/XML2ARFF-Converter

XML to ARFF converter for Weka data mining app

Primary LanguageJava

XML2ARFF converter for Weka. It uses: 1. Weka.jar, 2. SAX parser

- This is specific to stackoverflow.com's datadump which is in XML format.
- You will need to change the some files to make it work for your XML data dump. (XMLValues.java)
  - Create your POJO for instances of the data dump
  - Update other files with the values you have in your XML file.


Sample inout file: (Presently I am only reading Score, ViewCount, Tags and Creation Date)
 <row 
	Id="3835644" 
	PostTypeId="1" 
	AcceptedAnswerId="xxxxxx" 
	CreationDate="2010-09-30T23:58:10.803" 
	Score="0" 
	ViewCount="48" 
	Body="body of the question goes here" 
	OwnerUserId="xxxxxx" 
	LastActivityDate="2010-10-01T00:22:57.203"
	ClosedDate="2010-10-01T06:06:01.407" 
	Title="title of the question goes hers" 
	Tags="tags go here" 
	AnswerCount="2" 
	CommentCount="1" 
	FavoriteCount="1" 
/>

TO-DO: Make it more generic.