{"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\/az\/blog\/administrirovanie\/razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk","title":{"rendered":"Elastic Stack (y\u0259ni Elasticsearch, y\u0259ni ELK) il\u0259 Machine Learning-i ara\u015fd\u0131r\u0131r\u0131q","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

\"Elastic
\n
\nXat\u0131rladaq ki, Elastic Stack-\u0131n \u0259sas\u0131n\u0131 qeyri-relyasiya veril\u0259nl\u0259r bazas\u0131 olan Elasticsearch, Kibana veb interfeysi v\u0259 m\u0259lumat toplama v\u0259 i\u015fl\u0259m\u0259 al\u0259tl\u0259ri (\u0259n m\u0259\u015fhuru Logstash, m\u00fcxt\u0259lif Beats, APM v\u0259 dig\u0259rl\u0259ri) t\u0259\u015fkil edir. Bu m\u0259hsul paketinin bir z\u00f6vq\u00fc is\u0259 ma\u015f\u0131n \u00f6yr\u0259nm\u0259 alqoritml\u0259ri vasit\u0259sil\u0259 m\u0259lumatlar\u0131n t\u0259hlili imkan\u0131d\u0131r. Bu m\u0259qal\u0259d\u0259 bu alqoritml\u0259rin n\u0259 oldu\u011fu il\u0259 tan\u0131\u015f olaca\u011f\u0131q. R\u0259dd etm\u0259d\u0259n davam edin.
\n<\/a><\/noindex>
\nMa\u015f\u0131n \u00f6yr\u0259nm\u0259 \u2014 \u015f\u0259rti pulsuz Elastic Stack-in pullu funksiyas\u0131d\u0131r v\u0259 X-Pack paketin\u0259 daxildir. Ondan istifad\u0259 etm\u0259y\u0259 ba\u015flamaq \u00fc\u00e7\u00fcn qura\u015fd\u0131rmadan sonra 30 g\u00fcnl\u00fck s\u0131naq m\u00fcdd\u0259tini aktivl\u0259\u015fdirm\u0259k kifay\u0259tdir. S\u0131naq m\u00fcdd\u0259ti bitdikd\u0259n sonra onun uzad\u0131lmas\u0131 \u00fc\u00e7\u00fcn d\u0259st\u0259k t\u0259l\u0259b ed\u0259 bil\u0259rsiniz v\u0259 ya abun\u0259 sat\u0131n ala bil\u0259rsiniz. Abun\u0259 haqq\u0131 veril\u0259nl\u0259r h\u0259cmin\u0259 deyil, istifad\u0259 olunan d\u00fcy\u00fcnl\u0259rin say\u0131na \u0259saslan\u0131r. B\u0259li, veril\u0259nl\u0259r h\u0259cmi \u0259slind\u0259 laz\u0131m olan d\u00fcy\u00fcnl\u0259rin say\u0131na t\u0259sir edir, lakin h\u0259l\u0259 d\u0259 bel\u0259 bir lisenziya yana\u015fmas\u0131 \u015firk\u0259tin b\u00fcdc\u0259sini n\u0259z\u0259r\u0259 alaraq daha insafl\u0131d\u0131r. Y\u00fcks\u0259k m\u0259hsuldarl\u0131\u011fa ehtiyac yoxdursa \u2014 q\u0259na\u0259t ed\u0259 bil\u0259rsiniz.<\/p>\n

Elastic Stack-d\u0259 ML C++ il\u0259 yaz\u0131l\u0131b v\u0259 Elasticsearch-un i\u015fl\u0259diyi JVM-d\u0259n k\u0259narda f\u0259aliyy\u0259t g\u00f6st\u0259rir. Y\u0259ni prosesi (bu, avtomatik a\u015fkarlanma adlan\u0131r) JVM-in \u0259yl\u0259c\u0259yind\u0259n ba\u015fqa h\u0259r \u015feyi istehlak edir. Demo d\u0259stind\u0259 bu o q\u0259d\u0259r d\u0259 kritik deyil, lakin istehsal m\u00fchitind\u0259 ML v\u0259zif\u0259l\u0259ri \u00fc\u00e7\u00fcn x\u00fcsusi d\u00fcy\u00fcnl\u0259r ay\u0131rmaq vacibdir.<\/p>\n

Ma\u015f\u0131n \u00f6yr\u0259nm\u0259 alqoritml\u0259ri iki kateqoriyaya b\u00f6l\u00fcn\u00fcr - n\u0259zar\u0259t alt\u0131nda<\/a><\/noindex> v\u0259 n\u0259zar\u0259t olmadan<\/a><\/noindex>. Elastic Stack-d\u0259 alqoritm \u00abn\u0259zar\u0259t olmadan\u00bb kateqoriyas\u0131ndan. Bu ba\u011flant\u0131ya<\/a><\/noindex> ged\u0259r\u0259k ma\u015f\u0131n \u00f6yr\u0259nm\u0259 alqoritml\u0259rinin riyazi aparat\u0131n\u0131 g\u00f6r\u0259 bil\u0259rsiniz.<\/p>\n

T\u0259hlil aparmaq \u00fc\u00e7\u00fcn ma\u015f\u0131n \u00f6yr\u0259nm\u0259 alqoritmi, Elasticsearch indeksl\u0259rind\u0259 saxlan\u0131lan veril\u0259nl\u0259rd\u0259n istifad\u0259 edir. T\u0259hlil \u00fc\u00e7\u00fcn tap\u015f\u0131r\u0131qlar yaratmaq h\u0259m Kibana interfeysind\u0259n, h\u0259m d\u0259 API vasit\u0259sil\u0259 m\u00fcmk\u00fcnd\u00fcr. Kibana vasit\u0259sil\u0259 ed\u0259rk\u0259n b\u0259zi \u015feyl\u0259ri bilm\u0259k m\u00fctl\u0259q deyil. M\u0259s\u0259l\u0259n, alqoritmin i\u015f prosesind\u0259 istifad\u0259 etdiyi \u0259lav\u0259 indeksl\u0259r. <\/p>\n

T\u0259hlil prosesind\u0259 istifad\u0259 edil\u0259n \u0259lav\u0259 indeksl\u0259r<\/b>.ml-state \u2014 statistik modell\u0259r (t\u0259hlil parametrl\u0259ri) haqq\u0131nda m\u0259lumat;
\n.ml-anomalies-* \u2014 ML alqoritml\u0259rinin i\u015f n\u0259tic\u0259l\u0259ri;
\n.ml-notifications \u2014 t\u0259hlil n\u0259tic\u0259l\u0259ri \u00fczr\u0259 bildiri\u015f parametrl\u0259ri.<\/p>\n

\"Elastic
\n
\nElasticsearch bazas\u0131nda veril\u0259nl\u0259rin strukturu indeksl\u0259rd\u0259n v\u0259 i\u00e7\u0259risind\u0259 saxlan\u0131lan s\u0259n\u0259dl\u0259rd\u0259n ibar\u0259tdir. Relyasiya veril\u0259nl\u0259r bazas\u0131 il\u0259 m\u00fcqayis\u0259 ets\u0259k, indeks veril\u0259nl\u0259r bazas\u0131n\u0131n sxemin\u0259, s\u0259n\u0259d is\u0259 c\u0259dv\u0259ld\u0259ki qeyd il\u0259 m\u00fcqayis\u0259 oluna bil\u0259r. Bu m\u00fcqayis\u0259 \u015f\u0259rtidir v\u0259 yaln\u0131z Elasticsearch haqq\u0131nda e\u015fid\u0259nl\u0259r \u00fc\u00e7\u00fcn material\u0131n daha ayd\u0131n anla\u015f\u0131lmas\u0131 \u00fc\u00e7\u00fcn sad\u0259l\u0259\u015fdirilmi\u015fdir.<\/p>\n

API \u00fcz\u0259rind\u0259n veb interfeys il\u0259 eyni funksiyan\u0131 \u0259ld\u0259 etm\u0259k m\u00fcmk\u00fcnd\u00fcr, buna g\u00f6r\u0259 d\u0259 konseptl\u0259rin ba\u015fa d\u00fc\u015f\u00fclm\u0259si v\u0259 ayd\u0131nl\u0131\u011f\u0131 \u00fc\u00e7\u00fcn Kibana vasit\u0259sil\u0259 nec\u0259 qura\u015fd\u0131r\u0131laca\u011f\u0131n\u0131 g\u00f6st\u0259r\u0259c\u0259yik. Sol menyuda Machine Learning b\u00f6lm\u0259si var, burada yeni bir i\u015f (Job) yarada bil\u0259rsiniz. Kibana interfeysind\u0259 bu a\u015fa\u011f\u0131dak\u0131 \u015f\u0259kild\u0259kil\u0259r kimi g\u00f6r\u00fcn\u00fcr. \u0130ndi h\u0259r i\u015f n\u00f6v\u00fcn\u00fc ara\u015fd\u0131raca\u011f\u0131q v\u0259 burada konstru edil\u0259 bil\u0259c\u0259k analiz n\u00f6vl\u0259rini g\u00f6st\u0259r\u0259c\u0259yik.<\/p>\n

\"Elastic
\n
\nSingle Metric \u2014 bir metrikan\u0131n analizi, Multi Metric \u2014 iki v\u0259 ya daha \u00e7ox metrikan\u0131n analizi. H\u0259r iki halda, h\u0259r bir metrika izol\u0259 edilmi\u015f m\u00fchitd\u0259 analiz edilir, y\u0259ni algoritm, Multi Metric v\u0259ziyy\u0259tind\u0259 g\u00f6r\u00fcn\u0259 bil\u0259c\u0259yi kimi eyni zamanda analiz edil\u0259n metrikalar\u0131n davran\u0131\u015f\u0131n\u0131 n\u0259z\u0259r\u0259 alm\u0131r. M\u00fcxt\u0259lif metrikalar aras\u0131ndak\u0131 korrelyasiyan\u0131 hesablamaq \u00fc\u00e7\u00fcn Population analizi t\u0259tbiq oluna bil\u0259r. Advanced is\u0259 m\u00fc\u0259yy\u0259n tap\u015f\u0131r\u0131qlar \u00fc\u00e7\u00fcn \u0259lav\u0259 se\u00e7iml\u0259rl\u0259 algoritmlar\u0131n inc\u0259 t\u0259nziml\u0259nm\u0259sidir. <\/p>\n

Single Metric<\/h2>\n

\nBir t\u0259k metrikan\u0131n d\u0259yi\u015fiklikl\u0259rinin analizi \u2014 burada ed\u0259 bil\u0259c\u0259yiniz \u0259n sad\u0259 \u015feydir. Create Job d\u00fcym\u0259sin\u0259 basd\u0131qdan sonra, algoritm anomalil\u0259ri axtaracaq.<\/p>\n

\"Elastic
\n
\nBo\u015fluqda Aggregation<\/i> an\u0131 axtar\u0131\u015f \u00fc\u00e7\u00fcn yana\u015fma se\u00e7m\u0259k m\u00fcmk\u00fcnd\u00fcr. M\u0259s\u0259l\u0259n, Min<\/i> anomalil\u0259ri tipik d\u0259y\u0259rl\u0259rin alt\u0131ndak\u0131 qiym\u0259tl\u0259r say\u0131lacaq. Max, High Mean, Low, Mean, Distinct v\u0259 ba\u015fqa se\u00e7iml\u0259r d\u0259 var. B\u00fct\u00fcn funksiyalar\u0131n t\u0259svirin\u0259<\/i> linkd\u0259n baxmaq m\u00fcmk\u00fcnd\u00fcr.<\/a><\/noindex>.<\/p>\n

Bo\u015fluqda Field<\/i> analiz aparaca\u011f\u0131m\u0131z s\u0259n\u0259din say\u0131sal sah\u0259sini g\u00f6st\u0259r\u0259r.<\/p>\n

Bo\u015fluqda Bucket span<\/i><\/a><\/noindex> \u2014 analiz edil\u0259c\u0259k zaman interval\u0131n\u0131n d\u0259qiqliyi. Avtomatik se\u00e7imi etibar ed\u0259 bil\u0259r v\u0259 ya \u0259l il\u0259 se\u00e7\u0259 bil\u0259rsiniz. A\u015fa\u011f\u0131dak\u0131 \u015f\u0259kill\u0259rd\u0259 \u00e7ox a\u015fa\u011f\u0131 d\u0259qiqliyin n\u00fcmun\u0259si verilib \u2014 anomalinin ke\u00e7m\u0259si m\u00fcmk\u00fcnd\u00fcr. Bu t\u0259nziml\u0259m\u0259 il\u0259 algoritmin anomalil\u0259r\u0259 qar\u015f\u0131 h\u0259ssasl\u0131\u011f\u0131n\u0131 d\u0259yi\u015fm\u0259k m\u00fcmk\u00fcnd\u00fcr.<\/p>\n

\"Elastic
\n
\nToplad\u0131lan m\u0259lumatlar\u0131n m\u00fcdd\u0259ti \u2014 analiz effektivliyin\u0259 t\u0259sir ed\u0259n \u0259sas \u015feydir. Algoritm analiz ed\u0259rk\u0259n t\u0259krarlanan intervallar\u0131 m\u00fc\u0259yy\u0259n edir, etibarl\u0131l\u0131q intervallar\u0131 (b\u0259sl\u0259nm\u0259 x\u0259ttl\u0259ri) hesablay\u0131r v\u0259 anomalil\u0259ri a\u015fkar edir \u2014 metrikan\u0131n adi davran\u0131\u015f\u0131ndan qeyri-adi sapmalar. M\u0259s\u0259l\u0259n:<\/p>\n

Ki\u00e7ik bir m\u0259lumat hiss\u0259si \u00fc\u00e7\u00fcn b\u0259sl\u0259nm\u0259 x\u0259ttl\u0259ri:<\/p>\n

\"Elastic
\n
\nAlgoritmin \u00f6yr\u0259nm\u0259k \u00fc\u00e7\u00fcn bir \u015feyl\u0259ri olduqda \u2014 b\u0259sl\u0259nm\u0259 x\u0259ttl\u0259ri bel\u0259 g\u00f6r\u00fcn\u00fcr:<\/p>\n

\"Elastic
\n
\n\u0130\u015fin i\u015f\u0259 sal\u0131nmas\u0131ndan sonra, algoritm normalardan anomalil\u0259ri m\u00fc\u0259yy\u0259n edir v\u0259 onlar\u0131 anomalinin ehtimal\u0131na g\u00f6r\u0259 s\u0131ralay\u0131r (m\u00fcvafiq etiketin r\u0259ngi parantezd\u0259 g\u00f6st\u0259rilir):<\/p>\n

Warning (mavi): 25-d\u0259n az
\nMinor (sar\u0131): 25-50
\nMajor (nar\u0131nc\u0131): 50-75
\nCritical (q\u0131rm\u0131z\u0131): 75-100<\/p>\n

A\u015fa\u011f\u0131dak\u0131 qrafikd\u0259 tap\u0131lan anomalil\u0259rin n\u00fcmun\u0259si.<\/p>\n

\"Elastic
\n
\nBurada 94 say\u0131n\u0131 g\u00f6rm\u0259k m\u00fcmk\u00fcnd\u00fcr ki, bu da anomalinin ehtimal\u0131n\u0131 g\u00f6st\u0259rir. Ayd\u0131n olur ki, d\u0259y\u0259rin 100-\u0259 yax\u0131n olmas\u0131 dem\u0259kdir ki, qar\u015f\u0131da anomalidir. Qrafikin alt\u0131nda olan s\u00fctunda metrikan\u0131n d\u0259y\u0259rinin orada meydana g\u0259lm\u0259 ehtimal\u0131 0.000063634% oldu\u011fu kimi qeyd olunur.<\/p>\n

Kibana'da anomalil\u0259rin axtar\u0131\u015f\u0131 il\u0259 yana\u015f\u0131, proqnozla\u015fd\u0131rma da ba\u015flaya bil\u0259rsiniz. Bu, sad\u0259dir v\u0259 eyni anomalil\u0259r t\u0259qdimat\u0131ndan \u2014 d\u00fcym\u0259 il\u0259 Forecast<\/i> sa\u011f \u00fcst k\u00f6\u015fede.<\/p>\n

\"Elastic
\n
\nTahmin en fazla 8 hafta ileriye olu\u015fturulur. \u00c7ok istense bile, daha fazlas\u0131 tasar\u0131m gere\u011fi m\u00fcmk\u00fcn de\u011fildir.<\/p>\n

\"Elastic
\n
\nBaz\u0131 durumlarda tahmin \u00e7ok faydal\u0131 olabilir; \u00f6rne\u011fin, altyap\u0131ya kullan\u0131c\u0131 y\u00fck\u00fcn\u00fcn izlenmesi s\u0131ras\u0131nda.<\/p>\n

\u00c7oklu \u00d6l\u00e7\u00fcm<\/h2>\n

\nElastic Stack'teki bir sonraki ML f\u0131rsat\u0131na ge\u00e7iyoruz - birden fazla \u00f6l\u00e7\u00fcm\u00fcn bir arada analizi. Ancak bu, bir \u00f6l\u00e7\u00fcm\u00fcn di\u011ferine olan ba\u011f\u0131ml\u0131l\u0131\u011f\u0131n\u0131n analiz edilece\u011fi anlam\u0131na gelmez. Bu, yaln\u0131zca bir ekran \u00fczerinde \u00e7oklu \u00f6l\u00e7\u00fcmle tekil \u00f6l\u00e7\u00fcm\u00fcn ayn\u0131s\u0131d\u0131r ve birinin di\u011ferine olan etkilerini kar\u015f\u0131la\u015ft\u0131rmak i\u00e7in kolayl\u0131k sa\u011flar. Bir \u00f6l\u00e7\u00fcm\u00fcn di\u011ferine olan ba\u011f\u0131ml\u0131l\u0131\u011f\u0131n\u0131n analizi, Population k\u0131sm\u0131nda ele al\u0131nacakt\u0131r.<\/p>\n

\u00c7oklu \u00d6l\u00e7\u00fcm\u00fcn karesine t\u0131klad\u0131ktan sonra, ayarlar\u0131n bulundu\u011fu bir pencere a\u00e7\u0131lacakt\u0131r. Bunlara daha detayl\u0131 bakal\u0131m.<\/p>\n

\"Elastic
\n
\n\u00d6ncelikle analiz edilecek alanlar\u0131 se\u00e7mek ve bu alanlara g\u00f6re verileri birle\u015ftirmek gerekir. Buradaki birle\u015ftirme se\u00e7enekleri, Tek \u00d6l\u00e7\u00fcm i\u00e7in olanlarla ayn\u0131d\u0131r (v\u0259 ba\u015fqa se\u00e7iml\u0259r d\u0259 var. B\u00fct\u00fcn funksiyalar\u0131n t\u0259svirin\u0259<\/i> ve di\u011ferleri). Daha sonra veriler, istenirse, alanlardan birine g\u00f6re ayr\u0131labilir (alan Verileri Ay\u0131r<\/i>). \u00d6rnekte bunu OriginAirportID<\/i>alan\u0131na g\u00f6re yapt\u0131k. Sa\u011fdaki \u00f6l\u00e7\u00fcm grafi\u011finin art\u0131k birden fazla grafik olarak sunuldu\u011funa dikkat edin.<\/p>\n

\"Elastic
\n
\nAlan Anahtar Alanlar (Etkileyiciler)<\/i> bulunan anomalleri do\u011frudan etkiler. Varsay\u0131lan olarak burada her zaman en az bir de\u011fer olacakt\u0131r, ayr\u0131ca ek de\u011ferler ekleyebilirsiniz. Algoritma, analiz s\u0131ras\u0131nda bu alanlar\u0131n etkisini dikkate alacak ve en \"etkileyici\" de\u011ferleri g\u00f6sterecektir.<\/p>\n

Ba\u015flat\u0131ld\u0131ktan sonra Kibana aray\u00fcz\u00fcnde yakla\u015f\u0131k olarak \u015f\u00f6yle bir g\u00f6r\u00fcnt\u00fc ortaya \u00e7\u0131kacak.<\/p>\n

\"Elastic
\n
\nBu, belirtti\u011fimiz alan\u0131n her bir de\u011feri i\u00e7in anomali s\u0131cakl\u0131k haritas\u0131d\u0131r, OriginAirportID<\/i>. Tek \u00d6l\u00e7\u00fcm durumundaki gibi, renk anormal sapma seviyesini belirtir. Sahada anormal derecede \u00e7ok oturum a\u00e7ma gibi durumlar\u0131 izlemek i\u00e7in \u00f6rne\u011fin \u00e7al\u0131\u015fma istasyonlar\u0131 \u00fczerinden benzer bir analiz yapmak kolayd\u0131r. Zaten belirtmi\u015f oldu\u011fumuz Verileri Ay\u0131r<\/i>Olay G\u00fcnl\u00fc\u011f\u00fc Windows'ta \u015f\u00fcpheli olaylar , bunlar\u0131 burada toplay\u0131p analiz etmek de m\u00fcmk\u00fcnd\u00fcr.<\/a><\/noindex>S\u0131cakl\u0131k haritas\u0131n\u0131n alt\u0131nda anomali listesidir; her birinden detayl\u0131 analiz i\u00e7in Tek \u00d6l\u00e7\u00fcm g\u00f6r\u00fcn\u00fcm\u00fcne ge\u00e7ilebilir.<\/p>\n

Population<\/p>\n

Elastic Stack'te farkl\u0131 metrikler aras\u0131ndaki korelasyonlarda anomali aramak i\u00e7in \u00f6zel bir Population analizi vard\u0131r. Bu, belirli bir sunucunun performans\u0131nda ola\u011fand\u0131\u015f\u0131 de\u011ferleri aramak i\u00e7in kullan\u0131labilir; \u00f6rne\u011fin, hedef sisteme y\u00f6nelik isteklerin artmas\u0131 durumunda.<\/h2>\n

\nBu g\u00f6rselde, Population alan\u0131nda analiz edilen metriklere referans al\u0131nacak bir de\u011fer belirtilmi\u015ftir. Bu, s\u00fcre\u00e7 ad\u0131d\u0131r. Sonu\u00e7ta, her bir s\u00fcrecin CPU y\u00fck\u00fcn\u00fcn birbirine olan etkisini g\u00f6rece\u011fiz.<\/p>\n

\"Elastic
\n
\nDikkat edin, analiz edilen veri grafi\u011fi Tek \u00d6l\u00e7\u00fcm ve \u00c7oklu \u00d6l\u00e7\u00fcm durumlar\u0131ndan farkl\u0131d\u0131r. Bu, Kibana'da tasar\u0131m gere\u011fi, analiz edilen verilerin de\u011fer da\u011f\u0131l\u0131m\u0131n\u0131n daha iyi alg\u0131lanmas\u0131 amac\u0131yla yap\u0131lm\u0131\u015ft\u0131r.<\/p>\n

Grafikten, s\u00fcrecin anormal bir \u015fekilde davrand\u0131\u011f\u0131 g\u00f6r\u00fcnmektedir<\/p>\n

\"Elastic
\n
\nstress stres<\/i> (deyim ki, x\u00fcsusi bir proqramla yarad\u0131l\u0131b) serverd\u0259 poipu<\/i>, bu anomaliyan\u0131n yaranmas\u0131na t\u0259sir ed\u0259n (v\u0259 ya t\u0259sir ed\u0259n) \u015f\u0259xs.<\/p>\n

\u0130r\u0259lil\u0259mi\u015f<\/h2>\n

\nAnalitika inc\u0259 t\u0259nziml\u0259m\u0259 il\u0259. \u0130r\u0259lil\u0259mi\u015f t\u0259hlil zaman\u0131 Kibana-da \u0259lav\u0259 t\u0259nziml\u0259m\u0259l\u0259r g\u00f6r\u00fcn\u00fcr. Yarad\u0131lmas\u0131 menyusunda \u0130r\u0259lil\u0259mi\u015f d\u00fcym\u0259sin\u0259 basd\u0131qdan sonra bel\u0259 bir p\u0259nc\u0259r\u0259 a\u00e7\u0131l\u0131r. \u0130\u015f Detallar\u0131<\/i> , \u0259sas t\u0259nziml\u0259m\u0259l\u0259ri ehtiva etm\u0259diyin\u0259 g\u00f6r\u0259 bil\u0259r\u0259kd\u0259n burax\u0131l\u0131b.<\/p>\n

\"Elastic
\n
\n\u0130 summary_count_field_name<\/i> ist\u0259y\u0259 ba\u011fl\u0131 olaraq, s\u0259n\u0259dl\u0259rd\u0259n toplanm\u0131\u015f d\u0259y\u0259rl\u0259ri \u0259hat\u0259 ed\u0259n bir sah\u0259nin ad\u0131n\u0131 g\u00f6st\u0259r\u0259 bil\u0259rsiniz. Bu n\u00fcmun\u0259d\u0259 - d\u0259qiq\u0259d\u0259ki hadis\u0259l\u0259rin say\u0131. categorization_field_name<\/i><\/a><\/noindex> s\u0259n\u0259din i\u00e7\u0259risind\u0259 d\u0259yi\u015fk\u0259n bir d\u0259y\u0259r olan bir sah\u0259nin ad\u0131n\u0131 g\u00f6st\u0259rir. Bu sah\u0259nin maskas\u0131 analiz olunan m\u0259lumatlar\u0131 alt qruplara ay\u0131rma\u011fa imkan verir. N\u0259z\u0259rd\u0259n qa\u00e7\u0131rmay\u0131n Detektor \u0259lav\u0259 et<\/i> \u00f6l\u00e7\u00fcs\u00fcn\u00fc \u0259vv\u0259lki ill\u00fcstrasiyada.<\/p>\n

\"Elastic
\n
\nBurada m\u00fc\u0259yy\u0259n bir tap\u015f\u0131r\u0131q \u00fc\u00e7\u00fcn anomaliyan\u0131 a\u015fkar etm\u0259yi t\u0259nziml\u0259m\u0259k \u00fc\u00e7\u00fcn \u0259lav\u0259 t\u0259nziml\u0259m\u0259 bloku var. X\u00fcsusi istifad\u0259 hallar\u0131n\u0131 (x\u00fcsus\u0259n t\u0259hl\u00fck\u0259sizlik il\u0259 ba\u011fl\u0131) n\u00f6vb\u0259ti m\u0259qal\u0259l\u0259rd\u0259 m\u00fczakir\u0259 etm\u0259yi planla\u015fd\u0131r\u0131r\u0131q. N\u00fcmun\u0259 \u00fc\u00e7\u00fcn, bax\u0131n<\/a><\/noindex> t\u0259dqiq edilmi\u015f hallardan birin\u0259. Bu, nadir hallarda g\u00f6r\u00fcn\u0259n d\u0259y\u0259rl\u0259rin axtar\u0131lmas\u0131 il\u0259 ba\u011fl\u0131d\u0131r v\u0259 rare<\/a><\/noindex>.<\/p>\n

Bo\u015fluqda function<\/i> anomalilary axtarmaq \u00fc\u00e7\u00fcn m\u00fc\u0259yy\u0259n bir funksiyan\u0131 se\u00e7\u0259 bil\u0259rsiniz. Bunun yan\u0131nda, rare<\/i>, bir ne\u00e7\u0259 maraql\u0131 funksiya daha var - g\u00fcn\u00fcn vaxt\u0131<\/i> v\u0259 h\u0259ft\u0259nin vaxt\u0131<\/i><\/a><\/noindex>. Onlar m\u00fcvafiq olaraq g\u00fcn v\u0259 ya h\u0259ft\u0259 \u0259rzind\u0259 metrikl\u0259rin davran\u0131\u015f\u0131ndak\u0131 anomaliyalar\u0131 a\u015fkar edir. Dig\u0259r analiz funksiyalar\u0131 s\u0259n\u0259dd\u0259 var<\/a><\/noindex>.<\/p>\n

\u0130 field_name<\/i> analiz edil\u0259c\u0259k s\u0259n\u0259din sah\u0259sini g\u00f6st\u0259rir. By_field_name<\/i> burada g\u00f6st\u0259ril\u0259n s\u0259n\u0259d sah\u0259sinin h\u0259r bir ayr\u0131 d\u0259y\u0259ri \u00fczr\u0259 analiz n\u0259tic\u0259l\u0259rini ay\u0131rmaq \u00fc\u00e7\u00fcn istifad\u0259 edil\u0259 bil\u0259r. \u018fg\u0259r over_field_name<\/i> doldurulursa, o zaman \u0259vv\u0259lki analizini apard\u0131\u011f\u0131m\u0131z population analizi haz\u0131rlan\u0131r. \u018fg\u0259r partition_field_name<\/i>g\u00f6st\u0259rilirs\u0259, bu s\u0259n\u0259d sah\u0259sin\u0259 \u0259saslanaraq h\u0259r d\u0259y\u0259r \u00fc\u00e7\u00fcn ayr\u0131 \u0259sas x\u0259tl\u0259rin hesablanmas\u0131 h\u0259yata ke\u00e7irilir (d\u0259y\u0259r \u00fc\u00e7\u00fcn n\u00fcmun\u0259, m\u0259s\u0259l\u0259n, serverin ad\u0131 v\u0259 ya serverd\u0259ki prosesin ad\u0131 ola bil\u0259r). exclude_frequent<\/i> se\u00e7im ed\u0259 bil\u0259rsiniz ham\u0131s\u0131<\/i> v\u0259 he\u00e7 biri<\/i>, bu, s\u0259n\u0259d sah\u0259l\u0259rinin tez-tez g\u00f6r\u00fcn\u0259n d\u0259y\u0259rl\u0259rinin istisna (v\u0259 ya daxil edilm\u0259si) olaca\u011f\u0131n\u0131 ifad\u0259 edir.<\/p>\n

M\u0259qal\u0259d\u0259 Elastic Stack-da ma\u015f\u0131n \u00f6yr\u0259nm\u0259sinin imkanlar\u0131 haqq\u0131nda maksimum q\u0131sa s\u00f6yl\u0259m\u0259y\u0259 \u00e7al\u0131\u015fd\u0131q, h\u0259l\u0259 d\u0259 bir \u00e7ox detal bo\u015fda qald\u0131. Elastic Stack il\u0259 hans\u0131 hallar\u0131 h\u0259ll ed\u0259 bildiyinizi v\u0259 onu hans\u0131 tap\u015f\u0131r\u0131qlar \u00fc\u00e7\u00fcn istifad\u0259 etdiyinizi \u015f\u0259rhl\u0259rd\u0259 biz\u0259 bildirin. Biziml\u0259 \u0259laq\u0259 saxlamaq \u00fc\u00e7\u00fcn Habrda \u015f\u0259xsi mesajlardan v\u0259 ya veb saytdak\u0131 \u0259laq\u0259 formalar\u0131ndan istifad\u0259 ed\u0259 bil\u0259rsiniz.<\/a><\/noindex>.
\n
M\u0259nb\u0259: 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\udd47Elastic Stack-da Ma\u015f\u0131n \u00d6yr\u0259nm\u0259sini Anlay\u0131r\u0131q (o, h\u0259m\u00e7inin Elasticsearch, h\u0259m\u00e7inin ELK) | ProHoster","description":"Yenid\u0259n xat\u0131rladaq.","canonical_url":"https:\/\/prohoster.info\/az\/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":"az_AZ","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.","og:url":"https:\/\/prohoster.info\/az\/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\/az\/wp-json\/wp\/v2\/posts\/35274","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/comments?post=35274"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/posts\/35274\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/media\/26487"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/media?parent=35274"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/categories?post=35274"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/az\/wp-json\/wp\/v2\/tags?post=35274"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}