-
Notifications
You must be signed in to change notification settings - Fork 62
/
algorithms.html
807 lines (603 loc) · 85.7 KB
/
algorithms.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>analyzer.algorithms — Skyline 1.0.4-dev documentation</title>
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../_static/skyline.styles.css" type="text/css" />
<link rel="top" title="Skyline 1.0.4-dev documentation" href="../../index.html"/>
<link rel="up" title="Module code" href="../index.html"/>
<script src="../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../index.html" class="icon icon-home"> Skyline
</a>
<div class="version">
1.0
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../requirements.html">Requirements</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../getting-started.html">Getting started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../running-in-python-virtualenv.html">Running Skyline in a Python virtualenv</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../upgrading.html">Upgrading</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../getting-data-into-skyline.html">Getting data into Skyline</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../alert-testing.html">Alert testing</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../horizon.html">Horizon</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../analyzer.html">Analyzer</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../analyzer-optimizations.html">Analyzer Optimizations</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../mirage.html">Mirage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../boundary.html">Boundary</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../crucible.html">Crucible</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../panorama.html">Panorama</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../webapp.html">Webapp</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../redis-integration.html">Redis integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../skyline-and-friends.html">Skyline and friends</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../logging.html">Logging</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../tuning-tips.html">Tuning tips</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../tuning-tips.html#smaller-deployments">Smaller deployments</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../tuning-tips.html#reliability">Reliability</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../monitoring-skyline.html">Monitoring Skyline</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../debian-and-vagrant-installation-tips.html">Debian and Vagrant Installation Tips</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../building-documentation.html">Building documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../releases.html">Release Notes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../whats-new.html">What’s new</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../development/index.html">Development</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../roadmap.html">Roadmap</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../skyline.html">skyline package</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../index.html">Skyline</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index.html">Docs</a> »</li>
<li><a href="../index.html">Module code</a> »</li>
<li>analyzer.algorithms</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for analyzer.algorithms</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">pandas</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">scipy</span>
<span class="kn">import</span> <span class="nn">statsmodels.api</span> <span class="kn">as</span> <span class="nn">sm</span>
<span class="kn">import</span> <span class="nn">traceback</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">from</span> <span class="nn">time</span> <span class="kn">import</span> <span class="n">time</span>
<span class="kn">import</span> <span class="nn">os.path</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">from</span> <span class="nn">os</span> <span class="kn">import</span> <span class="n">getpid</span>
<span class="kn">from</span> <span class="nn">timeit</span> <span class="kn">import</span> <span class="n">default_timer</span> <span class="k">as</span> <span class="n">timer</span>
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">realpath</span><span class="p">(</span><span class="n">__file__</span><span class="p">)),</span> <span class="n">os</span><span class="o">.</span><span class="n">pardir</span><span class="p">))</span>
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">__file__</span><span class="p">))</span>
<span class="kn">from</span> <span class="nn">settings</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">ALGORITHMS</span><span class="p">,</span>
<span class="n">CONSENSUS</span><span class="p">,</span>
<span class="n">FULL_DURATION</span><span class="p">,</span>
<span class="n">MAX_TOLERABLE_BOREDOM</span><span class="p">,</span>
<span class="n">MIN_TOLERABLE_LENGTH</span><span class="p">,</span>
<span class="n">STALE_PERIOD</span><span class="p">,</span>
<span class="n">REDIS_SOCKET_PATH</span><span class="p">,</span>
<span class="n">ENABLE_SECOND_ORDER</span><span class="p">,</span>
<span class="n">BOREDOM_SET_SIZE</span><span class="p">,</span>
<span class="n">PANDAS_VERSION</span><span class="p">,</span>
<span class="n">RUN_OPTIMIZED_WORKFLOW</span><span class="p">,</span>
<span class="n">SKYLINE_TMP_DIR</span><span class="p">,</span>
<span class="n">ENABLE_ALGORITHM_RUN_METRICS</span><span class="p">,</span>
<span class="n">ENABLE_ALL_ALGORITHMS_RUN_METRICS</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">from</span> <span class="nn">algorithm_exceptions</span> <span class="kn">import</span> <span class="o">*</span>
<span class="n">skyline_app</span> <span class="o">=</span> <span class="s1">'analyzer'</span>
<span class="n">skyline_app_logger</span> <span class="o">=</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">Log'</span> <span class="o">%</span> <span class="n">skyline_app</span>
<span class="n">logger</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="n">skyline_app_logger</span><span class="p">)</span>
<span class="k">if</span> <span class="n">ENABLE_SECOND_ORDER</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">redis</span> <span class="kn">import</span> <span class="n">StrictRedis</span>
<span class="kn">from</span> <span class="nn">msgpack</span> <span class="kn">import</span> <span class="n">unpackb</span><span class="p">,</span> <span class="n">packb</span>
<span class="n">redis_conn</span> <span class="o">=</span> <span class="n">StrictRedis</span><span class="p">(</span><span class="n">unix_socket_path</span><span class="o">=</span><span class="n">REDIS_SOCKET_PATH</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">send_algorithm_run_metrics</span> <span class="o">=</span> <span class="n">ENABLE_ALGORITHM_RUN_METRICS</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">send_algorithm_run_metrics</span> <span class="o">=</span> <span class="bp">False</span>
<span class="sd">"""</span>
<span class="sd">This is no man's land. Do anything you want in here,</span>
<span class="sd">as long as you return a boolean that determines whether the input timeseries is</span>
<span class="sd">anomalous or not.</span>
<span class="sd">The key here is to return a True or False boolean.</span>
<span class="sd">You should use the pythonic except mechanism to ensure any excpetions do not</span>
<span class="sd">cause things to halt and the record_algorithm_error utility can be used to</span>
<span class="sd">sample any algorithm errors to log.</span>
<span class="sd">To add an algorithm, define it here, and add its name to settings.ALGORITHMS.</span>
<span class="sd">"""</span>
<div class="viewcode-block" id="tail_avg"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.tail_avg">[docs]</a><span class="k">def</span> <span class="nf">tail_avg</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This is a utility function used to calculate the average of the last three</span>
<span class="sd"> datapoints in the series as a measure, instead of just the last datapoint.</span>
<span class="sd"> It reduces noise, but it also reduces sensitivity and increases the delay</span>
<span class="sd"> to detection.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">t</span> <span class="o">=</span> <span class="p">(</span><span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">3</span><span class="p">][</span><span class="mi">1</span><span class="p">])</span> <span class="o">/</span> <span class="mi">3</span>
<span class="k">return</span> <span class="n">t</span>
<span class="k">except</span> <span class="ne">IndexError</span><span class="p">:</span>
<span class="k">return</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span></div>
<div class="viewcode-block" id="median_absolute_deviation"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.median_absolute_deviation">[docs]</a><span class="k">def</span> <span class="nf">median_absolute_deviation</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the deviation of its latest datapoint with</span>
<span class="sd"> respect to the median is X times larger than the median of deviations.</span>
<span class="sd"> """</span>
<span class="c1"># logger.info('Running ' + str(get_function_name()))</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">median</span> <span class="o">=</span> <span class="n">series</span><span class="o">.</span><span class="n">median</span><span class="p">()</span>
<span class="n">demedianed</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">series</span> <span class="o">-</span> <span class="n">median</span><span class="p">)</span>
<span class="n">median_deviation</span> <span class="o">=</span> <span class="n">demedianed</span><span class="o">.</span><span class="n">median</span><span class="p">()</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span>
<span class="c1"># The test statistic is infinite when the median is zero,</span>
<span class="c1"># so it becomes super sensitive. We play it safe and skip when this happens.</span>
<span class="k">if</span> <span class="n">median_deviation</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="k">if</span> <span class="n">PANDAS_VERSION</span> <span class="o"><</span> <span class="s1">'0.17.0'</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">test_statistic</span> <span class="o">=</span> <span class="n">demedianed</span><span class="o">.</span><span class="n">iget</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">/</span> <span class="n">median_deviation</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">test_statistic</span> <span class="o">=</span> <span class="n">demedianed</span><span class="o">.</span><span class="n">iat</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">/</span> <span class="n">median_deviation</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span>
<span class="c1"># Completely arbitary...triggers if the median deviation is</span>
<span class="c1"># 6 times bigger than the median</span>
<span class="k">if</span> <span class="n">test_statistic</span> <span class="o">></span> <span class="mi">6</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="c1"># As per https://github.com/etsy/skyline/pull/104 by @rugger74</span>
<span class="c1"># Although never seen this should return False if not > arbitary_value</span>
<span class="c1"># 20160523 @earthgecko</span>
<span class="k">return</span> <span class="bp">False</span></div>
<div class="viewcode-block" id="grubbs"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.grubbs">[docs]</a><span class="k">def</span> <span class="nf">grubbs</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the Z score is greater than the Grubb's score.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">series</span><span class="p">)</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">series</span><span class="p">)</span>
<span class="n">tail_average</span> <span class="o">=</span> <span class="n">tail_avg</span><span class="p">(</span><span class="n">timeseries</span><span class="p">)</span>
<span class="n">z_score</span> <span class="o">=</span> <span class="p">(</span><span class="n">tail_average</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">/</span> <span class="n">stdDev</span>
<span class="n">len_series</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">series</span><span class="p">)</span>
<span class="n">threshold</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">stats</span><span class="o">.</span><span class="n">t</span><span class="o">.</span><span class="n">isf</span><span class="p">(</span><span class="o">.</span><span class="mo">05</span> <span class="o">/</span> <span class="p">(</span><span class="mi">2</span> <span class="o">*</span> <span class="n">len_series</span><span class="p">),</span> <span class="n">len_series</span> <span class="o">-</span> <span class="mi">2</span><span class="p">)</span>
<span class="n">threshold_squared</span> <span class="o">=</span> <span class="n">threshold</span> <span class="o">*</span> <span class="n">threshold</span>
<span class="n">grubbs_score</span> <span class="o">=</span> <span class="p">((</span><span class="n">len_series</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="n">len_series</span><span class="p">))</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="n">threshold_squared</span> <span class="o">/</span> <span class="p">(</span><span class="n">len_series</span> <span class="o">-</span> <span class="mi">2</span> <span class="o">+</span> <span class="n">threshold_squared</span><span class="p">))</span>
<span class="k">return</span> <span class="n">z_score</span> <span class="o">></span> <span class="n">grubbs_score</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="first_hour_average"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.first_hour_average">[docs]</a><span class="k">def</span> <span class="nf">first_hour_average</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Calcuate the simple average over one hour, FULL_DURATION seconds ago.</span>
<span class="sd"> A timeseries is anomalous if the average of the last three datapoints</span>
<span class="sd"> are outside of three standard deviations of this value.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">last_hour_threshold</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="p">(</span><span class="n">FULL_DURATION</span> <span class="o">-</span> <span class="mi">3600</span><span class="p">)</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span> <span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="n">last_hour_threshold</span><span class="p">])</span>
<span class="n">mean</span> <span class="o">=</span> <span class="p">(</span><span class="n">series</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="p">(</span><span class="n">series</span><span class="p">)</span><span class="o">.</span><span class="n">std</span><span class="p">()</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">tail_avg</span><span class="p">(</span><span class="n">timeseries</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">t</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="stddev_from_average"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.stddev_from_average">[docs]</a><span class="k">def</span> <span class="nf">stddev_from_average</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the absolute value of the average of the latest</span>
<span class="sd"> three datapoint minus the moving average is greater than three standard</span>
<span class="sd"> deviations of the average. This does not exponentially weight the MA and so</span>
<span class="sd"> is better for detecting anomalies with respect to the entire series.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">series</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="n">series</span><span class="o">.</span><span class="n">std</span><span class="p">()</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">tail_avg</span><span class="p">(</span><span class="n">timeseries</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">t</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="stddev_from_moving_average"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.stddev_from_moving_average">[docs]</a><span class="k">def</span> <span class="nf">stddev_from_moving_average</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the absolute value of the average of the latest</span>
<span class="sd"> three datapoint minus the moving average is greater than three standard</span>
<span class="sd"> deviations of the moving average. This is better for finding anomalies with</span>
<span class="sd"> respect to the short term trends.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="k">if</span> <span class="n">PANDAS_VERSION</span> <span class="o"><</span> <span class="s1">'0.18.0'</span><span class="p">:</span>
<span class="n">expAverage</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">stats</span><span class="o">.</span><span class="n">moments</span><span class="o">.</span><span class="n">ewma</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">com</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">stats</span><span class="o">.</span><span class="n">moments</span><span class="o">.</span><span class="n">ewmstd</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">com</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">expAverage</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="o">.</span><span class="n">ewm</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">ignore_na</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">min_periods</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">adjust</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">com</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="o">.</span><span class="n">ewm</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">ignore_na</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">min_periods</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">adjust</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">com</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">bias</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
<span class="k">if</span> <span class="n">PANDAS_VERSION</span> <span class="o"><</span> <span class="s1">'0.17.0'</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">series</span><span class="o">.</span><span class="n">iget</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">-</span> <span class="n">expAverage</span><span class="o">.</span><span class="n">iget</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">))</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span><span class="o">.</span><span class="n">iget</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">series</span><span class="o">.</span><span class="n">iat</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">-</span> <span class="n">expAverage</span><span class="o">.</span><span class="n">iat</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span><span class="o">.</span><span class="n">iat</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="c1"># http://stackoverflow.com/questions/28757389/loc-vs-iloc-vs-ix-vs-at-vs-iat</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="mean_subtraction_cumulation"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.mean_subtraction_cumulation">[docs]</a><span class="k">def</span> <span class="nf">mean_subtraction_cumulation</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the value of the next datapoint in the</span>
<span class="sd"> series is farther than three standard deviations out in cumulative terms</span>
<span class="sd"> after subtracting the mean from each data point.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">else</span> <span class="mi">0</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">series</span> <span class="o">-</span> <span class="n">series</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="nb">len</span><span class="p">(</span><span class="n">series</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="n">series</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="nb">len</span><span class="p">(</span><span class="n">series</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">std</span><span class="p">()</span>
<span class="k">if</span> <span class="n">PANDAS_VERSION</span> <span class="o"><</span> <span class="s1">'0.18.0'</span><span class="p">:</span>
<span class="n">expAverage</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">stats</span><span class="o">.</span><span class="n">moments</span><span class="o">.</span><span class="n">ewma</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">com</span><span class="o">=</span><span class="mi">15</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">expAverage</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="o">.</span><span class="n">ewm</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">ignore_na</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">min_periods</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">adjust</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">com</span><span class="o">=</span><span class="mi">15</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="k">if</span> <span class="n">PANDAS_VERSION</span> <span class="o"><</span> <span class="s1">'0.17.0'</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">series</span><span class="o">.</span><span class="n">iget</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">))</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">series</span><span class="o">.</span><span class="n">iat</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="least_squares"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.least_squares">[docs]</a><span class="k">def</span> <span class="nf">least_squares</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the average of the last three datapoints</span>
<span class="sd"> on a projected least squares model is greater than three sigma.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">t</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">t</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">A</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">vstack</span><span class="p">([</span><span class="n">x</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">))])</span><span class="o">.</span><span class="n">T</span>
<span class="n">results</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">lstsq</span><span class="p">(</span><span class="n">A</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
<span class="n">residual</span> <span class="o">=</span> <span class="n">results</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="n">m</span><span class="p">,</span> <span class="n">c</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">lstsq</span><span class="p">(</span><span class="n">A</span><span class="p">,</span> <span class="n">y</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">errors</span> <span class="o">=</span> <span class="p">[]</span>
<span class="c1"># Evaluate append once, not every time in the loop - this gains ~0.020 s on</span>
<span class="c1"># every timeseries potentially @earthgecko #1310</span>
<span class="n">append_error</span> <span class="o">=</span> <span class="n">errors</span><span class="o">.</span><span class="n">append</span>
<span class="c1"># Further a question exists related to performance and accruracy with</span>
<span class="c1"># regards to how many datapoints are in the sample, currently all datapoints</span>
<span class="c1"># are used but this may not be the ideal or most efficient computation or</span>
<span class="c1"># fit for a timeseries... @earthgecko is checking graphite...</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">y</span><span class="p">):</span>
<span class="n">projected</span> <span class="o">=</span> <span class="n">m</span> <span class="o">*</span> <span class="n">x</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="n">c</span>
<span class="n">error</span> <span class="o">=</span> <span class="n">value</span> <span class="o">-</span> <span class="n">projected</span>
<span class="c1"># errors.append(error) # @earthgecko #1310</span>
<span class="n">append_error</span><span class="p">(</span><span class="n">error</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">errors</span><span class="p">)</span> <span class="o"><</span> <span class="mi">3</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="n">std_dev</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">errors</span><span class="p">)</span>
<span class="n">t</span> <span class="o">=</span> <span class="p">(</span><span class="n">errors</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="n">errors</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">]</span> <span class="o">+</span> <span class="n">errors</span><span class="p">[</span><span class="o">-</span><span class="mi">3</span><span class="p">])</span> <span class="o">/</span> <span class="mi">3</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">t</span><span class="p">)</span> <span class="o">></span> <span class="n">std_dev</span> <span class="o">*</span> <span class="mi">3</span> <span class="ow">and</span> <span class="nb">round</span><span class="p">(</span><span class="n">std_dev</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="nb">round</span><span class="p">(</span><span class="n">t</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">0</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="histogram_bins"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.histogram_bins">[docs]</a><span class="k">def</span> <span class="nf">histogram_bins</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if the average of the last three datapoints falls</span>
<span class="sd"> into a histogram bin with less than 20 other datapoints (you'll need to tweak</span>
<span class="sd"> that number depending on your data)</span>
<span class="sd"> Returns: the size of the bin which contains the tail_avg. Smaller bin size</span>
<span class="sd"> means more anomalous.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">tail_avg</span><span class="p">(</span><span class="n">timeseries</span><span class="p">)</span>
<span class="n">h</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">histogram</span><span class="p">(</span><span class="n">series</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="mi">15</span><span class="p">)</span>
<span class="n">bins</span> <span class="o">=</span> <span class="n">h</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="k">for</span> <span class="n">index</span><span class="p">,</span> <span class="n">bin_size</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">h</span><span class="p">[</span><span class="mi">0</span><span class="p">]):</span>
<span class="k">if</span> <span class="n">bin_size</span> <span class="o"><=</span> <span class="mi">20</span><span class="p">:</span>
<span class="c1"># Is it in the first bin?</span>
<span class="k">if</span> <span class="n">index</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">if</span> <span class="n">t</span> <span class="o"><=</span> <span class="n">bins</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="c1"># Is it in the current bin?</span>
<span class="k">elif</span> <span class="n">t</span> <span class="o">>=</span> <span class="n">bins</span><span class="p">[</span><span class="n">index</span><span class="p">]</span> <span class="ow">and</span> <span class="n">t</span> <span class="o"><</span> <span class="n">bins</span><span class="p">[</span><span class="n">index</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]:</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span></div>
<div class="viewcode-block" id="ks_test"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.ks_test">[docs]</a><span class="k">def</span> <span class="nf">ks_test</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A timeseries is anomalous if 2 sample Kolmogorov-Smirnov test indicates</span>
<span class="sd"> that data distribution for last 10 minutes is different from last hour.</span>
<span class="sd"> It produces false positives on non-stationary series so Augmented</span>
<span class="sd"> Dickey-Fuller test applied to check for stationarity.</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">hour_ago</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="mi">3600</span>
<span class="n">ten_minutes_ago</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="mi">600</span>
<span class="n">reference</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span> <span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">>=</span> <span class="n">hour_ago</span> <span class="ow">and</span> <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="n">ten_minutes_ago</span><span class="p">])</span>
<span class="n">probe</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span> <span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">>=</span> <span class="n">ten_minutes_ago</span><span class="p">])</span>
<span class="k">if</span> <span class="n">reference</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">20</span> <span class="ow">or</span> <span class="n">probe</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">20</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="n">ks_d</span><span class="p">,</span> <span class="n">ks_p_value</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">stats</span><span class="o">.</span><span class="n">ks_2samp</span><span class="p">(</span><span class="n">reference</span><span class="p">,</span> <span class="n">probe</span><span class="p">)</span>
<span class="k">if</span> <span class="n">ks_p_value</span> <span class="o"><</span> <span class="mf">0.05</span> <span class="ow">and</span> <span class="n">ks_d</span> <span class="o">></span> <span class="mf">0.5</span><span class="p">:</span>
<span class="n">adf</span> <span class="o">=</span> <span class="n">sm</span><span class="o">.</span><span class="n">tsa</span><span class="o">.</span><span class="n">stattools</span><span class="o">.</span><span class="n">adfuller</span><span class="p">(</span><span class="n">reference</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
<span class="k">if</span> <span class="n">adf</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><</span> <span class="mf">0.05</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">traceback_format_exc_string</span> <span class="o">=</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">()</span>
<span class="n">algorithm_name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">get_function_name</span><span class="p">())</span>
<span class="n">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">None</span>
<span class="k">return</span> <span class="bp">False</span></div>
<span class="sd">"""</span>
<span class="sd">THE END of NO MAN'S LAND</span>
<span class="sd">THE START of UTILITY FUNCTIONS</span>
<span class="sd">"""</span>
<div class="viewcode-block" id="get_function_name"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.get_function_name">[docs]</a><span class="k">def</span> <span class="nf">get_function_name</span><span class="p">():</span>
<span class="sd">"""</span>
<span class="sd"> This is a utility function is used to determine what algorithm is reporting</span>
<span class="sd"> an algorithm error when the record_algorithm_error is used.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">traceback</span><span class="o">.</span><span class="n">extract_stack</span><span class="p">(</span><span class="bp">None</span><span class="p">,</span> <span class="mi">2</span><span class="p">)[</span><span class="mi">0</span><span class="p">][</span><span class="mi">2</span><span class="p">]</span></div>
<div class="viewcode-block" id="record_algorithm_error"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.record_algorithm_error">[docs]</a><span class="k">def</span> <span class="nf">record_algorithm_error</span><span class="p">(</span><span class="n">algorithm_name</span><span class="p">,</span> <span class="n">traceback_format_exc_string</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This utility function is used to facilitate the traceback from any algorithm</span>
<span class="sd"> errors. The algorithm functions themselves we want to run super fast and</span>
<span class="sd"> without fail in terms of stopping the function returning and not reporting</span>
<span class="sd"> anything to the log, so the pythonic except is used to "sample" any</span>
<span class="sd"> algorithm errors to a tmp file and report once per run rather than spewing</span>
<span class="sd"> tons of errors into the log.</span>
<span class="sd"> .. note::</span>
<span class="sd"> algorithm errors tmp file clean up</span>
<span class="sd"> the algorithm error tmp files are handled and cleaned up in</span>
<span class="sd"> :class:`Analyzer` after all the spawned processes are completed.</span>
<span class="sd"> :param algorithm_name: the algoritm function name</span>
<span class="sd"> :type algorithm_name: str</span>
<span class="sd"> :param traceback_format_exc_string: the traceback_format_exc string</span>
<span class="sd"> :type traceback_format_exc_string: str</span>
<span class="sd"> :return:</span>
<span class="sd"> - ``True`` the error string was written to the algorithm_error_file</span>
<span class="sd"> - ``False`` the error string was not written to the algorithm_error_file</span>
<span class="sd"> :rtype:</span>
<span class="sd"> - boolean</span>
<span class="sd"> """</span>
<span class="n">current_process_pid</span> <span class="o">=</span> <span class="n">getpid</span><span class="p">()</span>
<span class="n">algorithm_error_file</span> <span class="o">=</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">/</span><span class="si">%s</span><span class="s1">.</span><span class="si">%s</span><span class="s1">.</span><span class="si">%s</span><span class="s1">.algorithm.error'</span> <span class="o">%</span> <span class="p">(</span>
<span class="n">SKYLINE_TMP_DIR</span><span class="p">,</span> <span class="n">skyline_app</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">current_process_pid</span><span class="p">),</span> <span class="n">algorithm_name</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">algorithm_error_file</span><span class="p">,</span> <span class="s1">'w'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">traceback_format_exc_string</span><span class="p">))</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="k">except</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">False</span></div>
<div class="viewcode-block" id="determine_median"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.determine_median">[docs]</a><span class="k">def</span> <span class="nf">determine_median</span><span class="p">(</span><span class="n">timeseries</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Determine the median of the values in the timeseries</span>
<span class="sd"> """</span>
<span class="c1"># logger.info('Running ' + str(get_function_name()))</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">np_array</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">])</span>
<span class="k">except</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">array_median</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">np_array</span><span class="p">)</span>
<span class="k">return</span> <span class="n">array_median</span>
<span class="k">except</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="k">return</span> <span class="bp">False</span></div>
<div class="viewcode-block" id="is_anomalously_anomalous"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.is_anomalously_anomalous">[docs]</a><span class="k">def</span> <span class="nf">is_anomalously_anomalous</span><span class="p">(</span><span class="n">metric_name</span><span class="p">,</span> <span class="n">ensemble</span><span class="p">,</span> <span class="n">datapoint</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This method runs a meta-analysis on the metric to determine whether the</span>
<span class="sd"> metric has a past history of triggering. TODO: weight intervals based on datapoint</span>
<span class="sd"> """</span>
<span class="c1"># We want the datapoint to avoid triggering twice on the same data</span>
<span class="n">new_trigger</span> <span class="o">=</span> <span class="p">[</span><span class="n">time</span><span class="p">(),</span> <span class="n">datapoint</span><span class="p">]</span>
<span class="c1"># Get the old history</span>
<span class="n">raw_trigger_history</span> <span class="o">=</span> <span class="n">redis_conn</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'trigger_history.'</span> <span class="o">+</span> <span class="n">metric_name</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">raw_trigger_history</span><span class="p">:</span>
<span class="n">redis_conn</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="s1">'trigger_history.'</span> <span class="o">+</span> <span class="n">metric_name</span><span class="p">,</span> <span class="n">packb</span><span class="p">([(</span><span class="n">time</span><span class="p">(),</span> <span class="n">datapoint</span><span class="p">)]))</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="n">trigger_history</span> <span class="o">=</span> <span class="n">unpackb</span><span class="p">(</span><span class="n">raw_trigger_history</span><span class="p">)</span>
<span class="c1"># Are we (probably) triggering on the same data?</span>
<span class="k">if</span> <span class="p">(</span><span class="n">new_trigger</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="n">trigger_history</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span> <span class="ow">and</span>
<span class="n">new_trigger</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">-</span> <span class="n">trigger_history</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> <span class="o"><=</span> <span class="mi">300</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">False</span>
<span class="c1"># Update the history</span>
<span class="n">trigger_history</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">new_trigger</span><span class="p">)</span>
<span class="n">redis_conn</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="s1">'trigger_history.'</span> <span class="o">+</span> <span class="n">metric_name</span><span class="p">,</span> <span class="n">packb</span><span class="p">(</span><span class="n">trigger_history</span><span class="p">))</span>
<span class="c1"># Should we surface the anomaly?</span>
<span class="n">trigger_times</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">trigger_history</span><span class="p">]</span>
<span class="n">intervals</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">trigger_times</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> <span class="o">-</span> <span class="n">trigger_times</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">trigger_times</span><span class="p">)</span>
<span class="k">if</span> <span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">trigger_times</span><span class="p">)</span>
<span class="p">]</span>
<span class="n">series</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">Series</span><span class="p">(</span><span class="n">intervals</span><span class="p">)</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">series</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="n">stdDev</span> <span class="o">=</span> <span class="n">series</span><span class="o">.</span><span class="n">std</span><span class="p">()</span>
<span class="k">return</span> <span class="nb">abs</span><span class="p">(</span><span class="n">intervals</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">></span> <span class="mi">3</span> <span class="o">*</span> <span class="n">stdDev</span></div>
<div class="viewcode-block" id="run_selected_algorithm"><a class="viewcode-back" href="../../skyline.analyzer.html#analyzer.algorithms.run_selected_algorithm">[docs]</a><span class="k">def</span> <span class="nf">run_selected_algorithm</span><span class="p">(</span><span class="n">timeseries</span><span class="p">,</span> <span class="n">metric_name</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Filter timeseries and run selected algorithm.</span>
<span class="sd"> """</span>
<span class="c1"># Get rid of short series</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">timeseries</span><span class="p">)</span> <span class="o"><</span> <span class="n">MIN_TOLERABLE_LENGTH</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">TooShort</span><span class="p">()</span>
<span class="c1"># Get rid of stale series</span>
<span class="k">if</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> <span class="o">></span> <span class="n">STALE_PERIOD</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">Stale</span><span class="p">()</span>
<span class="c1"># Get rid of boring series</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">item</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="n">MAX_TOLERABLE_BOREDOM</span><span class="p">:]))</span> <span class="o">==</span> <span class="n">BOREDOM_SET_SIZE</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">Boring</span><span class="p">()</span>
<span class="c1"># RUN_OPTIMIZED_WORKFLOW - replaces the original ensemble method:</span>
<span class="c1"># ensemble = [globals()[algorithm](timeseries) for algorithm in ALGORITHMS]</span>
<span class="c1"># which runs all timeseries through all ALGORITHMS</span>
<span class="n">final_ensemble</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">number_of_algorithms_triggered</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">number_of_algorithms_run</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">number_of_algorithms</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">ALGORITHMS</span><span class="p">)</span>
<span class="n">maximum_false_count</span> <span class="o">=</span> <span class="n">number_of_algorithms</span> <span class="o">-</span> <span class="n">CONSENSUS</span> <span class="o">+</span> <span class="mi">1</span>
<span class="c1"># logger.info('the maximum_false_count is %s, above which CONSENSUS cannot be achieved' % (str(maximum_false_count)))</span>
<span class="n">consensus_possible</span> <span class="o">=</span> <span class="bp">True</span>
<span class="c1"># DEVELOPMENT: this is for a development version of analyzer only</span>
<span class="k">if</span> <span class="n">skyline_app</span> <span class="o">==</span> <span class="s1">'analyzer_dev'</span><span class="p">:</span>
<span class="n">time_all_algorithms</span> <span class="o">=</span> <span class="bp">True</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">time_all_algorithms</span> <span class="o">=</span> <span class="bp">False</span>
<span class="n">algorithm_tmp_file_prefix</span> <span class="o">=</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">/</span><span class="si">%s</span><span class="s1">.'</span> <span class="o">%</span> <span class="p">(</span><span class="n">SKYLINE_TMP_DIR</span><span class="p">,</span> <span class="n">skyline_app</span><span class="p">)</span>
<span class="k">for</span> <span class="n">algorithm</span> <span class="ow">in</span> <span class="n">ALGORITHMS</span><span class="p">:</span>
<span class="k">if</span> <span class="n">consensus_possible</span><span class="p">:</span>
<span class="k">if</span> <span class="n">send_algorithm_run_metrics</span><span class="p">:</span>
<span class="n">algorithm_count_file</span> <span class="o">=</span> <span class="s1">'</span><span class="si">%s%s</span><span class="s1">.count'</span> <span class="o">%</span> <span class="p">(</span><span class="n">algorithm_tmp_file_prefix</span><span class="p">,</span> <span class="n">algorithm</span><span class="p">)</span>
<span class="n">algorithm_timings_file</span> <span class="o">=</span> <span class="s1">'</span><span class="si">%s%s</span><span class="s1">.timings'</span> <span class="o">%</span> <span class="p">(</span><span class="n">algorithm_tmp_file_prefix</span><span class="p">,</span> <span class="n">algorithm</span><span class="p">)</span>
<span class="n">run_algorithm</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">run_algorithm</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">algorithm</span><span class="p">)</span>
<span class="n">number_of_algorithms_run</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">if</span> <span class="n">send_algorithm_run_metrics</span><span class="p">:</span>
<span class="n">start</span> <span class="o">=</span> <span class="n">timer</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">algorithm_result</span> <span class="o">=</span> <span class="p">[</span><span class="nb">globals</span><span class="p">()[</span><span class="n">test_algorithm</span><span class="p">](</span><span class="n">timeseries</span><span class="p">)</span> <span class="k">for</span> <span class="n">test_algorithm</span> <span class="ow">in</span> <span class="n">run_algorithm</span><span class="p">]</span>
<span class="k">except</span><span class="p">:</span>
<span class="c1"># logger.error('%s failed' % (algorithm))</span>
<span class="n">algorithm_result</span> <span class="o">=</span> <span class="p">[</span><span class="bp">None</span><span class="p">]</span>
<span class="k">if</span> <span class="n">send_algorithm_run_metrics</span><span class="p">:</span>
<span class="n">end</span> <span class="o">=</span> <span class="n">timer</span><span class="p">()</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">algorithm_count_file</span><span class="p">,</span> <span class="s1">'a'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s1">'1</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">algorithm_timings_file</span><span class="p">,</span> <span class="s1">'a'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s1">'</span><span class="si">%.6f</span><span class="se">\n</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="n">end</span> <span class="o">-</span> <span class="n">start</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">algorithm_result</span> <span class="o">=</span> <span class="p">[</span><span class="bp">False</span><span class="p">]</span>
<span class="c1"># logger.info('CONSENSUS NOT ACHIEVABLE - skipping %s' % (str(algorithm)))</span>
<span class="k">if</span> <span class="n">algorithm_result</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">True</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">True</span>
<span class="n">number_of_algorithms_triggered</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="c1"># logger.info('algorithm %s triggerred' % (str(algorithm)))</span>
<span class="k">elif</span> <span class="n">algorithm_result</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">False</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">False</span>
<span class="k">elif</span> <span class="n">algorithm_result</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">None</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">algorithm_result</span> <span class="o">=</span> <span class="bp">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">False</span>
<span class="n">final_ensemble</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">result</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">RUN_OPTIMIZED_WORKFLOW</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">if</span> <span class="n">time_all_algorithms</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">if</span> <span class="n">ENABLE_ALL_ALGORITHMS_RUN_METRICS</span><span class="p">:</span>
<span class="k">continue</span>
<span class="n">false_count</span> <span class="o">=</span> <span class="n">final_ensemble</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">False</span><span class="p">)</span>
<span class="n">true_count</span> <span class="o">=</span> <span class="n">final_ensemble</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">True</span><span class="p">)</span>
<span class="c1"># logger.info('current false_count %s' % (str(false_count)))</span>
<span class="k">if</span> <span class="n">final_ensemble</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">False</span><span class="p">)</span> <span class="o">>=</span> <span class="n">maximum_false_count</span><span class="p">:</span>
<span class="n">consensus_possible</span> <span class="o">=</span> <span class="bp">False</span>
<span class="c1"># logger.info('CONSENSUS cannot be reached as %s algorithms have already not been triggered' % (str(false_count)))</span>
<span class="n">skip_algorithms_count</span> <span class="o">=</span> <span class="n">number_of_algorithms</span> <span class="o">-</span> <span class="n">number_of_algorithms_run</span>
<span class="c1"># logger.info('skipping %s algorithms' % (str(skip_algorithms_count)))</span>
<span class="c1"># logger.info('final_ensemble: %s' % (str(final_ensemble)))</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># ensemble = [globals()[algorithm](timeseries) for algorithm in ALGORITHMS]</span>
<span class="n">ensemble</span> <span class="o">=</span> <span class="n">final_ensemble</span>
<span class="n">threshold</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">ensemble</span><span class="p">)</span> <span class="o">-</span> <span class="n">CONSENSUS</span>
<span class="k">if</span> <span class="n">ensemble</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="bp">False</span><span class="p">)</span> <span class="o"><=</span> <span class="n">threshold</span><span class="p">:</span>
<span class="k">if</span> <span class="n">ENABLE_SECOND_ORDER</span><span class="p">:</span>
<span class="k">if</span> <span class="n">is_anomalously_anomalous</span><span class="p">(</span><span class="n">metric_name</span><span class="p">,</span> <span class="n">ensemble</span><span class="p">,</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]):</span>
<span class="k">return</span> <span class="bp">True</span><span class="p">,</span> <span class="n">ensemble</span><span class="p">,</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">True</span><span class="p">,</span> <span class="n">ensemble</span><span class="p">,</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
<span class="k">return</span> <span class="bp">False</span><span class="p">,</span> <span class="n">ensemble</span><span class="p">,</span> <span class="n">timeseries</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">'Algorithm error: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">())</span>
<span class="k">return</span> <span class="bp">False</span><span class="p">,</span> <span class="p">[],</span> <span class="mi">1</span></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
© Copyright 2013-2014, Etsy Inc; 2015, Abe Stanway; 2015-2016, Gary Wilson.
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../',
VERSION:'1.0.4-dev',
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>
<script type="text/javascript" src="../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.StickyNav.enable();
});
</script>
</body>
</html>