Great that it worked! Note that the examples for fracture (bag of words/bag of cuis) is just scratching the surface of feature representations - there are a gazillion ways to export the document (bag of words per section, include negation status, ...) Doing this via SQL makes it super easy
Best, VJ On Wed, Jul 30, 2014 at 9:07 PM, Clayton Turner <caturn...@g.cofc.edu> wrote: > Awesome!! > > It worked! > > The only things I had to change (since I'm on Windows) was flipping the > slashes when necessary and removing the first slash when specifying the > -Dlog4j.configuration=file:/... > > Thank you so much for putting up with my issues > > -Clayton > > > On Wed, Jul 30, 2014 at 2:48 PM, vijay garla <vnga...@gmail.com> wrote: > > > Can you try this: > > copy > > > > > https://code.google.com/p/ytex/source/browse/trunk/workspace/examples/fracture/cui/export.template.xml > > to CTAKES_HOME\desc\ctakes-ytex\fracture\cui.xml > > replace %DB_SCHEMA% with your database schema name (value of db.schema in > > your ytex.properties file) > > > > Then from a command prompt, execute the following commands: > > cd CTAKES_HOME > > bin\setenv.bat > > java -cp %CLASSPATH% > > -Dlog4j.configuration=file:/%CTAKES_HOME%/config/log4j.xml -Xmx256m > > org.apache.ctakes.ytex.kernel.SparseDataExporterImpl -prop > > desc\ctakes-ytex\fracture\cui.xml -type weka > > > > Tell me if you run into any issues. > > > > I will add this to the ctakes confluence doc. > > > > Best, > > > > VJ > > > > > > On Wed, Jul 30, 2014 at 5:11 PM, Clayton Turner <caturn...@g.cofc.edu> > > wrote: > > > > > Hi, I'm trying to export the data I get from running the pipeline > through > > > the Collection Processing Engine. > > > > > > I set up the pipeline where I have a directory where all the XML is > > output > > > to, but I am having issues at this point. > > > > > > I've tried using the built in Exporter from the Data Mining section on > > this > > > page https://cwiki.apache.org/confluence/display/CTAKES/User%27s+Guide > > but > > > those notes are out of date. Even altering directories to match the > files > > > still gives me errors about not being able to find the ExporterImpl > > class. > > > The class version of this file only exists outside of the target > > directory > > > for the ctakes snapshot and attempting to use it still fails. > > > > > > I then ventured to here: > > > > > > > > > https://code.google.com/p/ytex/source/browse/#svn%2Ftrunk%2Fworkspace%2Fexamples%2Ffracture > > > > > > The files here match up to the data mining section from the previous > > link - > > > so I created my export.xml file and changed everything that needed to > be > > > changed for my example (tried to even run bone fracture), but I cannot > > get > > > data exported, no matter what I do. > > > > > > Is there a way to use some new(er) implementation of the > > > SparseDataExporterImpl class or is there an alternative for extracting > > data > > > for use with weka? > > > > > > I've messaged about this in the past but I don't believe I was thorough > > > enough with my issues. > > > > > > Thanks in advance, > > > Clayton > > > > > > > > > -- > -- > Clayton Turner > email: caturn...@g.cofc.edu > phone: (843)-424-3784 > web: claytonturner.blogspot.com > > ------------------------------------------------------------------------------------------------- > “When scientifically investigating the natural world, the only thing worse > than a blind believer is a seeing denier.” > - Neil deGrasse Tyson >
