Parallel K-means Clustering

This project is aimed at adapting Parallel K-means algorithm based on map reduce framework using Hadoop to make the clustering method applicable to large scale data. We compared parallel k-means with serial k means. We use speedup, scaleup and sizeup to evaluate the performances of our proposed algorithm. The results show that the proposed algorithm can process large datasets on commodity hardware effectively. Tools Used: Apache Hadoop version 1.2.1.