Statistical widgets for Orange platform

Amela Rakanović (2013) Statistical widgets for Orange platform. EngD thesis.

Preview

Abstract

Orange is an open source data mining tool with command-line and graphical user interface. It offers plenty of machine learning algorithms and visualization, but almost none of the established statistical data analysis methods. The goal of this work was to fill that gap and develop four graphical widgets for Orange. Each widget contains interactive user interface, required statistical tests and visualizations of data. With added widgets it is easier and more intuitive to run statistical analysis, store the majority of charts and connect with other widgets. The widgets were developed in the programming language Python 2 with the help of the libraries SciPy and NumPy.

Item Type:

Thesis (EngD thesis)

Keywords:

statistics, hypothesis tests, widgets, user interface, data visualization, plotting

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
izr. prof. dr. Janez Demšar	257	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=10096724)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

2125

Date Deposited:

03 Sep 2013 16:54

Last Modified:

13 Sep 2013 14:55

URI:

http://eprints.fri.uni-lj.si/id/eprint/2125

Actions (login required)

View Item