joyoyoyoyoyo · November 29, 2017 14:15
diff --git a/frequency_sort.sh b/frequency_sort.sh
 sort corpus_locations.csv | uniq -c | sort -nr > corpus_locations_count.tsv
diff --git a/just_fulltext.sh b/just_fulltext.sh
 apt-get install xpath

 for file in $(find . -iname '*.xml')
 do
  echo $file
  xpath -e '//note/text()' $file > $file.txt
 done
diff --git a/just_locations.sh b/just_locations.sh
 for file in $(find . -iname '*.ner')
 do
  echo $file
  awk -F 'START:location>|<END' '{print $2}' $file >> corpus_locations.csv
 done
diff --git a/ner-markup.sh b/ner-markup.sh
 for file in $(find . -iname '*.txt')
 do
  echo $file
  /root/apache-opennlp-1.5.3/bin/opennlp TokenNameFinder /root/apache-opennlp-1.5.3/bin/en-ner-location.bin <  $file > $file.ner
 done
	apt-get install xpath

	for file in $(find . -iname '*.xml')
	do
	echo $file
	xpath -e '//note/text()' $file > $file.txt
	done
	for file in $(find . -iname '*.ner')
	do
	echo $file
	awk -F 'START:location>\|<END' '{print $2}' $file >> corpus_locations.csv
	done
	for file in $(find . -iname '*.txt')
	do
	echo $file
	/root/apache-opennlp-1.5.3/bin/opennlp TokenNameFinder /root/apache-opennlp-1.5.3/bin/en-ner-location.bin < $file > $file.ner
	done