1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
|
<!DOCTYPE html>
<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<title>Feature Extraction and Transformation - MLlib - Spark 1.5.0 Documentation</title>
<link rel="stylesheet" href="css/bootstrap.min.css">
<style>
body {
padding-top: 60px;
padding-bottom: 40px;
}
</style>
<meta name="viewport" content="width=device-width">
<link rel="stylesheet" href="css/bootstrap-responsive.min.css">
<link rel="stylesheet" href="css/main.css">
<script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
<link rel="stylesheet" href="css/pygments-default.css">
<!-- Google analytics script -->
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-32518208-2']);
_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>
</head>
<body>
<!--[if lt IE 7]>
<p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
<![endif]-->
<!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
<div class="navbar navbar-fixed-top" id="topbar">
<div class="navbar-inner">
<div class="container">
<div class="brand"><a href="index.html">
<img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">1.5.0</span>
</div>
<ul class="nav">
<!--TODO(andyk): Add class="active" attribute to li some how.-->
<li><a href="index.html">Overview</a></li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="quick-start.html">Quick Start</a></li>
<li><a href="programming-guide.html">Spark Programming Guide</a></li>
<li class="divider"></li>
<li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
<li><a href="sql-programming-guide.html">DataFrames and SQL</a></li>
<li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
<li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li>
<li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
<li><a href="sparkr.html">SparkR (R on Spark)</a></li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="api/scala/index.html#org.apache.spark.package">Scala</a></li>
<li><a href="api/java/index.html">Java</a></li>
<li><a href="api/python/index.html">Python</a></li>
<li><a href="api/R/index.html">R</a></li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="cluster-overview.html">Overview</a></li>
<li><a href="submitting-applications.html">Submitting Applications</a></li>
<li class="divider"></li>
<li><a href="spark-standalone.html">Spark Standalone</a></li>
<li><a href="running-on-mesos.html">Mesos</a></li>
<li><a href="running-on-yarn.html">YARN</a></li>
<li class="divider"></li>
<li><a href="ec2-scripts.html">Amazon EC2</a></li>
</ul>
</li>
<li class="dropdown">
<a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="configuration.html">Configuration</a></li>
<li><a href="monitoring.html">Monitoring</a></li>
<li><a href="tuning.html">Tuning Guide</a></li>
<li><a href="job-scheduling.html">Job Scheduling</a></li>
<li><a href="security.html">Security</a></li>
<li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
<li><a href="hadoop-third-party-distributions.html">3<sup>rd</sup>-Party Hadoop Distros</a></li>
<li class="divider"></li>
<li><a href="building-spark.html">Building Spark</a></li>
<li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
<li><a href="https://cwiki.apache.org/confluence/display/SPARK/Supplemental+Spark+Projects">Supplemental Projects</a></li>
</ul>
</li>
</ul>
<!--<p class="navbar-text pull-right"><span class="version-text">v1.5.0</span></p>-->
</div>
</div>
</div>
<div class="container" id="content">
<h1 class="title"><a href="mllib-guide.html">MLlib</a> - Feature Extraction and Transformation</h1>
<ul id="markdown-toc">
<li><a href="#tf-idf">TF-IDF</a></li>
<li><a href="#word2vec">Word2Vec</a> <ul>
<li><a href="#model">Model</a></li>
<li><a href="#example">Example</a></li>
</ul>
</li>
<li><a href="#standardscaler">StandardScaler</a> <ul>
<li><a href="#model-fitting">Model Fitting</a></li>
<li><a href="#example-1">Example</a></li>
</ul>
</li>
<li><a href="#normalizer">Normalizer</a> <ul>
<li><a href="#example-2">Example</a></li>
</ul>
</li>
<li><a href="#feature-selection">Feature selection</a> <ul>
<li><a href="#chisqselector">ChiSqSelector</a> <ul>
<li><a href="#model-fitting-1">Model Fitting</a></li>
<li><a href="#example-3">Example</a></li>
</ul>
</li>
</ul>
</li>
<li><a href="#elementwiseproduct">ElementwiseProduct</a> <ul>
<li><a href="#example-4">Example</a></li>
</ul>
</li>
<li><a href="#pca">PCA</a> <ul>
<li><a href="#example-5">Example</a></li>
</ul>
</li>
</ul>
<h2 id="tf-idf">TF-IDF</h2>
<p><a href="http://en.wikipedia.org/wiki/Tf%E2%80%93idf">Term frequency-inverse document frequency (TF-IDF)</a> is a feature
vectorization method widely used in text mining to reflect the importance of a term to a document in the corpus.
Denote a term by <code>$t$</code>, a document by <code>$d$</code>, and the corpus by <code>$D$</code>.
Term frequency <code>$TF(t, d)$</code> is the number of times that term <code>$t$</code> appears in document <code>$d$</code>,
while document frequency <code>$DF(t, D)$</code> is the number of documents that contains term <code>$t$</code>.
If we only use term frequency to measure the importance, it is very easy to over-emphasize terms that
appear very often but carry little information about the document, e.g., “a”, “the”, and “of”.
If a term appears very often across the corpus, it means it doesn’t carry special information about
a particular document.
Inverse document frequency is a numerical measure of how much information a term provides:
<code>\[
IDF(t, D) = \log \frac{|D| + 1}{DF(t, D) + 1},
\]</code>
where <code>$|D|$</code> is the total number of documents in the corpus.
Since logarithm is used, if a term appears in all documents, its IDF value becomes 0.
Note that a smoothing term is applied to avoid dividing by zero for terms outside the corpus.
The TF-IDF measure is simply the product of TF and IDF:
<code>\[
TFIDF(t, d, D) = TF(t, d) \cdot IDF(t, D).
\]</code>
There are several variants on the definition of term frequency and document frequency.
In MLlib, we separate TF and IDF to make them flexible.</p>
<p>Our implementation of term frequency utilizes the
<a href="http://en.wikipedia.org/wiki/Feature_hashing">hashing trick</a>.
A raw feature is mapped into an index (term) by applying a hash function.
Then term frequencies are calculated based on the mapped indices.
This approach avoids the need to compute a global term-to-index map,
which can be expensive for a large corpus, but it suffers from potential hash collisions,
where different raw features may become the same term after hashing.
To reduce the chance of collision, we can increase the target feature dimension, i.e.,
the number of buckets of the hash table.
The default feature dimension is <code>$2^{20} = 1,048,576$</code>.</p>
<p><strong>Note:</strong> MLlib doesn’t provide tools for text segmentation.
We refer users to the <a href="http://nlp.stanford.edu/">Stanford NLP Group</a> and
<a href="https://github.com/scalanlp/chalk">scalanlp/chalk</a>.</p>
<div class="codetabs">
<div data-lang="scala">
<p>TF and IDF are implemented in <a href="api/scala/index.html#org.apache.spark.mllib.feature.HashingTF">HashingTF</a>
and <a href="api/scala/index.html#org.apache.spark.mllib.feature.IDF">IDF</a>.
<code>HashingTF</code> takes an <code>RDD[Iterable[_]]</code> as the input.
Each record could be an iterable of strings or other types.</p>
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.rdd.RDD</span>
<span class="k">import</span> <span class="nn">org.apache.spark.SparkContext</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.HashingTF</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span>
<span class="k">val</span> <span class="n">sc</span><span class="k">:</span> <span class="kt">SparkContext</span> <span class="o">=</span> <span class="o">...</span>
<span class="c1">// Load documents (one per line).</span>
<span class="k">val</span> <span class="n">documents</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">Seq</span><span class="o">[</span><span class="kt">String</span><span class="o">]]</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"..."</span><span class="o">).</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="s">" "</span><span class="o">).</span><span class="n">toSeq</span><span class="o">)</span>
<span class="k">val</span> <span class="n">hashingTF</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">HashingTF</span><span class="o">()</span>
<span class="k">val</span> <span class="n">tf</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">Vector</span><span class="o">]</span> <span class="k">=</span> <span class="n">hashingTF</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">documents</span><span class="o">)</span></code></pre></div>
<p>While applying <code>HashingTF</code> only needs a single pass to the data, applying <code>IDF</code> needs two passes:
first to compute the IDF vector and second to scale the term frequencies by IDF.</p>
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.IDF</span>
<span class="c1">// ... continue from the previous example</span>
<span class="n">tf</span><span class="o">.</span><span class="n">cache</span><span class="o">()</span>
<span class="k">val</span> <span class="n">idf</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">IDF</span><span class="o">().</span><span class="n">fit</span><span class="o">(</span><span class="n">tf</span><span class="o">)</span>
<span class="k">val</span> <span class="n">tfidf</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">Vector</span><span class="o">]</span> <span class="k">=</span> <span class="n">idf</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">tf</span><span class="o">)</span></code></pre></div>
<p>MLlib’s IDF implementation provides an option for ignoring terms which occur in less than a
minimum number of documents. In such cases, the IDF for these terms is set to 0. This feature
can be used by passing the <code>minDocFreq</code> value to the IDF constructor.</p>
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.IDF</span>
<span class="c1">// ... continue from the previous example</span>
<span class="n">tf</span><span class="o">.</span><span class="n">cache</span><span class="o">()</span>
<span class="k">val</span> <span class="n">idf</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">IDF</span><span class="o">(</span><span class="n">minDocFreq</span> <span class="k">=</span> <span class="mi">2</span><span class="o">).</span><span class="n">fit</span><span class="o">(</span><span class="n">tf</span><span class="o">)</span>
<span class="k">val</span> <span class="n">tfidf</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">Vector</span><span class="o">]</span> <span class="k">=</span> <span class="n">idf</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">tf</span><span class="o">)</span></code></pre></div>
</div>
<div data-lang="python">
<p>TF and IDF are implemented in <a href="api/python/pyspark.mllib.html#pyspark.mllib.feature.HashingTF">HashingTF</a>
and <a href="api/python/pyspark.mllib.html#pyspark.mllib.feature.IDF">IDF</a>.
<code>HashingTF</code> takes an RDD of list as the input.
Each record could be an iterable of strings or other types.</p>
<div class="highlight"><pre><code class="language-python" data-lang="python"><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.feature</span> <span class="kn">import</span> <span class="n">HashingTF</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">()</span>
<span class="c"># Load documents (one per line).</span>
<span class="n">documents</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="s">"..."</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">line</span><span class="p">:</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">" "</span><span class="p">))</span>
<span class="n">hashingTF</span> <span class="o">=</span> <span class="n">HashingTF</span><span class="p">()</span>
<span class="n">tf</span> <span class="o">=</span> <span class="n">hashingTF</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">documents</span><span class="p">)</span></code></pre></div>
<p>While applying <code>HashingTF</code> only needs a single pass to the data, applying <code>IDF</code> needs two passes:
first to compute the IDF vector and second to scale the term frequencies by IDF.</p>
<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.feature</span> <span class="kn">import</span> <span class="n">IDF</span>
<span class="c"># ... continue from the previous example</span>
<span class="n">tf</span><span class="o">.</span><span class="n">cache</span><span class="p">()</span>
<span class="n">idf</span> <span class="o">=</span> <span class="n">IDF</span><span class="p">()</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">tf</span><span class="p">)</span>
<span class="n">tfidf</span> <span class="o">=</span> <span class="n">idf</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">tf</span><span class="p">)</span></code></pre></div>
<p>MLLib’s IDF implementation provides an option for ignoring terms which occur in less than a
minimum number of documents. In such cases, the IDF for these terms is set to 0. This feature
can be used by passing the <code>minDocFreq</code> value to the IDF constructor.</p>
<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="c"># ... continue from the previous example</span>
<span class="n">tf</span><span class="o">.</span><span class="n">cache</span><span class="p">()</span>
<span class="n">idf</span> <span class="o">=</span> <span class="n">IDF</span><span class="p">(</span><span class="n">minDocFreq</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">tf</span><span class="p">)</span>
<span class="n">tfidf</span> <span class="o">=</span> <span class="n">idf</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">tf</span><span class="p">)</span></code></pre></div>
</div>
</div>
<h2 id="word2vec">Word2Vec</h2>
<p><a href="https://code.google.com/p/word2vec/">Word2Vec</a> computes distributed vector representation of words.
The main advantage of the distributed
representations is that similar words are close in the vector space, which makes generalization to
novel patterns easier and model estimation more robust. Distributed vector representation is
showed to be useful in many natural language processing applications such as named entity
recognition, disambiguation, parsing, tagging and machine translation.</p>
<h3 id="model">Model</h3>
<p>In our implementation of Word2Vec, we used skip-gram model. The training objective of skip-gram is
to learn word vector representations that are good at predicting its context in the same sentence.
Mathematically, given a sequence of training words <code>$w_1, w_2, \dots, w_T$</code>, the objective of the
skip-gram model is to maximize the average log-likelihood
<code>\[
\frac{1}{T} \sum_{t = 1}^{T}\sum_{j=-k}^{j=k} \log p(w_{t+j} | w_t)
\]</code>
where $k$ is the size of the training window. </p>
<p>In the skip-gram model, every word $w$ is associated with two vectors $u_w$ and $v_w$ which are
vector representations of $w$ as word and context respectively. The probability of correctly
predicting word $w_i$ given word $w_j$ is determined by the softmax model, which is
<code>\[
p(w_i | w_j ) = \frac{\exp(u_{w_i}^{\top}v_{w_j})}{\sum_{l=1}^{V} \exp(u_l^{\top}v_{w_j})}
\]</code>
where $V$ is the vocabulary size. </p>
<p>The skip-gram model with softmax is expensive because the cost of computing $\log p(w_i | w_j)$
is proportional to $V$, which can be easily in order of millions. To speed up training of Word2Vec,
we used hierarchical softmax, which reduced the complexity of computing of $\log p(w_i | w_j)$ to
$O(\log(V))$</p>
<h3 id="example">Example</h3>
<p>The example below demonstrates how to load a text file, parse it as an RDD of <code>Seq[String]</code>,
construct a <code>Word2Vec</code> instance and then fit a <code>Word2VecModel</code> with the input data. Finally,
we display the top 40 synonyms of the specified word. To run the example, first download
the <a href="http://mattmahoney.net/dc/text8.zip">text8</a> data and extract it to your preferred directory.
Here we assume the extracted file is <code>text8</code> and in same directory as you run the spark shell. </p>
<div class="codetabs">
<div data-lang="scala">
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.rdd._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.SparkContext._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.</span><span class="o">{</span><span class="nc">Word2Vec</span><span class="o">,</span> <span class="nc">Word2VecModel</span><span class="o">}</span>
<span class="k">val</span> <span class="n">input</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"text8"</span><span class="o">).</span><span class="n">map</span><span class="o">(</span><span class="n">line</span> <span class="k">=></span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="s">" "</span><span class="o">).</span><span class="n">toSeq</span><span class="o">)</span>
<span class="k">val</span> <span class="n">word2vec</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">Word2Vec</span><span class="o">()</span>
<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="n">word2vec</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">input</span><span class="o">)</span>
<span class="k">val</span> <span class="n">synonyms</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">findSynonyms</span><span class="o">(</span><span class="s">"china"</span><span class="o">,</span> <span class="mi">40</span><span class="o">)</span>
<span class="k">for</span><span class="o">((</span><span class="n">synonym</span><span class="o">,</span> <span class="n">cosineSimilarity</span><span class="o">)</span> <span class="k"><-</span> <span class="n">synonyms</span><span class="o">)</span> <span class="o">{</span>
<span class="n">println</span><span class="o">(</span><span class="n">s</span><span class="s">"$synonym $cosineSimilarity"</span><span class="o">)</span>
<span class="o">}</span>
<span class="c1">// Save and load model</span>
<span class="n">model</span><span class="o">.</span><span class="n">save</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"myModelPath"</span><span class="o">)</span>
<span class="k">val</span> <span class="n">sameModel</span> <span class="k">=</span> <span class="nc">Word2VecModel</span><span class="o">.</span><span class="n">load</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"myModelPath"</span><span class="o">)</span></code></pre></div>
</div>
<div data-lang="python">
<div class="highlight"><pre><code class="language-python" data-lang="python"><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.feature</span> <span class="kn">import</span> <span class="n">Word2Vec</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="n">appName</span><span class="o">=</span><span class="s">'Word2Vec'</span><span class="p">)</span>
<span class="n">inp</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="s">"text8_lines"</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">row</span><span class="p">:</span> <span class="n">row</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">" "</span><span class="p">))</span>
<span class="n">word2vec</span> <span class="o">=</span> <span class="n">Word2Vec</span><span class="p">()</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">word2vec</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">inp</span><span class="p">)</span>
<span class="n">synonyms</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="s">'china'</span><span class="p">,</span> <span class="mi">40</span><span class="p">)</span>
<span class="k">for</span> <span class="n">word</span><span class="p">,</span> <span class="n">cosine_distance</span> <span class="ow">in</span> <span class="n">synonyms</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s">"{}: {}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">word</span><span class="p">,</span> <span class="n">cosine_distance</span><span class="p">))</span></code></pre></div>
</div>
</div>
<h2 id="standardscaler">StandardScaler</h2>
<p>Standardizes features by scaling to unit variance and/or removing the mean using column summary
statistics on the samples in the training set. This is a very common pre-processing step.</p>
<p>For example, RBF kernel of Support Vector Machines or the L1 and L2 regularized linear models
typically work better when all features have unit variance and/or zero mean.</p>
<p>Standardization can improve the convergence rate during the optimization process, and also prevents
against features with very large variances exerting an overly large influence during model training.</p>
<h3 id="model-fitting">Model Fitting</h3>
<p><a href="api/scala/index.html#org.apache.spark.mllib.feature.StandardScaler"><code>StandardScaler</code></a> has the
following parameters in the constructor:</p>
<ul>
<li><code>withMean</code> False by default. Centers the data with mean before scaling. It will build a dense
output, so this does not work on sparse input and will raise an exception.</li>
<li><code>withStd</code> True by default. Scales the data to unit standard deviation.</li>
</ul>
<p>We provide a <a href="api/scala/index.html#org.apache.spark.mllib.feature.StandardScaler"><code>fit</code></a> method in
<code>StandardScaler</code> which can take an input of <code>RDD[Vector]</code>, learn the summary statistics, and then
return a model which can transform the input dataset into unit standard deviation and/or zero mean features
depending how we configure the <code>StandardScaler</code>.</p>
<p>This model implements <a href="api/scala/index.html#org.apache.spark.mllib.feature.VectorTransformer"><code>VectorTransformer</code></a>
which can apply the standardization on a <code>Vector</code> to produce a transformed <code>Vector</code> or on
an <code>RDD[Vector]</code> to produce a transformed <code>RDD[Vector]</code>.</p>
<p>Note that if the variance of a feature is zero, it will return default <code>0.0</code> value in the <code>Vector</code>
for that feature.</p>
<h3 id="example-1">Example</h3>
<p>The example below demonstrates how to load a dataset in libsvm format, and standardize the features
so that the new features have unit standard deviation and/or zero mean.</p>
<div class="codetabs">
<div data-lang="scala">
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.SparkContext._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.StandardScaler</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span>
<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">)</span>
<span class="k">val</span> <span class="n">scaler1</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">StandardScaler</span><span class="o">().</span><span class="n">fit</span><span class="o">(</span><span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="o">))</span>
<span class="k">val</span> <span class="n">scaler2</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">StandardScaler</span><span class="o">(</span><span class="n">withMean</span> <span class="k">=</span> <span class="kc">true</span><span class="o">,</span> <span class="n">withStd</span> <span class="k">=</span> <span class="kc">true</span><span class="o">).</span><span class="n">fit</span><span class="o">(</span><span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="o">))</span>
<span class="c1">// scaler3 is an identical model to scaler2, and will produce identical transformations</span>
<span class="k">val</span> <span class="n">scaler3</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">StandardScalerModel</span><span class="o">(</span><span class="n">scaler2</span><span class="o">.</span><span class="n">std</span><span class="o">,</span> <span class="n">scaler2</span><span class="o">.</span><span class="n">mean</span><span class="o">)</span>
<span class="c1">// data1 will be unit variance.</span>
<span class="k">val</span> <span class="n">data1</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="n">scaler1</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="o">)))</span>
<span class="c1">// Without converting the features into dense vectors, transformation with zero mean will raise</span>
<span class="c1">// exception on sparse vector.</span>
<span class="c1">// data2 will be unit variance and zero mean.</span>
<span class="k">val</span> <span class="n">data2</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="n">scaler2</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="o">.</span><span class="n">toArray</span><span class="o">))))</span></code></pre></div>
</div>
<div data-lang="python">
<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">MLUtils</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="kn">from</span> <span class="nn">pyspark.mllib.feature</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="p">)</span>
<span class="n">label</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">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">label</span><span class="p">)</span>
<span class="n">features</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">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="p">)</span>
<span class="n">scaler1</span> <span class="o">=</span> <span class="n">StandardScaler</span><span class="p">()</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">features</span><span class="p">)</span>
<span class="n">scaler2</span> <span class="o">=</span> <span class="n">StandardScaler</span><span class="p">(</span><span class="n">withMean</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">withStd</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">features</span><span class="p">)</span>
<span class="c"># scaler3 is an identical model to scaler2, and will produce identical transformations</span>
<span class="n">scaler3</span> <span class="o">=</span> <span class="n">StandardScalerModel</span><span class="p">(</span><span class="n">scaler2</span><span class="o">.</span><span class="n">std</span><span class="p">,</span> <span class="n">scaler2</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
<span class="c"># data1 will be unit variance.</span>
<span class="n">data1</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">zip</span><span class="p">(</span><span class="n">scaler1</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">features</span><span class="p">))</span>
<span class="c"># Without converting the features into dense vectors, transformation with zero mean will raise</span>
<span class="c"># exception on sparse vector.</span>
<span class="c"># data2 will be unit variance and zero mean.</span>
<span class="n">data2</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">zip</span><span class="p">(</span><span class="n">scaler1</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">features</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">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">toArray</span><span class="p">()))))</span></code></pre></div>
</div>
</div>
<h2 id="normalizer">Normalizer</h2>
<p>Normalizer scales individual samples to have unit $L^p$ norm. This is a common operation for text
classification or clustering. For example, the dot product of two $L^2$ normalized TF-IDF vectors
is the cosine similarity of the vectors.</p>
<p><a href="api/scala/index.html#org.apache.spark.mllib.feature.Normalizer"><code>Normalizer</code></a> has the following
parameter in the constructor:</p>
<ul>
<li><code>p</code> Normalization in $L^p$ space, $p = 2$ by default.</li>
</ul>
<p><code>Normalizer</code> implements <a href="api/scala/index.html#org.apache.spark.mllib.feature.VectorTransformer"><code>VectorTransformer</code></a>
which can apply the normalization on a <code>Vector</code> to produce a transformed <code>Vector</code> or on
an <code>RDD[Vector]</code> to produce a transformed <code>RDD[Vector]</code>.</p>
<p>Note that if the norm of the input is zero, it will return the input vector.</p>
<h3 id="example-2">Example</h3>
<p>The example below demonstrates how to load a dataset in libsvm format, and normalizes the features
with $L^2$ norm, and $L^\infty$ norm.</p>
<div class="codetabs">
<div data-lang="scala">
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.SparkContext._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.Normalizer</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span>
<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">)</span>
<span class="k">val</span> <span class="n">normalizer1</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">Normalizer</span><span class="o">()</span>
<span class="k">val</span> <span class="n">normalizer2</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">Normalizer</span><span class="o">(</span><span class="n">p</span> <span class="k">=</span> <span class="nc">Double</span><span class="o">.</span><span class="nc">PositiveInfinity</span><span class="o">)</span>
<span class="c1">// Each sample in data1 will be normalized using $L^2$ norm.</span>
<span class="k">val</span> <span class="n">data1</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="n">normalizer1</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="o">)))</span>
<span class="c1">// Each sample in data2 will be normalized using $L^\infty$ norm.</span>
<span class="k">val</span> <span class="n">data2</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="n">normalizer2</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="o">)))</span></code></pre></div>
</div>
<div data-lang="python">
<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">MLUtils</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="kn">from</span> <span class="nn">pyspark.mllib.feature</span> <span class="kn">import</span> <span class="n">Normalizer</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="p">)</span>
<span class="n">labels</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">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">label</span><span class="p">)</span>
<span class="n">features</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">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">features</span><span class="p">)</span>
<span class="n">normalizer1</span> <span class="o">=</span> <span class="n">Normalizer</span><span class="p">()</span>
<span class="n">normalizer2</span> <span class="o">=</span> <span class="n">Normalizer</span><span class="p">(</span><span class="n">p</span><span class="o">=</span><span class="nb">float</span><span class="p">(</span><span class="s">"inf"</span><span class="p">))</span>
<span class="c"># Each sample in data1 will be normalized using $L^2$ norm.</span>
<span class="n">data1</span> <span class="o">=</span> <span class="n">labels</span><span class="o">.</span><span class="n">zip</span><span class="p">(</span><span class="n">normalizer1</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">features</span><span class="p">))</span>
<span class="c"># Each sample in data2 will be normalized using $L^\infty$ norm.</span>
<span class="n">data2</span> <span class="o">=</span> <span class="n">labels</span><span class="o">.</span><span class="n">zip</span><span class="p">(</span><span class="n">normalizer2</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">features</span><span class="p">))</span></code></pre></div>
</div>
</div>
<h2 id="feature-selection">Feature selection</h2>
<p><a href="http://en.wikipedia.org/wiki/Feature_selection">Feature selection</a> allows selecting the most relevant features for use in model construction. Feature selection reduces the size of the vector space and, in turn, the complexity of any subsequent operation with vectors. The number of features to select can be tuned using a held-out validation set.</p>
<h3 id="chisqselector">ChiSqSelector</h3>
<p><a href="api/scala/index.html#org.apache.spark.mllib.feature.ChiSqSelector"><code>ChiSqSelector</code></a> stands for Chi-Squared feature selection. It operates on labeled data with categorical features. <code>ChiSqSelector</code> orders features based on a Chi-Squared test of independence from the class, and then filters (selects) the top features which the class label depends on the most. This is akin to yielding the features with the most predictive power.</p>
<h4 id="model-fitting-1">Model Fitting</h4>
<p><a href="api/scala/index.html#org.apache.spark.mllib.feature.ChiSqSelector"><code>ChiSqSelector</code></a> has the
following parameters in the constructor:</p>
<ul>
<li><code>numTopFeatures</code> number of top features that the selector will select (filter).</li>
</ul>
<p>We provide a <a href="api/scala/index.html#org.apache.spark.mllib.feature.ChiSqSelector"><code>fit</code></a> method in
<code>ChiSqSelector</code> which can take an input of <code>RDD[LabeledPoint]</code> with categorical features, learn the summary statistics, and then
return a <code>ChiSqSelectorModel</code> which can transform an input dataset into the reduced feature space.</p>
<p>This model implements <a href="api/scala/index.html#org.apache.spark.mllib.feature.VectorTransformer"><code>VectorTransformer</code></a>
which can apply the Chi-Squared feature selection on a <code>Vector</code> to produce a reduced <code>Vector</code> or on
an <code>RDD[Vector]</code> to produce a reduced <code>RDD[Vector]</code>.</p>
<p>Note that the user can also construct a <code>ChiSqSelectorModel</code> by hand by providing an array of selected feature indices (which must be sorted in ascending order).</p>
<h4 id="example-3">Example</h4>
<p>The following example shows the basic use of ChiSqSelector. The data set used has a feature matrix consisting of greyscale values that vary from 0 to 255 for each feature.</p>
<div class="codetabs">
<div data-lang="scala">
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.SparkContext._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.ChiSqSelector</span>
<span class="c1">// Load some data in libsvm format</span>
<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">)</span>
<span class="c1">// Discretize data in 16 equal bins since ChiSqSelector requires categorical features</span>
<span class="c1">// Even though features are doubles, the ChiSqSelector treats each unique value as a category</span>
<span class="k">val</span> <span class="n">discretizedData</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">lp</span> <span class="k">=></span>
<span class="nc">LabeledPoint</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="n">features</span><span class="o">.</span><span class="n">toArray</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">x</span> <span class="k">=></span> <span class="o">(</span><span class="n">x</span> <span class="o">/</span> <span class="mi">16</span><span class="o">).</span><span class="n">floor</span> <span class="o">}</span> <span class="o">)</span> <span class="o">)</span>
<span class="o">}</span>
<span class="c1">// Create ChiSqSelector that will select top 50 of 692 features</span>
<span class="k">val</span> <span class="n">selector</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">ChiSqSelector</span><span class="o">(</span><span class="mi">50</span><span class="o">)</span>
<span class="c1">// Create ChiSqSelector model (selecting features)</span>
<span class="k">val</span> <span class="n">transformer</span> <span class="k">=</span> <span class="n">selector</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">discretizedData</span><span class="o">)</span>
<span class="c1">// Filter the top 50 features from each feature vector</span>
<span class="k">val</span> <span class="n">filteredData</span> <span class="k">=</span> <span class="n">discretizedData</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">lp</span> <span class="k">=></span>
<span class="nc">LabeledPoint</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="n">features</span><span class="o">))</span>
<span class="o">}</span></code></pre></div>
</div>
<div data-lang="java">
<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kn">import</span> <span class="nn">org.apache.spark.SparkConf</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaRDD</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.api.java.function.Function</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.feature.ChiSqSelector</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.feature.ChiSqSelectorModel</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span><span class="o">;</span>
<span class="n">SparkConf</span> <span class="n">sparkConf</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">SparkConf</span><span class="o">().</span><span class="na">setAppName</span><span class="o">(</span><span class="s">"JavaChiSqSelector"</span><span class="o">);</span>
<span class="n">JavaSparkContext</span> <span class="n">sc</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">JavaSparkContext</span><span class="o">(</span><span class="n">sparkConf</span><span class="o">);</span>
<span class="n">JavaRDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">points</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="na">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">.</span><span class="na">sc</span><span class="o">(),</span>
<span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">).</span><span class="na">toJavaRDD</span><span class="o">().</span><span class="na">cache</span><span class="o">();</span>
<span class="c1">// Discretize data in 16 equal bins since ChiSqSelector requires categorical features</span>
<span class="c1">// Even though features are doubles, the ChiSqSelector treats each unique value as a category</span>
<span class="n">JavaRDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">discretizedData</span> <span class="o">=</span> <span class="n">points</span><span class="o">.</span><span class="na">map</span><span class="o">(</span>
<span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">,</span> <span class="n">LabeledPoint</span><span class="o">>()</span> <span class="o">{</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="n">LabeledPoint</span> <span class="nf">call</span><span class="o">(</span><span class="n">LabeledPoint</span> <span class="n">lp</span><span class="o">)</span> <span class="o">{</span>
<span class="kd">final</span> <span class="kt">double</span><span class="o">[]</span> <span class="n">discretizedFeatures</span> <span class="o">=</span> <span class="k">new</span> <span class="kt">double</span><span class="o">[</span><span class="n">lp</span><span class="o">.</span><span class="na">features</span><span class="o">().</span><span class="na">size</span><span class="o">()];</span>
<span class="k">for</span> <span class="o">(</span><span class="kt">int</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="o">;</span> <span class="n">i</span> <span class="o"><</span> <span class="n">lp</span><span class="o">.</span><span class="na">features</span><span class="o">().</span><span class="na">size</span><span class="o">();</span> <span class="o">++</span><span class="n">i</span><span class="o">)</span> <span class="o">{</span>
<span class="n">discretizedFeatures</span><span class="o">[</span><span class="n">i</span><span class="o">]</span> <span class="o">=</span> <span class="n">Math</span><span class="o">.</span><span class="na">floor</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="na">features</span><span class="o">().</span><span class="na">apply</span><span class="o">(</span><span class="n">i</span><span class="o">)</span> <span class="o">/</span> <span class="mi">16</span><span class="o">);</span>
<span class="o">}</span>
<span class="k">return</span> <span class="k">new</span> <span class="nf">LabeledPoint</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="na">label</span><span class="o">(),</span> <span class="n">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="n">discretizedFeatures</span><span class="o">));</span>
<span class="o">}</span>
<span class="o">});</span>
<span class="c1">// Create ChiSqSelector that will select top 50 of 692 features</span>
<span class="n">ChiSqSelector</span> <span class="n">selector</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">ChiSqSelector</span><span class="o">(</span><span class="mi">50</span><span class="o">);</span>
<span class="c1">// Create ChiSqSelector model (selecting features)</span>
<span class="kd">final</span> <span class="n">ChiSqSelectorModel</span> <span class="n">transformer</span> <span class="o">=</span> <span class="n">selector</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">discretizedData</span><span class="o">.</span><span class="na">rdd</span><span class="o">());</span>
<span class="c1">// Filter the top 50 features from each feature vector</span>
<span class="n">JavaRDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">filteredData</span> <span class="o">=</span> <span class="n">discretizedData</span><span class="o">.</span><span class="na">map</span><span class="o">(</span>
<span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">,</span> <span class="n">LabeledPoint</span><span class="o">>()</span> <span class="o">{</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="n">LabeledPoint</span> <span class="nf">call</span><span class="o">(</span><span class="n">LabeledPoint</span> <span class="n">lp</span><span class="o">)</span> <span class="o">{</span>
<span class="k">return</span> <span class="k">new</span> <span class="nf">LabeledPoint</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="na">label</span><span class="o">(),</span> <span class="n">transformer</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">lp</span><span class="o">.</span><span class="na">features</span><span class="o">()));</span>
<span class="o">}</span>
<span class="o">}</span>
<span class="o">);</span>
<span class="n">sc</span><span class="o">.</span><span class="na">stop</span><span class="o">();</span></code></pre></div>
</div>
</div>
<h2 id="elementwiseproduct">ElementwiseProduct</h2>
<p>ElementwiseProduct multiplies each input vector by a provided “weight” vector, using element-wise multiplication. In other words, it scales each column of the dataset by a scalar multiplier. This represents the <a href="https://en.wikipedia.org/wiki/Hadamard_product_%28matrices%29">Hadamard product</a> between the input vector, <code>v</code> and transforming vector, <code>w</code>, to yield a result vector.</p>
<p><code>\[ \begin{pmatrix}
v_1 \\
\vdots \\
v_N
\end{pmatrix} \circ \begin{pmatrix}
w_1 \\
\vdots \\
w_N
\end{pmatrix}
= \begin{pmatrix}
v_1 w_1 \\
\vdots \\
v_N w_N
\end{pmatrix}
\]</code></p>
<p><a href="api/scala/index.html#org.apache.spark.mllib.feature.ElementwiseProduct"><code>ElementwiseProduct</code></a> has the following parameter in the constructor:</p>
<ul>
<li><code>w</code>: the transforming vector.</li>
</ul>
<p><code>ElementwiseProduct</code> implements <a href="api/scala/index.html#org.apache.spark.mllib.feature.VectorTransformer"><code>VectorTransformer</code></a> which can apply the weighting on a <code>Vector</code> to produce a transformed <code>Vector</code> or on an <code>RDD[Vector]</code> to produce a transformed <code>RDD[Vector]</code>.</p>
<h3 id="example-4">Example</h3>
<p>This example below demonstrates how to transform vectors using a transforming vector value.</p>
<div class="codetabs">
<div data-lang="scala">
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.SparkContext._</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.ElementwiseProduct</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span>
<span class="c1">// Create some vector data; also works for sparse vectors</span>
<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">1.0</span><span class="o">,</span> <span class="mf">2.0</span><span class="o">,</span> <span class="mf">3.0</span><span class="o">),</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">4.0</span><span class="o">,</span> <span class="mf">5.0</span><span class="o">,</span> <span class="mf">6.0</span><span class="o">)))</span>
<span class="k">val</span> <span class="n">transformingVector</span> <span class="k">=</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">0.0</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">,</span> <span class="mf">2.0</span><span class="o">)</span>
<span class="k">val</span> <span class="n">transformer</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">ElementwiseProduct</span><span class="o">(</span><span class="n">transformingVector</span><span class="o">)</span>
<span class="c1">// Batch transform and per-row transform give the same results:</span>
<span class="k">val</span> <span class="n">transformedData</span> <span class="k">=</span> <span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">data</span><span class="o">)</span>
<span class="k">val</span> <span class="n">transformedData2</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">x</span><span class="o">))</span></code></pre></div>
</div>
<div data-lang="java">
<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kn">import</span> <span class="nn">java.util.Arrays</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaRDD</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.feature.ElementwiseProduct</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span><span class="o">;</span>
<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span>
<span class="c1">// Create some vector data; also works for sparse vectors</span>
<span class="n">JavaRDD</span><span class="o"><</span><span class="n">Vector</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="na">parallelize</span><span class="o">(</span><span class="n">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span>
<span class="n">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">1.0</span><span class="o">,</span> <span class="mf">2.0</span><span class="o">,</span> <span class="mf">3.0</span><span class="o">),</span> <span class="n">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">4.0</span><span class="o">,</span> <span class="mf">5.0</span><span class="o">,</span> <span class="mf">6.0</span><span class="o">)));</span>
<span class="n">Vector</span> <span class="n">transformingVector</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">0.0</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">,</span> <span class="mf">2.0</span><span class="o">);</span>
<span class="n">ElementwiseProduct</span> <span class="n">transformer</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">ElementwiseProduct</span><span class="o">(</span><span class="n">transformingVector</span><span class="o">);</span>
<span class="c1">// Batch transform and per-row transform give the same results:</span>
<span class="n">JavaRDD</span><span class="o"><</span><span class="n">Vector</span><span class="o">></span> <span class="n">transformedData</span> <span class="o">=</span> <span class="n">transformer</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">data</span><span class="o">);</span>
<span class="n">JavaRDD</span><span class="o"><</span><span class="n">Vector</span><span class="o">></span> <span class="n">transformedData2</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="na">map</span><span class="o">(</span>
<span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">Vector</span><span class="o">,</span> <span class="n">Vector</span><span class="o">>()</span> <span class="o">{</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="n">Vector</span> <span class="nf">call</span><span class="o">(</span><span class="n">Vector</span> <span class="n">v</span><span class="o">)</span> <span class="o">{</span>
<span class="k">return</span> <span class="n">transformer</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">v</span><span class="o">);</span>
<span class="o">}</span>
<span class="o">}</span>
<span class="o">);</span></code></pre></div>
</div>
<div data-lang="python">
<div class="highlight"><pre><code class="language-python" data-lang="python"><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.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.feature</span> <span class="kn">import</span> <span class="n">ElementwiseProduct</span>
<span class="c"># Load and parse the data</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">()</span>
<span class="n">data</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="s">"data/mllib/kmeans_data.txt"</span><span class="p">)</span>
<span class="n">parsedData</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">x</span><span class="p">:</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">t</span><span class="p">)</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">x</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">" "</span><span class="p">)])</span>
<span class="c"># Create weight vector.</span>
<span class="n">transformingVector</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">,</span> <span class="mf">2.0</span><span class="p">])</span>
<span class="n">transformer</span> <span class="o">=</span> <span class="n">ElementwiseProduct</span><span class="p">(</span><span class="n">transformingVector</span><span class="p">)</span>
<span class="c"># Batch transform</span>
<span class="n">transformedData</span> <span class="o">=</span> <span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">parsedData</span><span class="p">)</span>
<span class="c"># Single-row transform</span>
<span class="n">transformedData2</span> <span class="o">=</span> <span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">parsedData</span><span class="o">.</span><span class="n">first</span><span class="p">())</span></code></pre></div>
</div>
</div>
<h2 id="pca">PCA</h2>
<p>A feature transformer that projects vectors to a low-dimensional space using PCA.
Details you can read at <a href="mllib-dimensionality-reduction.html">dimensionality reduction</a>.</p>
<h3 id="example-5">Example</h3>
<p>The following code demonstrates how to compute principal components on a <code>Vector</code>
and use them to project the vectors into a low-dimensional space while keeping associated labels
for calculation a <a href="(mllib-linear-methods.html)">Linear Regression</a></p>
<div class="codetabs">
<div data-lang="scala">
<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.regression.LinearRegressionWithSGD</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span>
<span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.PCA</span>
<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"data/mllib/ridge-data/lpsa.data"</span><span class="o">).</span><span class="n">map</span> <span class="o">{</span> <span class="n">line</span> <span class="k">=></span>
<span class="k">val</span> <span class="n">parts</span> <span class="k">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="sc">','</span><span class="o">)</span>
<span class="nc">LabeledPoint</span><span class="o">(</span><span class="n">parts</span><span class="o">(</span><span class="mi">0</span><span class="o">).</span><span class="n">toDouble</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="n">parts</span><span class="o">(</span><span class="mi">1</span><span class="o">).</span><span class="n">split</span><span class="o">(</span><span class="sc">' '</span><span class="o">).</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">toDouble</span><span class="o">)))</span>
<span class="o">}.</span><span class="n">cache</span><span class="o">()</span>
<span class="k">val</span> <span class="n">splits</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">randomSplit</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="mf">0.6</span><span class="o">,</span> <span class="mf">0.4</span><span class="o">),</span> <span class="n">seed</span> <span class="k">=</span> <span class="mi">11L</span><span class="o">)</span>
<span class="k">val</span> <span class="n">training</span> <span class="k">=</span> <span class="n">splits</span><span class="o">(</span><span class="mi">0</span><span class="o">).</span><span class="n">cache</span><span class="o">()</span>
<span class="k">val</span> <span class="n">test</span> <span class="k">=</span> <span class="n">splits</span><span class="o">(</span><span class="mi">1</span><span class="o">)</span>
<span class="k">val</span> <span class="n">pca</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">PCA</span><span class="o">(</span><span class="n">training</span><span class="o">.</span><span class="n">first</span><span class="o">().</span><span class="n">features</span><span class="o">.</span><span class="n">size</span><span class="o">/</span><span class="mi">2</span><span class="o">).</span><span class="n">fit</span><span class="o">(</span><span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">features</span><span class="o">))</span>
<span class="k">val</span> <span class="n">training_pca</span> <span class="k">=</span> <span class="n">training</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">p</span> <span class="k">=></span> <span class="n">p</span><span class="o">.</span><span class="n">copy</span><span class="o">(</span><span class="n">features</span> <span class="k">=</span> <span class="n">pca</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">p</span><span class="o">.</span><span class="n">features</span><span class="o">)))</span>
<span class="k">val</span> <span class="n">test_pca</span> <span class="k">=</span> <span class="n">test</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">p</span> <span class="k">=></span> <span class="n">p</span><span class="o">.</span><span class="n">copy</span><span class="o">(</span><span class="n">features</span> <span class="k">=</span> <span class="n">pca</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">p</span><span class="o">.</span><span class="n">features</span><span class="o">)))</span>
<span class="k">val</span> <span class="n">numIterations</span> <span class="k">=</span> <span class="mi">100</span>
<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="nc">LinearRegressionWithSGD</span><span class="o">.</span><span class="n">train</span><span class="o">(</span><span class="n">training</span><span class="o">,</span> <span class="n">numIterations</span><span class="o">)</span>
<span class="k">val</span> <span class="n">model_pca</span> <span class="k">=</span> <span class="nc">LinearRegressionWithSGD</span><span class="o">.</span><span class="n">train</span><span class="o">(</span><span class="n">training_pca</span><span class="o">,</span> <span class="n">numIterations</span><span class="o">)</span>
<span class="k">val</span> <span class="n">valuesAndPreds</span> <span class="k">=</span> <span class="n">test</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">point</span> <span class="k">=></span>
<span class="k">val</span> <span class="n">score</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="n">point</span><span class="o">.</span><span class="n">features</span><span class="o">)</span>
<span class="o">(</span><span class="n">score</span><span class="o">,</span> <span class="n">point</span><span class="o">.</span><span class="n">label</span><span class="o">)</span>
<span class="o">}</span>
<span class="k">val</span> <span class="n">valuesAndPreds_pca</span> <span class="k">=</span> <span class="n">test_pca</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">point</span> <span class="k">=></span>
<span class="k">val</span> <span class="n">score</span> <span class="k">=</span> <span class="n">model_pca</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="n">point</span><span class="o">.</span><span class="n">features</span><span class="o">)</span>
<span class="o">(</span><span class="n">score</span><span class="o">,</span> <span class="n">point</span><span class="o">.</span><span class="n">label</span><span class="o">)</span>
<span class="o">}</span>
<span class="k">val</span> <span class="nc">MSE</span> <span class="k">=</span> <span class="n">valuesAndPreds</span><span class="o">.</span><span class="n">map</span><span class="o">{</span><span class="k">case</span><span class="o">(</span><span class="n">v</span><span class="o">,</span> <span class="n">p</span><span class="o">)</span> <span class="k">=></span> <span class="n">math</span><span class="o">.</span><span class="n">pow</span><span class="o">((</span><span class="n">v</span> <span class="o">-</span> <span class="n">p</span><span class="o">),</span> <span class="mi">2</span><span class="o">)}.</span><span class="n">mean</span><span class="o">()</span>
<span class="k">val</span> <span class="nc">MSE_pca</span> <span class="k">=</span> <span class="n">valuesAndPreds_pca</span><span class="o">.</span><span class="n">map</span><span class="o">{</span><span class="k">case</span><span class="o">(</span><span class="n">v</span><span class="o">,</span> <span class="n">p</span><span class="o">)</span> <span class="k">=></span> <span class="n">math</span><span class="o">.</span><span class="n">pow</span><span class="o">((</span><span class="n">v</span> <span class="o">-</span> <span class="n">p</span><span class="o">),</span> <span class="mi">2</span><span class="o">)}.</span><span class="n">mean</span><span class="o">()</span>
<span class="n">println</span><span class="o">(</span><span class="s">"Mean Squared Error = "</span> <span class="o">+</span> <span class="nc">MSE</span><span class="o">)</span>
<span class="n">println</span><span class="o">(</span><span class="s">"PCA Mean Squared Error = "</span> <span class="o">+</span> <span class="nc">MSE_pca</span><span class="o">)</span></code></pre></div>
</div>
</div>
</div> <!-- /container -->
<script src="js/vendor/jquery-1.8.0.min.js"></script>
<script src="js/vendor/bootstrap.min.js"></script>
<script src="js/vendor/anchor.min.js"></script>
<script src="js/main.js"></script>
<!-- MathJax Section -->
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
TeX: { equationNumbers: { autoNumber: "AMS" } }
});
</script>
<script>
// Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS.
// We could use "//cdn.mathjax...", but that won't support "file://".
(function(d, script) {
script = d.createElement('script');
script.type = 'text/javascript';
script.async = true;
script.onload = function(){
MathJax.Hub.Config({
tex2jax: {
inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ],
displayMath: [ ["$$","$$"], ["\\[", "\\]"] ],
processEscapes: true,
skipTags: ['script', 'noscript', 'style', 'textarea', 'pre']
}
});
};
script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') +
'cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
d.getElementsByTagName('head')[0].appendChild(script);
}(document));
</script>
</body>
</html>
|