Hello,
1- Can we debug Hadoop/Mahout with the available bin files? Or we have to do
rebuild them? Probably they are compiled with optimizations
2- I cannot find a procedure on how to build Hadoop/Mahout in debug mode. If
anyone knows, please let me know.
Since I am a gcc/make guy, maybe these
Hello everyone,
I'm currently writing an application which uses Mahout's NaiveBayes
classification algorithm. In my program, the requirements of my application
reflect a typical classification problem.
1. Train a NaiveBayes model and save it.
2. Use the saved NaiveBayes model to classify new data.
TestNaiveBayesDriver.java
On Friday, March 14, 2014 8:27 AM, Tharindu Rusira tharindurus...@gmail.com
wrote:
Hello everyone,
I'm currently writing an application which uses Mahout's NaiveBayes
classification algorithm. In my program, the requirements of my application
reflect a typical
Hi,
I'm running Mahout 0.9 and Hadoop 1.1.1 and I'm following the
examples/bin/cluster-reuters.sh script, but manually entering commands
because the script crashes. Data preparation runs smoothly, but when I
call cvb, it times out prior to writing topics. Any ideas? Thanks in
advance and here
Its not a timeout but an exception that's being thrown while generating
ldatopics due to a list of terms being empty. Looking into it
On Friday, March 14, 2014 12:16 PM, Steven Cullens srcull...@gmail.com wrote:
Hi,
I'm running Mahout 0.9 and Hadoop 1.1.1 and I'm following the
the issue is that the numTerms in dictionary is 0.
learning for LDA on
reuters-lda/reuters-matrix/matrix (numTerms: 0), finding 5-topics, with
document/topic prior 1.0E-4, topic/term prior 1.0E-4. Maximum iterations
to run will be 2, unless the change in perplexity is less than 0.0. Topic
I misspelled dictionary when calling cvb. Thanks for your help, Suneel.
Otherwise, I'd be at the office on the weekend trying to figure out the
problem.
On Fri, Mar 14, 2014 at 12:41 PM, Suneel Marthi suneel_mar...@yahoo.comwrote:
the issue is that the numTerms in dictionary is 0.
learning