Re: [Scikit-learn-general] Graduate student contributing

2014-05-17 Thread Robert Layton
Thanks for your interest -- if you are looking for something to do, then have a look through bugs for starters -- we have a lot of PRs that need to be tested, bugs that need to be fixed. On 18 May 2014 12:42, Ronnie Ghose wrote: > do we have existing grad students contributing: yes > all you d

Re: [Scikit-learn-general] Scikit-learn-general Digest, Vol 52, Issue 21

2014-05-17 Thread Luca Puggini
Hi, I am wondering how sklearn.linear_model.LinearRegression works when p the number of variables is larger than n the number of samples. When p>n the least square estimator is not defined and so I was expecting to receive an error. When I run LinearRegressio with p>n I get an error only some tim

Re: [Scikit-learn-general] Graduate student contributing

2014-05-17 Thread Ronnie Ghose
do we have existing grad students contributing: yes all you do is submit pull requests and discuss your work: no paperwork. On Sat, May 17, 2014 at 9:17 PM, Sayan Ghosh wrote: > Hi, > > I am doing my PhD in an US university on machine learning. I am funded > through a graduate school fellowshi

[Scikit-learn-general] Graduate student contributing

2014-05-17 Thread Sayan Ghosh
Hi, I am doing my PhD in an US university on machine learning. I am funded through a graduate school fellowship. I am an international student, and hence not eligible for any source of income other than the fellowship. I actively use scikit-learn and wish to contribute to it and give back to the

[Scikit-learn-general] Wikipedia Example on Forward/Backward and Viterbi Algorithm

2014-05-17 Thread Subhabrata Banerjee
Dear Group, I had posted one request to Scikit Learn group regarding Hidden Markov Model(HMM) library rather specifically on Forward Probability and Viterbi Algorithm. One of your esteemed members had kindly pointed out an answer on it. He kindly suggested that, I should look into the following U

Re: [Scikit-learn-general] SVM class probabilities: Scikit vs Weka

2014-05-17 Thread Richard Cubek
On 05/17/2014 02:50 AM, Robert McGibbon wrote: > Have you tried comparing the results given by the two packages to one > another on an example dataset? > > -Robert No, because it won't show my anything about a qualitative difference in the implementations. I could take a simple 2D example as I did

Re: [Scikit-learn-general] Scikit learn HMM Library

2014-05-17 Thread Subhabrata Banerjee
Dear Sir, Thank you for the link. I was going through https://github.com/hmmlearn/hmmlearn/blob/master/hmmlearn/tests/test_hmm.py I saw you had written def setup_example_hmm(self): # Example from http://en.wikipedia.org/wiki/Forward-backward_algorithm Do you approve of Wikipedia Forward_B