Re: [Scikit-learn-general] [GSoC2015 Improve GMM module]

Hi Olivier, Andreas, Loïc and group, I have finished the derivations of VBGMM and DPGMM with four types of covariance matrix. The draft includes the updating functions, lower bound and predictive distributions. Next, I will shift my focus

Re: [Scikit-learn-general] [GSoC2015 Improve GMM module]

Anyway, thanks for your advice! I am OK with LaTeX now when using snippets and auto-completion within my IDE. Wei On Sat, Jun 6, 2015 at 11:46 AM, Sturla Molden wrote: > On 05/06/15 22:12, Wei Xue wrote: > > > I published a new post > >

Re: [Scikit-learn-general] Sample weighting in RandomizedSearchCV

Until sample_weight is directly supported in Pipeline, you need to prefix `sample_weight` by the step name with '__'. So for Pipeline([('a', A()), ('b', B())] use fit_params={'a__sample_weight': sample_weight, 'b__sample_weight': sample_weight} or similar. HTH On 10 June 2015 at 03:57, José Guilh

Re: [Scikit-learn-general] Sample weighting in RandomizedSearchCV

Hi Andy, Thanks for your reply. The full traceback is below, weights.shape and the training data shape are: (773,) (773, 82) I weas using a ExtraTreeClassifier but the same thing happens with an SVC. It doesn't seem to be an estimator-specific issue. """ Traceback (most recent call last): Fi

Re: [Scikit-learn-general] Facial Recognition and Facial Detection using sklearn

I was getting too many down votes on the stackoverflow question. I'm copying and pasting the question to the mailing list instead. I'm using Python to do facial recognition and came across a bit of code here. Please,

[Scikit-learn-general] Facial Recognition and Facial Detection using sklearn

Hi guys, I posted a question to Stack Overflow that you can find here ( http://stackoverflow.com/questions/30734692/scikit-learn-python-facial-recognition-and-facial-detection ). Basically, my problem is that I put over 300 pictures of myself (captured by slicing a video of myself into frames) in

Re: [Scikit-learn-general] Combining 2 Models with different targets

Hello, I'm not sure I understand your problem. Of course, if you limit your dataset to class 2 and 4 to predict if your observation belongs to 2 or not (and 4 or not), this will perform better than if you have all the classes together. The latter is just much more complicated. If observations from

Re: [Scikit-learn-general] Model evaluation on multiclass with ROC curves

There is currently no such function unfortunately. Is there a standard definition of multi-class roc-curves? Per-class? On 06/09/2015 05:43 AM, Herbert Schulz wrote: Hello everyone, is there a way in scikit-learn to evaluate my prediction ( multiclass ) with a ROC curve ? For example: One vs A

[Scikit-learn-general] Combining 2 Models with different targets

Hello, My question is the following: i have an multiclass problem ( classes 1-5 prediction). If i split the data into classes 1,3,5 ( first dataset) and classes 2 and 4 (second dataset). I trained models with every dataset separately. I'm getting better results insteat of using all classes in on

[Scikit-learn-general] Model evaluation on multiclass with ROC curves

Hello everyone, is there a way in scikit-learn to evaluate my prediction ( multiclass ) with a ROC curve ? For example: One vs All ? I'm searching just a function for that, if there is no one implemented in scikit learn to plot this, it is fine :). ps. I know there is an one vs all approach for