Dear all,
First of all, thanks a lot for your work with the Scikit-learn package, it
is great and saved a lot of implementation time for me.
I've been having some time figuring out how to use the LASSO (via LARS),
though. I was trained with the "gamma" notation for the minimization
function for the LASSO (i.e. the notation used in Tibshirani's
paper<http://www-stat.stanford.edu/~tibs/lasso/lasso.pdf>),
so I'm really lost in figuring out what the relation between the alpha
parameter (according to the sci-kit-learn notation of the minimizing
function <http://scikit-learn.org/0.10/modules/linear_model.html#lasso>)
and the gamma parameter. I know how to get the grid of "gammas" that span
the possible ranges of values, but I can't seem to find the relation
between that and the grid of possible alpha parameters.
However, after reading through the tutorials, I found out that there's
actually a function which returns a "grid" of possible alphas, the
lasso_path<http://scikit-learn.org/0.10/modules/generated/sklearn.linear_model.lasso_path.html#sklearn.linear_model.lasso_path>function
in linear_models(). However, this also computes a list of "models"
along this grid...is there a way to only return the alphas? I need this
because I have my own version of Cross-Validation coded, which I really
need to use. For that matter, I only need a grid of alphas where to test
the model.
Cheers and thanks in advance for your responses!
--
Néstor
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
