Menu
▾
▴
Re: [Cuitools-users] Cuitools 0.27 testall.sh
|
From: Ted P. <tpederse@d.umn.edu> - 2011-01-01 16:40:48
|
Hi Bridget, See comments inline... On Sat, Jan 1, 2011 at 9:29 AM, bthomson <bth...@em...> wrote: > Hi Ted, > > I am going throught the log file now. I know that errors are generated > order1vec.pl which have always happened. Since it was an external program, I > haven't messed with it. Maybe I should replace it with an update version of > it? The version of order1vec.pl in SenseClusters is from 2008, so I suspect you have the most current version of that already...? Also, if I'm not mistaken don't you have some modifications to order1vec.pl in the CuiTools version? I don't remember exactly what they are (or if you have them even). Ah, in looking at the code I see the following.... # 3 JUNE 2008: # # THIS PROGRAM ORIGINALLY BELONGED TO THE SenseClusters PACKAGE # VERSION 0.95 (http://senseclusters.sourceforge.net) DEVELOPED # BY Ted Pedersen, Amruta Purandare, Anagha Kulkarni, and Mahesh # Joshi. ITS ORIGINALLY NAME IS ORDER1VEC - IT HAS BEEN MODIFIED # AND CHANGED TO SIMORDER1VEC AND INCLUDED IN CuiTools DISTRIBUTION Some of the order1vec.pl errors look to me like a missing file or something.... Test A11 for order1vec.pl Running order1vec.pl --extarget --target test-A11.target test-A11.sval2 test-A11 .regex Use of uninitialized value $outputfile in concatenation (.) or string at /usr/bi n/order1vec.pl line 660, <DATA> line 206. Use of uninitialized value $outputfile in concatenation (.) or string at /usr/bi n/order1vec.pl line 660, <DATA> line 206. Could not open output file: Also, I ran a test of the SenseClusters order1vec.pl and it came back clean, so I'm wondering if there might not be something specific to the CuiTools version? > > There are two internal errors: > > 1. Error in Testing/supervised/internal/supervised-disambiguate Test 3 > > supervised-disambiguate.pl --ngramcount "--ngram 1" --wekacv 10 > --directory output mm/adjustment.mm > > > 2. Error in Testing/supervised/internal/mm2arff Test 2 > > mm2arff.pl --sentence --stcount --ngram 1 output mm/art.mm > > > I do not get them on one of my machines and do on the other so was able to > do a comparison. The difference was the versions of Text-NSP. I was messing > around with Text-NSP package on one of my computers in order to get some > internal count information for another project a while back, and forgot to > revert back. I ended up lower casing everything in the process. When I > released CuiTools the other day, I went through and updated the test cases > including the mm format which meant updating all of the test cases I think > including the supervised tests. I also revised the output format of the > supervised-disambiguate program last month so I also could have done it then > as well. I just can't remember. Understood, and I'm glad this isn't a major issue! > > Either way, I will get these test cases fixed and update CuiTools to run on > metamap10. That sounds great! Thanks, Ted > > Sorry for these errors! > > Thanks, > > Bridget > > On Fri, 31 Dec 2010, Ted Pedersen wrote: > >> Hi Bridget, >> >> I decided to go ahead and install the new CuiTools (since I'm in the >> process of setting up a new system I recently installed MetaMap and >> Weka and so it seemed like good timing). The install generally seems >> to have went well, except there are a few glitches in the testall.sh >> output. >> >> Any ideas on any of those, and any things I should look at to sort >> those out? Here's a little bit on my setup.... >> >> ted@linux-qdw9:~/Download/CuiTools-0.27/Testing> echo $WEKAHOME >> /home/ted/Download/weka-3-6-4 >> ted@linux-qdw9:~/Download/CuiTools-0.27/Testing> echo $METAMAP_PATH >> /home/ted/Download/public_mm >> ted@linux-qdw9:~/Download/CuiTools-0.27/Testing> echo $CUITOOLSHOME >> /home/ted/Download/CuiTools-0.27 >> ted@linux-qdw9:~/Download/CuiTools-0.27/Testing> uname -a >> Linux linux-qdw9 2.6.34.7-0.5-desktop #1 SMP PREEMPT 2010-10-25 >> 08:40:12 +0200 i686 i686 i386 GNU/Linux >> >> I have not yet downloaded or installed the NLM WSD data, but didn't >> think I would need that quite yet... >> >> I've attached a log file, hopefully the mailing list let's that through? >> >> Thanks, >> Ted >> >> >> >> >> -- >> Ted Pedersen >> http://www.d.umn.edu/~tpederse >> > -- Ted Pedersen http://www.d.umn.edu/~tpederse |