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
|
<!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.evaluation — PySpark 1.5.0 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: '1.5.0',
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 1.5.0 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 1.5.0 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.evaluation</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="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">callMLlibFunc</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SQLContext</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">StructField</span><span class="p">,</span> <span class="n">StructType</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">,</span> <span class="n">IntegerType</span><span class="p">,</span> <span class="n">ArrayType</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'BinaryClassificationMetrics'</span><span class="p">,</span> <span class="s">'RegressionMetrics'</span><span class="p">,</span>
<span class="s">'MulticlassMetrics'</span><span class="p">,</span> <span class="s">'RankingMetrics'</span><span class="p">]</span>
<div class="viewcode-block" id="BinaryClassificationMetrics"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.BinaryClassificationMetrics">[docs]</a><span class="k">class</span> <span class="nc">BinaryClassificationMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Evaluator for binary classification.</span>
<span class="sd"> :param scoreAndLabels: an RDD of (score, label) pairs</span>
<span class="sd"> >>> scoreAndLabels = sc.parallelize([</span>
<span class="sd"> ... (0.1, 0.0), (0.1, 1.0), (0.4, 0.0), (0.6, 0.0), (0.6, 1.0), (0.6, 1.0), (0.8, 1.0)], 2)</span>
<span class="sd"> >>> metrics = BinaryClassificationMetrics(scoreAndLabels)</span>
<span class="sd"> >>> metrics.areaUnderROC</span>
<span class="sd"> 0.70...</span>
<span class="sd"> >>> metrics.areaUnderPR</span>
<span class="sd"> 0.83...</span>
<span class="sd"> >>> metrics.unpersist()</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scoreAndLabels</span><span class="p">):</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">scoreAndLabels</span><span class="o">.</span><span class="n">ctx</span>
<span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">scoreAndLabels</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">StructType</span><span class="p">([</span>
<span class="n">StructField</span><span class="p">(</span><span class="s">"score"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="bp">False</span><span class="p">),</span>
<span class="n">StructField</span><span class="p">(</span><span class="s">"label"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="bp">False</span><span class="p">)]))</span>
<span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">BinaryClassificationMetrics</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">BinaryClassificationMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">areaUnderROC</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Computes the area under the receiver operating characteristic</span>
<span class="sd"> (ROC) curve.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"areaUnderROC"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">areaUnderPR</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Computes the area under the precision-recall curve.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"areaUnderPR"</span><span class="p">)</span>
<div class="viewcode-block" id="BinaryClassificationMetrics.unpersist"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.BinaryClassificationMetrics.unpersist">[docs]</a> <span class="k">def</span> <span class="nf">unpersist</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Unpersists intermediate RDDs used in the computation.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"unpersist"</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="RegressionMetrics"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.RegressionMetrics">[docs]</a><span class="k">class</span> <span class="nc">RegressionMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Evaluator for regression.</span>
<span class="sd"> :param predictionAndObservations: an RDD of (prediction,</span>
<span class="sd"> observation) pairs.</span>
<span class="sd"> >>> predictionAndObservations = sc.parallelize([</span>
<span class="sd"> ... (2.5, 3.0), (0.0, -0.5), (2.0, 2.0), (8.0, 7.0)])</span>
<span class="sd"> >>> metrics = RegressionMetrics(predictionAndObservations)</span>
<span class="sd"> >>> metrics.explainedVariance</span>
<span class="sd"> 8.859...</span>
<span class="sd"> >>> metrics.meanAbsoluteError</span>
<span class="sd"> 0.5...</span>
<span class="sd"> >>> metrics.meanSquaredError</span>
<span class="sd"> 0.37...</span>
<span class="sd"> >>> metrics.rootMeanSquaredError</span>
<span class="sd"> 0.61...</span>
<span class="sd"> >>> metrics.r2</span>
<span class="sd"> 0.94...</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndObservations</span><span class="p">):</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndObservations</span><span class="o">.</span><span class="n">ctx</span>
<span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">predictionAndObservations</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">StructType</span><span class="p">([</span>
<span class="n">StructField</span><span class="p">(</span><span class="s">"prediction"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="bp">False</span><span class="p">),</span>
<span class="n">StructField</span><span class="p">(</span><span class="s">"observation"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="bp">False</span><span class="p">)]))</span>
<span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">RegressionMetrics</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">RegressionMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">explainedVariance</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the explained variance regression score.</span>
<span class="sd"> explainedVariance = 1 - variance(y - \hat{y}) / variance(y)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"explainedVariance"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">meanAbsoluteError</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the mean absolute error, which is a risk function corresponding to the</span>
<span class="sd"> expected value of the absolute error loss or l1-norm loss.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"meanAbsoluteError"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">meanSquaredError</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the mean squared error, which is a risk function corresponding to the</span>
<span class="sd"> expected value of the squared error loss or quadratic loss.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"meanSquaredError"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">rootMeanSquaredError</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the root mean squared error, which is defined as the square root of</span>
<span class="sd"> the mean squared error.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"rootMeanSquaredError"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">r2</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns R^2^, the coefficient of determination.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"r2"</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="MulticlassMetrics"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics">[docs]</a><span class="k">class</span> <span class="nc">MulticlassMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Evaluator for multiclass classification.</span>
<span class="sd"> :param predictionAndLabels an RDD of (prediction, label) pairs.</span>
<span class="sd"> >>> predictionAndLabels = sc.parallelize([(0.0, 0.0), (0.0, 1.0), (0.0, 0.0),</span>
<span class="sd"> ... (1.0, 0.0), (1.0, 1.0), (1.0, 1.0), (1.0, 1.0), (2.0, 2.0), (2.0, 0.0)])</span>
<span class="sd"> >>> metrics = MulticlassMetrics(predictionAndLabels)</span>
<span class="sd"> >>> metrics.confusionMatrix().toArray()</span>
<span class="sd"> array([[ 2., 1., 1.],</span>
<span class="sd"> [ 1., 3., 0.],</span>
<span class="sd"> [ 0., 0., 1.]])</span>
<span class="sd"> >>> metrics.falsePositiveRate(0.0)</span>
<span class="sd"> 0.2...</span>
<span class="sd"> >>> metrics.precision(1.0)</span>
<span class="sd"> 0.75...</span>
<span class="sd"> >>> metrics.recall(2.0)</span>
<span class="sd"> 1.0...</span>
<span class="sd"> >>> metrics.fMeasure(0.0, 2.0)</span>
<span class="sd"> 0.52...</span>
<span class="sd"> >>> metrics.precision()</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.recall()</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.weightedFalsePositiveRate</span>
<span class="sd"> 0.19...</span>
<span class="sd"> >>> metrics.weightedPrecision</span>
<span class="sd"> 0.68...</span>
<span class="sd"> >>> metrics.weightedRecall</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.weightedFMeasure()</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.weightedFMeasure(2.0)</span>
<span class="sd"> 0.65...</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndLabels</span><span class="p">):</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">ctx</span>
<span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">StructType</span><span class="p">([</span>
<span class="n">StructField</span><span class="p">(</span><span class="s">"prediction"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="bp">False</span><span class="p">),</span>
<span class="n">StructField</span><span class="p">(</span><span class="s">"label"</span><span class="p">,</span> <span class="n">DoubleType</span><span class="p">(),</span> <span class="n">nullable</span><span class="o">=</span><span class="bp">False</span><span class="p">)]))</span>
<span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">MulticlassMetrics</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">MulticlassMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="MulticlassMetrics.confusionMatrix"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.confusionMatrix">[docs]</a> <span class="k">def</span> <span class="nf">confusionMatrix</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns confusion matrix: predicted classes are in columns,</span>
<span class="sd"> they are ordered by class label ascending, as in "labels".</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"confusionMatrix"</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="MulticlassMetrics.truePositiveRate"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.truePositiveRate">[docs]</a> <span class="k">def</span> <span class="nf">truePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns true positive rate for a given label (category).</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"truePositiveRate"</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="MulticlassMetrics.falsePositiveRate"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.falsePositiveRate">[docs]</a> <span class="k">def</span> <span class="nf">falsePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns false positive rate for a given label (category).</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"falsePositiveRate"</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="MulticlassMetrics.precision"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.precision">[docs]</a> <span class="k">def</span> <span class="nf">precision</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns precision or precision for a given label (category) if specified.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"precision"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"precision"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span>
</div>
<div class="viewcode-block" id="MulticlassMetrics.recall"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.recall">[docs]</a> <span class="k">def</span> <span class="nf">recall</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns recall or recall for a given label (category) if specified.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"recall"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"recall"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span>
</div>
<div class="viewcode-block" id="MulticlassMetrics.fMeasure"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.fMeasure">[docs]</a> <span class="k">def</span> <span class="nf">fMeasure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns f-measure or f-measure for a given label (category) if specified.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">beta</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"fMeasure"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"fMeasure"</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s">"If the beta parameter is specified, label can not be none"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"fMeasure"</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span>
</div>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">weightedTruePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns weighted true positive rate.</span>
<span class="sd"> (equals to precision, recall and f-measure)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weightedTruePositiveRate"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">weightedFalsePositiveRate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns weighted false positive rate.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weightedFalsePositiveRate"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">weightedRecall</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns weighted averaged recall.</span>
<span class="sd"> (equals to precision, recall and f-measure)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weightedRecall"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">weightedPrecision</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns weighted averaged precision.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weightedPrecision"</span><span class="p">)</span>
<div class="viewcode-block" id="MulticlassMetrics.weightedFMeasure"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.MulticlassMetrics.weightedFMeasure">[docs]</a> <span class="k">def</span> <span class="nf">weightedFMeasure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns weighted averaged f-measure.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">beta</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weightedFMeasure"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weightedFMeasure"</span><span class="p">,</span> <span class="n">beta</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="RankingMetrics"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.RankingMetrics">[docs]</a><span class="k">class</span> <span class="nc">RankingMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Evaluator for ranking algorithms.</span>
<span class="sd"> :param predictionAndLabels: an RDD of (predicted ranking,</span>
<span class="sd"> ground truth set) pairs.</span>
<span class="sd"> >>> predictionAndLabels = sc.parallelize([</span>
<span class="sd"> ... ([1, 6, 2, 7, 8, 3, 9, 10, 4, 5], [1, 2, 3, 4, 5]),</span>
<span class="sd"> ... ([4, 1, 5, 6, 2, 7, 3, 8, 9, 10], [1, 2, 3]),</span>
<span class="sd"> ... ([1, 2, 3, 4, 5], [])])</span>
<span class="sd"> >>> metrics = RankingMetrics(predictionAndLabels)</span>
<span class="sd"> >>> metrics.precisionAt(1)</span>
<span class="sd"> 0.33...</span>
<span class="sd"> >>> metrics.precisionAt(5)</span>
<span class="sd"> 0.26...</span>
<span class="sd"> >>> metrics.precisionAt(15)</span>
<span class="sd"> 0.17...</span>
<span class="sd"> >>> metrics.meanAveragePrecision</span>
<span class="sd"> 0.35...</span>
<span class="sd"> >>> metrics.ndcgAt(3)</span>
<span class="sd"> 0.33...</span>
<span class="sd"> >>> metrics.ndcgAt(10)</span>
<span class="sd"> 0.48...</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndLabels</span><span class="p">):</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">ctx</span>
<span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">,</span>
<span class="n">schema</span><span class="o">=</span><span class="n">sql_ctx</span><span class="o">.</span><span class="n">_inferSchema</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">))</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"newRankingMetrics"</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">RankingMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="RankingMetrics.precisionAt"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.RankingMetrics.precisionAt">[docs]</a> <span class="k">def</span> <span class="nf">precisionAt</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Compute the average precision of all the queries, truncated at ranking position k.</span>
<span class="sd"> If for a query, the ranking algorithm returns n (n < k) results, the precision value</span>
<span class="sd"> will be computed as #(relevant items retrieved) / k. This formula also applies when</span>
<span class="sd"> the size of the ground truth set is less than k.</span>
<span class="sd"> If a query has an empty ground truth set, zero will be used as precision together</span>
<span class="sd"> with a log warning.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"precisionAt"</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">))</span>
</div>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">meanAveragePrecision</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the mean average precision (MAP) of all the queries.</span>
<span class="sd"> If a query has an empty ground truth set, the average precision will be zero and</span>
<span class="sd"> a log warining is generated.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"meanAveragePrecision"</span><span class="p">)</span>
<div class="viewcode-block" id="RankingMetrics.ndcgAt"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.evaluation.RankingMetrics.ndcgAt">[docs]</a> <span class="k">def</span> <span class="nf">ndcgAt</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Compute the average NDCG value of all the queries, truncated at ranking position k.</span>
<span class="sd"> The discounted cumulative gain at position k is computed as:</span>
<span class="sd"> sum,,i=1,,^k^ (2^{relevance of ''i''th item}^ - 1) / log(i + 1),</span>
<span class="sd"> and the NDCG is obtained by dividing the DCG value on the ground truth set.</span>
<span class="sd"> In the current implementation, the relevance value is binary.</span>
<span class="sd"> If a query has an empty ground truth set, zero will be used as NDCG together with</span>
<span class="sd"> a log warning.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"ndcgAt"</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">))</span>
</div></div>
<span class="k">class</span> <span class="nc">MultilabelMetrics</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Evaluator for multilabel classification.</span>
<span class="sd"> :param predictionAndLabels: an RDD of (predictions, labels) pairs,</span>
<span class="sd"> both are non-null Arrays, each with</span>
<span class="sd"> unique elements.</span>
<span class="sd"> >>> predictionAndLabels = sc.parallelize([([0.0, 1.0], [0.0, 2.0]), ([0.0, 2.0], [0.0, 1.0]),</span>
<span class="sd"> ... ([], [0.0]), ([2.0], [2.0]), ([2.0, 0.0], [2.0, 0.0]),</span>
<span class="sd"> ... ([0.0, 1.0, 2.0], [0.0, 1.0]), ([1.0], [1.0, 2.0])])</span>
<span class="sd"> >>> metrics = MultilabelMetrics(predictionAndLabels)</span>
<span class="sd"> >>> metrics.precision(0.0)</span>
<span class="sd"> 1.0</span>
<span class="sd"> >>> metrics.recall(1.0)</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.f1Measure(2.0)</span>
<span class="sd"> 0.5</span>
<span class="sd"> >>> metrics.precision()</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.recall()</span>
<span class="sd"> 0.64...</span>
<span class="sd"> >>> metrics.f1Measure()</span>
<span class="sd"> 0.63...</span>
<span class="sd"> >>> metrics.microPrecision</span>
<span class="sd"> 0.72...</span>
<span class="sd"> >>> metrics.microRecall</span>
<span class="sd"> 0.66...</span>
<span class="sd"> >>> metrics.microF1Measure</span>
<span class="sd"> 0.69...</span>
<span class="sd"> >>> metrics.hammingLoss</span>
<span class="sd"> 0.33...</span>
<span class="sd"> >>> metrics.subsetAccuracy</span>
<span class="sd"> 0.28...</span>
<span class="sd"> >>> metrics.accuracy</span>
<span class="sd"> 0.54...</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">predictionAndLabels</span><span class="p">):</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">predictionAndLabels</span><span class="o">.</span><span class="n">ctx</span>
<span class="n">sql_ctx</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">sql_ctx</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">,</span>
<span class="n">schema</span><span class="o">=</span><span class="n">sql_ctx</span><span class="o">.</span><span class="n">_inferSchema</span><span class="p">(</span><span class="n">predictionAndLabels</span><span class="p">))</span>
<span class="n">java_class</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">MultilabelMetrics</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">java_class</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">MultilabelMetrics</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">precision</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns precision or precision for a given label (category) if specified.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"precision"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"precision"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">recall</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns recall or recall for a given label (category) if specified.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"recall"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"recall"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">f1Measure</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns f1Measure or f1Measure for a given label (category) if specified.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"f1Measure"</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"f1Measure"</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">))</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">microPrecision</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns micro-averaged label-based precision.</span>
<span class="sd"> (equals to micro-averaged document-based precision)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"microPrecision"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">microRecall</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns micro-averaged label-based recall.</span>
<span class="sd"> (equals to micro-averaged document-based recall)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"microRecall"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">microF1Measure</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns micro-averaged label-based f1-measure.</span>
<span class="sd"> (equals to micro-averaged document-based f1-measure)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"microF1Measure"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">hammingLoss</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns Hamming-loss.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"hammingLoss"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">subsetAccuracy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns subset accuracy.</span>
<span class="sd"> (for equal sets of labels)</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"subsetAccuracy"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">accuracy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns accuracy.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"accuracy"</span><span class="p">)</span>
<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</span> <span class="kn">import</span> <span class="n">SparkContext</span>
<span class="kn">import</span> <span class="nn">pyspark.mllib.evaluation</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">evaluation</span><span class="o">.</span><span class="n">__dict__</span><span class="o">.</span><span class="n">copy</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">SparkContext</span><span class="p">(</span><span class="s">'local[4]'</span><span class="p">,</span> <span class="s">'PythonTest'</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 1.5.0 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>
|
