> I'm -1 on log_likelihood, because the quantity the ``score`` method is
> returning is actually the log likelihood. The ``eval`` method is returning
> the log-likelihood per point, which is equivalent to the log-probability of
> that point under the model, and also equivalent to the log of the
> normalized density under the model.
>
> BTW, the HMM module uses `score` for the log-probability of a single
observation too... ((n, n_features) is the shape of a single time series,
not of an entire dataset). But we already knew that the HMM module is
inconsistent with the rest of the package :)
Mathieu
------------------------------------------------------------------------------
See everything from the browser to the database with AppDynamics
Get end-to-end visibility with application monitoring from AppDynamics
Isolate bottlenecks and diagnose root cause in seconds.
Start your free trial of AppDynamics Pro today!
http://pubads.g.doubleclick.net/gampad/clk?id=48808831&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
