Uploaded July 2012 | Updated November 2026, 3 hours ago
This is part 3 of the speech titled: "Hadoop: Apache's Open Source Implementation of Google's Map/Reduce Framework" given by the Hacked Existence Team at Defcon 17 in Las Vegas.
In part 3 we start by looking at using awk to reorganize our input data set and the efficiency that is gained by this reorganization when performed on the Netflix data set.
We then look at the mapper code for some of our Netflix programs and compare execution times between mappers written in Java, Python and Awk.
After the mappers, we look at some reducer code written in Java.
All of the source code and project details from this speech can be found on the project page here: hackedexistence.com/project-hadoop.html
This is part 3 of the speech titled: "Hadoop: Apache's Open Source Implementation of Google's Map/Reduce Framework" given by the Hacked Existence Team at Defcon 17 in Las Vegas.
In part 3 we start by looking at using awk to reorganize our input data set and the efficiency that is gained by this reorganization when performed on the Netflix data set.
We then look at the mapper code for some of our Netflix programs and compare execution times between mappers written in Java, Python and Awk.
After the mappers, we look at some reducer code written in Java.
All of the source code and project details from this speech can be found on the project page here: hackedexistence.com/project-hadoop.html










