> Is there a utility to compute the confidence interval?
You could try boostrapping (or maybe, if you have enough data, a
jack-knife approach, as some estimators like the nearest-neighbor don't
like having twice the same data point).
G
Cool, I hope I have time to review it the next couple of days.
On 11/02/2014 07:44 PM, Aaron Staple wrote:
> Hi folks,
>
> I went ahead and made a POC for a more complete implementation of
> option #4:
>
> https://github.com/staple/scikit-learn/commit/e76fa8887cd35ad7a249ee157067cd12c89bdefb
>
>
