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

cutoff parameter

Browse Source
This commit is contained in:
patrycjalazna 2021-03-28 16:22:31 +02:00
parent a95c33308e
commit 58db37cb76
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
avocado-preprocessing.sh
View File

@ -4,17 +4,22 @@
kaggle datasets download -d timmate/avocado-prices-2020
unzip -o avocado-prices-2020.zip
wc -l avocado-updated-2020.csv
echo "$1 'AAAAAAAAAAAAAAAAA"
# przetwarzanie pliku
grep -P "^$" -n avocado-updated-2020.csv
# usuniecie zbednej kolumny year (redundantne dane)
cut -d -f12 --complement avocado-updated-2020.csv
cut -d ',' -f12 --complement avocado-updated-2020.csv
head -n 1 avocado-updated-2020.csv> header.csv
head -n 1 avocado-updated-2020.csv > header.csv
head -n -1 avocado-updated-2020.csv | shuf > avocado-updated-2020-shuf.csv
echo "$1 AAAAAAAAAAAAAAAAA"
head -n "-$1" avocado-updated-2020-shuf.csv > avocado-2020.csv
wc -l avocado-2020.csv
# podzial na train/dev/test
head -n 6609 avocado-updated-2020-shuf.csv > avocado-updated-2020-test.csv
head -n 13218 avocado-updated-2020-shuf.csv | tail -n 6609 > avocado-updated-2020-dev.csv