Abstract

In today's society has entered the era of big data, data of the diversity and the amount of data increases to the data storage and processing brought great challenges, Hadoop HDFS and MapReduce better solves the these two problems. Classical K-means algorithm is the most widely used one based on the partition of the clustering algorithm. At the completion of the cluster configuration based on, the k-means algorithm in cluster mode of operation principle and in the cluster mode realized kmeans algorithm, and the experimental results are research and analysis, summarized the k-means algorithm is run on the Hadoop platform's strengths and limitations.

This work is licensed under a Creative Commons Attribution 4.0 License.