There is a menu full of references starting here: http://mahout.apache.org/users/sparkbindings/home.html
Mahout-Samsara is a Linear Algebra DSL written as an extension of Scala that includes most of the R-Like primitives you need. As opposed to MLlib, which has a good number of algorithms but lacks the generality. They both run on Spark and can be combined in your own code. The Linear Regression Ted mentions is in Hadoop MapReduce and so is not a good starting point code-wise. On Jun 1, 2015, at 4:53 AM, Punit Naik <[email protected]> wrote: So is the MapReduce implementation of Regression written in Mahout-Samsara? I have written stable MapReduce codes for Regression, that is why I was interested. Thank You Punit Naik On Sun, May 31, 2015 at 9:22 PM, Scott Lett, PhD <[email protected]> wrote: > Ted, > Where is the first place to start learning Mahout-Samsara? > Looking forward to learning more, > Scott > > -----Original Message----- > From: Ted Dunning [mailto:[email protected]] > Sent: Saturday, May 30, 2015 12:33 AM > To: [email protected] > Subject: Re: Regression using MapReduce > > Mahout is deprecating pretty much all of the classic MapReduce > implementations in any case in favor of algorithms based fundamentally on a > new linear algebra system known as Mahout-Samsara. > > > > On Fri, May 29, 2015 at 10:52 PM, Punit Naik <[email protected]> > wrote: > >> Hello all users >> >> I just wanted to know if Mahout has MapReduce implementation of >> Regression algorithms or not. >> >> Thank You >> >> Punit Naik >> > >
