Loading bolzano-address-trees/download_prepare.sh +4 −0 Original line number Diff line number Diff line Loading @@ -29,5 +29,9 @@ iconv -f ISO-8859-1 -t "UTF-8" L.trees | tail -n +14 | sed 's/.*://' | awk '{p # convert file into UTF-8 format | remove header | remove IDs | sort by number of nodes (equivalent to number of "{") iconv -f ISO-8859-1 -t "UTF-8" R.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../R_preprocessed.txt # prepare dataset with a single label # | remove non-bracket chars. | add single dummy label 'o' > save to file cat ../L_preprocessed.txt | sed 's/[^\{\}]//g' | sed 's/[\{]/\{o/g' > ../L_preprocessed_single_label.txt # go back to the folder cd .. No newline at end of file Loading
bolzano-address-trees/download_prepare.sh +4 −0 Original line number Diff line number Diff line Loading @@ -29,5 +29,9 @@ iconv -f ISO-8859-1 -t "UTF-8" L.trees | tail -n +14 | sed 's/.*://' | awk '{p # convert file into UTF-8 format | remove header | remove IDs | sort by number of nodes (equivalent to number of "{") iconv -f ISO-8859-1 -t "UTF-8" R.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../R_preprocessed.txt # prepare dataset with a single label # | remove non-bracket chars. | add single dummy label 'o' > save to file cat ../L_preprocessed.txt | sed 's/[^\{\}]//g' | sed 's/[\{]/\{o/g' > ../L_preprocessed_single_label.txt # go back to the folder cd .. No newline at end of file