Aditya, thanks for offering to help! Let us know if there's any paperwork you need us to help submit for your participation.
Best Andrew On Mon, Feb 27, 2017 at 11:54 PM, Aditya <adityasarma...@gmail.com> wrote: > Hello Trevor, > > Apache Software Foundation has been accepted as a mentoring organization in > GSOC '17. Congratulations on that! > > When you mentioned GLM, I hope you were referring to the Issue > https://issues.apache.org/jira/browse/MAHOUT-1941 ? I will get in touch > with Saikat through the mailing list. > > Also, I've been giving some thought of implementing a new algorithm. I am > familiar with most Data Mining algorithms (Apriori, Decision Tree, Various > types of clustering algorithms) as well as basic Machine Learning > algorithms like Regression, Neural Networks. > > A clarification in regard to new algorithm development. Is there a plan for > incorporating new algorithms (other than Generalized Linear Model) in the > near future. Or any improvements / optimizations to existing algorithms? > > Regards, > Aditya > > > > > > > On Sun, Feb 26, 2017 at 5:03 AM, Trevor Grant <trevor.d.gr...@gmail.com> > wrote: > > > You are correct, Java and Scala are very similar. In fact you can import > > Java into scala (and theoretically the other way around too). > > > > Documentation... yea- that would be great... I'm trying to get the > website > > migrated from CMS (current system) to a Jekyll based system similar to > > Zeppelin or Flink... in the mean time, everyone I think is kind of > > standing-by on writing new docs. Including me. > > > > The only named algorithm in the road map right now is GLM- talk to Saikat > > and Jim I think are taking a crack at that. > > > > You are free (and encouraged) to implement algorithms you already > > understand well. > > > > As far as ASF in GSoC, candidly I don't know for sure. I'm not super > > familiar with that initiative. You could ask on > d...@community.apache.org > > - > > I remember seeing some chatter over there. > > > > best, > > tg > > > > > > Trevor Grant > > Data Scientist > > https://github.com/rawkintrevo > > http://stackexchange.com/users/3002022/rawkintrevo > > http://trevorgrant.org > > > > *"Fortunate is he, who is able to know the causes of things." -Virgil* > > > > > > On Sat, Feb 25, 2017 at 3:36 AM, Aditya <adityasarma...@gmail.com> > wrote: > > > > > Hello Trevor, > > > > > > I have gone through the two links that you sent me. Although I am not > > > familiar with scala, I was able to figure out that the files > > Fitter.scala, > > > Model.scala, UnsupervisedFitter.scala contain traits (which are similar > > to > > > interfaces in Java) and the LinearRegressionModel.scala contains the > core > > > code for regression. I wasn't able to understand specific syntactic > terms > > > like *trait LinearRegressionModel[K] extends RegressionModel[K]*, what > > is K > > > here? > > > > > > With respect to my knowledge in Scala, I've never had the opportunity > to > > > learn / work in Scala but I got a sense that it's model is similar to > > that > > > of Java. Having worked in Java, I could see some basic similarities in > > both > > > the languages' models. I've read that Scala is a language where OOP > meets > > > the functional paradigm. > > > > > > Also, Could you let me know where I could find the list of algorithms > > that > > > Mahout implements along with its documentation and what algorithms are > > > planned to be implemented soon? > > > The main web page just lists down the names. > > > > > > Thanks, > > > Aditya > > > > > > > > > On Thu, Feb 23, 2017 at 6:57 PM, Trevor Grant < > trevor.d.gr...@gmail.com> > > > wrote: > > > > > > > Hey Aditya- > > > > > > > > First of all, welcome to the community. We'd love to have you help > > > > contribute. > > > > > > > > The new algorithms framework is certainly a 'target rich > environment'. > > > > > > > > Since you already are familiar with DBSCAN, why not start there? > > > > > > > > If you check out: > > > > https://github.com/apache/mahout/tree/master/math-scala/ > > > > src/main/scala/org/apache/mahout/math/algorithms > > > > > > > > You'll see in general what our framework looks like.. > > > > > > > > You'll need to create a ClassificationModel trait similar to: > > > > https://github.com/apache/mahout/blob/master/math-scala/ > > > > src/main/scala/org/apache/mahout/math/algorithms/ > > > > regression/RegressorModel.scala > > > > > > > > Then you'll extend the the ClassificationModel with DBSCAN (or > possibly > > > > some intermediate trait, as LinearRegressionModel does before OLS). > > > > > > > > Perhaps I should have started by asking- how well do you know scala? > > > > > > > > Anyway, those are good places to get started! Let me know if I can > > help. > > > > > > > > tg > > > > > > > > Trevor Grant > > > > Data Scientist > > > > https://github.com/rawkintrevo > > > > http://stackexchange.com/users/3002022/rawkintrevo > > > > http://trevorgrant.org > > > > > > > > *"Fortunate is he, who is able to know the causes of things." > -Virgil* > > > > > > > > > > > > On Wed, Feb 22, 2017 at 4:23 PM, Aditya <adityasarma...@gmail.com> > > > wrote: > > > > > > > > > Hello everyone! > > > > > > > > > > I'm a senior year computer science student from Birla Institute of > > > > > Technology and Science, India. I have experience in fields like > Data > > > > Mining > > > > > and Machine Learning. Apart from doing basic coursework which > > included > > > > Data > > > > > Mining, Parallel Computing, and Machine Learning I have also worked > > on > > > > > research projects where I worked on building scalable DBSCAN like > > > > > clustering algorithms. > > > > > > > > > > I have gone through the Apache Mahout website and was wondering if > I > > > > > could *contribute > > > > > to Mahout in terms of algorithm **development / improvising > existing > > > > > algorithms.* > > > > > > > > > > I would be grateful if you could provide me with a starting point, > > from > > > > > where I can pick up and understand the Mahout ecosystem. I have no > > > > previous > > > > > experience in working with Apache Mahout or Spark but I have worked > > > with > > > > > the Map reduce model before (but haven't used Hadoop) > > > > > > > > > > I wish to work full time during summer and take part in the Google > > > Summer > > > > > of Code 2017 program by contributing to Apache Mahout. > > > > > > > > > > > > > > > Awaiting your replies! > > > > > > > > > > Cheers! > > > > > Aditya > > > > > > > > > > > > > > >
