Pros and Cons of Certain Quantitative Languages

[mhy]

Thank you for your already helpful informations, guys.

However we did not speak about the statistical/ mathematical libraries at all. I am picking out some typical statistical issues in quantitative analysis.

Are there libraries for
- Missings handling
- Matrix and dataframe data type
- Robust regression
- Alternative GLM distribution plugins, e.g. Tweedie's Poisson Gamma distribution (for running a GLM with Tweedie Distrubtion for instance)
- Decision Trees (CART and CHAID)
- Support Vector Machines
- Neural Networks

available in

Java, C++, Python, MATLAB, R?

Martin

I'm almost certain these are available in R:

-Missings handling
-Matrix/dataframe
-Robust regression
-Decision Trees
-SVM
-NN

 

[Polter]

Thank you for your already helpful informations, guys.

However we did not speak about the statistical/ mathematical libraries at all. I am picking out some typical statistical issues in quantitative analysis.

Are there libraries for
- Missings handling
- Matrix and dataframe data type
- Robust regression
- Alternative GLM distribution plugins, e.g. Tweedie's Poisson Gamma distribution (for running a GLM with Tweedie Distrubtion for instance)
- Decision Trees (CART and CHAID)
- Support Vector Machines
- Neural Networks

available in

Java, C++, Python, MATLAB, R?

Definite YES for R for most of these: http://cran.r-project.org/web/views/

Also yes for many of these for Python -- in particular, take a look at the packages comprising the SciPy Stack specification: http://scipy.org/stackspec.html

C++:
http://en.cppreference.com/w/cpp/numeric
http://www.boost.org/doc/libs/?view=category_Math
// In particular: http://www.boost.org/doc/libs/master/libs/math/
// Take note of: http://www.boost.org/doc/libs/master/libs/math/doc/html/dist.html
http://dlib.net/
http://mlpack.org/
http://image.diku.dk/shark/
http://shogun-toolbox.org/
https://github.com/JohnLangford/vowpal_wabbit
http://opencv.org/
http://caffe.berkeleyvision.org/
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
http://www.csie.ntu.edu.tw/~cjlin/liblinear/
http://www.sgi.com/tech/mlc/
http://waffles.sourceforge.net/
Linear Algebra (matrices, vectors): either http://eigen.tuxfamily.org/ or http://viennacl.sourceforge.net/ or https://github.com/NumScale/nt2

Java:
http://www.cs.waikato.ac.nz/ml/weka/
http://spark.apache.org/mllib/
https://mahout.apache.org/
https://github.com/EdwardRaff/JSAT/tree/master
// seems relatively scarce in comparison, but then again, I'm not a heavy Java user -- perhaps there's more?

HTH!

 

[Martin Thomson]

I'm almost certain these are available in R:

-Missings handling
-Matrix/dataframe
-Robust regression
-Decision Trees
-SVM
-NN

- Alternative GLM distribution plugins, e.g. Tweedie's Poisson Gamma distribution (for running a GLM with Tweedie Distrubtion for instance)

are available in R as well.

E.g. http://cran.r-project.org/web/packages/tweedie/tweedie.pdf

Martin