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

ghead to head

Browse Source
This commit is contained in:
patrycjalazna 2021-03-28 15:24:06 +02:00
parent 2f272b6b44
commit a0f3f901dc
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
avocado-preprocessing.sh
View File

@ -11,13 +11,12 @@ grep -P "^$" -n avocado-updated-2020.csv
# usuniecie zbednej kolumny year (redundantne dane) # usuniecie zbednej kolumny year (redundantne dane)
cut -d -f12 --complement avocado-updated-2020.csv cut -d -f12 --complement avocado-updated-2020.csv
apt-get install ghead head -n 1 avocado-updated-2020.csv> header.csv
ghead -n 1 avocado-updated-2020.csv> header.csv head -n -1 avocado-updated-2020.csv | shuf > avocado-updated-2020-shuf.csv
ghead -n -1 avocado-updated-2020.csv | shuf > avocado-updated-2020-shuf.csv
# podzial na train/dev/test # podzial na train/dev/test
ghead -n 6609 avocado-updated-2020-shuf.csv > avocado-updated-2020-test.csv head -n 6609 avocado-updated-2020-shuf.csv > avocado-updated-2020-test.csv
ghead -n 13218 avocado-updated-2020-shuf.csv | tail -n 6609 > avocado-updated-2020-dev.csv head -n 13218 avocado-updated-2020-shuf.csv | tail -n 6609 > avocado-updated-2020-dev.csv
tail -n +13219 avocado-updated-2020-shuf.csv > avocado-updated-2020-train.csv tail -n +13219 avocado-updated-2020-shuf.csv > avocado-updated-2020-train.csv
wc -l avocado-updated-2020-*.csv wc -l avocado-updated-2020-*.csv