From 0d1787fe23bfd16e91803c07210113d9496eade3 Mon Sep 17 00:00:00 2001 From: patrycjalazna Date: Sun, 28 Mar 2021 17:11:30 +0200 Subject: [PATCH] cutoff --- avocado-preprocessing.sh | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/avocado-preprocessing.sh b/avocado-preprocessing.sh index 2967a76..80405b4 100755 --- a/avocado-preprocessing.sh +++ b/avocado-preprocessing.sh @@ -16,14 +16,14 @@ head -n -1 avocado-updated-2020.csv | shuf > avocado-updated-2020-shuf.csv head -n "$1" avocado-updated-2020-shuf.csv > avocado-2020.csv TRUNCATED_SIZE=$(wc -l avocado-2020.csv | awk '{print $1}') -TEST_SIZE=0,2*$TRUNCATED_SIZE -DEV_SIZE=2*0,2*$TRUNCATED_SIZE -TRAIN_SIZE=2*0,2*$TRUNCATED_SIZE+1 +declare -i test_size=0,2*$TRUNCATED_SIZE +declare -i dev_size=2*0,2*$TRUNCATED_SIZE +declare -i train_size=2*0,2*$TRUNCATED_SIZE+1 # podzial na train/dev/test 6/2/2 -head -n $TEST_SIZE avocado-2020.csv > avocado-updated-2020-test.csv -head -n $DEV_SIZE avocado-2020.csv | tail -n $TEST_SIZE > avocado-updated-2020-dev.csv -tail -n +$TRAIN_SIZE avocado-2020.csv > avocado-updated-2020-train.csv +head -n $test_size avocado-2020.csv > avocado-updated-2020-test.csv +head -n $dev_size avocado-2020.csv | tail -n $TEST_SIZE > avocado-updated-2020-dev.csv +tail -n +$train_size avocado-2020.csv > avocado-updated-2020-train.csv wc -l avocado-updated-2020-*.csv