Commit 5056dc25 authored by Mateusz Pawlik's avatar Mateusz Pawlik

bolzano: Added command to make all labels equal - for an example of a worst case experiment.

parent f9b4a2bc
...@@ -29,5 +29,9 @@ iconv -f ISO-8859-1 -t "UTF-8" L.trees | tail -n +14 | sed 's/.*://' | awk '{p ...@@ -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 "{") # 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 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 # go back to the folder
cd .. cd ..
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment