Sorry - I figured why the shape of cv_values is (30,3)
But what is the default scoring used by RidgeCV?
Thanks,
Josh
On Wed, Oct 23, 2013 at 3:44 PM, Josh Wasserstein <[email protected]>wrote:
> Also, assuming:
> X.shape is (30,54)
> y.shape is (30,)
>
> When I run
> from sklearn.linear_model import RidgeCV
> reg = RidgeCV(store_cv_values=True)
> reg.fit(X,y)
>
> I get
> > reg.cv_values_.shape
> (30,3)
>
> From what I read in the documentation, by default RidgeCV uses (efficient
> Leave-One-Out), so I would imagine I would get 30 scores (one per sample),
> but why do I have three columns? What are these numbers supposed to
> represent?
>
> Thanks,
>
> Josh
>
>
>
> On Wed, Oct 23, 2013 at 3:38 PM, Josh Wasserstein
> <[email protected]>wrote:
>
>> According to the documentation of RidgeCV, the default scoring is *None.
>> *What does that mean? Which scoring metric does it use?
>>
>> Shouldn't it be one of:
>> * Explained variance
>> * Mean absolute error
>> * Mean squared error
>> * R^2
>>
>> Here is the entry from the documentation:
>>
>> *scoring* : string, callable or None, optional, default: None
>>
>> A string (see model evaluation documentation) or a scorer callable object
>> / function with signature scorer(estimator, X, y).
>>
>> Thanks,
>>
>> Josh
>>
>
>
------------------------------------------------------------------------------
October Webinars: Code for Performance
Free Intel webinars can help you accelerate application performance.
Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from
the latest Intel processors and coprocessors. See abstracts and register >
http://pubads.g.doubleclick.net/gampad/clk?id=60135991&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
