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 16:39:22 +02:00
parent e334ad1bf6
commit f9386a6a32
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

@ -3,8 +3,8 @@
# pobranie zbioru danych
kaggle datasets download -d timmate/avocado-prices-2020
unzip -o avocado-prices-2020.zip
wc -l avocado-updated-2020.csv
total_size = $(wc -l avocado-updated-2020.csv)
echo size $total_size
# przetwarzanie pliku
grep -P "^$" -n avocado-updated-2020.csv
@ -16,10 +16,10 @@ 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
wc -l avocado-2020.csv
truncated_size = $(wc -l avocado-2020.csv)
echo truncated size $truncated_size
# podzial na train/dev/test
# 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