{"id":35274,"date":"2019-10-31T22:03:22","date_gmt":"2019-10-31T19:03:22","guid":{"rendered":"https:\/\/prohoster.info\/blog\/razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk\/"},"modified":"2019-10-31T22:03:22","modified_gmt":"2019-10-31T19:03:22","slug":"razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk","title":{"rendered":"T\u00eb kuptojm\u00eb Machine Learning n\u00eb Elastic Stack (nj\u00ebsoj Elasticsearch, nj\u00ebsoj ELK)","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

\"T\u00eb
\n
\nKujtojm\u00eb se thelbi i Elastic Stack p\u00ebrb\u00ebhet nga nj\u00eb baz\u00eb t\u00eb dh\u00ebnash jo-relacionale Elasticsearch, nd\u00ebrfaqe web Kibana dhe mbledh\u00ebs-p\u00ebrpunues t\u00eb t\u00eb dh\u00ebnave (m\u00eb i njohuri \u00ebsht\u00eb Logstash, Beats t\u00eb ndrysh\u00ebm, APM dhe t\u00eb tjer\u00eb). Nj\u00eb nga shtesat e k\u00ebndshme t\u00eb t\u00eb gjith\u00eb k\u00ebtij stoku produktesh \u00ebsht\u00eb analiza e t\u00eb dh\u00ebnave p\u00ebrmes algoritmeve t\u00eb m\u00ebsimit t\u00eb makineris\u00eb. N\u00eb k\u00ebt\u00eb artikull ne shpjegojm\u00eb se \u00e7far\u00eb p\u00ebrfaq\u00ebsojn\u00eb k\u00ebta algoritme. Ju lutemi, ndiqni p\u00ebr m\u00eb shum\u00eb.
\n<\/a><\/noindex>
\nM\u00ebsimi i makineris\u00eb \u00ebsht\u00eb nj\u00eb funksion me pages\u00eb i Elastic Stack q\u00eb \u00ebsht\u00eb kushtimisht falas dhe p\u00ebrfshihet n\u00eb paket\u00ebn X-Pack. P\u00ebr t\u00eb filluar ta p\u00ebrdorni, mjafton pas instalimit t\u00eb aktivizoni nj\u00eb prov\u00eb 30-ditore. Pas skadimit t\u00eb periudh\u00ebs provuese, mund t\u00eb k\u00ebrkoni ndihm\u00ebn p\u00ebr ta zgjatur at\u00eb ose t\u00eb blini nj\u00eb abonim. \u00c7mimi i abonimit llogaritet jo nga volumi i t\u00eb dh\u00ebnave, por nga numri i nodave n\u00eb p\u00ebrdorim. Jo, volumi i t\u00eb dh\u00ebnave ndikon, padyshim, n\u00eb numrin e nodave t\u00eb nevojshme, por megjithat\u00eb ky qasje p\u00ebr licencim \u00ebsht\u00eb m\u00eb e humanizuar ndaj buxhetit t\u00eb kompanis\u00eb. N\u00ebse nuk keni nevoj\u00eb p\u00ebr performanc\u00eb t\u00eb lart\u00eb \u2014 mund t\u00eb kurseni.<\/p>\n

ML n\u00eb Elastic Stack \u00ebsht\u00eb shkruar n\u00eb C++ dhe funksionon jasht\u00eb JVM-s\u00eb, ku ekzekutohet vet\u00eb Elasticsearch. Pra, procesi (i quajtur autodetect) konsumon gjith\u00e7ka q\u00eb JVM nuk e p\u00ebrpunon. N\u00eb nj\u00eb sken\u00eb demo kjo nuk \u00ebsht\u00eb aq kritike, por n\u00eb mjedis produktiv \u00ebsht\u00eb e r\u00ebnd\u00ebsishme t\u00eb p\u00ebrzgjedh\u00ebsh node t\u00eb ve\u00e7anta p\u00ebr detyrat e ML.<\/p>\n

Algoritmet e m\u00ebsimit t\u00eb makinerive ndahen n\u00eb dy kategori \u2014 me m\u00ebsues<\/a><\/noindex> dhe pa m\u00ebsues<\/a><\/noindex>. N\u00eb Elastic Stack algoritmi bie n\u00eb kategorin\u00eb \"pa m\u00ebsues\". Mund t\u00eb shihni kjo lidhje<\/a><\/noindex> aparatin matematikor t\u00eb algoritmeve t\u00eb m\u00ebsimit t\u00eb makinerive.<\/p>\n

P\u00ebr t\u00eb kryer analiz\u00ebn, algoritmi i m\u00ebsimit t\u00eb makinerive p\u00ebrdor t\u00eb dh\u00ebnat q\u00eb ruhen n\u00eb indekset Elasticsearch. Mund t\u00eb krijoni detyra p\u00ebr analiza si nga nd\u00ebrfaqja Kibana ashtu edhe p\u00ebrmes API-s\u00eb. N\u00ebse e b\u00ebni k\u00ebt\u00eb p\u00ebrmes Kibana, disa gj\u00ebra nuk \u00ebsht\u00eb e nevojshme t'i dini. P\u00ebr shembull, indekset shtes\u00eb q\u00eb p\u00ebrdor algoritmi gjat\u00eb funksionimit. <\/p>\n

Indekset shtes\u00eb t\u00eb p\u00ebrdorur gjat\u00eb analiz\u00ebs<\/b>.ml-state \u2014 informacion mbi modelet statistikore (konfigurimet e analiz\u00ebs);
\n.ml-anomalies-* \u2014 rezultatet e pun\u00ebs s\u00eb algoritmeve ML;
\n.ml-notifications \u2014 konfigurimet e njoftimeve p\u00ebr rezultatet e analiz\u00ebs.<\/p>\n

\"T\u00eb
\n
\nStruktura e t\u00eb dh\u00ebnave n\u00eb baz\u00ebn Elasticsearch p\u00ebrb\u00ebhet nga indekset dhe dokumentet q\u00eb ruhen n\u00eb to. N\u00ebse e krahasojm\u00eb me nj\u00eb baz\u00eb t\u00eb dh\u00ebnash relationale, indeksi mund t\u00eb krahasohet me diagramin e baz\u00ebs s\u00eb dh\u00ebnash, nd\u00ebrsa dokumenti me nj\u00eb rekord n\u00eb tabel\u00eb. Ky krahasim \u00ebsht\u00eb i kushtezuar dhe \u00ebsht\u00eb dh\u00ebn\u00eb p\u00ebr t\u00eb thjeshtuar kuptimin e materialeve t\u00eb m\u00ebtejshme p\u00ebr ata q\u00eb kan\u00eb d\u00ebgjuar vet\u00ebm p\u00ebr Elasticsearch.<\/p>\n

P\u00ebrmes API \u00ebsht\u00eb i disponuesh\u00ebm i nj\u00ebjti funksionalitet si p\u00ebrmes nd\u00ebrfaqes n\u00eb ueb, prandaj p\u00ebr ilust\u00ebrim dhe p\u00ebr t\u00eb kuptuar konceptet do t\u00eb tregojm\u00eb se si t\u00eb konfigurojm\u00eb p\u00ebrmes Kibana. N\u00eb menun\u00eb e majt\u00eb ka nj\u00eb seksion Machine Learning, ku mund t\u00eb krijoni nj\u00eb pun\u00eb t\u00eb re (Job). N\u00eb nd\u00ebrfaqen Kibana, kjo duket si n\u00eb imazhin m\u00eb posht\u00eb. Tani do t\u00eb shqyrtojm\u00eb \u00e7do tip pun\u00eb dhe do t\u00eb tregojm\u00eb llojet e analizave q\u00eb mund t\u00eb nd\u00ebrtohen k\u00ebtu.<\/p>\n

\"T\u00eb
\n
\nSingle Metric \u2014 analiza e nj\u00eb metrik\u00eb, Multi Metric \u2014 analiza e dy ose m\u00eb shum\u00eb metrike. N\u00eb t\u00eb dyja rastet, \u00e7do metrik\u00eb analizohet n\u00eb nj\u00eb mjedis t\u00eb izoluar, pra algoritmi nuk merr parasysh sjelljen e metrikeve q\u00eb analizohen paralelisht, si\u00e7 mund t\u00eb dukej n\u00eb rastin e Multi Metric. P\u00ebr t\u00eb b\u00ebr\u00eb llogaritjet duke marr\u00eb parasysh korrelacionin midis ndryshimeve t\u00eb ndryshme, mund t\u00eb aplikohet analiza e Popullat\u00ebs. Nd\u00ebrsa Advanced \u2014 \u00ebsht\u00eb optimizimi i algoritmeve me mund\u00ebsi t\u00eb tjera p\u00ebr detyra t\u00eb caktuara. <\/p>\n

Single Metric<\/h2>\n

\nAnaliza e ndryshimeve t\u00eb nj\u00eb metrike t\u00eb vetme \u2014 \u00ebsht\u00eb di\u00e7ka shum\u00eb e thjesht\u00eb q\u00eb mund t\u00eb b\u00ebhet k\u00ebtu. Pas klikimit n\u00eb Create Job, algoritmi do t\u00eb k\u00ebrkoj\u00eb anomalit\u00eb.<\/p>\n

\"T\u00eb
\n
\nN\u00eb fush\u00ebn Aggregation<\/i> mund t\u00eb zgjidhni qasjen p\u00ebr k\u00ebrkimin e anomalive. P\u00ebr shembull, n\u00eb Min<\/i> do t\u00eb konsiderohen anomali vlerat q\u00eb jan\u00eb m\u00eb t\u00eb ul\u00ebta se tipiket. Ekzistojn\u00eb Max, High Mean, Low, Mean, Distinct<\/i> dhe t\u00eb tjera. P\u00ebrshkrimin e t\u00eb gjitha funksioneve mund ta shihni n\u00eb lidhje<\/a><\/noindex>.<\/p>\n

N\u00eb fush\u00ebn Field<\/i> \u00ebsht\u00eb e specifikuar nj\u00eb fush\u00eb numerike n\u00eb dokument, mbi t\u00eb cil\u00ebn do t\u00eb b\u00ebjm\u00eb analiz\u00ebn.<\/p>\n

N\u00eb fush\u00ebn Bucket span<\/i><\/a><\/noindex> \u2014 granulariteti i intervaleve n\u00eb linj\u00ebn e koh\u00ebs, mbi t\u00eb cil\u00ebt do t\u00eb b\u00ebhet analiza. Mund t\u00eb besoni automatizimin ose t\u00eb zgjidhni manualisht. N\u00eb figur\u00ebn m\u00eb posht\u00eb tregohet nj\u00eb shembull i granularitetit shum\u00eb t\u00eb ul\u00ebt \u2014 mund t\u00eb kaloni nj\u00eb anomalie. Me k\u00ebt\u00eb cil\u00ebsim mund t\u00eb ndryshoni ndjeshm\u00ebrin\u00eb e algoritmit ndaj anomaliave.<\/p>\n

\"T\u00eb
\n
\nKoh\u00ebzgjatja e t\u00eb dh\u00ebnave t\u00eb mbledhura \u00ebsht\u00eb nj\u00eb faktor ky\u00e7 q\u00eb ndikon n\u00eb efikasitetin e analiz\u00ebs. Gjat\u00eb analiz\u00ebs, algoritmi p\u00ebrcakton intervalet e p\u00ebrs\u00ebritura, llogarit intervalin e besimit (bazat) dhe zbulon anomali \u2014 devijime t\u00eb pazakonta nga sjellja normale e metrik\u00ebs. P\u00ebr nj\u00eb shembull:<\/p>\n

Bazat p\u00ebr nj\u00eb interval t\u00eb vog\u00ebl t\u00eb dh\u00ebnash:<\/p>\n

\"T\u00eb
\n
\nKur algoritmi ka me \u00e7far\u00eb t\u00eb m\u00ebsoj\u00eb \u2014 bazat duken k\u00ebshtu:<\/p>\n

\"T\u00eb
\n
\nPas nisjes s\u00eb detyr\u00ebs, algoritmi p\u00ebrcakton devijimet anomale nga norma dhe i rendit ato sipas probabilitetit t\u00eb anomalis\u00eb (n\u00eb paranteza \u00ebsht\u00eb ngjyra e etiket\u00ebs p\u00ebrkat\u00ebse):<\/p>\n

Warning (blu): m\u00eb pak se 25
\nMinor (yellow): 25-50
\nMajor (orange): 50-75
\nCritical (red): 75-100<\/p>\n

N\u00eb grafikun m\u00eb posht\u00eb \u00ebsht\u00eb nj\u00eb shembull me anomali t\u00eb gjetura.<\/p>\n

\"T\u00eb
\n
\nK\u00ebtu shikohet numri 94, i cili tregon probabilitetin e nj\u00eb anomali. Natyrisht, n\u00ebse vlera \u00ebsht\u00eb af\u00ebr 100, kjo tregon se kemi t\u00eb b\u00ebjm\u00eb me nj\u00eb anomalit\u00eb. N\u00eb kolon\u00ebn posht\u00eb grafik\u00ebve sh\u00ebnohet nj\u00eb probabilitet shum\u00eb i vog\u00ebl prej 0.000063634% p\u00ebr t\u00eb pasur nj\u00eb vler\u00eb t\u00eb metrik\u00ebs atje.<\/p>\n

P\u00ebrve\u00e7 k\u00ebrkimit t\u00eb anomali n\u00eb Kibana, mund t\u00eb nisni parashikimin. Kjo \u00ebsht\u00eb shum\u00eb e thjesht\u00eb dhe b\u00ebhet nga e nj\u00ebjta pamje me anomali \u2014 butoni Forecast<\/i> n\u00eb k\u00ebndin e sip\u00ebrm t\u00eb djatht\u00eb.<\/p>\n

\"T\u00eb
\n
\nParashikimi nd\u00ebrtohet maksimumi 8 jav\u00eb p\u00ebrpara. Edhe pse d\u00ebshira p\u00ebr m\u00eb shum\u00eb \u00ebsht\u00eb e madhe \u2014 m\u00eb shum\u00eb nuk lejohet sipas dizajnit.<\/p>\n

\"T\u00eb
\n
\nN\u00eb disa situata, parashikimi do t\u00eb jet\u00eb shum\u00eb i dobish\u00ebm, p\u00ebr shembull, kur monitorohet ngarkesa e p\u00ebrdoruesve n\u00eb infrastruktur\u00eb.<\/p>\n

Multi Metric<\/h2>\n

\nT\u00eb kalojm\u00eb te mund\u00ebsia tjet\u00ebr ML n\u00eb Elastic Stack \u2014 analiza e disa metrikave n\u00eb nj\u00eb grup. Por kjo nuk do t\u00eb thot\u00eb se do t\u00eb analizohet var\u00ebsia e nj\u00eb metrike nga tjetra. Ky \u00ebsht\u00eb nj\u00ebsoj si Single Metric, vet\u00ebm me shum\u00eb metrika n\u00eb nj\u00eb ekran p\u00ebr t\u00eb leht\u00ebsuar krahasimin e ndikimit t\u00eb nj\u00ebra-tjetr\u00ebs. Do t\u00eb flasim p\u00ebr analiz\u00ebn e var\u00ebsis\u00eb s\u00eb nj\u00eb metrike nga tjetra n\u00eb pjes\u00ebn e Population.<\/p>\n

Pas klikimit n\u00eb katrorin me Multi Metric, do t\u00eb shfaqet nj\u00eb dritare me cil\u00ebsimet. Do t'i ndalem m\u00eb n\u00eb detaje atyre.<\/p>\n

\"T\u00eb
\n
\np\u00ebr t\u00eb filluar, nevojitet t\u00eb zgjidhni fushat p\u00ebr analiz\u00eb dhe aggregimin e t\u00eb dh\u00ebnave n\u00eb to. Opsionet e agregimit k\u00ebtu jan\u00eb ato q\u00eb jan\u00eb p\u00ebrdorur p\u00ebr Metrik\u00ebn e Vetme (Max, High Mean, Low, Mean, Distinct<\/i> dhe t\u00eb tjera). M\u00eb pas, t\u00eb dh\u00ebnat mund t\u00eb ndahen sipas nj\u00ebrit nga fushat (fusha Ndarja e t\u00eb Dh\u00ebnave<\/i>). N\u00eb k\u00ebt\u00eb shembull, ne e b\u00ebm\u00eb k\u00ebt\u00eb sipas fush\u00ebs OriginAirportID<\/i>. Vini re se grafiku i metrikeve t\u00eb djathtas tani paraqitet si nj\u00eb s\u00ebr\u00eb grafiku.<\/p>\n

\"T\u00eb
\n
\nFusha Fushat Ky\u00e7e (Influencers)<\/i> ka nj\u00eb ndikim t\u00eb drejtp\u00ebrdrejt\u00eb n\u00eb anomali q\u00eb jan\u00eb gjetur. N\u00eb m\u00ebnyr\u00eb t\u00eb parazgjedhur, do t\u00eb ket\u00eb gjithmon\u00eb t\u00eb pakt\u00ebn nj\u00eb vler\u00eb k\u00ebtu, dhe ju mund t\u00eb shtoni t\u00eb tjera. Algoritmi do t\u00eb marr\u00eb parasysh ndikimin e k\u00ebtyre fushave gjat\u00eb analiz\u00ebs dhe do t\u00eb tregoj\u00eb vlerat m\u00eb 't\u00eb ndikueshme'.<\/p>\n

Pas nisjes, n\u00eb nd\u00ebrfaqen Kibana do t\u00eb shfaqet nj\u00eb pamje si kjo.<\/p>\n

\"T\u00eb
\n
\nKjo \u00ebsht\u00eb e ashtuquajtura hart\u00eb e nxeht\u00ebsis\u00eb s\u00eb anomali p\u00ebr \u00e7do vler\u00eb t\u00eb fush\u00ebs OriginAirportID<\/i>, e cila \u00ebsht\u00eb sh\u00ebnuar n\u00eb Ndarja e t\u00eb Dh\u00ebnave<\/i>. Ashtu si n\u00eb rastin e Metrik\u00ebs s\u00eb Vetme, ngjyra tregon nivelin e devijimit anormal. Nj\u00eb analiz\u00eb e ngjashme \u00ebsht\u00eb e p\u00ebrshtatshme t\u00eb b\u00ebhet, p\u00ebr shembull, p\u00ebr stacionet e pun\u00ebs p\u00ebr t\u00eb ndjekur ato, ku ka nj\u00eb sasi t\u00eb dyshimt\u00eb t\u00eb autorizimeve etj. Ne kemi shkruar m\u00eb par\u00eb p\u00ebr ngjarjet e dyshimta n\u00eb EventLog Windows<\/a><\/noindex>, t\u00eb cilat gjithashtu mund t\u00eb mblidhen dhe analizohen k\u00ebtu.<\/p>\n

N\u00ebn hart\u00ebn termike \u00ebsht\u00eb lista e anomalive, nga e cila \u00e7do nj\u00eb mund t\u00eb \u00e7oj\u00eb n\u00eb pamjen Single Metric p\u00ebr nj\u00eb analiz\u00eb t\u00eb detajuar.<\/p>\n

Popullata<\/h2>\n

\nP\u00ebr t\u00eb k\u00ebrkuar anomalit\u00eb midis korelacion\u00ebve t\u00eb metrikave t\u00eb ndryshme n\u00eb Elastic Stack, ka nj\u00eb analiz\u00eb t\u00eb specializuar Popullata. Pik\u00ebrisht me ndihm\u00ebn e saj mund t\u00eb k\u00ebrkohen vlera anomale n\u00eb performanc\u00ebn e ndonj\u00eb serveri n\u00eb krahasim me t\u00eb tjer\u00ebt, p\u00ebr shembull, gjat\u00eb rritjes s\u00eb numrit t\u00eb k\u00ebrkesave ndaj sistemit t\u00eb synuar.<\/p>\n

\"T\u00eb
\n
\nN\u00eb k\u00ebt\u00eb ilustrim, n\u00eb fush\u00ebn Popullata tregohet vlera ndaj t\u00eb cil\u00ebs do t\u00eb referohen metrikat q\u00eb po analizohet. N\u00eb k\u00ebt\u00eb rast, \u00ebsht\u00eb emri i procesit. Si rezultat, ne do t\u00eb shohim se si ngarkesa e procesorit nga secili prej proces\u00ebve ka ndikuar nj\u00ebri te tjetri.<\/p>\n

Vini re se grafiku i t\u00eb dh\u00ebnave t\u00eb analizuara \u00ebsht\u00eb ndryshe nga rastet me Single Metric dhe Multi Metric. Kjo u b\u00eb n\u00eb Kibana p\u00ebr t\u00eb p\u00ebrmir\u00ebsuar perceptimin e shp\u00ebrndarjes s\u00eb vlerave t\u00eb t\u00eb dh\u00ebnave t\u00eb analizuara.<\/p>\n

\"T\u00eb
\n
\nNga grafiku tregohet se procesi stress<\/i> (p\u00ebr ta th\u00ebn\u00eb, i gjeneruar nga nj\u00eb utilitar t\u00eb ve\u00e7ant\u00eb) n\u00eb serverin poipu<\/i>, i cili ndikoi (apo u b\u00eb influencues) n\u00eb shfaqjen e k\u00ebsaj anomalie.<\/p>\n

Advanced<\/h2>\n

\nAnalitika me p\u00ebrshtatje t\u00eb holl\u00ebsishme. N\u00eb analiz\u00ebn Advanced n\u00eb Kibana shfaqen cil\u00ebsime shtes\u00eb. Pasi t\u00eb klikoni n\u00eb menun\u00eb e krijimit mbi pllak\u00ebn Advanced, gjithashtu shfaqet nj\u00eb dritare e till\u00eb me skeda. Skeda Detajet e Pun\u00ebs<\/i> e kemi l\u00ebn\u00eb q\u00ebllimisht m\u00ebnjan\u00eb, aty jan\u00eb cil\u00ebsimet baz\u00eb q\u00eb nuk i p\u00ebrkasin drejtp\u00ebrdrejt p\u00ebr konfigurimin e analiz\u00ebs.<\/p>\n

\"T\u00eb
\n
\nN\u00eb summary_count_field_name<\/i> opsionale mund t\u00eb specifikoni emrin e fush\u00ebs nga dokumentet q\u00eb p\u00ebrmban vlera t\u00eb agreguara. N\u00eb k\u00ebt\u00eb shembull \u2014 numri i ngjarjeve p\u00ebr minut\u00eb. N\u00eb categorization_field_name<\/i><\/a><\/noindex> jysh specifikohet emri i fush\u00ebs n\u00eb dokument q\u00eb p\u00ebrmban nj\u00eb vler\u00eb t\u00eb caktuar. N\u00eb p\u00ebrputhje me k\u00ebt\u00eb fush\u00eb, t\u00eb dh\u00ebnat e analizuar mund t\u00eb ndahen n\u00eb n\u00ebngrupe. V\u00ebreni butonin Shto detektor<\/i> n\u00eb iluztrimin e m\u00ebparsh\u00ebm. M\u00eb posht\u00eb \u00ebsht\u00eb rezultati i klikimit mbi k\u00ebt\u00eb buton.<\/p>\n

\"T\u00eb
\n
\nK\u00ebtu \u00ebsht\u00eb nj\u00eb bllok shtes\u00eb cil\u00ebsimesh p\u00ebr konfigurimin e detektorit t\u00eb anomalive p\u00ebr nj\u00eb detyr\u00eb t\u00eb caktuar. Raste t\u00eb caktuara p\u00ebrdorimi (ve\u00e7an\u00ebrisht p\u00ebr sigurin\u00eb) ne planifikojm\u00eb t'i shqyrtojm\u00eb n\u00eb artikujt e ardhsh\u00ebm. P\u00ebr shembull, shikoni<\/a><\/noindex> nj\u00eb nga rastet e shqyrtuara. Ai lidhet me k\u00ebrkimin e vlerave t\u00eb rralla dhe realizohet funksioni rare<\/a><\/noindex>.<\/p>\n

N\u00eb fush\u00ebn function<\/i> mund t\u00eb zgjidhet nj\u00eb funksion specifik p\u00ebr k\u00ebrkimin e anomali. P\u00ebrve\u00e7 t\u00eb ralla<\/i>, ka edhe disa funksione interesante \u2014 koha_e_dit\u00ebs<\/i> dhe koha_e_jav\u00ebs<\/i><\/a><\/noindex>. Ato zbulojn\u00eb anomali n\u00eb sjelljen e metrikeve gjat\u00eb dit\u00ebs ose jav\u00ebs p\u00ebrkat\u00ebsisht. Funkcioni tjet\u00ebr i analiz\u00ebs gjendet n\u00eb dokumentacion<\/a><\/noindex>.<\/p>\n

N\u00eb emri_i_fush\u00ebs<\/i> specifikon fush\u00ebn e dokumentit sipas s\u00eb cil\u00ebs do t\u00eb kryhet analiza. Nga_emri_i_fush\u00ebs<\/i> mund t\u00eb p\u00ebrdoret p\u00ebr t\u00eb ndar\u00eb rezultatet e analiz\u00ebs sipas \u00e7do vler\u00eb t\u00eb ve\u00e7ant\u00eb t\u00eb caktuar k\u00ebtu n\u00eb fush\u00ebn e dokumentit. N\u00ebse plot\u00ebson p\u00ebrmes_emrit_t\u00eb_fush\u00ebs<\/i> do t\u00eb p\u00ebrfitohet nj\u00eb analiz\u00eb populations, si\u00e7 shqyrtuam m\u00eb lart. N\u00ebse specifikohet nj\u00eb vler\u00eb n\u00eb fusha_partition<\/i>, at\u00ebher\u00eb p\u00ebr k\u00ebt\u00eb fush\u00eb dokumenti do t\u00eb llogariten linja baz\u00eb t\u00eb ndryshme p\u00ebr \u00e7do vler\u00eb (si vlera mund t\u00eb sh\u00ebrbej\u00eb, p\u00ebr shembull, emri i serverit ose procesit n\u00eb server). N\u00eb p\u00ebrjashto_t\u00eb_frekuentat<\/i> mund t\u00eb zgjidhet all<\/i> ose none<\/i>, q\u00eb do t\u00eb thot\u00eb p\u00ebrjashtim (ose p\u00ebrfshirje) e vlerave t\u00eb zakonshme t\u00eb fushave t\u00eb dokumente.<\/p>\n

N\u00eb k\u00ebt\u00eb artikull, p\u00ebrpiqemi t\u00eb japim nj\u00eb p\u00ebrmbledhje sa m\u00eb t\u00eb sakt\u00eb t\u00eb mund\u00ebsive t\u00eb m\u00ebsimit t\u00eb makinerive n\u00eb Elastic Stack, duke l\u00ebn\u00eb shum\u00eb detaje pas sken\u00ebs. Na tregoni n\u00eb komentet se cilat raste keni arritur t\u00eb zgjidhni me ndihm\u00ebn e Elastic Stack dhe p\u00ebr cilat detyra e p\u00ebrdorni at\u00eb. P\u00ebr t'u lidhur me ne, mund t\u00eb p\u00ebrdorni mesazhet personale n\u00eb Habr ose form\u00ebn e kontaktit n\u00eb faqen e internetit<\/a><\/noindex>.
\n
Burimi: habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041d\u0430\u043f\u043e\u043c\u043d\u0438\u043c, \u0447\u0442\u043e \u0432 \u043e\u0441\u043d\u043e\u0432\u0435 Elastic Stack \u043b\u0435\u0436\u0430\u0442 \u043d\u0435\u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u0430\u044f \u0431\u0430\u0437\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 Elasticsearch, \u0432\u0435\u0431-\u0438\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 Kibana \u0438 \u0441\u0431\u043e\u0440\u0449\u0438\u043a\u0438-\u043e\u0431\u0440\u0430\u0431\u043e\u0442\u0447\u0438\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 (\u0441\u0430\u043c\u044b\u0439 \u0438\u0437\u0432\u0435\u0441\u0442\u043d\u044b\u0439 Logstash, \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0435 Beats, APM \u0438 \u0434\u0440\u0443\u0433\u0438\u0435). \u041e\u0434\u043d\u043e \u0438\u0437 \u043f\u0440\u0438\u044f\u0442\u043d\u044b\u0445 \u0434\u043e\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0439 \u0432\u0441\u0435\u0433\u043e \u043f\u0435\u0440\u0435\u0447\u0438\u0441\u043b\u0435\u043d\u043d\u043e\u0433\u043e \u0441\u0442\u0435\u043a\u0430 \u043f\u0440\u043e\u0434\u0443\u043a\u0442\u043e\u0432 \u2014 \u0430\u043d\u0430\u043b\u0438\u0437 \u0434\u0430\u043d\u043d\u044b\u0445 \u043f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f. \u0412 \u0441\u0442\u0430\u0442\u044c\u0435 \u043c\u044b \u0440\u0430\u0437\u0431\u0438\u0440\u0430\u0435\u043c\u0441\u044f \u0447\u0442\u043e \u0438\u0437 \u0441\u0435\u0431\u044f \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 \u044d\u0442\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b. \u041f\u0440\u043e\u0441\u0438\u043c \u043f\u043e\u0434 \u043a\u0430\u0442. \u041c\u0430\u0448\u0438\u043d\u043d\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":26487,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[688],"tags":[],"class_list":["post-35274","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-administrirovanie"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47T\u00eb shpjegojm\u00eb M\u00ebsimin e Makin\u00ebs n\u00eb Elastic Stack (i njohur gjithashtu si Elasticsearch, ELK) | ProHoster","description":"Kujtojm\u00eb se n\u00eb themel t\u00eb Elastic Stack q\u00ebndron baza e dh\u00ebnash jo-reduktuese Elasticsearch, nd\u00ebrfaqja e uebit Kibana dhe mbledh\u00ebsit-p\u00ebrpunues t\u00eb t\u00eb dh\u00ebnave (m\u00eb i njohuri Logstash, Beats t\u00eb ndryshme, APM dhe t\u00eb tjer\u00eb). Nj\u00eb nga shtesat e k\u00ebndshme t\u00eb gjith\u00eb k\u00ebtij grumbulli produktesh \u00ebsht\u00eb analiza e t\u00eb dh\u00ebnave me ndihm\u00ebn e algoritmeve t\u00eb m\u00ebsimit t\u00eb makinerive. N\u00eb k\u00ebt\u00eb artikull, ne shqyrtojm\u00eb se \u00e7far\u00eb p\u00ebrfaq\u00ebsojn\u00eb k\u00ebta algoritme. Ju lutemi t\u00eb vazhdoni m\u00eb posht\u00eb. M\u00ebsimi i makin\u00ebs","canonical_url":"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"sq_AL","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u0420\u0430\u0437\u0431\u0438\u0440\u0430\u0435\u043c\u0441\u044f \u0441 Machine Learning \u0432 Elastic Stack (\u043e\u043d \u0436\u0435 Elasticsearch, \u043e\u043d \u0436\u0435 ELK) | ProHoster","og:description":"\u041d\u0430\u043f\u043e\u043c\u043d\u0438\u043c, \u0447\u0442\u043e \u0432 \u043e\u0441\u043d\u043e\u0432\u0435 Elastic Stack \u043b\u0435\u0436\u0430\u0442 \u043d\u0435\u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u0430\u044f \u0431\u0430\u0437\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 Elasticsearch, \u0432\u0435\u0431-\u0438\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 Kibana \u0438 \u0441\u0431\u043e\u0440\u0449\u0438\u043a\u0438-\u043e\u0431\u0440\u0430\u0431\u043e\u0442\u0447\u0438\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 (\u0441\u0430\u043c\u044b\u0439 \u0438\u0437\u0432\u0435\u0441\u0442\u043d\u044b\u0439 Logstash, \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0435 Beats, APM \u0438 \u0434\u0440\u0443\u0433\u0438\u0435). \u041e\u0434\u043d\u043e \u0438\u0437 \u043f\u0440\u0438\u044f\u0442\u043d\u044b\u0445 \u0434\u043e\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0439 \u0432\u0441\u0435\u0433\u043e \u043f\u0435\u0440\u0435\u0447\u0438\u0441\u043b\u0435\u043d\u043d\u043e\u0433\u043e \u0441\u0442\u0435\u043a\u0430 \u043f\u0440\u043e\u0434\u0443\u043a\u0442\u043e\u0432 \u2014 \u0430\u043d\u0430\u043b\u0438\u0437 \u0434\u0430\u043d\u043d\u044b\u0445 \u043f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f. \u0412 \u0441\u0442\u0430\u0442\u044c\u0435 \u043c\u044b \u0440\u0430\u0437\u0431\u0438\u0440\u0430\u0435\u043c\u0441\u044f \u0447\u0442\u043e \u0438\u0437 \u0441\u0435\u0431\u044f \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 \u044d\u0442\u0438 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b. \u041f\u0440\u043e\u0441\u0438\u043c \u043f\u043e\u0434 \u043a\u0430\u0442. \u041c\u0430\u0448\u0438\u043d\u043d\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435","og:url":"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-10-31T19:03:22+00:00","article:modified_time":"2019-10-31T19:03:22+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"35274","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-21 22:37:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 02:07:28","updated":"2026-01-21 22:37:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/35274","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/comments?post=35274"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/35274\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media\/26487"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media?parent=35274"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/categories?post=35274"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/tags?post=35274"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}