Re: [Scikit-learn-general] MultinomialNB partial_fit in 0.14?

2013/10/9 Ryan Rosario : > I had the same issue on a fresh clone from Git after building and > installing it. > > I was able to fix the issue by removing the six.with_metaclass() call in > the base class DiscreteNB in naive_bayes.py and then building and > reinstalling, but this doesn't seem like a

Re: [Scikit-learn-general] recommendation systems

2013/10/9 Eustache DIEMERT : > Another issue that comes from times to times is the fitness of the sklearn > API wrt to recommendation tasks. > > I believe it's pretty good if one has to manipulate - e.g.factorize - (item, > user) matrices, but it falls short when dealing with explore/exploit > scen

Re: [Scikit-learn-general] recommendation systems

Another issue that comes from times to times is the fitness of the sklearn API wrt to recommendation tasks. I believe it's pretty good if one has to manipulate - e.g.factorize - (item, user) matrices, but it falls short when dealing with explore/exploit scenarios. An example of that is the bandit

Re: [Scikit-learn-general] MultinomialNB partial_fit in 0.14?

I had the same issue on a fresh clone from Git after building and installing it. I was able to fix the issue by removing the six.with_metaclass() call in the base class DiscreteNB in naive_bayes.py and then building and reinstalling, but this doesn't seem like a good fix for a wider audience. I f

Re: [Scikit-learn-general] MultinomialNB partial_fit in 0.14?

On Tue, Oct 08, 2013 at 09:05:52PM +, Ryan Rosario wrote: > I am trying to use the partial_fit function on a MultinomialNB object in > 0.14-git. > The API documentation for 0.14 says that this function exists. When I > try to use it, I get an error: 0.14-git is before the release of 0.14, so i

Re: [Scikit-learn-general] recommendation systems

I believe there is already a recommender framework in the scikits family already called crab? http://muricoca.github.io/crab/ Few days back, one of the committers to sklearn spoke about the fact that he detected code in crab that looked like his own. Given that there is so much reuse, would it

[Scikit-learn-general] MultinomialNB partial_fit in 0.14?

Hi, I am trying to use the partial_fit function on a MultinomialNB object in 0.14-git. The API documentation for 0.14 says that this function exists. When I try to use it, I get an error: AttributeError: 'MultinomialNB' object has no attribute 'partial_fit' My code looks like the following: m

Re: [Scikit-learn-general] recommendation systems

On Tue, Oct 8, 2013 at 11:32 PM, Olivier Grisel wrote: > 2013/10/8 Gael Varoquaux : > > On Tue, Oct 08, 2013 at 07:47:40AM +0200, Gilles Louppe wrote: > >> Unfortunately, algorithms for recommender systems are not planned in > >> scikit-learn in the short or mid-term. > > > > Indeed in the short t

Re: [Scikit-learn-general] dev website rebuild

2013/10/8 Jaques Grobler : > +10 too! I am back at my desk, feel free to drop by when ready so that we can discuss how to do that and get started with the rackspace cloud stuff. -- Olivier -- October Webinars: Code for

Re: [Scikit-learn-general] recommendation systems

2013/10/8 Gael Varoquaux : > On Tue, Oct 08, 2013 at 07:47:40AM +0200, Gilles Louppe wrote: >> Unfortunately, algorithms for recommender systems are not planned in >> scikit-learn in the short or mid-term. > > Indeed in the short term, but are we sure that we want to close the door > to contributio

Re: [Scikit-learn-general] linear_model.SGDClassifier(): ValueError: ndarray is not C-contiguous when calling partial_fit()

Hi Tom, that's a bug - I'll open a ticket for it. A quick fix: call partial_fit instead of fit just before the ``for`` loop. - Peter 2013/10/4 Tom Kenter > Dear all, > > I am trying to run a linear_model.SGDClassifier() and have it update after > every example it classifies. > My code works f