Hi Vincent. Thanks! I'm poking around now. It looks like you'll need to
edit the scipy.io.loadmat call to use struct_as_record=False so that it
won't fail as written with newer scipys. Couple other bugs that I'm less
sure of the origin. But thanks for throwing what you have up, it looks like
i
On Wed, Oct 05, 2011 at 10:29:43AM +0200, Lars Buitinck wrote:
> > In the third paragraph of his paper, he mentions:
> > Even when software packages do not use the inefficient primitive [stepwise,
> > procedural] algorithm (as SciPy (Eads,2007) and the R (R Development Core
> > Team, 2011) methods h
2011/10/5 Brian Holt :
> Is there a way to specify the number of cluster centres required by
> meanshift? From the documentation and a bit of playing around, it seems
> like algorithm decides how many cluster centres to discover...
This is supposed to be the main selling point of the mean shift :
> Is there a way to specify the number of cluster centres required by
> meanshift? From the documentation and a bit of playing around, it seems
> like algorithm decides how many cluster centres to discover...
as far as I know that's the whole point of meanshift, the number of clusters
is data-dri
Is there a way to specify the number of cluster centres required by
meanshift? From the documentation and a bit of playing around, it seems
like algorithm decides how many cluster centres to discover...
--
All the data con
I am sooo happy to see trees.I will be a very very active user
and cant wait to take it for a test drive
On Wed, Oct 5, 2011 at 8:12 PM, Brian Holt wrote:
> Hi, PR310 is nearly ready to be merged, if anyone has any further comment,
> please let me know.
> Link: https://github.com/scik
Hi, PR310 is nearly ready to be merged, if anyone has any further comment,
please let me know.
Link: https://github.com/scikit-learn/scikit-learn/pull/310
This pull request contains an implementation of Classification and
Regression Trees. This version is highly optimised and is significantly
fas
2011/10/4 Conrad Lee :
> On Tue, Oct 4, 2011 at 10:36 PM, Gael Varoquaux
> wrote:
>>
>> On Tue, Oct 04, 2011 at 10:27:01PM +0200, Lars Buitinck wrote:
>> > You must mean from Θ(n² lg n) to Θ(n²). A generic Θ(n² lg n) algo is
>> > listed in many textbooks [1], I sure hope we don't have the naive al
Hi, PR364 is nearly ready to be merged, if anyone has any further comment,
please let me know.
Link:
https://github.com/scikit-learn/scikit-learn/pull/364#issuecomment-2295448
This PR adds the Silhouette Coefficient to metrics, and refactors the
metrics module a little.
- Robert
--
My public
