Comments on: Mahout - Clustering (聚类篇)

By: Anonymous

Anonymous — Thu, 09 Jul 2015 13:16:45 +0000

In reply to ok. 执行mahout org.apache.lucene.benchmark.utils.ExtractReuters ./reuters-sgm ./reuters-out时报错说没有添加“mahout org.apache.lucene.benchmark.utils.ExtractReuters”这个类，这个类不是mahout自带的吗，还是跟版本有关系，劳烦博主指教。

By: ok

ok — Thu, 28 May 2015 04:48:16 +0000

In reply to darrenan. 用这个来解决 mahout clusterdump -i /user/coder4/reuters-kmeans/clusters-2-final -d /user/coder4/reuters-sparse/dictionary.file-0 -dt sequencefile -o reuters-kmeans-cluster-dump -b 10 -n 20

By: darrenan

darrenan — Tue, 09 Dec 2014 09:15:27 +0000

In reply to darrenan. 烦请楼主帮忙解决一下

By: darrenan

darrenan — Tue, 09 Dec 2014 09:13:17 +0000

mahout kmeans -i/user/coder4/reuters-sparse/tfidf-vectors -c/user/coder4/reuters-canopy-centroids/clusters-0-final -o/user/coder4/reuters-kmeans -dm org.apache.mahout.common.distance.CosineDistanceMeasure -x200- ow --clustering 按照楼主的指示，一直无法执行，报错如下： INFO hdfs.DFSClient: Could not complete /sport/sport_result/clusters-0/part-00003 retrying... INFO hdfs.DFSClient: Could not complete /sport/sport_result/clusters-0/part-00009 retrying...

By: question

question — Tue, 14 Oct 2014 07:16:51 +0000

如何发给你邮箱，有些问题请教

By: 啊

Tue, 16 Sep 2014 13:25:06 +0000

mahout clusterdump -i /user/coder4/reuters-kmeans/clusters-2-final -d ./reuters-sparse/dictionary.file-0 -dt sequencefile -o ./reuters-kmeans-cluster-dump/ -n 20
这一步失败，出现数组下表超出的异常，同样的现象参考：http://www.dataguru.cn/forum.php?mod=viewthread&tid=236472

希望博主能够解决这个问题，谢谢！

By: Anonymous

Anonymous — Thu, 17 Jul 2014 06:36:25 +0000

写的非常好！赞+1