标签：
一、环境搭建
1. 下载
2. 解压
3.
mahout org.apache.mahout.clustering.syntheticcontrol.kmeans.Job
hdfs dfs -ls /output
转换成普通文本
hdfs dfs -ls /output/clusteredPoints
mahout seqdumper -i output/clusteredPoints -o dataset/clusteredPoints
cat clusteredPoints | more
cat clusteredPoints | awk `{print $2}` | sort | uniq
mahout vectordump -i output/data -o dataset/raw_data
标签：
原文地址：http://www.cnblogs.com/yeahwell/p/5826972.html
