[Cuitools-users] cuitools v0.19, testing --nspconfig option

[Ted P. <tpederse@d.umn.edu>]

Hi Bridget,

I was doing a little experimenting with the --nspconfig option, and it
seems like it might not be recognizing the --score option with
statistic::

This was my configuration file, which is a slightly modified version
of your example in the perldoc...

ngramcount:: count:: --ngram 2 --remove 3 statistic:: ll.pm --score 3.841

cuicount:: count:: --ngram 2 --remove 3 statistic:: ll.pm --score 3.841

stcount:: count:: --ngram 1 --remove 3

It got the following error...

Defaults options set:
 --seed 1
 --javaparams "-Xmx600m"
 --cv 10
 --weka weka.classifiers.bayes.NaiveBayes
 --line


User defined options set:
 --lc
 --nspconfig ./ted-err.txt
     ngramcount:: count:: --ngram 2 --remove 3 statistic:: ll.pm --score 3.841
     cuicount:: count:: --ngram 2 --remove 3 statistic:: ll.pm --score 3.841
     stcount:: count:: --ngram 1 --remove 3


Output Directories:
 WEKA directory   : ted-err.weka
 ARFF directory   : ted-err.arff
 RESULTS directory: ted-err.results
 LOG directory    : ted-err.log

FILE: Demos/TDP.mm/energy.mm
Unknown option: score
Use of uninitialized value in scalar chomp at /usr/local/bin/count.pl line 341.
Output file statistic:: already exists! Overwrite (Y/N)? Could not open NSP outp
ut file ted-err.log/ngram.0.374441146691428.input.cnt
ERROR: The ARFF file (ted-err.arff/energy/1.arff.train) is empty

Now, after this happened I thought perhaps statistic:: needed to be on
its own line, so I formatted it like this:

ngramcount:: count:: --ngram 2 --remove 3
statistic:: ll.pm --score 3.841

cuicount:: count:: --ngram 2 --remove 3
statistic:: ll.pm --score 3.841

stcount:: count:: --ngram 1 --remove 3

However, in this case it seemed like the statistic:: portion was
simply ignored. So I think we might want to have some simple parsing
of the file to either detect that statistic:: is being used invalidly
here, or to allow line breaks in the middle of the lines (ie treat the
two files above as identical, which is probably the better option).

Thanks!
Ted

--
Ted Pedersen
http://www.d.umn.edu/~tpederse