SFTJIRA
https://sft.its.cern.ch/jira
This file is an XML representation of an issueen-us8.3.480300513-09-2019[ROOT-6664] Problems fitting sub-ranges with RooChebychev
https://sft.its.cern.ch/jira/browse/ROOT-6664
ROOT<p>Hello,</p>
<p>I am performing a fit of a blinded dataset using a RooChebychev.<br/>
I have already posted this issue on the ROOT forum in June, but I didn't get any reply. Now we are a little stuck with our analysis because we need to be able to perform this kind of fit.</p>
<p>I did lots of checks try to debug the problem, but I didn't manage to find any good solution. </p>
<p>In attachment you can find a macro that shows the problem. The macro is divided into "TEST1" and "TEST2". <br/>
– TEST1 generates a dataset using a 1st order Chebychev in the mass region <span class="error">[4700,5900]</span> and a "blinded" dataset reducing the full dataset to the two sub-regions <span class="error">[4700,5100]</span> and <span class="error">[5500,4900]</span>. Then, it performs two fits:<br/>
1) fit the "full" dataset and plot the results (lines 75-79 )<br/>
2) fit the "blinded" dataset and plots the results (lines 86-90).</p>
<p>– TEST2, similar to TEST1, but with a different PDF (1st order Chebychev + Gaussian)</p>
<p>Now, if I do this test using a RooExponential, the fit is OK on both full and blinded dataset (you can try that commenting RooChebychev and de-commenting RooExponential), whereas if I do the test using RooChebychev, when I do the fit on the two sub-ranges, ROOT crashes and exits due to the assert() present in the RooChebychev.cxx (lines 141-142). In attachment you can find the bt obtained running lldb on my laptop.</p>
<p>I added some prints to RooChebychev.cxx</p>
<p>_x.min(rangeName)<br/>
_x.max(rangeName)<br/>
xminfull<br/>
xmaxfull </p>
<p>Now, looking at RooChebychev.h, if I understood correctly, "_x" should correspond to the variable "mass" (in my case) and so xminfull = _x.min() should always be equal to 4700, and xmaxfull = _x.max() should always be equal to 5900.<br/>
When I try to do the fit in the two sub-ranges I got this print (before ROOT crashes)</p>
<p> _x.min(rangeName) = 4700<br/>
_x.max(rangeName) = 5900<br/>
xminfull = 4700<br/>
xmaxfull = 5100</p>
<p>As you can see, it seems that the ranges are swapped, and so the assert() fails and exits ROOT. "rangeName" should be "SB1" or "SB2" (defined in lines 54-55).</p>
<p>I have tried to investigate the problem in more detail, but I din't find any proper solution. Maybe there is some problem in dealing with the ranges in the RooChebychev.cxx (maybe some problem in RooProxy?).<br/>
Looking at RooAbsOptTestStatistic.cxx, in lines 286-365 RooFit make adjustments for the fit ranges, I saw that, commenting line 311, ROOT does not crash, the fit with the Chebychev only seems to be OK (but not the normalisation, that is wrong), whereas the fit Chebychev+Gaussian converges but the chi2 is huge (so the fitted curve does not fit the data and the normalisation is wrong).</p>
<p>I hope these tests can help in figure out where the problem is. Let me know if I can help with some other tests and if you need more information.</p>
<p>Thanks a lot in advance!</p>
<p>Cheers,</p>
<p>Cristiano</p><p>Mac Os X 10.9.4 (X86-64)<br/>
ROOT 5.34/20<br/>
Apple LLVM version 5.1 (clang-503.0.40) (based on LLVM 3.4svn)<br/>
Target: x86_64-apple-darwin13.3.0<br/>
Thread model: posix</p>ROOT-6664Problems fitting sub-ranges with RooChebychevBugHighClosedFixedWouter VerkerkeCristiano AlpigianiMon, 8 Sep 2014 15:32:28 +0200Thu, 21 Mar 2019 22:16:56 +0100Mon, 29 Sep 2014 11:28:32 +02005.34/24RooFit/RooStats74<p>There is no reason to the assert to be there. Sometimes one wants to compute the integral of the pdf in a range larger than the definition. Since it is a polynomial there is no problem for the function to be evaluated outside its range. <br/>
The given test program has been tested using numerical integration and the same result is obtained</p><p>Hi, <br/>
The problem, remaining after removing the assert, is due to the definition of RooChebyshev (and it is the same for RooBernstein). <br/>
The evaluation of the polynomial depends on the defined range, therefore when doing a simultaneous fit on two separate ranges (e.g. the sidebands) RooFIt defines two RooChebyshev objects, each one with its own range.<br/>
The polynomial effective parameters depends therefore on the range and they are at the end different for the two ranges. <br/>
This is not the case when using a RooPolynomial, where the returned value in ::evaluate does not depend on the range. <br/>
I am not sure what is the best solution for this problem. </p>
<p> Lorenzo</p><p>Thinking more, a possible solution is to add in RooChebyshev two new data members (_xmin, _xmax) which in the constructor are assigned from the current variable range, but they cannot then be modified later on. This solution fixes the problem observed in the test program. </p><p>This attached version of RooChebyshev seems to fix the problem. Needs to be confirmed before committing that fix</p><p>The problem is now fixed in 5.34, 6.02 and master by a new version of RooChebyshev using a reference range for evaluating the polynomial.<br/>
A similar fix is expected for RooBernstein</p><p>To be more precise, this was fixed in the patch release v5-34-22 </p>Actual EndThu, 21 Mar 2019 22:16:56 +0100DevelopmentRank0|102nbk:Rank (Obsolete)9223372036854775807