Raspodijeljeno ocjenjivanje brzih tokova podataka

master's thesis

• Title (english): Distributed scoring of fast data streams
• Author: Boris Vezmar
• Mentor: Boris Vrdoljak (mentor)
• Committee member: Boris Vrdoljak (predsjednik povjerenstva)
• Committee member: Mario Brčić (član povjerenstva)
• Committee member: Marko Horvat (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Definirani su prediktivni modeli i ocjenjivanje prediktivnih modela te je
razmotreno nekoliko osnovnih vrsta prediktivnih modela. Dan je primjer rada s
prediktivnim modelima korištenjem biblioteke Apache Spark MLlib.

Proučena je platforma Kubernetes uključujući kontejnerizirano
postavljanje aplikacija i servisa. Rad s kontejnerima prikazan je na primjeru
rada s platformom Docker. Definirana je arhitektura Kubernetes grozda
i temeljni Kubernetes objekti. Dan je primjer rada s platformom Kubernetes.

Proučena je platforma Apache Kafka. Definirani su temeljni koncepti i
komponente platforme Apache Kafka.

Implementiran je servis za ocjenjivanje prediktivnih modela, pri čemu su
proučene temeljne komponente implementacije.

Abstract (english)

Predictive models, as well as predictive model scoring were defined and
several basic predictive models were considered. An example of working with
predictive models using the Apache Spark MLlib library was given.

The Kubernetes platform was examined, including the containerized deployment of applications and services. Work with containers was demonstrated using work with the Docker platform as an example. Kubernetes cluster architecture and fundamental Kubernetes objects were defined. An example of working with the Kubernetes platform was given.

The Apache Kafka platform was examined. Basic concepts and components of the Apache Kafka platform were defined.

A service for scoring predictive models was implemented, whereby fundamental implementation components were examined.

• Keywords: prediktivni modeli; ocjenjivanje prediktivnih modela; Apache Spark; Kubernetes; grozd; Docker; Apache Kafka; Log4j
• Keywords (english): predictive models; predictive models scoring; Apache Spark; Kubernetes; cluster; Docker; Apache Kafka; Log4j
• Language: croatian
• URN:NBN: urn:nbn:hr:168:215491
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 14:09:25