s434742/ium_434742
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

cutoff

Browse Source
This commit is contained in:
patrycjalazna 2021-03-28 16:55:29 +02:00
parent b6c1bb0227
commit c7945e9cf0
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
avocado-preprocessing.sh
View File

@ -3,7 +3,7 @@
# pobranie zbioru danych
kaggle datasets download -d timmate/avocado-prices-2020
unzip -o avocado-prices-2020.zip
TOTAL_SIZE=$(wc -l avocado-updated-2020.csv)
TOTAL_SIZE=$(wc -l avocado-updated-2020.csv | awk '{print $1}')
echo "size $TOTAL_SIZE"
# przetwarzanie pliku
@ -16,13 +16,13 @@ head -n 1 avocado-updated-2020.csv > header.csv
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)
TRUNCATED_SIZE=$(wc -l avocado-2020.csv | awk '{print $1}')
echo "truncated size $TRUNCATED_SIZE"
# podzial na train/dev/test 6/2/2
head -n 6609 avocado-2020.csv > avocado-updated-2020-test.csv
head -n 13218 avocado-2020.csv | tail -n 6609 > avocado-updated-2020-dev.csv
tail -n +13219 avocado-2020.csv > avocado-updated-2020-train.csv
head -n (0,2*$TRUNCATED_SIZE) avocado-2020.csv > avocado-updated-2020-test.csv
head -n (2*0,2*$TRUNCATED_SIZE) avocado-2020.csv | tail -n (0,2*$TRUNCATED_SIZE) > avocado-updated-2020-dev.csv
tail -n +((2*0,2*$TRUNCATED_SIZE)+1) avocado-2020.csv > avocado-updated-2020-train.csv
wc -l avocado-updated-2020-*.csv