<div dir="ltr">Hello, <div><br></div><div>I clearly could have provided better documentation.</div><div><br></div><div>There was an issue I believe in the predict function when single.tree was set to TRUE.</div><div><br></div><div>The first 6 trees of the model are printed out to show the the first two trees for each of the three classes.</div><div><br></div><div>The first set of predictions are shown for using 1 and 2 trees. </div><div><br></div><div>The maths show that the manual addition of values from each of the trees match the first set of predictions. </div><div><br></div><div>The second set of predictions do not match the expected result from each tree. </div><div><br></div><div>Example:</div><div>search document for <span style="color:rgb(0,0,0);font-family:monospace;white-space:pre-wrap">0.1126044</span> shows that the value of a two-tree prediction matches arithmetically, but the addend to 0.1126044 is not found in results for single.tree prediction.</div><div><br></div><div>search document for <span style="color:rgb(0,0,0);font-family:monospace;white-space:pre-wrap">-0.04196866</span><span style="color:rgb(0,0,0);white-space:pre-wrap"><font face="arial, helvetica, sans-serif"> shows that this value is found in predictions for two-tree sum and single.tree = TRUE result, and switches class position from prediction set 1 to prediction set1 (single.tree).</font></span></div><div><span style="color:rgb(0,0,0);white-space:pre-wrap"><font face="arial, helvetica, sans-serif"><br></font></span></div><div><span style="color:rgb(0,0,0);white-space:pre-wrap"><font face="arial, helvetica, sans-serif">David</font></span></div><div><br></div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Tue, Mar 27, 2018 at 8:08 AM, Andreas Tille <span dir="ltr"><<a href="mailto:andreas@an3as.eu" target="_blank">andreas@an3as.eu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hello Harry,<br>
<br>
On Tue, Mar 27, 2018 at 02:41:28PM +0100, Harry Southworth wrote:<br>
> That post is about 2.5 years old and the version of gbm is 2.1.1.<br>
<br>
That's correct. The original maintainer seems to have lost interest and<br>
I'm now trying to polish the list of bugs in any R package in Debian.<br>
<br>
> The version on CRAN is now 2.1.3 but has status ORPHANED.<br>
<br>
Thats the currently packaged version of gbm in Debian but I have no<br>
sign that the issue has changed (bug reporter is in CC).<br>
<br>
> Since then, gbm maintenance got moved around a couple more times. You<br>
> can find it's current page here:<br>
> <a href="https://github.com/gbm-developers" rel="noreferrer" target="_blank">https://github.com/gbm-<wbr>developers</a><br>
><br>
> To address, the question: I don't understand it.<br>
<br>
Puh, that's relaxing for me since I do not understanding it as well. ;-)<br>
<br>
> However, I do recall<br>
> that there were a number of known bugs in the multinomial<br>
> functionality and that that functionality was dropped from gbm3 (a<br>
> newer version, rewritten from the ground up, but whose development<br>
> appears to have stalled).<br>
><br>
> I've posted in GitHub, but don't know how likely it is that you'll get<br>
> a helpful response.<br>
<br>
That's a very helpful response. I subscribed issue #21 and will wait<br>
for a better answer.<br>
<br>
> Sorry not to be more helpful,<br>
<br>
Thanks a lot for the quick response<br>
<br>
Andreas.<br>
<br>
Control: forwarded -1 <a href="https://github.com/gbm-developers/gbm/issues/21" rel="noreferrer" target="_blank">https://github.com/gbm-<wbr>developers/gbm/issues/21</a><br>
<br>
> On 27 March 2018 at 13:27, Andreas Tille <<a href="mailto:andreas@an3as.eu">andreas@an3as.eu</a>> wrote:<br>
> > Hello Harry,<br>
> ><br>
> > the R packaging team is maintaining gbm in Debian. A user has filed a<br>
> > bug report against version 2.1.1 which I would like to bring to your<br>
> > attention. Please have a look here where the problem is explicitly<br>
> > described:<br>
> ><br>
> > <a href="https://bugs.debian.org/805395" rel="noreferrer" target="_blank">https://bugs.debian.org/805395</a><br>
> ><br>
> > Could you please comment on this? I admit I do not fully understand<br>
> > what exactly is incorrect here and what to expect. May be some test<br>
> > case would help to confirm the integrity of the code.<br>
> ><br>
> > Kind regards<br>
> ><br>
> > Andreas.<br>
> ><br>
> ><br>
> > Control: tags -1 help<br>
> > Control: forwarded -1 Harry Southworth <<a href="mailto:harry.southworth@gmail.com">harry.southworth@gmail.com</a>><br>
> ><br>
> ><br>
> > --<br>
> > <a href="http://fam-tille.de" rel="noreferrer" target="_blank">http://fam-tille.de</a><br>
><br>
<span class="HOEnZb"><font color="#888888"><br>
--<br>
<a href="http://fam-tille.de" rel="noreferrer" target="_blank">http://fam-tille.de</a><br>
</font></span></blockquote></div><br></div>