Hi Mercè, Would you send me your file? I am not able to reproduce the error. I apologize if you already sent it. I am not seeing it in the thread.
I put what I did to test it below so you could reproduce what I have done on an example test set. I will check on : In the folder "MyNSP/man/man3" I've got "Text::NSP::Measures::4D::MI:: ll.3pm" There shouldn't be a ll.3pm in 4D. I must have something wrong in there. Thanks, Bridget ------------- Here is what I am doing: The text file contains the following: this is a test sentence just a sentence this is a test sentence I save that to a file called test.txt. Then I run the following: bridget@atlas:~/nsp-test$ count.pl --ngram 4 test.4 test.txt The test.4 file contains: 10 this<>is<>a<>test<>2 2 2 3 2 2 2 2 2 2 2 2 2 2 2 is<>a<>test<>sentence<>2 2 3 2 3 2 2 2 2 2 2 2 2 2 2 sentence<>this<>is<>a<>1 2 1 1 2 1 1 1 1 1 1 1 1 1 1 test<>sentence<>just<>a<>1 1 2 1 2 1 1 1 1 1 1 1 1 1 1 just<>a<>sentence<>this<>1 1 3 2 1 1 1 1 1 1 1 1 1 1 1 a<>sentence<>this<>is<>1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 a<>test<>sentence<>just<>1 2 1 2 1 1 1 1 1 1 1 1 1 1 1 sentence<>just<>a<>sentence<>1 2 1 3 3 1 1 1 1 1 1 1 1 1 1 Then I run the Log Likelihood for 4-grams over it: bridget@atlas:~/nsp-test$ statistic.pl --ngram 4 ll test.4ll test.4 Please note here that input file is the count.pl file generated from the above step (test.4). This may be the cause of the error. The test.4ll contains: 10 is<>a<>test<>sentence<>1 29.8708 2 2 3 2 3 2 2 2 2 2 2 2 2 2 2 this<>is<>a<>test<>2 29.6804 2 2 2 3 2 2 2 2 2 2 2 2 2 2 2 sentence<>just<>a<>sentence<>3 27.3805 1 2 1 3 3 1 1 1 1 1 1 1 1 1 1 just<>a<>sentence<>this<>4 22.4273 1 1 3 2 1 1 1 1 1 1 1 1 1 1 1 sentence<>this<>is<>a<>5 19.9354 1 2 1 1 2 1 1 1 1 1 1 1 1 1 1 test<>sentence<>just<>a<>5 19.9354 1 1 2 1 2 1 1 1 1 1 1 1 1 1 1 a<>sentence<>this<>is<>5 19.9354 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 a<>test<>sentence<>just<>5 19.9354 1 2 1 2 1 1 1 1 1 1 1 1 1 1 1 Let me know if you get anything different. On Wed, Mar 27, 2013 at 11:45 AM, mercevg <merc...@yahoo.es> wrote: > ** > > > Ted, > > Changing the command line the following error message appears: > > "Use of uninitialized value $Text::NSP::Measures::4D::expected_values in > string eq at /etc/perl/Text/NSP/Measures/4D.pm line 839, <SRC> line 1265.^C" > > It could be due to files already installed? > In the folder "MyNSP/man/man3" I've got > "Text::NSP::Measures::4D::MI::ll.3pm" > > Thank you, > Mercè > > --- In ngram@yahoogroups.com, Ted Pedersen <tpederse@...> wrote: > > > > I think there is a slight typo in your command : > > > > statistic.pl --ngram 4 ll4.pm output.txt intput.txt > > > > (the module name should be ll4.pm) > > > > I hope this helps! Let me know if you continue to have any trouble... > > > > Good luck, > > Ted > > > > On Wed, Mar 27, 2013 at 9:06 AM, mercevg <mercevg@...> wrote: > > > Ted, > > > > > > I've received your answer without problem. I'll try to follow up with > another email address. > > > > > > A sample of my 4-grams file: > > > procesamiento<>del<>lenguaje<>natural<>9 19 55 22 19 10 9 9 20 16 18 9 > 9 9 16 > > > recuperación<>de<>información<>textual<>4 15 287 30 5 15 14 4 25 4 5 > 14 4 4 4 > > > estadístico<>del<>lenguaje<>natural<>3 5 55 22 19 3 3 3 20 16 18 3 3 3 > 16 > > > aparición<>en<>el<>documento<>2 4 93 95 22 3 2 3 18 6 4 2 3 2 3 > > > > > > Command line: > > > statistic.pl --ngram 4 ll.3pm 4-grams-ll.txt 4-grams.txt > > > > > > Program answer: > > > "Measure not defined for 4-grams" > > > > > > I've got Text-NSP v.1.25. > > > > > > Thank you. > > > Mercè > > > > > > --- In ngram@yahoogroups.com, Ted Pedersen <tpederse@> wrote: > > >> > > >> Merce, I got an email error when responding directly to your yahoo.es > > >> account. Could you follow up with another email address or use the > > >> group...? > > >> > > >> Thanks, > > >> Ted > > >> > > >> > > >> ---------- Forwarded message ---------- > > >> From: Ted Pedersen <tpederse@> > > >> Date: Wed, Mar 27, 2013 at 8:29 AM > > >> Subject: Re: ll4 giving me trouble with 4-grams > > >> To: mercevg <mercevg@> > > >> > > >> > > >> Hi Merce, > > >> > > >> Could you send me whatever error output you are getting, plus a small > > >> sample of your ngram file? > > >> > > >> Thanks! > > >> Ted > > >> > > >> On Wed, Mar 27, 2013 at 8:12 AM, mercevg <mercevg@> wrote: > > >> > Hi, > > >> > > > >> > I would like to know how to calculate with Statistical.pl 4-grams > using log-likelihood ratio. > > >> > > > >> > To calculate 3-grams I've run the program as follows: > > >> > statistic.pl --ngram 3 tmi3.pm three.ngram.tmi3 three.ngram > > >> > > > >> > But using log-likelihood ratio it doesn't work. > > >> > > > >> > Thanks > > >> > > > >> > Mercè > > >> > > > >> > > > >> > > > > > > > > > > >
