s452094-mlworkshops/get_data.sh

7 lines
275 B
Bash
Raw Normal View History

2020-04-03 13:56:48 +02:00
cat wikiniews_results.tsv | cut -f2 -s > hypothesis.txt
2020-04-03 14:00:47 +02:00
cat wikiniews_results.tsv | cut -f3 -s > reference.txt
2020-04-03 13:56:48 +02:00
awk 'BEGIN{FS=OFS="\t"}{print $0,"(sp1_"NR")"}' < reference.txt > reference.trn
2020-04-03 14:02:37 +02:00
awk 'BEGIN{FS=OFS="\t"}{print $0,"(sp1_"NR")"}' < hypothesis.txt > hypothesis.trn