The basic algorithms are not too bad - I have implemented PMF and KPMF
(probabilistic matrix factorization and kernelized PMF) in Python fairly
recently. Non-optimized, but the runtime was still not terrible - one form
of PMF is basically a tweaked stochastic gradient descent.
I talked (very briefly) with Jake about this at SciPy. One of the questions
is how to specify "missing" data, as sklearn typically expects full (or
"full sparse" if that makes sense) matrices. If there is a good way to
specify which data is "missing", then many of these algorithms become very
similar to existing things in sklearn.decomposition , except they only use
the non-missing data.
It would be neat to have though - lots of very cool applications. I would
be glad to help with this if the API stuff can be fleshed out.
Kyle
On Wed, Oct 9, 2013 at 1:08 PM, Robert G <[email protected]> wrote:
> Currently, the go-to solutions for prototyping recommender systems are
> MyMediaLite and Graphchi. Both of which are command line tools implemented
> in C# and C++. It would be useful to have tools for prototyping
> recommender systems in a python environment. I'm sure that many would
> support it.
>
> On Oct 8, 2013, at 10:31 PM,
> [email protected] wrote:
>
> Re: recommendation systems
>
>
>
>
> ------------------------------------------------------------------------------
> October Webinars: Code for Performance
> Free Intel webinars can help you accelerate application performance.
> Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most
> from
> the latest Intel processors and coprocessors. See abstracts and register >
> http://pubads.g.doubleclick.net/gampad/clk?id=60134071&iu=/4140/ostg.clktrk
> _______________________________________________
> Scikit-learn-general mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
------------------------------------------------------------------------------
October Webinars: Code for Performance
Free Intel webinars can help you accelerate application performance.
Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from
the latest Intel processors and coprocessors. See abstracts and register >
http://pubads.g.doubleclick.net/gampad/clk?id=60134071&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
