colloc-reuters.sh

#!/bin/sh

# Running in top level directory, per http://permalink.gmane.org/gmane.comp.apache.mahout.user/5689
# via https://cwiki.apache.org/MAHOUT/collocations.html

# I've tried this from top level dir, both with and without MAHOUT_LOCAL=true set.
# In both cases, I get seemingly nothing.
#
# e.g. running with cluster I got two files, and analysing 
# ./bin/mahout seqdumper -s part-r-00001  ...gives 
# 		Input Path: part-r-00001
# 		Key class: class org.apache.hadoop.io.Text Value Class: class org.apache.hadoop.io.DoubleWritable
# 		Count: 0


M=./bin/mahout

echo $M seqdirectory  -i ./examples/bin/work/reuters-out/   -o ./examples/bin/work/reuters-out-seqdir   -c UTF-8 -chunk 5 
$M seqdirectory  -i ./examples/bin/work/reuters-out/   -o ./examples/bin/work/reuters-out-seqdir   -c UTF-8 -chunk 5 
echo 


echo $M seq2sparse   -i ./examples/bin/work/reuters-out-seqdir/ -o ./examples/bin/work/reuters-out-seqdir-sparse 
$M seq2sparse   -i ./examples/bin/work/reuters-out-seqdir/ -o ./examples/bin/work/reuters-out-seqdir-sparse 
echo 

echo $M org.apache.mahout.vectorizer.collocations.llr.CollocDriver  -i ./examples/bin/work/reuters-out-seqdir-sparse/tokenized-documents -o \
  -o ./examples/bin/work/reuters-colloc  -a org.apache.mahout.vectorizer.DefaultAnalyzer -ng 3
$M org.apache.mahout.vectorizer.collocations.llr.CollocDriver  -i ./examples/bin/work/reuters-out-seqdir-sparse/tokenized-documents -o \
  -o ./examples/bin/work/reuters-colloc  -a org.apache.mahout.vectorizer.DefaultAnalyzer -ng 3
echo

./bin/mahout seqdumper -s ./examples/bin/work/reuters-colloc/ngrams//part-r-00000  
												# | less