Currently we have a pagerank example for both hadoop and spark. Most of the pagerank code for hadoop was borrowed from https://github.com/danielepantaleone/hadoop-pagerank The spark pagerank is part of the spark examples that come preinstalled.
The spark logistic regression example is based off the psuedocode in the spark paper.
We also have scripts for installing hadoop and Spark, as well as one for clearing page caches. The excel file containing execution times for logistic regression is included as well