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

preprocessing script added

Browse Source
This commit is contained in:
patrycjalazna 2021-03-28 12:23:39 +02:00
parent 9226d17c20
commit ece8db04cf
1 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
avocado-preprocessing.sh Executable file
View File

@ -0,0 +1,38 @@
# zadanie 5
# pobranie zbioru danych
kaggle datasets download -d timmate/avocado-prices-2020
unzip -o avocado-prices-2020.zip
wc -l avocado-updated-2020.csv
# przetwarzanie pliku
grep -P "^$" -n avocado-updated-2020.csv
# usuniecie zbednej kolumny year (redundantne dane)
cut -d -f12 --complement avocado-updated-2020.csv
ghead -n 1 avocado-updated-2020.csv> header.csv
ghead -n -1 avocado-updated-2020.csv | shuf > avocado-updated-2020-shuf.csv
# podzial na train/dev/test
ghead -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
tail -n +13219 avocado-updated-2020-shuf.csv > avocado-updated-2020-train.csv
wc -l avocado-updated-2020-*.csv
cat header.csv avocado-updated-2020-test.csv > test.csv
cat header.csv avocado-updated-2020-dev.csv > dev.csv
cat header.csv avocado-updated-2020-train.csv > train.csv
# usuniecie pomocniczych plikow
rm avocado-updated-2020-test.csv
rm avocado-updated-2020-dev.csv
rm avocado-updated-2020-train.csv
rm avocado-updated-2020-shuf.csv
rm avocado-prices-2020.zip
rm header.csv
# # 7. Parametry zadania [1 pkt]
# head -n $1 data.shuffled > zadanie7.data
# cat header.csv zadanie7.data > zadanie7.csv