Online Classification and Frequent Pattern Mining using Map-Reduce

by Robin Anil for The Apache Software Foundation

Last summer I worked on implementing a high precision (Complementary) Naïve Bayes classifier for text data. The model building used Hadoop and scaled well for large dataset like Wikipedia. My proposal has two broad objectives. 1. Create an an online + batch classification system for the current NB/CNB Classifier using HBase 2. Implement Parallel FP Growth algorithm and create a tag-tag relationship from the wikipedia dataset using the same.