No anomalies detected

[robin-karlsson]

In the sample for phone calls anomaly detection we noticed that you won’t get any anomalies detected with version 5.5. Running the sample with version 5.3 works.

Not sure if this is an intended change in the library requiring an update of sample data or if this is due to a problem in the TimeSeries part?

---

Document Details

⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.

• ID: 5e6266e1-f8e5-d303-7ddc-be2d6e47f831
• Version Independent ID: 2ae35df3-cf3a-ed1c-b466-a8be8a9729c3
• Content: Tutorial: Detect anomalies in phone calls - ML.NET
• Content Source: docs/machine-learning/tutorials/phone-calls-anomaly-detection.md
• Product: dotnet-ml
• GitHub Login: @luisquintanilla
• Microsoft Alias: luquinta

[luisquintanilla]

Hi @robin-karlsson

Sorry to hear you ran into issues. Would you be able to share the output / error you're getting.

Thanks

[luisquintanilla]

Thanks for raising this issue @robin-karlsson. I was able to reproduce

1.5.2 Output

Detect period of the series
Period of the series is: 7.
Detect anomaly points in the series
Index   Anomaly ExpectedValue   UpperBoundary   LowerBoundary
0,0,36.841787256739266,41.14206982401966,32.541504689458876
1,0,35.67303618137362,39.97331874865401,31.372753614093227
2,0,34.710132999891826,39.029491313022824,30.390774686760828
3,0,33.44765248883495,37.786086547816545,29.10921842985335
4,0,28.937110922276364,33.25646923540736,24.61775260914537
5,0,5.143895892785781,9.444178460066171,0.843613325505391
6,0,5.163325228419392,9.463607795699783,0.8630426611390014
7,0,36.76414836240396,41.06443092968435,32.46386579512357
8,0,35.77908590657007,40.07936847385046,31.478803339289676
9,0,34.547259536635245,38.847542103915636,30.246976969354854
10,0,33.55193524820608,37.871293561337076,29.23257693507508
11,0,29.091800129624648,33.392082696905035,24.79151756234426
12,0,5.154836630338823,9.455119197619213,0.8545540630584334
13,0,5.234332502492464,9.534615069772855,0.934049935212073
14,0,36.54992549471526,40.85020806199565,32.24964292743487
15,0,35.79526470980883,40.095547277089224,31.494982142528443
16,0,34.34099013096804,38.64127269824843,30.040707563687647
17,0,33.61201516582131,37.9122977331017,29.31173259854092
18,0,29.223563320561812,33.5238458878422,24.923280753281425
19,0,5.170512168851533,9.470794736131923,0.8702296015711433
20,0,5.2614938889462834,9.561776456226674,0.9612113216658926
21,0,36.37103858487317,40.67132115215356,32.07075601759278
22,0,35.813544599026855,40.113827166307246,31.513262031746464
23,0,34.05600492733225,38.356287494612644,29.755722360051863
24,0,33.65828319077884,37.95856575805923,29.358000623498448
25,0,29.381125690882463,33.681408258162854,25.080843123602072
26,0,5.261543539820418,9.561826107100808,0.9612609725400283
27,0,5.4873712582971805,9.787653825577571,1.1870886910167897
28,1,36.504694001629254,40.804976568909645,32.20441143434886  <-- alert is on, detected anomaly
29,0,36.056960964529836,40.35724353181023,31.756678397249445
30,0,33.88234878237759,38.18263134965798,29.5820662150972
31,0,33.92784857369604,38.085121010124574,29.770576137267504
32,0,29.945506014510265,34.1027784509388,25.78823357808173
33,0,5.878525831440632,10.035798267869167,1.7212533950120967
34,0,6.252886214212062,10.410158650640597,2.0956137777835266
35,0,37.18404534222705,41.32872980034376,33.039360884110344
36,0,36.83107452935755,40.97575898747426,32.686390071240844
37,0,34.26556446342024,38.41024892153695,30.120880005303533
38,0,34.71284744107857,38.85753189919528,30.568162982961866
39,0,30.6318593911151,34.789131827543635,26.474586954686565
40,0,5.8421334626776575,9.999405899106193,1.6848610262491217
41,0,5.315133091466097,9.472405527894633,1.1578606550375614
42,0,34.87155077154678,39.019122600615404,30.723978942478155
43,0,35.56278990178399,39.707474359900694,31.41810544366728
44,1,33.06370143379212,37.208385891908826,28.91901697567541  <-- alert is on, detected anomaly
45,0,32.49251041707055,36.637194875187255,28.34782595895384
46,0,29.042343064117933,33.18702752223464,24.89765860600123
47,0,4.699873324239948,8.844557782356654,0.5551888661232418
48,0,5.25774359828668,9.402428056403387,1.1130591401699732
49,0,34.70382982079732,38.844173613357356,30.56348602823728
50,0,36.205476696654856,40.345820489214894,32.06513290409482
51,0,35.01806767666058,39.15841146922062,30.87772388410054
52,0,33.8621356196155,38.00247941217554,29.721791827055462
53,0,30.050263511910696,34.1949479700274,25.905579053793993
54,0,5.38360786974173,9.528292327858436,1.2389234116250236
55,0,5.319212934297795,9.463897392414502,1.174528476181088
56,1,34.35814874418968,38.43248334636359,30.283814142015764  <-- alert is on, detected anomaly
57,0,34.80435115782249,38.8786857599964,30.730016555648575
58,0,32.64542281055228,36.79010726866899,28.500738352435576
59,0,30.388031426358786,34.535603255427404,26.240459597290165
60,0,28.372553851863646,32.65208360455492,24.093024099172375
61,0,4.054080143996516,8.333609896687783,-0.22544960869475084
62,0,4.708195658058664,8.987725410749931,0.42866590536739757
63,0,34.596454086638985,38.74402591570761,30.44888225757036
64,0,35.324588715619726,39.47216054468835,31.1770168865511
65,0,33.738156132843564,37.849109348464836,29.62720291722229
66,0,33.210967276887935,37.28530187906185,29.136632674714022
67,0,29.552710321333503,33.62704492350742,25.478375719159587
68,0,4.799342685155514,8.873677287329429,0.7250080829815992
69,0,5.244467834526498,9.421400011959088,1.0675356570939076
70,1,35.22957940044675,39.50910915313802,30.950049647755485  <-- alert is on, detected anomaly
71,0,35.72010274618195,39.89703492361454,31.54317056874936
72,0,34.31525818437954,38.38959278655345,30.240923582205625
73,0,33.46142030440133,37.63835248183392,29.28448812696874
74,0,29.799690914683158,34.07922066737443,25.520161161991886
75,0,4.762673307392623,9.061342947775344,0.4640036670099015
76,0,5.041497330134712,9.359306858208885,0.7236878020605388
77,0,35.1453728688598,39.47845435705336,30.812291380666245

1.5.5 Output

Detect period of the series
Period of the series is: 7.
Detect anomaly points in the series
Index   Anomaly ExpectedValue   UpperBoundary   LowerBoundary
0,0,36.841787256739266,57.91634186966726,15.767232643811276
1,0,35.67303618137362,56.74759079430161,14.598481568445628
2,0,34.710132999891826,55.87815572801981,13.542110271763839
3,0,33.44765248883495,54.70914333216294,12.186161645506957
4,0,28.937110922276364,50.105133650404355,7.769088194148374
5,0,5.143895892785781,26.218450505713772,-15.930658720142208
6,0,5.163325228419392,26.237879841347382,-15.911229384508598
7,0,36.76414836240396,57.83870297533195,15.689593749475968
8,0,35.77908590657007,56.85364051949806,14.704531293642077
9,0,34.547259536635245,55.621814149563235,13.472704923707255
10,0,33.55193524820608,54.719957976334065,12.383912520078091
11,0,29.091800129624648,50.16635474255264,8.017245516696654
12,0,5.154836630338823,26.229391243266814,-15.919717982589166
13,0,5.234332502492464,26.308887115420454,-15.840222110435526
14,0,36.54992549471526,57.62448010764325,15.47537088178727
15,0,35.79526470980883,56.869819322736824,14.720710096880843
16,0,34.34099013096804,55.41554474389603,13.266435518040048
17,0,33.61201516582131,54.6865697787493,12.537460552893322
18,0,29.223563320561812,50.298117933489806,8.149008707633818
19,0,5.170512168851533,26.245066781779524,-15.904042444076456
20,0,5.2614938889462834,26.336048501874274,-15.813060723981707
21,0,36.37103858487317,57.44559319780116,15.296483971945179
22,0,35.813544599026855,56.888099211954845,14.738989986098865
23,0,34.05600492733225,55.13055954026024,12.981450314404263
24,0,33.65828319077884,54.73283780370683,12.583728577850849
25,0,29.381125690882463,50.45568030381045,8.306571077954473
26,0,5.261543539820418,26.33609815274841,-15.813011073107571
27,0,5.4873712582971805,26.56192587122517,-15.58718335463081
28,0,32.780765740881456,53.85532035380945,11.706211127953466
29,0,36.056960964529836,57.131515577457826,14.982406351601846
30,0,33.88234878237759,54.95690339530558,12.8077941694496
31,0,33.92784857369604,54.301676332224034,13.554020815168045
32,0,29.945506014510265,50.31933377303825,9.571678255982278
33,0,5.878525831440632,26.25235358996862,-14.495301927087356
34,0,6.252886214212062,26.626713972740053,-14.12094154431593
35,0,37.18404534222705,57.49619401275504,16.871896671699062
36,0,36.83107452935755,57.14322319988554,16.51892585882956
37,0,34.376155062464,54.68830373299199,14.064006391936012
38,0,34.71284744107857,55.02499611160656,14.400698770550584
39,0,30.6318593911151,51.005687149643094,10.258031632587105
40,0,5.8421334626776575,26.21596122120565,-14.531694295850333
41,0,5.315133091466097,25.68896084999409,-15.058694667061893
42,0,34.87155077154678,55.197847099674775,14.545254443418784
43,0,35.56278990178399,55.874938572311976,15.250641231255997
44,0,23.336790657536003,43.64893932806399,3.024641987008014
45,0,32.49251041707055,52.80465908759854,12.180361746542559
46,0,29.042343064117933,49.35449173464592,8.730194393589947
47,0,4.699873324239948,25.012021994767938,-15.61227534628804
48,0,5.25774359828668,25.56989226881467,-15.054405072241309
49,0,34.814013762209456,55.10489386313744,14.52313366128147
50,0,36.205476696654856,56.49635679758285,15.914596595726863
51,0,35.01806767666058,55.30894777758857,14.727187575732586
52,0,33.8621356196155,54.15301572054349,13.571255518687508
53,0,30.050263511910696,50.36241218243869,9.738114841382703
54,0,5.38360786974173,25.69575654026972,-14.928540800786259
55,0,5.319212934297795,25.631361604825784,-14.992935736230194
56,0,27.980095314481456,47.94754090020945,8.01264972875347
57,0,34.80435115782249,54.77179674355048,14.836905572094494
58,0,32.710506482464,53.02265515299199,12.398357811936009
59,0,30.127693840554183,50.453990168682175,9.801397512426192
60,0,28.372553851863646,49.34542297999164,7.399684723735653
61,0,4.054080143996516,25.026949272124504,-16.918788984131474
62,0,4.708195658058664,25.681064786186653,-16.264673470069326
63,0,34.596454086638985,54.92275041476698,14.27015775851099
64,0,35.324588715619726,55.65088504374772,14.99829238749173
65,0,33.738156132843564,53.885027089771555,13.591285175915573
66,0,33.210967276887935,53.17841286261593,13.243521691159941
67,0,29.552710321333503,49.52015590706149,9.585264735605513
68,0,4.5436067444814565,24.511052330209452,-15.423838841246537
69,0,5.244467834526498,25.714625191454488,-15.225689522401494
70,0,43.785900220354904,64.7587693484829,22.813031092226915
71,0,35.72010274618195,56.19026010310994,15.24994538925396
72,0,34.31525818437954,54.28270377010753,14.347812598651544
73,0,33.46142030440133,53.93157766132932,12.991262947473338
74,0,29.799690914683158,50.77256004281115,8.826821786555165
75,0,4.762673307392623,25.82932483552061,-16.30397822073536
76,0,5.041497330134712,26.201931258262704,-16.118936597993283
77,0,35.1453728688598,56.380636968187794,13.91010876953181

[luisquintanilla]

@guinao @michaelgsharp thoughts?

[robin-karlsson]

Hi @robin-karlsson

Sorry to hear you ran into issues. Would you be able to share the output / error you're getting.

Thanks

@luisquintanilla I saw that you managed to reproduce now. Please give me a ping if you need me for something else. I can confirm that my output looked very similar to yours.

Thanks

[luisquintanilla]

Hi @robin-karlsson apologies for the delay on this.

I just tried the latest version 1.6.0 to see if it works and the issue persist. This does not seem to be a documentation issue as you can get it working with version 1.5.2.

I've raised an issue on the dotnet/machinelearning repo to track this. In the meantime, I'll update the document to specify you need to use version 1.5.2 and close the issue. To track the progress of this, please see dotnet/machinelearning#5891

Thanks again for bringing this to our attention.