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
|
<!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.random — 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> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> »</li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for pyspark.mllib.random</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 "License"); 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 "AS IS" 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="sd">"""</span>
<span class="sd">Python package for random data generation.</span>
<span class="sd">"""</span>
<span class="kn">from</span> <span class="nn">functools</span> <span class="kn">import</span> <span class="n">wraps</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="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'RandomRDDs'</span><span class="p">,</span> <span class="p">]</span>
<span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="n">f</span><span class="p">):</span>
<span class="nd">@wraps</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">func</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="o">*</span><span class="n">a</span><span class="p">,</span> <span class="o">**</span><span class="n">kw</span><span class="p">):</span>
<span class="n">rdd</span> <span class="o">=</span> <span class="n">f</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="o">*</span><span class="n">a</span><span class="p">,</span> <span class="o">**</span><span class="n">kw</span><span class="p">)</span>
<span class="k">return</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">vec</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="k">return</span> <span class="n">func</span>
<div class="viewcode-block" id="RandomRDDs"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs">[docs]</a><span class="k">class</span> <span class="nc">RandomRDDs</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generator methods for creating RDDs comprised of i.i.d samples from</span>
<span class="sd"> some distribution.</span>
<span class="sd"> """</span>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="RandomRDDs.uniformRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.uniformRDD">[docs]</a> <span class="k">def</span> <span class="nf">uniformRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of i.i.d. samples from the</span>
<span class="sd"> uniform distribution U(0.0, 1.0).</span>
<span class="sd"> To transform the distribution in the generated RDD from U(0.0, 1.0)</span>
<span class="sd"> to U(a, b), use</span>
<span class="sd"> C{RandomRDDs.uniformRDD(sc, n, p, seed)\</span>
<span class="sd"> .map(lambda v: a + (b - a) * v)}</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param size: Size of the RDD.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of float comprised of i.i.d. samples ~ `U(0.0, 1.0)`.</span>
<span class="sd"> >>> x = RandomRDDs.uniformRDD(sc, 100).collect()</span>
<span class="sd"> >>> len(x)</span>
<span class="sd"> 100</span>
<span class="sd"> >>> max(x) <= 1.0 and min(x) >= 0.0</span>
<span class="sd"> True</span>
<span class="sd"> >>> RandomRDDs.uniformRDD(sc, 100, 4).getNumPartitions()</span>
<span class="sd"> 4</span>
<span class="sd"> >>> parts = RandomRDDs.uniformRDD(sc, 100, seed=4).getNumPartitions()</span>
<span class="sd"> >>> parts == sc.defaultParallelism</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"uniformRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="RandomRDDs.normalRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.normalRDD">[docs]</a> <span class="k">def</span> <span class="nf">normalRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of i.i.d. samples from the standard normal</span>
<span class="sd"> distribution.</span>
<span class="sd"> To transform the distribution in the generated RDD from standard normal</span>
<span class="sd"> to some other normal N(mean, sigma^2), use</span>
<span class="sd"> C{RandomRDDs.normal(sc, n, p, seed)\</span>
<span class="sd"> .map(lambda v: mean + sigma * v)}</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param size: Size of the RDD.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of float comprised of i.i.d. samples ~ N(0.0, 1.0).</span>
<span class="sd"> >>> x = RandomRDDs.normalRDD(sc, 1000, seed=1)</span>
<span class="sd"> >>> stats = x.stats()</span>
<span class="sd"> >>> stats.count()</span>
<span class="sd"> 1000</span>
<span class="sd"> >>> abs(stats.mean() - 0.0) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> >>> abs(stats.stdev() - 1.0) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"normalRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="RandomRDDs.logNormalRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.logNormalRDD">[docs]</a> <span class="k">def</span> <span class="nf">logNormalRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of i.i.d. samples from the log normal</span>
<span class="sd"> distribution with the input mean and standard distribution.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param mean: mean for the log Normal distribution</span>
<span class="sd"> :param std: std for the log Normal distribution</span>
<span class="sd"> :param size: Size of the RDD.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of float comprised of i.i.d. samples ~ log N(mean, std).</span>
<span class="sd"> >>> from math import sqrt, exp</span>
<span class="sd"> >>> mean = 0.0</span>
<span class="sd"> >>> std = 1.0</span>
<span class="sd"> >>> expMean = exp(mean + 0.5 * std * std)</span>
<span class="sd"> >>> expStd = sqrt((exp(std * std) - 1.0) * exp(2.0 * mean + std * std))</span>
<span class="sd"> >>> x = RandomRDDs.logNormalRDD(sc, mean, std, 1000, seed=2)</span>
<span class="sd"> >>> stats = x.stats()</span>
<span class="sd"> >>> stats.count()</span>
<span class="sd"> 1000</span>
<span class="sd"> >>> abs(stats.mean() - expMean) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> abs(stats.stdev() - expStd) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"logNormalRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</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="nb">float</span><span class="p">(</span><span class="n">std</span><span class="p">),</span>
<span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="RandomRDDs.poissonRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.poissonRDD">[docs]</a> <span class="k">def</span> <span class="nf">poissonRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of i.i.d. samples from the Poisson</span>
<span class="sd"> distribution with the input mean.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param mean: Mean, or lambda, for the Poisson distribution.</span>
<span class="sd"> :param size: Size of the RDD.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of float comprised of i.i.d. samples ~ Pois(mean).</span>
<span class="sd"> >>> mean = 100.0</span>
<span class="sd"> >>> x = RandomRDDs.poissonRDD(sc, mean, 1000, seed=2)</span>
<span class="sd"> >>> stats = x.stats()</span>
<span class="sd"> >>> stats.count()</span>
<span class="sd"> 1000</span>
<span class="sd"> >>> abs(stats.mean() - mean) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> abs(stats.stdev() - sqrt(mean)) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"poissonRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</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="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="RandomRDDs.exponentialRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.exponentialRDD">[docs]</a> <span class="k">def</span> <span class="nf">exponentialRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of i.i.d. samples from the Exponential</span>
<span class="sd"> distribution with the input mean.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param mean: Mean, or 1 / lambda, for the Exponential distribution.</span>
<span class="sd"> :param size: Size of the RDD.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of float comprised of i.i.d. samples ~ Exp(mean).</span>
<span class="sd"> >>> mean = 2.0</span>
<span class="sd"> >>> x = RandomRDDs.exponentialRDD(sc, mean, 1000, seed=2)</span>
<span class="sd"> >>> stats = x.stats()</span>
<span class="sd"> >>> stats.count()</span>
<span class="sd"> 1000</span>
<span class="sd"> >>> abs(stats.mean() - mean) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> abs(stats.stdev() - sqrt(mean)) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"exponentialRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</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="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="RandomRDDs.gammaRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.gammaRDD">[docs]</a> <span class="k">def</span> <span class="nf">gammaRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">shape</span><span class="p">,</span> <span class="n">scale</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of i.i.d. samples from the Gamma</span>
<span class="sd"> distribution with the input shape and scale.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param shape: shape (> 0) parameter for the Gamma distribution</span>
<span class="sd"> :param scale: scale (> 0) parameter for the Gamma distribution</span>
<span class="sd"> :param size: Size of the RDD.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of float comprised of i.i.d. samples ~ Gamma(shape, scale).</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> shape = 1.0</span>
<span class="sd"> >>> scale = 2.0</span>
<span class="sd"> >>> expMean = shape * scale</span>
<span class="sd"> >>> expStd = sqrt(shape * scale * scale)</span>
<span class="sd"> >>> x = RandomRDDs.gammaRDD(sc, shape, scale, 1000, seed=2)</span>
<span class="sd"> >>> stats = x.stats()</span>
<span class="sd"> >>> stats.count()</span>
<span class="sd"> 1000</span>
<span class="sd"> >>> abs(stats.mean() - expMean) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> >>> abs(stats.stdev() - expStd) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"gammaRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">shape</span><span class="p">),</span>
<span class="nb">float</span><span class="p">(</span><span class="n">scale</span><span class="p">),</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<span class="nd">@toArray</span>
<div class="viewcode-block" id="RandomRDDs.uniformVectorRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.uniformVectorRDD">[docs]</a> <span class="k">def</span> <span class="nf">uniformVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span>
<span class="sd"> from the uniform distribution U(0.0, 1.0).</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param numRows: Number of Vectors in the RDD.</span>
<span class="sd"> :param numCols: Number of elements in each Vector.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD.</span>
<span class="sd"> :param seed: Seed for the RNG that generates the seed for the generator in each partition.</span>
<span class="sd"> :return: RDD of Vector with vectors containing i.i.d samples ~ `U(0.0, 1.0)`.</span>
<span class="sd"> >>> import numpy as np</span>
<span class="sd"> >>> mat = np.matrix(RandomRDDs.uniformVectorRDD(sc, 10, 10).collect())</span>
<span class="sd"> >>> mat.shape</span>
<span class="sd"> (10, 10)</span>
<span class="sd"> >>> mat.max() <= 1.0 and mat.min() >= 0.0</span>
<span class="sd"> True</span>
<span class="sd"> >>> RandomRDDs.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions()</span>
<span class="sd"> 4</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"uniformVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<span class="nd">@toArray</span>
<div class="viewcode-block" id="RandomRDDs.normalVectorRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.normalVectorRDD">[docs]</a> <span class="k">def</span> <span class="nf">normalVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span>
<span class="sd"> from the standard normal distribution.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param numRows: Number of Vectors in the RDD.</span>
<span class="sd"> :param numCols: Number of elements in each Vector.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of Vector with vectors containing i.i.d. samples ~ `N(0.0, 1.0)`.</span>
<span class="sd"> >>> import numpy as np</span>
<span class="sd"> >>> mat = np.matrix(RandomRDDs.normalVectorRDD(sc, 100, 100, seed=1).collect())</span>
<span class="sd"> >>> mat.shape</span>
<span class="sd"> (100, 100)</span>
<span class="sd"> >>> abs(mat.mean() - 0.0) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> >>> abs(mat.std() - 1.0) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"normalVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<span class="nd">@toArray</span>
<div class="viewcode-block" id="RandomRDDs.logNormalVectorRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.logNormalVectorRDD">[docs]</a> <span class="k">def</span> <span class="nf">logNormalVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span>
<span class="sd"> from the log normal distribution.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param mean: Mean of the log normal distribution</span>
<span class="sd"> :param std: Standard Deviation of the log normal distribution</span>
<span class="sd"> :param numRows: Number of Vectors in the RDD.</span>
<span class="sd"> :param numCols: Number of elements in each Vector.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of Vector with vectors containing i.i.d. samples ~ log `N(mean, std)`.</span>
<span class="sd"> >>> import numpy as np</span>
<span class="sd"> >>> from math import sqrt, exp</span>
<span class="sd"> >>> mean = 0.0</span>
<span class="sd"> >>> std = 1.0</span>
<span class="sd"> >>> expMean = exp(mean + 0.5 * std * std)</span>
<span class="sd"> >>> expStd = sqrt((exp(std * std) - 1.0) * exp(2.0 * mean + std * std))</span>
<span class="sd"> >>> m = RandomRDDs.logNormalVectorRDD(sc, mean, std, 100, 100, seed=1).collect()</span>
<span class="sd"> >>> mat = np.matrix(m)</span>
<span class="sd"> >>> mat.shape</span>
<span class="sd"> (100, 100)</span>
<span class="sd"> >>> abs(mat.mean() - expMean) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> >>> abs(mat.std() - expStd) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"logNormalVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</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="nb">float</span><span class="p">(</span><span class="n">std</span><span class="p">),</span>
<span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<span class="nd">@toArray</span>
<div class="viewcode-block" id="RandomRDDs.poissonVectorRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.poissonVectorRDD">[docs]</a> <span class="k">def</span> <span class="nf">poissonVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span>
<span class="sd"> from the Poisson distribution with the input mean.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param mean: Mean, or lambda, for the Poisson distribution.</span>
<span class="sd"> :param numRows: Number of Vectors in the RDD.</span>
<span class="sd"> :param numCols: Number of elements in each Vector.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`)</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of Vector with vectors containing i.i.d. samples ~ Pois(mean).</span>
<span class="sd"> >>> import numpy as np</span>
<span class="sd"> >>> mean = 100.0</span>
<span class="sd"> >>> rdd = RandomRDDs.poissonVectorRDD(sc, mean, 100, 100, seed=1)</span>
<span class="sd"> >>> mat = np.mat(rdd.collect())</span>
<span class="sd"> >>> mat.shape</span>
<span class="sd"> (100, 100)</span>
<span class="sd"> >>> abs(mat.mean() - mean) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> abs(mat.std() - sqrt(mean)) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"poissonVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</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="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span>
<span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<span class="nd">@toArray</span>
<div class="viewcode-block" id="RandomRDDs.exponentialVectorRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.exponentialVectorRDD">[docs]</a> <span class="k">def</span> <span class="nf">exponentialVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span>
<span class="sd"> from the Exponential distribution with the input mean.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param mean: Mean, or 1 / lambda, for the Exponential distribution.</span>
<span class="sd"> :param numRows: Number of Vectors in the RDD.</span>
<span class="sd"> :param numCols: Number of elements in each Vector.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`)</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of Vector with vectors containing i.i.d. samples ~ Exp(mean).</span>
<span class="sd"> >>> import numpy as np</span>
<span class="sd"> >>> mean = 0.5</span>
<span class="sd"> >>> rdd = RandomRDDs.exponentialVectorRDD(sc, mean, 100, 100, seed=1)</span>
<span class="sd"> >>> mat = np.mat(rdd.collect())</span>
<span class="sd"> >>> mat.shape</span>
<span class="sd"> (100, 100)</span>
<span class="sd"> >>> abs(mat.mean() - mean) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> abs(mat.std() - sqrt(mean)) < 0.5</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"exponentialVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</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="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span>
<span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span>
</div>
<span class="nd">@staticmethod</span>
<span class="nd">@toArray</span>
<div class="viewcode-block" id="RandomRDDs.gammaVectorRDD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.random.RandomRDDs.gammaVectorRDD">[docs]</a> <span class="k">def</span> <span class="nf">gammaVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">shape</span><span class="p">,</span> <span class="n">scale</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span>
<span class="sd"> from the Gamma distribution.</span>
<span class="sd"> :param sc: SparkContext used to create the RDD.</span>
<span class="sd"> :param shape: Shape (> 0) of the Gamma distribution</span>
<span class="sd"> :param scale: Scale (> 0) of the Gamma distribution</span>
<span class="sd"> :param numRows: Number of Vectors in the RDD.</span>
<span class="sd"> :param numCols: Number of elements in each Vector.</span>
<span class="sd"> :param numPartitions: Number of partitions in the RDD (default: `sc.defaultParallelism`).</span>
<span class="sd"> :param seed: Random seed (default: a random long integer).</span>
<span class="sd"> :return: RDD of Vector with vectors containing i.i.d. samples ~ Gamma(shape, scale).</span>
<span class="sd"> >>> import numpy as np</span>
<span class="sd"> >>> from math import sqrt</span>
<span class="sd"> >>> shape = 1.0</span>
<span class="sd"> >>> scale = 2.0</span>
<span class="sd"> >>> expMean = shape * scale</span>
<span class="sd"> >>> expStd = sqrt(shape * scale * scale)</span>
<span class="sd"> >>> mat = np.matrix(RandomRDDs.gammaVectorRDD(sc, shape, scale, 100, 100, seed=1).collect())</span>
<span class="sd"> >>> mat.shape</span>
<span class="sd"> (100, 100)</span>
<span class="sd"> >>> abs(mat.mean() - expMean) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> >>> abs(mat.std() - expStd) < 0.1</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"gammaVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">shape</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">scale</span><span class="p">),</span>
<span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</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">'sc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">'local[2]'</span><span class="p">,</span> <span class="s">'PythonTest'</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">'sc'</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">"__main__"</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> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
</ul>
</div>
<div class="footer" role="contentinfo">
© Copyright .
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.3.1.
</div>
</body>
</html>
|
