{"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\/et\/blog\/administrirovanie\/razbiraemsya-s-machine-learning-v-elastic-stack-on-zhe-elasticsearch-on-zhe-elk","title":{"rendered":"R\u00e4\u00e4gime Machine Learningist Elastic Stackis (tuntud ka kui Elasticsearch, ELK)","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

\"R\u00e4\u00e4gime
\n
\nTulet meenutama, et Elastic Stacki aluseks on mitte-suhteline andmebaas Elasticsearch, veebiliides Kibana ja andmete kogumise t\u00f6\u00f6tlejad (k\u00f5ige tuntum on Logstash, erinevad Beats, APM ja teised). \u00dcks meeldiv lisand kogu sellele tootevalikule on andmete anal\u00fc\u00fcs masin\u00f5ppe algoritmide abil. Artiklis uurime, mis need algoritmid endast kujutavad. Palun, lugege edasi.
\n<\/a><\/noindex>
\nMasin\u00f5pe on tasuline funktsioon tingimuslikult tasuta Elastic Stackis ja kuulub X-Packi paketti. Selle kasutamiseks on piisav, kui aktiveerida 30 p\u00e4eva prooviversioon p\u00e4rast installimist. Prooviperioodi l\u00f5ppemisel saab taotleda selle pikendamist v\u00f5i osta tellimuse. Tellimuse hind ei s\u00f5ltu andmemahust, vaid kasutatavate nodede arvust. Jah, andmemahu suurus m\u00f5jutab t\u00f5epoolest vajalike node'ide arvu, kuid selline litsentsimise l\u00e4henemine on siiski ettev\u00f5tte eelarve suhtes humanitaarsem. Kui k\u00f5rge j\u00f5udlus pole vajalik, on v\u00f5imalik ka kokku hoida.<\/p>\n

ML Elastic Stackis on kirjutatud C++ ja t\u00f6\u00f6tab v\u00e4ljaspool JVM-i, kus Elasticsearch ise t\u00f6\u00f6tab. See t\u00e4hendab, et protsess (mis muide on nimetatud autodetectiks) kasutab k\u00f5ik, mida JVM ei kasuta. Demoversioonis ei ole see nii kriitiline, kuid tootmiskeskkonnas on oluline eraldada eraldi s\u00f5lmed ML \u00fclesannete jaoks.<\/p>\n

Masin\u00f5ppe algoritmid jagunevad kaheks kategooriaks \u2014 \u00f5petusega<\/a><\/noindex> ja ilma \u00f5petuseta<\/a><\/noindex>. Elastic Stackis on algoritm kategooriast \u201eilma \u00f5petuseta\u201c. Matemaatikaaparaati masin\u00f5ppe algoritmidest saab vaadata. . Seal on kirjeldatud arhitektuuri<\/a><\/noindex> Anal\u00fc\u00fcsi teostamiseks kasutab masin\u00f5ppe algoritm kasutatavand dataid, mis on salvestatud Elasticsearchi indeksitesse. Anal\u00fc\u00fcsiv\u00f5imalusi saab luua nii Kibana liidese kui ka API kaudu. Kui kasutada Kibana, ei pea m\u00f5ningaid asju teadma. N\u00e4iteks t\u00e4iendavad indeksid, mida algoritm t\u00f6\u00f6protsessis kasutab.<\/p>\n

T\u00e4iendavad indeksid, mida kasutatakse anal\u00fc\u00fcsi k\u00e4igus <\/p>\n

.ml-state \u2014 teave statistiliste mudelite (anal\u00fc\u00fcsi seadistuste) kohta;<\/b>.ml-anomalies-* \u2014 masin\u00f5ppe algoritmide t\u00f6\u00f6 tulemused;
\n.ml-notifications \u2014 teavitamise seadistused anal\u00fc\u00fcsi tulemuste kohta.
\n.ml-notifications \u2014 anal\u00fc\u00fcsi tulemuste teavitamise seaded.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nElasticsearchi andmeestruktuur koosneb indeksitest ja neid sisaldavatest dokumentidest. Kui v\u00f5rrelda seda relatsioonilise andmebaasiga, siis saab indeksit v\u00f5rrelda andmebaasi skeemiga ja dokumenti tabeli kirjeiga. See v\u00f5rdlus on tingimuslik ja on toodud arusaadavuse lihtsustamiseks nendele, kes on Elasticsearchi kohta vaid kuulnud.<\/p>\n

API kaudu on saadaval sama funktsionaalsus nagu veebiliidese kaudu, seet\u00f5ttu n\u00e4itame selguse ja kontseptsioonide m\u00f5istmise huvides, kuidas seadeid Kibana kaudu seadistada. Vasakul men\u00fc\u00fcs on sektsioon Machine Learning, kus saab luua uue \u00fclesande (Job). Kibana liideses n\u00e4eb see v\u00e4lja nagu alloleval pildil. N\u00fc\u00fcd k\u00e4sitleme iga \u00fclesande t\u00fc\u00fcpi ja n\u00e4itame anal\u00fc\u00fcse, mida siin luua on v\u00f5imalik.<\/p>\n

\"R\u00e4\u00e4gime
\n
\n\u00dcksik m\u00f5\u00f5dik \u2014 \u00fche m\u00f5\u00f5diku anal\u00fc\u00fcs, mitme m\u00f5\u00f5diku \u2014 kahe v\u00f5i enama m\u00f5\u00f5diku anal\u00fc\u00fcs. M\u00f5lemal juhul anal\u00fc\u00fcsitakse iga m\u00f5\u00f5dikut isoleeritud keskkonnas, st algoritm ei arvesta paralleelselt anal\u00fc\u00fcsitud m\u00f5\u00f5dikute k\u00e4itumist, nagu v\u00f5iks tunduda mitme m\u00f5\u00f5diku puhul. Erinevate m\u00f5\u00f5dikute korrelatsiooni arvestamiseks v\u00f5ib kasutada populatsiooni anal\u00fc\u00fcsi. T\u00e4iustatud \u2014 see on algoritmide t\u00e4iendav seadistamine lisav\u00f5imalustega kindlate \u00fclesannete jaoks. <\/p>\n

\u00dcksik m\u00f5\u00f5dik<\/h2>\n

\n\u00dcheainsa m\u00f5\u00f5diku muutuste anal\u00fc\u00fcs on k\u00f5ige lihtsam, mida siinkohal teha. P\u00e4rast nupu 'Loo t\u00f6\u00f6' vajutamist otsib algoritm anomaaliaid.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nV\u00e4ljal Kogumine<\/i> v\u00f5ib valida anomaaliate otsimise l\u00e4henemisviisi. N\u00e4iteks, kui Min<\/i> peetakse anomaalseteks v\u00e4\u00e4rtusi, mis on allpool t\u00fc\u00fcpilisi. On Max, K\u00f5rge keskmine, Madal, Keskmine, Erakordne<\/i> ja teised. K\u00f5iki funktsioone saab vaadata lingi kaudu<\/a><\/noindex>.<\/p>\n

V\u00e4ljal V\u00e4li<\/i> m\u00e4rgitakse dokumentis numbriline v\u00e4li, mille p\u00f5hjal teeme anal\u00fc\u00fcsi.<\/p>\n

V\u00e4ljal Konteineri ulatus<\/i><\/a><\/noindex> \u2014 ajakava granulaarsus, mille alusel anal\u00fc\u00fcs viiakse l\u00e4bi. Saate usaldada automaatset s\u00fcsteemi v\u00f5i valida manuaalselt. Alloleval pildil on toodud liiga madala granulaarsuse n\u00e4ide \u2014 v\u00f5ite j\u00e4tta t\u00e4helepanuta anomaalia. Selle seadistuse abil saate muuta algoritmi tundlikkust anomaaliate suhtes.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nKogutud andmete kestus on v\u00f5tmetegur, mis m\u00f5jutab anal\u00fc\u00fcsi t\u00f5husust. Anal\u00fc\u00fcsi k\u00e4igus m\u00e4\u00e4rab algoritm korduvad ajavahemikud, arvutab usaldusintervallid (p\u00f5hisirged) ja tuvastab anomaaliad \u2014 ebatavalised k\u00f5rvalekalded meetri tavap\u00e4rasest k\u00e4itumisest. Lihtsaks n\u00e4iteks:<\/p>\n

P\u00f5hisirged v\u00e4ikese andmeosalusega:<\/p>\n

\"R\u00e4\u00e4gime
\n
\nKui algoritmil on, mille p\u00f5hjal \u00f5ppida \u2014 n\u00e4evad p\u00f5hisirged v\u00e4lja sellised:<\/p>\n

\"R\u00e4\u00e4gime
\n
\nP\u00e4rast \u00fclesande k\u00e4ivitamist tuvastab algoritm normist anomaalsed k\u00f5rvalekalded ja j\u00e4rjestab need anomaalia t\u00f5en\u00e4osuse alusel (k\u00f5rvaltoodud number t\u00e4histab vastava sildi v\u00e4rvi):<\/p>\n

Warning (sinine): v\u00e4hem kui 25
\nMinor (kollane): 25-50
\nMajor (oran\u017e): 50-75
\nCritical (punane): 75-100<\/p>\n

Alloleval graafikul on toodud n\u00e4ide leitud anomaaliatest.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nSiin on n\u00e4ha arvu 94, mis n\u00e4itab anomaalia t\u00f5en\u00e4osust. Kui v\u00e4\u00e4rtus on l\u00e4hedane 100-le, siis me n\u00e4eme anomaaliat. Diagrammi all oleva veeru jaoks on n\u00e4idatud t\u00e4htsusetult v\u00e4ike t\u00f5en\u00e4osus 0,000063634% selle metrika v\u00e4\u00e4rtuse ilmnemiseks.<\/p>\n

Kibanas anomaaliate otsimise k\u00f5rval v\u00f5ib k\u00e4ivitada ka prognoosimise. Seda saab teha h\u00f5lpsalt samast anomaalia vaatest \u2014 nupp Prognoos<\/i> paremas \u00fclanurgas.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nPrognoos ehitatakse maksimaalselt 8 n\u00e4dalat ette. Isegi kui v\u00e4ga tahaks, ei saa rohkem \u2014 selline on disain.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nM\u00f5nel juhul on prognoos v\u00e4ga kasulik, n\u00e4iteks kui j\u00e4lgitakse kasutaja koormust infrastruktuurile.<\/p>\n

Multi Metric<\/h2>\n

\nLiigume j\u00e4rgmise ML funktsiooni juurde Elastic Stackis \u2014 mitme metrika anal\u00fc\u00fcs samaaegselt. Kuid see ei t\u00e4henda, et anal\u00fc\u00fcsitakse \u00fche metri m\u00f5ju teisele. See on sama, mis Single Metric, ainult et mitme metrikaga \u00fchel ekraanil, et v\u00f5rrelda nende m\u00f5ju \u00fcksteisele. \u00dche metrika s\u00f5ltuvuse anal\u00fc\u00fcsimisest r\u00e4\u00e4gime osas Population.<\/p>\n

P\u00e4rast Multi Metric ruudu vajutamist ilmub seadeakna avamine. Neile peatume l\u00e4hemalt.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nEsmaltamiseks peab esmalt valima anal\u00fc\u00fcsi v\u00e4ljad ja andmete konsolideerimise need. Konsolideerimise v\u00f5imalused on samad, mis Single Metric jaoks (Max, K\u00f5rge keskmine, Madal, Keskmine, Erakordne<\/i> ja teised). Seej\u00e4rel jagatakse andmed soovi korral \u00fche v\u00e4lja j\u00e4rgi (v\u00e4li Split Data<\/i>). N\u00e4ites oleme seda teinud v\u00e4lja OriginAirportID<\/i>. Pange t\u00e4hele, et paremal poolel olevate m\u00f5\u00f5dikute graafik on n\u00fc\u00fcd esitatud mitme graafikuna.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nV\u00e4li Key Fields (Influencers)<\/i> m\u00f5jutab otseselt leitud anomaaliaid. Vaikimisi on siin alati v\u00e4hemalt \u00fcks v\u00e4\u00e4rtus, kuid te saate lisada t\u00e4iendavaid. Algoritm arvestab nende v\u00e4ljade m\u00f5ju anal\u00fc\u00fcsi k\u00e4igus ja n\u00e4itab k\u00f5ige \u201em\u00f5jukamaid\u201c v\u00e4\u00e4rtusi.<\/p>\n

P\u00e4rast k\u00e4ivitamist ilmub Kibana liidesesse umbes selline pilt.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nSee on nn anomaaliate soojuskaardiga iga v\u00e4ljade v\u00e4\u00e4rtuse kohta OriginAirportID<\/i>, mille oleme m\u00e4\u00e4ranud Split Data<\/i>. Nagu Single Metric puhul, t\u00e4histab v\u00e4rv anomaalse k\u00f5rvalekalde taset. Sarnast anal\u00fc\u00fcsi on mugav teha n\u00e4iteks t\u00f6\u00f6jaamade puhul, et j\u00e4lgida neid, kus on kahtlaselt palju volitusi jne. Oleme juba kirjutanud kahtlastest s\u00fcndmustest Windowsi EventLogis<\/a><\/noindex>, mida saab samuti siia koguda ja anal\u00fc\u00fcsida.<\/p>\n

Soojuskaardi all on anomaaliate loetelu, kust saab minna \u00dche M\u00f5\u00f5tme kuvamise juurde \u00fcksikasjalikuks anal\u00fc\u00fcsiks.<\/p>\n

Populatsioon<\/h2>\n

\nAneomaliate otsimiseks erinevate m\u00f5\u00f5tmete vahelise korrelatsiooni seas Elastic Stackis on olemas spetsialiseeritud populatsioonianal\u00fc\u00fcs. Just selle abil saab otsida anomaalseid v\u00e4\u00e4rtusi m\u00f5ne serveri j\u00f5udluses v\u00f5rreldes teistega, n\u00e4iteks suureneva p\u00e4ringute arvu korral sihts\u00fcsteemile.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nSelles illustratsioonis on populatsiooni v\u00e4ljas n\u00e4idatud v\u00e4\u00e4rtus, mille suhtes anal\u00fc\u00fcsitavad m\u00f5\u00f5tmed viitavad. Antud juhul on see protsessi nimi. Tulemusena n\u00e4eme, kuidas iga protsessi protsessorikoormus omavahel m\u00f5jutas.<\/p>\n

M\u00e4rkusena, et anal\u00fc\u00fcsitavate andmete graafik erineb \u00dche M\u00f5\u00f5tme ja Mitme M\u00f5\u00f5tme juhtudest. See on Kibana disaini poolt loodud, et parandada anal\u00fc\u00fcsitavate andmete v\u00e4\u00e4rtuste jaotuse tajumist.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nGraafikult on n\u00e4ha, et protsess stress<\/i> (\u00fctleme nii, et see on genereeritud spetsiaalse utiliidi kaudu) serveris poipu<\/i>, mis m\u00f5jutas (v\u00f5i oli selle anomaalia m\u00f5jutaja) selle anomaalia tekkimist.<\/p>\n

Advanced<\/h2>\n

\nT\u00e4psustatud anal\u00fc\u00fcs. Advanced anal\u00fc\u00fcsi puhul ilmuvad Kibanas t\u00e4iendavad s\u00e4tted. P\u00e4rast Advanced plaatide loomiseks men\u00fc\u00fcs klikkimist avaneb selline aken vahekaartidega. Vahekaart T\u00f6\u00f6 \u00fcksikasjad<\/i> j\u00e4eti teadlikult vahele, seal on p\u00f5hiseaded, mis ei seondu otseselt anal\u00fc\u00fcsi seadistamisega.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nV summary_count_field_name<\/i> on vabatahtlik, et m\u00e4\u00e4rata v\u00e4lja dokumentides olev v\u00e4lja nimi, mis sisaldab agrageeritud v\u00e4\u00e4rtusi. Antud n\u00e4ites \u2014 s\u00fcndmuste arv minutis. V categorization_field_name<\/i><\/a><\/noindex> m\u00e4\u00e4rab v\u00e4lja nime, mille v\u00e4\u00e4rtus dokument sisaldab mingit muutlikku v\u00e4\u00e4rtust. Selle v\u00e4lja mustri j\u00e4rgi saab anal\u00fc\u00fcsitud andmeid jagada alagrupikseks. Pange t\u00e4hele nuppu Lisa detektor<\/i> eelneval illustratsioonil. Allpool on tulemused p\u00e4rast selle nupu vajutamist.<\/p>\n

\"R\u00e4\u00e4gime
\n
\nSiin on t\u00e4iendav seadistuste plokk detektori seadistamiseks teatud \u00fclesande jaoks. Konkreetsete kasutusjuhtumite (eriti turvalisuse osas) \u00fcle arutame j\u00e4rgmistes artiklites. N\u00e4iteks, vaadake<\/a><\/noindex> \u00fchte selgitatud juhtumit. See on seotud harva esinevate v\u00e4\u00e4rtuste otsimisega ja see realiseeritakse funktsiooniga rare<\/a><\/noindex>.<\/p>\n

V\u00e4ljal function<\/i> saad valida kindla funktsiooni anomaaliate leidmiseks. Lisaks haruldane<\/i>, on veel paar huvitavat funktsiooni \u2014 p\u00e4eva_aeg<\/i> ja n\u00e4dala_aeg<\/i><\/a><\/noindex>. Need tuvastavad metoodika k\u00e4itumise anomaaliad p\u00e4eva v\u00f5i n\u00e4dala jooksul. \u00dclej\u00e4\u00e4nud anal\u00fc\u00fcsifunktsioonid on dokumentatsioonis<\/a><\/noindex>.<\/p>\n

V v\u00e4li_nimi<\/i> m\u00e4rkige dokumentide v\u00e4li, mille alusel anal\u00fc\u00fcs toimub. V\u00e4lja_nime j\u00e4rgi<\/i> saab kasutada tulemuste anal\u00fc\u00fcsi jagamiseks iga konkreetse v\u00e4\u00e4rtuse j\u00e4rgi, mis on siin dokumendi v\u00e4ljas m\u00e4rgitud. Kui t\u00e4idate \u00fcle_v\u00e4lja_nime<\/i> saate populatsiooni anal\u00fc\u00fcsi, millest juba varem r\u00e4\u00e4kisime. Kui m\u00e4\u00e4rata v\u00e4\u00e4rtus jaotuse_v\u00e4lja_nimi<\/i>, siis selle dokumendi v\u00e4lja alusel arvutatakse eraldi baasjooned iga v\u00e4\u00e4rtuse jaoks (n\u00e4iteks v\u00f5ib v\u00e4\u00e4rtus olla serveri v\u00f5i serveriprotsessi nimi). v\u00e4lja_sage<\/i> saab valida all<\/i> v\u00f5i ei midagi<\/i>, mis t\u00e4hendaks sagedaste dokumendi v\u00e4li v\u00e4\u00e4rtuste v\u00e4listamist (v\u00f5i kaasamist).<\/p>\n

Artiklis p\u00fc\u00fcdsime l\u00fchidalt tutvustada masin\u00f5ppe v\u00f5imalusi Elastic Stackis, kuid palju detaile j\u00e4i katte alla. R\u00e4\u00e4kige kommentaarides, milliseid juhtumeid olete Elastic Stacki abil lahendanud ja milliste \u00fclesannete jaoks te seda kasutate. Meiega \u00fchenduse saamiseks v\u00f5ite kasutada isiklikke s\u00f5numeid Habril v\u00f5i tagasisidevormi meie veebisaidil<\/a><\/noindex>.
\n
Allikas: 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\udd47Selgitame masin\u00f5pet Elastic Stackis (tuntud ka kui Elasticsearch, ELK) | ProHoster","description":"Tuletame meelde, et Elastic Stack p\u00f5hineb mitte-relationaalsel andmebaasil Elasticsearch, veebiliidesel Kibana ning andmete kogumise ja t\u00f6\u00f6tlemise vahenditel (k\u00f5ige tuntumad on Logstash, erinevad Beats, APM jne). \u00dcks meeldiv t\u00e4iendus kogu nimetatud tooteportfellile on andmete anal\u00fc\u00fcs masin\u00f5ppe algoritmide abil. Artiklis uurime, mis need algoritmid endast kujutavad. Palume lugeda edasi. Masin\u00f5pe","canonical_url":"https:\/\/prohoster.info\/et\/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":"et_EE","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\/et\/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\/et\/wp-json\/wp\/v2\/posts\/35274","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/comments?post=35274"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/posts\/35274\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/media\/26487"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/media?parent=35274"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/categories?post=35274"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/tags?post=35274"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}