Re: Has anyone implemented true L-LDA out of Mahout?

It seems that I have to feed LDA w/ both of topic-terms doc-topics. Can anyone tell me how to build a seed model to begin with? Given this labeled corpus example, 0 | 1 | 2 | 3 | total '4' terms - | - | - | - | - 3 | 1 | 0 | 0 - label 0 6 | 2 | 0 | 0 - label 0 0 | 0 | 3 | 1 - label 1 0 | 0 |

Re: Using SparseVectorsFromSequenceFiles () in Java

Darius, It seems you hit a Hadoop on Windows issue, it might have something to do with how Hadoop sets file permissions. Gokhan On Tue, Sep 17, 2013 at 3:02 PM, Darius Miliauskas dariui.miliaus...@gmail.com wrote: That's like a charm, Gokhan, your suggestion was on point again. However...

Running RecommenderJob remotely

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hi, I may be approaching this all wrong, but I have a shiny hadoop cluster (with HBase, HDFS etc running) and would like to leverage that to do Taste based recomendations (user based). I have been looking through the docs and Javadoc and see that

Re: running mahout on Hadoop 2.0.0-cdh4.3.1

Hi Rohit I also run into the IncompatibleClassChangeError when using the streaming k means feature. Apparently this only applies to some parts of the code base because I have not run into this issue with other distributed functionalities of mahout. Were you able to solve this? If so, what were

Re: Using SparseVectorsFromSequenceFiles () in Java

Hi again, Gokham, yeah, I stucked with this Windows issues since all my attempts to write the code face it (even tried to change libraries but it did not resolve). Darius 2013/9/18 Gokhan Capan gkhn...@gmail.com Darius, It seems you hit a Hadoop on Windows issue, it might have something to

Re: Using SparseVectorsFromSequenceFiles () in Java

Hi Darius, On Sep 18, 2013, at 1:10am, Gokhan Capan wrote: It seems you hit a Hadoop on Windows issue, it might have something to do with how Hadoop sets file permissions. From my experience, only the (old) 0.20.2 version of Hadoop works well with Cygwin, otherwise you run into file

Re: Reuters Example in WindowsCygwin

Thanks, Michael. I looked more deeper at cluster-reuters.sh, and tried to play with paths in System variables. I set $HADOOP_HOME as C:\cygwin64\usr\local\hadoop, and I got: DARIUS@DARIUS-PC /usr/local/mahout/examples/bin $ ./build-reuters.sh Please call cluster-reuters.sh directly next time.

Need More Details About MAHOUT_LOCAL

Hi, fans of mahout There is MAHOUT_LOCAL used in the script. In the file mahout it is described as # MAHOUT_LOCAL set to anything other than an empty string to force #mahout to run locally even if #HADOOP_CONF_DIR and HADOOP_HOME are set 1. Can somebody give more info about

Re: running mahout on Hadoop 2.0.0-cdh4.3.1

Hi Barrie, We were not able to solve this issue. Hence we decided to install Apache hadoop 1.04 version. Thanks, Rohit On Wed, Sep 18, 2013 at 8:32 AM, B Kersbergen kersberg...@gmail.com wrote: Hi Rohit I also run into the IncompatibleClassChangeError when using the streaming k means

Re: Preference to vectors for clustering

The simplest way to cluster users would be to take the output of PreparePreferenceMatrixJob, which creates a DistributedRowMatrix (DRM) of all user prefs. The rows are users the columns items, the values are preference values. Cluster the rows. Transpose that matrix and clustering rows will