Re: Installation question

Yes you are right. One more question. I ran "mvn install" in the root folder of Mahout and the output shows all things are done [INFO] [INFO] Reactor Summary: [INFO] [INFO] Mahout Build Tools .

Re: Installation question

Try mahout-distribution-0.9-src.tar.gz or mahout-distribution-0.9-src.zip if you want to build the project. The version you have contain

Re: Installation question

I have downloaded "mahout-distribution-0.9.tar.gz" and here is the content. hadoop@solaris:~/mahout-distribution-0.9$ ls bin  mahout-core-0.9.jar conf mahout-examples-0.9-job.jar docs mahout-examples-0.9.jar examples  

Re: Cluster Dumper in 0.9

In the same separate post that u r alluring to it was also discussed that you should upgrade to 0.9 which fixes that issue and running a seqdumper on clustered output should give the weight of the vectors and the distance of each vector from the cluster centroid. Did u try running a seqdumper o

Re: Cluster Dumper in 0.9

Thanks, make sense. Now in a seperate post we discussed that *"The Clustered output should display the vectors with the vectorid that belong to a specfic cluster along with the distance of that vector from the cluster center."* So, based on the above code, we are loosing few things for named vect

Re: complementary naive bayes classifier

Complementary Naive Bayes classification is for unbalanced datasets and is available in Mahout, see the relevant section in the Rennie paper on this subject - http://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf The code for Theta Normalization seems complete, so not sure as to why its stil

Re: Cluster Dumper in 0.9

The key in the CSV is the clusterId (and not the named vector). Here's the complete code snippet which should make sense. {Code}     Cluster cluster = clusterWritable.getValue();     line.append(cluster.getId());     List points = getClusterIdToPoints().get(cluster.getId());     if (points != n

Re: complementary naive bayes classifier

Suneel and Andrew, Many thanks for the clarification, I do have included the -c option when train the naive bayes. Will debug the code later on to discover more details. A general question, what are the options available in Mahout when we have very imbalanced data sets? Regards, On Fri, Feb 2

Re: Installation question

Hi, Regarding the Maven message you get, it seems that there is no pom.xml file in your mahout-distribution-0.9 directory. What file did you download? The one suffixed by -src.zip or -src.targ.gz ? Could you try a simple 'ls' (or 'dir' if you are using windows) to see which files you have ?  Re

Installation question

Hi, I have followed the steps stated in https://cwiki.apache.org/confluence/display/MAHOUT/BuildingMahout to install Mahout. However I get an error at "mvn install" hadoop@solaris:~/mahout-distribution-0.9$ mvn install [INFO] Scanning for projects... [INFO]

Re: Mahout with SQL SERVER

You can give o.a.m.cf.taste.impl.model.jdbc.GenericJDBCDataModel a try. If that doesn't work, you need to create a custom implementation of AbstractJDBCDataModel which shouldn't be too hard. --sebastian On 02/23/2014 06:11 PM, Ahmed Kamal wrote: Dear All , I just have a question. I chose to

Mahout with SQL SERVER

Dear All , I just have a question. I chose to use Apache Mahout as my recommendation engine but at the same time due to some reasons it would be easier if I could store my data in a MS SQL Server db. Can mahout be connected with SQL Server easily without any problems ? Could it result in perfo

Mahout installation and configuration on Windows

Hi, I am familiar with Hadoop and Machine Learning. I do know what Mahout is all about. To get started, I am looking for some tutorial/documentation on setting up Mahout and configuring it on a Windows machine. Can anyone share some links/references for this? Thank you! With Regards, Abhishek