site/docs/1.5.0/api/python/_modules/pyspark/mllib/util.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

<!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>pyspark.mllib.util &mdash; PySpark master documentation</title>
    
    <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
    <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
    
    <script type="text/javascript">
      var DOCUMENTATION_OPTIONS = {
        URL_ROOT:    '../../../',
        VERSION:     'master',
        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>
    <link rel="top" title="PySpark master documentation" href="../../../index.html" />
    <link rel="up" title="Module code" href="../../index.html" /> 
  </head>
  <body role="document">
    <div class="related" role="navigation" aria-label="related navigation">
      <h3>Navigation</h3>
      <ul>
        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> &raquo;</li>
          <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &raquo;</li> 
      </ul>
    </div>  

    <div class="document">
      <div class="documentwrapper">
        <div class="bodywrapper">
          <div class="body" role="main">
            
  <h1>Source code for pyspark.mllib.util</h1><div class="highlight"><pre>
<span class="c">#</span>
<span class="c"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c"># contributor license agreements.  See the NOTICE file distributed with</span>
<span class="c"># this work for additional information regarding copyright ownership.</span>
<span class="c"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c"># the License.  You may obtain a copy of the License at</span>
<span class="c">#</span>
<span class="c">#    http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c">#</span>
<span class="c"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c"># See the License for the specific language governing permissions and</span>
<span class="c"># limitations under the License.</span>
<span class="c">#</span>

<span class="kn">import</span> <span class="nn">sys</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">warnings</span>

<span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version</span> <span class="o">&gt;</span> <span class="s">&#39;3&#39;</span><span class="p">:</span>
    <span class="nb">xrange</span> <span class="o">=</span> <span class="nb">range</span>
    <span class="nb">basestring</span> <span class="o">=</span> <span class="nb">str</span>

<span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">callMLlibFunc</span><span class="p">,</span> <span class="n">inherit_doc</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">,</span> <span class="n">_convert_to_vector</span>


<div class="viewcode-block" id="MLUtils"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.MLUtils">[docs]</a><span class="k">class</span> <span class="nc">MLUtils</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>

    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Helper methods to load, save and pre-process data used in MLlib.</span>
<span class="sd">    &quot;&quot;&quot;</span>

    <span class="nd">@staticmethod</span>
    <span class="k">def</span> <span class="nf">_parse_libsvm_line</span><span class="p">(</span><span class="n">line</span><span class="p">,</span> <span class="n">multiclass</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Parses a line in LIBSVM format into (label, indices, values).</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">if</span> <span class="n">multiclass</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">&quot;deprecated&quot;</span><span class="p">,</span> <span class="ne">DeprecationWarning</span><span class="p">)</span>
        <span class="n">items</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="bp">None</span><span class="p">)</span>
        <span class="n">label</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">items</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
        <span class="n">nnz</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">items</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span>
        <span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">nnz</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">int32</span><span class="p">)</span>
        <span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">nnz</span><span class="p">)</span>
        <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">xrange</span><span class="p">(</span><span class="n">nnz</span><span class="p">):</span>
            <span class="n">index</span><span class="p">,</span> <span class="n">value</span> <span class="o">=</span> <span class="n">items</span><span class="p">[</span><span class="mi">1</span> <span class="o">+</span> <span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">&quot;:&quot;</span><span class="p">)</span>
            <span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">index</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span>
            <span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
        <span class="k">return</span> <span class="n">label</span><span class="p">,</span> <span class="n">indices</span><span class="p">,</span> <span class="n">values</span>

    <span class="nd">@staticmethod</span>
    <span class="k">def</span> <span class="nf">_convert_labeled_point_to_libsvm</span><span class="p">(</span><span class="n">p</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;Converts a LabeledPoint to a string in LIBSVM format.&quot;&quot;&quot;</span>
        <span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span>
        <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="n">LabeledPoint</span><span class="p">)</span>
        <span class="n">items</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">label</span><span class="p">)]</span>
        <span class="n">v</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">features</span><span class="p">)</span>
        <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span>
            <span class="n">nnz</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">indices</span><span class="p">)</span>
            <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">xrange</span><span class="p">(</span><span class="n">nnz</span><span class="p">):</span>
                <span class="n">items</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="s">&quot;:&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]))</span>
        <span class="k">else</span><span class="p">:</span>
            <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">xrange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">v</span><span class="p">)):</span>
                <span class="n">items</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">str</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="o">+</span> <span class="s">&quot;:&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="p">[</span><span class="n">i</span><span class="p">]))</span>
        <span class="k">return</span> <span class="s">&quot; &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">items</span><span class="p">)</span>

    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="MLUtils.loadLibSVMFile"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.MLUtils.loadLibSVMFile">[docs]</a>    <span class="k">def</span> <span class="nf">loadLibSVMFile</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">numFeatures</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">minPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">multiclass</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Loads labeled data in the LIBSVM format into an RDD of</span>
<span class="sd">        LabeledPoint. The LIBSVM format is a text-based format used by</span>
<span class="sd">        LIBSVM and LIBLINEAR. Each line represents a labeled sparse</span>
<span class="sd">        feature vector using the following format:</span>

<span class="sd">        label index1:value1 index2:value2 ...</span>

<span class="sd">        where the indices are one-based and in ascending order. This</span>
<span class="sd">        method parses each line into a LabeledPoint, where the feature</span>
<span class="sd">        indices are converted to zero-based.</span>

<span class="sd">        :param sc: Spark context</span>
<span class="sd">        :param path: file or directory path in any Hadoop-supported file</span>
<span class="sd">                     system URI</span>
<span class="sd">        :param numFeatures: number of features, which will be determined</span>
<span class="sd">                            from the input data if a nonpositive value</span>
<span class="sd">                            is given. This is useful when the dataset is</span>
<span class="sd">                            already split into multiple files and you</span>
<span class="sd">                            want to load them separately, because some</span>
<span class="sd">                            features may not present in certain files,</span>
<span class="sd">                            which leads to inconsistent feature</span>
<span class="sd">                            dimensions.</span>
<span class="sd">        :param minPartitions: min number of partitions</span>
<span class="sd">        @return: labeled data stored as an RDD of LabeledPoint</span>

<span class="sd">        &gt;&gt;&gt; from tempfile import NamedTemporaryFile</span>
<span class="sd">        &gt;&gt;&gt; from pyspark.mllib.util import MLUtils</span>
<span class="sd">        &gt;&gt;&gt; from pyspark.mllib.regression import LabeledPoint</span>
<span class="sd">        &gt;&gt;&gt; tempFile = NamedTemporaryFile(delete=True)</span>
<span class="sd">        &gt;&gt;&gt; _ = tempFile.write(b&quot;+1 1:1.0 3:2.0 5:3.0\\n-1\\n-1 2:4.0 4:5.0 6:6.0&quot;)</span>
<span class="sd">        &gt;&gt;&gt; tempFile.flush()</span>
<span class="sd">        &gt;&gt;&gt; examples = MLUtils.loadLibSVMFile(sc, tempFile.name).collect()</span>
<span class="sd">        &gt;&gt;&gt; tempFile.close()</span>
<span class="sd">        &gt;&gt;&gt; examples[0]</span>
<span class="sd">        LabeledPoint(1.0, (6,[0,2,4],[1.0,2.0,3.0]))</span>
<span class="sd">        &gt;&gt;&gt; examples[1]</span>
<span class="sd">        LabeledPoint(-1.0, (6,[],[]))</span>
<span class="sd">        &gt;&gt;&gt; examples[2]</span>
<span class="sd">        LabeledPoint(-1.0, (6,[1,3,5],[4.0,5.0,6.0]))</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span>
        <span class="k">if</span> <span class="n">multiclass</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
            <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">&quot;deprecated&quot;</span><span class="p">,</span> <span class="ne">DeprecationWarning</span><span class="p">)</span>

        <span class="n">lines</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">minPartitions</span><span class="p">)</span>
        <span class="n">parsed</span> <span class="o">=</span> <span class="n">lines</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">l</span><span class="p">:</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">_parse_libsvm_line</span><span class="p">(</span><span class="n">l</span><span class="p">))</span>
        <span class="k">if</span> <span class="n">numFeatures</span> <span class="o">&lt;=</span> <span class="mi">0</span><span class="p">:</span>
            <span class="n">parsed</span><span class="o">.</span><span class="n">cache</span><span class="p">()</span>
            <span class="n">numFeatures</span> <span class="o">=</span> <span class="n">parsed</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="o">-</span><span class="mi">1</span> <span class="k">if</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">size</span> <span class="o">==</span> <span class="mi">0</span> <span class="k">else</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="mi">1</span><span class="p">])</span><span class="o">.</span><span class="n">reduce</span><span class="p">(</span><span class="nb">max</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
        <span class="k">return</span> <span class="n">parsed</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">sparse</span><span class="p">(</span><span class="n">numFeatures</span><span class="p">,</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">x</span><span class="p">[</span><span class="mi">2</span><span class="p">])))</span>
</div>
    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="MLUtils.saveAsLibSVMFile"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.MLUtils.saveAsLibSVMFile">[docs]</a>    <span class="k">def</span> <span class="nf">saveAsLibSVMFile</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="nb">dir</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Save labeled data in LIBSVM format.</span>

<span class="sd">        :param data: an RDD of LabeledPoint to be saved</span>
<span class="sd">        :param dir: directory to save the data</span>

<span class="sd">        &gt;&gt;&gt; from tempfile import NamedTemporaryFile</span>
<span class="sd">        &gt;&gt;&gt; from fileinput import input</span>
<span class="sd">        &gt;&gt;&gt; from pyspark.mllib.regression import LabeledPoint</span>
<span class="sd">        &gt;&gt;&gt; from glob import glob</span>
<span class="sd">        &gt;&gt;&gt; from pyspark.mllib.util import MLUtils</span>
<span class="sd">        &gt;&gt;&gt; examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, 1.23), (2, 4.56)])), \</span>
<span class="sd">                        LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))]</span>
<span class="sd">        &gt;&gt;&gt; tempFile = NamedTemporaryFile(delete=True)</span>
<span class="sd">        &gt;&gt;&gt; tempFile.close()</span>
<span class="sd">        &gt;&gt;&gt; MLUtils.saveAsLibSVMFile(sc.parallelize(examples), tempFile.name)</span>
<span class="sd">        &gt;&gt;&gt; &#39;&#39;.join(sorted(input(glob(tempFile.name + &quot;/part-0000*&quot;))))</span>
<span class="sd">        &#39;0.0 1:1.01 2:2.02 3:3.03\\n1.1 1:1.23 3:4.56\\n&#39;</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">lines</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">p</span><span class="p">:</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">_convert_labeled_point_to_libsvm</span><span class="p">(</span><span class="n">p</span><span class="p">))</span>
        <span class="n">lines</span><span class="o">.</span><span class="n">saveAsTextFile</span><span class="p">(</span><span class="nb">dir</span><span class="p">)</span>
</div>
    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="MLUtils.loadLabeledPoints"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.MLUtils.loadLabeledPoints">[docs]</a>    <span class="k">def</span> <span class="nf">loadLabeledPoints</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">minPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Load labeled points saved using RDD.saveAsTextFile.</span>

<span class="sd">        :param sc: Spark context</span>
<span class="sd">        :param path: file or directory path in any Hadoop-supported file</span>
<span class="sd">                     system URI</span>
<span class="sd">        :param minPartitions: min number of partitions</span>
<span class="sd">        @return: labeled data stored as an RDD of LabeledPoint</span>

<span class="sd">        &gt;&gt;&gt; from tempfile import NamedTemporaryFile</span>
<span class="sd">        &gt;&gt;&gt; from pyspark.mllib.util import MLUtils</span>
<span class="sd">        &gt;&gt;&gt; from pyspark.mllib.regression import LabeledPoint</span>
<span class="sd">        &gt;&gt;&gt; examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, -1.23), (2, 4.56e-7)])), \</span>
<span class="sd">                        LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))]</span>
<span class="sd">        &gt;&gt;&gt; tempFile = NamedTemporaryFile(delete=True)</span>
<span class="sd">        &gt;&gt;&gt; tempFile.close()</span>
<span class="sd">        &gt;&gt;&gt; sc.parallelize(examples, 1).saveAsTextFile(tempFile.name)</span>
<span class="sd">        &gt;&gt;&gt; MLUtils.loadLabeledPoints(sc, tempFile.name).collect()</span>
<span class="sd">        [LabeledPoint(1.1, (3,[0,2],[-1.23,4.56e-07])), LabeledPoint(0.0, [1.01,2.02,3.03])]</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">minPartitions</span> <span class="o">=</span> <span class="n">minPartitions</span> <span class="ow">or</span> <span class="nb">min</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">defaultParallelism</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
        <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">&quot;loadLabeledPoints&quot;</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">minPartitions</span><span class="p">)</span>
</div>
    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="MLUtils.appendBias"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.MLUtils.appendBias">[docs]</a>    <span class="k">def</span> <span class="nf">appendBias</span><span class="p">(</span><span class="n">data</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Returns a new vector with `1.0` (bias) appended to</span>
<span class="sd">        the end of the input vector.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">vec</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
        <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vec</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span>
            <span class="n">newIndices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">vec</span><span class="p">))</span>
            <span class="n">newValues</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>
            <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">vec</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">newIndices</span><span class="p">,</span> <span class="n">newValues</span><span class="p">)</span>
        <span class="k">else</span><span class="p">:</span>
            <span class="k">return</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="mf">1.0</span><span class="p">))</span>
</div>
    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="MLUtils.loadVectors"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.MLUtils.loadVectors">[docs]</a>    <span class="k">def</span> <span class="nf">loadVectors</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Loads vectors saved using `RDD[Vector].saveAsTextFile`</span>
<span class="sd">        with the default number of partitions.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">&quot;loadVectors&quot;</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>

</div></div>
<div class="viewcode-block" id="Saveable"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.Saveable">[docs]</a><span class="k">class</span> <span class="nc">Saveable</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Mixin for models and transformers which may be saved as files.</span>
<span class="sd">    &quot;&quot;&quot;</span>

<div class="viewcode-block" id="Saveable.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.Saveable.save">[docs]</a>    <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Save this model to the given path.</span>

<span class="sd">        This saves:</span>
<span class="sd">         * human-readable (JSON) model metadata to path/metadata/</span>
<span class="sd">         * Parquet formatted data to path/data/</span>

<span class="sd">        The model may be loaded using py:meth:`Loader.load`.</span>

<span class="sd">        :param sc: Spark context used to save model data.</span>
<span class="sd">        :param path: Path specifying the directory in which to save</span>
<span class="sd">                     this model. If the directory already exists,</span>
<span class="sd">                     this method throws an exception.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">raise</span> <span class="ne">NotImplementedError</span>

</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="JavaSaveable"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.JavaSaveable">[docs]</a><span class="k">class</span> <span class="nc">JavaSaveable</span><span class="p">(</span><span class="n">Saveable</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Mixin for models that provide save() through their Scala</span>
<span class="sd">    implementation.</span>
<span class="sd">    &quot;&quot;&quot;</span>

<div class="viewcode-block" id="JavaSaveable.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.JavaSaveable.save">[docs]</a>    <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">SparkContext</span><span class="p">):</span>
            <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">&quot;sc should be a SparkContext, got type </span><span class="si">%s</span><span class="s">&quot;</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">sc</span><span class="p">))</span>
        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">basestring</span><span class="p">):</span>
            <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">&quot;path should be a basestring, got type </span><span class="si">%s</span><span class="s">&quot;</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">))</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span>

</div></div>
<div class="viewcode-block" id="Loader"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.Loader">[docs]</a><span class="k">class</span> <span class="nc">Loader</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Mixin for classes which can load saved models from files.</span>
<span class="sd">    &quot;&quot;&quot;</span>

    <span class="nd">@classmethod</span>
<div class="viewcode-block" id="Loader.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.Loader.load">[docs]</a>    <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Load a model from the given path. The model should have been</span>
<span class="sd">        saved using py:meth:`Saveable.save`.</span>

<span class="sd">        :param sc: Spark context used for loading model files.</span>
<span class="sd">        :param path: Path specifying the directory to which the model</span>
<span class="sd">                     was saved.</span>
<span class="sd">        :return: model instance</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">raise</span> <span class="bp">NotImplemented</span>

</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="JavaLoader"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.JavaLoader">[docs]</a><span class="k">class</span> <span class="nc">JavaLoader</span><span class="p">(</span><span class="n">Loader</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">    Mixin for classes which can load saved models using its Scala</span>
<span class="sd">    implementation.</span>
<span class="sd">    &quot;&quot;&quot;</span>

    <span class="nd">@classmethod</span>
    <span class="k">def</span> <span class="nf">_java_loader_class</span><span class="p">(</span><span class="n">cls</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Returns the full class name of the Java loader. The default</span>
<span class="sd">        implementation replaces &quot;pyspark&quot; by &quot;org.apache.spark&quot; in</span>
<span class="sd">        the Python full class name.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">java_package</span> <span class="o">=</span> <span class="n">cls</span><span class="o">.</span><span class="n">__module__</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s">&quot;pyspark&quot;</span><span class="p">,</span> <span class="s">&quot;org.apache.spark&quot;</span><span class="p">)</span>
        <span class="k">return</span> <span class="s">&quot;.&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">java_package</span><span class="p">,</span> <span class="n">cls</span><span class="o">.</span><span class="n">__name__</span><span class="p">])</span>

    <span class="nd">@classmethod</span>
    <span class="k">def</span> <span class="nf">_load_java</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Load a Java model from the given path.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">java_class</span> <span class="o">=</span> <span class="n">cls</span><span class="o">.</span><span class="n">_java_loader_class</span><span class="p">()</span>
        <span class="n">java_obj</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span>
        <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">java_class</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">&quot;.&quot;</span><span class="p">):</span>
            <span class="n">java_obj</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">java_obj</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
        <span class="k">return</span> <span class="n">java_obj</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span>

    <span class="nd">@classmethod</span>
<div class="viewcode-block" id="JavaLoader.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.JavaLoader.load">[docs]</a>    <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
        <span class="n">java_model</span> <span class="o">=</span> <span class="n">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
        <span class="k">return</span> <span class="n">cls</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>

</div></div>
<div class="viewcode-block" id="LinearDataGenerator"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.LinearDataGenerator">[docs]</a><span class="k">class</span> <span class="nc">LinearDataGenerator</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
    <span class="sd">&quot;&quot;&quot;Utils for generating linear data&quot;&quot;&quot;</span>

    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="LinearDataGenerator.generateLinearInput"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.LinearDataGenerator.generateLinearInput">[docs]</a>    <span class="k">def</span> <span class="nf">generateLinearInput</span><span class="p">(</span><span class="n">intercept</span><span class="p">,</span> <span class="n">weights</span><span class="p">,</span> <span class="n">xMean</span><span class="p">,</span> <span class="n">xVariance</span><span class="p">,</span>
                            <span class="n">nPoints</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">eps</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        :param: intercept bias factor, the term c in X&#39;w + c</span>
<span class="sd">        :param: weights   feature vector, the term w in X&#39;w + c</span>
<span class="sd">        :param: xMean     Point around which the data X is centered.</span>
<span class="sd">        :param: xVariance Variance of the given data</span>
<span class="sd">        :param: nPoints   Number of points to be generated</span>
<span class="sd">        :param: seed      Random Seed</span>
<span class="sd">        :param: eps       Used to scale the noise. If eps is set high,</span>
<span class="sd">                          the amount of gaussian noise added is more.</span>

<span class="sd">        Returns a list of LabeledPoints of length nPoints</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="n">weights</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">weight</span><span class="p">)</span> <span class="k">for</span> <span class="n">weight</span> <span class="ow">in</span> <span class="n">weights</span><span class="p">]</span>
        <span class="n">xMean</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">)</span> <span class="k">for</span> <span class="n">mean</span> <span class="ow">in</span> <span class="n">xMean</span><span class="p">]</span>
        <span class="n">xVariance</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">var</span><span class="p">)</span> <span class="k">for</span> <span class="n">var</span> <span class="ow">in</span> <span class="n">xVariance</span><span class="p">]</span>
        <span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="n">callMLlibFunc</span><span class="p">(</span>
            <span class="s">&quot;generateLinearInputWrapper&quot;</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> <span class="n">weights</span><span class="p">,</span> <span class="n">xMean</span><span class="p">,</span>
            <span class="n">xVariance</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">nPoints</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">seed</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">eps</span><span class="p">)))</span>
</div>
    <span class="nd">@staticmethod</span>
<div class="viewcode-block" id="LinearDataGenerator.generateLinearRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.tree.LinearDataGenerator.generateLinearRDD">[docs]</a>    <span class="k">def</span> <span class="nf">generateLinearRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">nexamples</span><span class="p">,</span> <span class="n">nfeatures</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span>
                          <span class="n">nParts</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">intercept</span><span class="o">=</span><span class="mf">0.0</span><span class="p">):</span>
        <span class="sd">&quot;&quot;&quot;</span>
<span class="sd">        Generate a RDD of LabeledPoints.</span>
<span class="sd">        &quot;&quot;&quot;</span>
        <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span>
            <span class="s">&quot;generateLinearRDDWrapper&quot;</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">nexamples</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">nfeatures</span><span class="p">),</span>
            <span class="nb">float</span><span class="p">(</span><span class="n">eps</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">nParts</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">intercept</span><span class="p">))</span>

</div></div>
<span class="k">def</span> <span class="nf">_test</span><span class="p">():</span>
    <span class="kn">import</span> <span class="nn">doctest</span>
    <span class="kn">from</span> <span class="nn">pyspark.context</span> <span class="kn">import</span> <span class="n">SparkContext</span>
    <span class="n">globs</span> <span class="o">=</span> <span class="nb">globals</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
    <span class="c"># The small batch size here ensures that we see multiple batches,</span>
    <span class="c"># even in these small test examples:</span>
    <span class="n">globs</span><span class="p">[</span><span class="s">&#39;sc&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">&#39;local[2]&#39;</span><span class="p">,</span> <span class="s">&#39;PythonTest&#39;</span><span class="p">,</span> <span class="n">batchSize</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
    <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span>
    <span class="n">globs</span><span class="p">[</span><span class="s">&#39;sc&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span>
    <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span>
        <span class="nb">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>


<span class="k">if</span> <span class="n">__name__</span> <span class="o">==</span> <span class="s">&quot;__main__&quot;</span><span class="p">:</span>
    <span class="n">_test</span><span class="p">()</span>
</pre></div>

          </div>
        </div>
      </div>
      <div class="sphinxsidebar" role="navigation" aria-label="main navigation">
        <div class="sphinxsidebarwrapper">
            <p class="logo"><a href="../../../index.html">
              <img class="logo" src="../../../_static/spark-logo-hd.png" alt="Logo"/>
            </a></p>
<div id="searchbox" style="display: none" role="search">
  <h3>Quick search</h3>
    <form class="search" action="../../../search.html" method="get">
      <input type="text" name="q" />
      <input type="submit" value="Go" />
      <input type="hidden" name="check_keywords" value="yes" />
      <input type="hidden" name="area" value="default" />
    </form>
    <p class="searchtip" style="font-size: 90%">
    Enter search terms or a module, class or function name.
    </p>
</div>
<script type="text/javascript">$('#searchbox').show(0);</script>
        </div>
      </div>
      <div class="clearer"></div>
    </div>
    <div class="related" role="navigation" aria-label="related navigation">
      <h3>Navigation</h3>
      <ul>
        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> &raquo;</li>
          <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &raquo;</li> 
      </ul>
    </div>
    <div class="footer" role="contentinfo">
        &copy; Copyright .
      Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.3.1.
    </div>
  </body>
</html>