This commit is contained in:
patrycjalazna 2021-03-28 17:08:07 +02:00
parent ed158ad5dd
commit 1495840296

View File

@ -4,7 +4,6 @@
kaggle datasets download -d timmate/avocado-prices-2020
unzip -o avocado-prices-2020.zip
TOTAL_SIZE=$(wc -l avocado-updated-2020.csv | awk '{print $1}')
echo "size $TOTAL_SIZE"
# przetwarzanie pliku
grep -P "^$" -n avocado-updated-2020.csv
@ -17,7 +16,6 @@ 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}')
echo "truncated size $TRUNCATED_SIZE"
TEST_SIZE=0,2*$TRUNCATED_SIZE
DEV_SIZE=2*0,2*$TRUNCATED_SIZE
TRAIN_SIZE=2*0,2*$TRUNCATED_SIZE+1