Hi Pierre-Luc, In addition to Andy's suggestion, you might have a look at the GBRT's code, which implements a function to update the values stored at leaves (== "terminal regions") https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/ensemble/gradient_boosting.py#L198
Is that what you are looking for when you mean "freeze"? Gilles On 18 February 2015 at 23:20, Andy <t3k...@gmail.com> wrote: > I think you can just implement a new estimator on top of the tree, by using > the apply function to get the leaf a sample ends up in. > Then you can update your class estimates or learn something else on top of > that. > > > > On 02/18/2015 01:31 PM, Pierre-Luc Bacon wrote: > > In the field of reinforcement learning (RL), the Fitted-Q algorithm of Ernst > 2005 (http://www.jmlr.org/papers/volume6/ernst05a/ernst05a.pdf) relies on > the ability to fix the tree structure to ensure convergence (see p. 515 of > the JMLR paper). > > The warm_start option is useful, but does not fully allow for the freezing > mechanism to take place. > > Fitted-Q is highly used in RL and adding a freezing option would definitely > receive a lot of interest. On the other, I understand that for the sake of > keeping the interface general this might not be possible. > > My understanding of ``tree.py`` is that such a thing might be achievable > with a custom ``Splitter`` that actually doesn't split anything but only > refreshes the leaves. > > Is there an easier workaround ? > > Best, > Pierre-Luc > > > ------------------------------------------------------------------------------ > Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server > from Actuate! Instantly Supercharge Your Business Reports and Dashboards > with Interactivity, Sharing, Native Excel Exports, App Integration & more > Get technology previously reserved for billion-dollar corporations, FREE > http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk > > > > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > > > > ------------------------------------------------------------------------------ > Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server > from Actuate! Instantly Supercharge Your Business Reports and Dashboards > with Interactivity, Sharing, Native Excel Exports, App Integration & more > Get technology previously reserved for billion-dollar corporations, FREE > http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > ------------------------------------------------------------------------------ Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server from Actuate! Instantly Supercharge Your Business Reports and Dashboards with Interactivity, Sharing, Native Excel Exports, App Integration & more Get technology previously reserved for billion-dollar corporations, FREE http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
