Archival post. This script was used to create external training data
for CICLING 2007 submission.

=================================================================

#!/bin/csh

# This script was used to create statistic files for different measures
# to be used as features for some other set of test/evaluation data.

# by ted pedersen, october 2006

set STOPLIST = /home/ted/Web/StopLists
# nyt-25.stop
# nyt-75.stop

set TRAINDATA = /home/CICLING/Train
# nyt-plain-clean-25-tr.txt
# nyt-plain-clean-75-tr.txt

foreach CORPUS (1 25 75)

foreach REMOVE (5 10 20 50)

set PREFIX = nyt-$CORPUS-$REMOVE

echo "running $PREFIX count"

count.pl --ngram 2 \
--token token.regex \
--remove $REMOVE \
--stop $STOPLIST/nyt-$CORPUS.stop \
$PREFIX.cnt2 \
$TRAINDATA/nyt-plain-clean-$CORPUS-tr.txt

foreach STAT (ll leftFisher pmi odds)

echo "running $PREFIX $STAT statistic"

if ($STAT == ll) then
set SCORE = 3.84
else if ($STAT == leftFisher) then
set SCORE = 0.95
else if ($STAT == pmi) then
set SCORE = 5.00
else if ($STAT == odds) then
set SCORE = 10000.00
else
echo "statistic error"
exit
endif

statistic.pl $STAT --precision 4 --score $SCORE $PREFIX.$STAT $PREFIX.cnt2

end

end

end




-------------------------------------------------------------------------
Using Tomcat but need to do more? Need to support web services, security?
Get stuff done quickly with pre-integrated technology to make your job easier
Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
_______________________________________________
senseclusters-developers mailing list
senseclusters-developers@list...
https://lists.sourceforge.net/lists/listinfo/senseclusters-developers