Re: [Scikit-learn-general] Pull request on Kalman filter

Hello everyone, My name is Daniel Duckworth, and I am the person responsible for this pull request. To give you a quick idea of my background, I'm going to be a first year PhD student at University of Massachusetts, Amherst this fall, and I've done (not really publication quality) research in Bay

Re: [Scikit-learn-general] Pull request on Kalman filter

On Thu, Aug 02, 2012 at 02:13:29PM +0900, Mathieu Blondel wrote: >This example is confusing: it doesn't use the fit method. I suspect that >all these parameters do not need to be specified if you use fit. In theory, that's correct. In practice, I have had little success with relying on fit

Re: [Scikit-learn-general] Pull request on Kalman filter

On Thu, Aug 2, 2012 at 1:55 PM, Gael Varoquaux < [email protected]> wrote: > > I need to pass in up to 5 n_state by n_state matrices, and 3 n_state long > vectors. This example is confusing: it doesn't use the fit method. I suspect that all these parameters do not need to be specifie

Re: [Scikit-learn-general] Pull request on Kalman filter

On Thu, Aug 02, 2012 at 01:40:30PM +1000, Robert Layton wrote: >Precursor: I say this as someone who knows nothing about Kalman filters. >I don't think the parameterisation issue is too big of a deal. But have you checked how bad the situation was? https://github.com/duckworthd/scikit-lear

Re: [Scikit-learn-general] Pull request on Kalman filter

On 2 August 2012 07:02, Gael Varoquaux wrote: > Hi list, > > **Warning** This is a _long_ mail. Probably way too long, as people's > attention is going to drop. The fact that it's that long probably > expresses how confused I am. > Core developers, please do read it: it's about a PR on which someo

[Scikit-learn-general] Pull request on Kalman filter

Hi list, **Warning** This is a _long_ mail. Probably way too long, as people's attention is going to drop. The fact that it's that long probably expresses how confused I am. Core developers, please do read it: it's about a PR on which someone has been putting many, many, hours. This long running

Re: [Scikit-learn-general] Release 0.12 schedule

On Wed, Aug 01, 2012 at 02:35:29PM +0200, Andreas Müller wrote: > Soon it is time for a new release. I notices some people are going on holiday > (I think Lars and Gilles), > so maybe it would be good for wait them to be back. > Therefore I'd suggest releasing at the end of August. > Any opinions?

Re: [Scikit-learn-general] Release 0.12 schedule

> > In mid-september there will be a scikit-learn sprint in Paris: > http://www.pycon.fr/2012/ but we don't need to wait for that sprint > to > make a new release. > I think releasing before that makes more sense. Usually sprints create lots of PRs that need to be reviewed. > I don't want to p

Re: [Scikit-learn-general] Release 0.12 schedule

fine with me. I'd personally be happy to have : https://github.com/scikit-learn/scikit-learn/pull/947 (group lasso) https://github.com/scikit-learn/scikit-learn/pull/899 (multi task lasso) finished and merged before the release. just putting a bit of pressure on fabian and me :) Alex On Wed,

Re: [Scikit-learn-general] Release 0.12 schedule

2012/8/1 Charanpal Dhanjal : > Hi Giles, > Just a note to say that I wrote some code to do CART pruning on sklearn > trees, and would be happy to send that along. Is that useful to you? The > only problem is that the code is rather messy, but I can spend some time > cleaning it up. There is alread

Re: [Scikit-learn-general] Release 0.12 schedule

Hi Giles, Just a note to say that I wrote some code to do CART pruning on sklearn trees, and would be happy to send that along. Is that useful to you? The only problem is that the code is rather messy, but I can spend some time cleaning it up. Best wishes, Charanpal On 01/08/12 14:46, Gilles Lo

Re: [Scikit-learn-general] Release 0.12 schedule

2012/8/1 Andreas Müller : > Hey Everybody. > Soon it is time for a new release. I notices some people are going on holiday > (I think Lars and Gilles), > so maybe it would be good for wait them to be back. I will be off the next 2 weeks. The weekend after that I will attend EuroScipy in Brussels

Re: [Scikit-learn-general] Release 0.12 schedule

Hi, I am indeed leaving for holiday very soon and will be disconnected until mid-Augustus. My personal wish list is short: - #986: A full lazy argsort implementation of the tree construction algorithm. - #941: Tree post-pruning I plan to work on both at my return. #941 shouldn't take much time,

[Scikit-learn-general] Release 0.12 schedule

Hey Everybody. Soon it is time for a new release. I notices some people are going on holiday (I think Lars and Gilles), so maybe it would be good for wait them to be back. Therefore I'd suggest releasing at the end of August. Any opinions? My wish list looks like this (from more realistic to less

Re: [Scikit-learn-general] Getting the classification confidence of the SVC in sklearn

Hi. The decision_function (http://scikit-learn.org/dev/modules/generated/sklearn.svm.SVC.html#sklearn.svm.SVC.decision_function) should give you what you want. Best, Andy - Ursprüngliche Mail - Von: "abdalrahman eweiwi" An: [email protected] Gesendet: Mittwoch

Re: [Scikit-learn-general] Getting the classification confidence of the SVC in sklearn

Hi there.. There's the `decision_function(..)` method which you could use for this, im sure: | | decision_function(self, X) | Distance of the samples X to the separating hyperplane. | Parameters | -- | X : array-like, shape = [n_samples, n_features] | | R

[Scikit-learn-general] Getting the classification confidence of the SVC in sklearn

Hi all, Is there a direct way to obtain the distance from the SVM seperating hyperplance to a test sample in sklearn? if no? Could you please direct me to the parameters I need in sklearn to obtain this distance? Thanks A.Eweiwi ---