant'</span><span class="p">,</span>
<span class="n">fill_value</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">zero_impute_scores</span> <span class="o">=</span> <span class="n">get_scores_for_imputer</span><span class="p">(</span><span class="n">imputer</span><span class="p">,</span> <span class="n">X_missing</span><span class="p">,</span> <span class="n">y_missing</span><span class="p">)</span>
<span class="c1"># Estimate the score after imputation (mean strategy) of the missing values</span>
<span class="n">imputer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.impute.SimpleImputer.html#sklearn.impute.SimpleImputer" title="View documentation for sklearn.impute.SimpleImputer"><span class="n">SimpleImputer</span></a><span class="p">(</span><span class="n">missing_values</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">strategy</span><span class="o">=</span><span class="s2">"mean"</span><span class="p">)</span>
<span class="n">mean_impute_scores</span> <span class="o">=</span> <span class="n">get_scores_for_imputer</span><span class="p">(</span><span class="n">imputer</span><span class="p">,</span> <span class="n">X_missing</span><span class="p">,</span> <span class="n">y_missing</span><span class="p">)</span>
<span class="c1"># Estimate the score after iterative imputation of the missing values</span>
<span class="n">imputer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.impute.IterativeImputer.html#sklearn.impute.IterativeImputer" title="View documentation for sklearn.impute.IterativeImputer"><span class="n">IterativeImputer</span></a><span class="p">(</span><span class="n">missing_values</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">n_nearest_features</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
<span class="n">iterative_impute_scores</span> <span class="o">=</span> <span class="n">get_scores_for_imputer</span><span class="p">(</span><span class="n">imputer</span><span class="p">,</span>
<span class="n">X_missing</span><span class="p">,</span>
<span class="n">y_missing</span><span class="p">)</span>
<span class="k">return</span> <span class="p">((</span><span class="n">full_scores</span><span class="o">.</span><span class="n">mean</span><span class="p">(),</span> <span class="n">full_scores</span><span class="o">.</span><span class="n">std</span><span class="p">()),</span>
<span class="p">(</span><span class="n">zero_impute_scores</span><span class="o">.</span><span class="n">mean</span><span class="p">(),</span> <span class="n">zero_impute_scores</span><span class="o">.</span><span class="n">std</span><span class="p">()),</span>
<span class="p">(</span><span class="n">mean_impute_scores</span><span class="o">.</span><span class="n">mean</span><span class="p">(),</span> <span class="n">mean_impute_scores</span><span class="o">.</span><span class="n">std</span><span class="p">()),</span>
<span class="p">(</span><span class="n">iterative_impute_scores</span><span class="o">.</span><span class="n">mean</span><span class="p">(),</span> <span class="n">iterative_impute_scores</span><span class="o">.</span><span class="n">std</span><span class="p">()))</span>
<span class="n">results_diabetes</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">get_results</span><span class="p">(</span><a href="../../modules/generated/sklearn.datasets.load_diabetes.html#sklearn.datasets.load_diabetes" title="View documentation for sklearn.datasets.load_diabetes"><span class="n">load_diabetes</span></a><span class="p">()))</span>
<span class="n">mses_diabetes</span> <span class="o">=</span> <span class="n">results_diabetes</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="o">-</span><span class="mi">1</span>
<span class="n">stds_diabetes</span> <span class="o">=</span> <span class="n">results_diabetes</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span>
<span class="n">results_boston</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">get_results</span><span class="p">(</span><a href="../../modules/generated/sklearn.datasets.load_boston.html#sklearn.datasets.load_boston" title="View documentation for sklearn.datasets.load_boston"><span class="n">load_boston</span></a><span class="p">()))</span>
<span class="n">mses_boston</span> <span class="o">=</span> <span class="n">results_boston</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="o">-</span><span class="mi">1</span>
<span class="n">stds_boston</span> <span class="o">=</span> <span class="n">results_boston</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span>
<span class="n">n_bars</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">mses_diabetes</span><span class="p">)</span>
<span class="n">xval</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.arange.html#numpy.arange" title="View documentation for numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="n">n_bars</span><span class="p">)</span>
<span class="n">x_labels</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'Full data'</span><span class="p">,</span>
<span class="s1">'Zero imputation'</span><span class="p">,</span>
<span class="s1">'Mean Imputation'</span><span class="p">,</span>
<span class="s1">'Multivariate Imputation'</span><span class="p">]</span>
<span class="n">colors</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'r'</span><span class="p">,</span> <span class="s1">'g'</span><span class="p">,</span> <span class="s1">'b'</span><span class="p">,</span> <span class="s1">'orange'</span><span class="p">]</span>
<span class="c1"># plot diabetes results</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.figure.html#matplotlib.pyplot.figure" title="View documentation for matplotlib.pyplot.figure"><span class="n">plt</span><span class="o">.</span><span class="n">figure</span></a><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">6</span><span class="p">))</span>
<span class="n">ax1</span> <span class="o">=</span> <a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplot.html#matplotlib.pyplot.subplot" title="View documentation for matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">121</span><span class="p">)</span>
<span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">xval</span><span class="p">:</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">barh</span><span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="n">mses_diabetes</span><span class="p">[</span><span class="n">j</span><span class="p">],</span> <span class="n">xerr</span><span class="o">=</span><span class="n">stds_diabetes</span><span class="p">[</span><span class="n">j</span><span class="p">],</span>
<span class="n">color</span><span class="o">=</span><span class="n">colors</span><span class="p">[</span><span class="n">j</span><span class="p">],</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.6</span><span class="p">,</span> <span class="n">align</span><span class="o">=</span><span class="s1">'center'</span><span class="p">)</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s1">'Imputation Techniques with Diabetes Data'</span><span class="p">)</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">set_xlim</span><span class="p">(</span><span class="n">left</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="n">mses_diabetes</span><span class="p">)</span> <span class="o">*</span> <span class="mf">0.9</span><span class="p">,</span>
<span class="n">right</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">mses_diabetes</span><span class="p">)</span> <span class="o">*</span> <span class="mf">1.1</span><span class="p">)</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">set_yticks</span><span class="p">(</span><span class="n">xval</span><span class="p">)</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s1">'MSE'</span><span class="p">)</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">invert_yaxis</span><span class="p">()</span>
<span class="n">ax1</span><span class="o">.</span><span class="n">set_yticklabels</span><span class="p">(</span><span class="n">x_labels</span><span class="p">)</span>
<span class="c1"># plot boston results</span>
<span class="n">ax2</span> <span class="o">=</span> <a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplot.html#matplotlib.pyplot.subplot" title="View documentation for matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">122</span><span class="p">)</span>
<span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">xval</span><span class="p">:</span>
<span class="n">ax2</span><span class="o">.</span><span class="n">barh</span><span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="n">mses_boston</span><span class="p">[</span><span class="n">j</span><span class="p">],</span> <span class="n">xerr</span><span class="o">=</span><span class="n">stds_boston</span><span class="p">[</span><span class="n">j</span><span class="p">],</span>
<span class="n">color</span><span class="o">=</span><span class="n">colors</span><span class="p">[</span><span class="n">j</span><span class="p">],</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.6</span><span class="p">,</span> <span class="n">align</span><span class="o">=</span><span class="s1">'center'</span><span class="p">)</span>
<span class="n">ax2</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s1">'Imputation Techniques with Boston Data'</span><span class="p">)</span>
<span class="n">ax2</span><span class="o">.</span><span class="n">set_yticks</span><span class="p">(</span><span class="n">xval</span><span class="p">)</span>
<span class="n">ax2</span><span class="o">.</span><span class="n">set_xlabel</span><span class="p">(</span><span class="s1">'MSE'</span><span class="p">)</span>
<span class="n">ax2</span><span class="o">.</span><span class="n">invert_yaxis</span><span class="p">()</span>
<span class="n">ax2</span><span class="o">.</span><span class="n">set_yticklabels</span><span class="p">([</span><span class="s1">''</span><span class="p">]</span> <span class="o">*</span> <span class="n">n_bars</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
</pre></div>
</div>
<p><strong>Total running time of the script:</strong> ( 0 minutes 11.569 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-impute-plot-missing-values-py">
<div class="sphx-glr-download docutils container">
<a class="reference download internal" href="../../_downloads/plot_missing_values.py" download=""><code class="xref download docutils literal"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_missing_values.py</span></code></a></div>
<div class="sphx-glr-download docutils container">
<a class="reference download internal" href="../../_downloads/plot_missing_values.ipynb" download=""><code class="xref download docutils literal"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_missing_values.ipynb</span></code></a></div>
</div>
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.readthedocs.io">Gallery generated by Sphinx-Gallery</a></p>
</div>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
</div>
<div class="footer">
© 2007 - 2019, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/impute/plot_missing_values.rst.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_iterative_imputer_variants_comparison.html">Previous
</a>
</div>
<div class="buttonNext">
<a href="../inspection/plot_partial_dependence.html">Next
</a>
</div>
</div>
<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>
(function() {
var cx = '016639176250731907682:tjtqbvtvij0';
var gcse = document.createElement('script'); gcse.type = 'text/javascript'; gcse.async = true;
gcse.src = 'https://cse.google.com/cse.js?cx=' + cx;
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(gcse, s);
})();
</script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>