On Thu, Dec 01, 2011 at 03:48:34PM -0700, María Helena Mejía Salazar wrote:
> I am running plot_dbscan.py example. Lines 45-48 have problems.
> metrics.adjusted_mutual_info_score method and metrics.silhouette_score
> don't exist.
Chances are that the examples work for the scikit-learn versio
On Sat, Nov 19, 2011 at 09:15:43PM -0500, James Bergstra wrote:
> 2. Gaussian process w. Expected Improvement global optimization.
> This is an established technique for global optimization that has
> about the right scaling properties to be good for hyper-parameter
> optimization.
Without knowin
On Thu, Nov 24, 2011 at 09:15:08PM +0100, Nelle Varoquaux wrote:
> The buildbot is back online !
Thanks Nelle. It's really great to now have 2 people on the project that
can handle issues on the Afpy server. Bus factor of scikit-learn@bbafpy
is going up!
G
---
On Mon, Nov 28, 2011 at 11:28:51AM +0100, Olivier Grisel wrote:
> > btw many are in joblib. I guess it makes no sense to fix them here?
> I think joblib should be fixed upstream (if Gael want's to use pep8 as
> a coding style convention for this project). I can grep them out of
> this report if th
Hi all,
I'm looking for an ML library for Python for our research team. I found
a quite comprehensive one - Orange - and a relatively new one -
scikits.learn.
Orange definitely look good given the number of methods implemented in
it, maturity and its GUI as a bonus.
But I'm a bit confused - if
> As a nitpick I'd say compute_variance instead of return_variance
> because the mean is still returned.
fair enough :)
Alex
--
All the data continuously generated in your IT infrastructure
contains a definitive record
On Fri, Dec 2, 2011 at 16:15, Alexandre Gramfort
wrote:
>> On the name though --- "eval_MSE" is a nonstandard term for "variance"
>> no? MSE usually refers to a loss criterion, for comparing predictions
>> with targets.
>
> return_variance
As a nitpick I'd say compute_variance instead of return_v
> On the name though --- "eval_MSE" is a nonstandard term for "variance"
> no? MSE usually refers to a loss criterion, for comparing predictions
> with targets.
return_variance
would work for me instead of
eval_MSE
(which should have been eval_mse anyway)
Alex
> Cool, good to know!
>
> On the name though --- "eval_MSE" is a nonstandard term for "variance"
> no? MSE usually refers to a loss criterion, for comparing predictions
> with targets.
>
MSE stands for "mean squared error". The GP predictor indeed ensures
minimum prediction variance (aka the mean
Hi,
I modified a little bit the program of demo dbscan (plot_dbscan.py). I am
using just distance (no similarities) and I am having bad results. There
are just 5 points, I changed the eps as the minimum distance between the
points and the number of minimun points are 2 since this is what I
req
On Fri, Dec 2, 2011 at 1:00 PM, Vincent Dubourg
wrote:
> On 02/12/2011 18:19, Alexandre Passos wrote:
>> On Fri, Dec 2, 2011 at 12:02, James Bergstra
>> wrote:
>>> On Tue, Nov 29, 2011 at 5:24 PM, Olivier Grisel
>>> wrote:
That makes sense. Fortunately we don't have an API to compute the
On 02/12/2011 18:19, Alexandre Passos wrote:
> On Fri, Dec 2, 2011 at 12:02, James Bergstra wrote:
>> On Tue, Nov 29, 2011 at 5:24 PM, Olivier Grisel
>> wrote:
>>> That makes sense. Fortunately we don't have an API to compute the
>>> expected variance of a prediction :)
> So what does the eval_M
2011/12/2 James Bergstra :
> I'm looking at the decision tree code and I'm not seeing any pruning
> logic, or other logic to prevent over-fitting (other than requiring
> that leaf nodes be sufficiently populated). Decision trees are not my
> specialty, but pruning / early stopping seem often to be
On Fri, Dec 2, 2011 at 12:02, James Bergstra wrote:
> On Tue, Nov 29, 2011 at 5:24 PM, Olivier Grisel
> wrote:
>> That makes sense. Fortunately we don't have an API to compute the
>> expected variance of a prediction :)
So what does the eval_MSE option do?
--
- Alexandre
-
I'm looking at the decision tree code and I'm not seeing any pruning
logic, or other logic to prevent over-fitting (other than requiring
that leaf nodes be sufficiently populated). Decision trees are not my
specialty, but pruning / early stopping seem often to be mentioned in
connection with trees
On Tue, Nov 29, 2011 at 5:24 PM, Olivier Grisel
wrote:
> That makes sense. Fortunately we don't have an API to compute the
> expected variance of a prediction :)
Slightly off-topic, but this is exactly what's necessary to use
existing regression algorithms for Bayesian optimization, even
internal
2011/12/2 Ian Goodfellow :
> On Fri, Oct 7, 2011 at 5:14 AM, Olivier Grisel
> wrote:
>> 2011/10/7 Ian Goodfellow :
>>> Thanks. Yes it does appear that liblinear uses only a 64 bit dense format,
>>> so this memory usage is normal/caused by the implementation of liblinear.
>>>
>>> You may want to u
17 matches
Mail list logo
