Design and implementation of Web log preprocessing based on Hadoop
Jing Wang · Telecom Engineering Technics and Standardization · 2011
Web log preprocessing is an important step in Web log mining,Web log is a prerequisite to obtain accurate information,directly affect the accuracy of the follow mining algorithms.Base on the massive Web log,this paper advanced an optimized Web log preprocessing method and implements it via distributed computing platform Hadoop.We compared the Hadoop platform’s performance with the stand-alone’s,thus proved the efficiency of Web log preprocessing on Hadoop.