s434765/ium_434765
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

script fix

Browse Source
This commit is contained in:
s434765 2021-03-27 21:00:42 +01:00
parent ac0c9704e4
commit 287e65b59d
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
get_data_simple.sh
View File

@ -5,15 +5,15 @@ if kaggle datasets download -d sgonkaggle/youtube-trend-with-subscriber && unzip
COUNT=$(wc -l "USvideos_modified.csv") COUNT=$(wc -l "USvideos_modified.csv")
echo "${COUNT}" echo "${COUNT}"
head -n -1 "USvideos_modified.csv" | shuf > "data_shuf" head -n -1 "USvideos_modified.csv" | shuf > "data_shuf"
head -n 544 data_shuf > data_test head -n 544 "data_shuf" > "data_test"
head -n 1088 data_shuf | tail -n 544 > data_dev head -n 1088 "data_shuf" | tail -n 544 > "data_dev"
head -n +1089 data_shuf > data_train head -n +1089 "data_shuf" > "data_train"
echo "Shuffled dataset" echo "Shuffled dataset"
wc -l data_shuf wc -l "data_shuf"
echo "Test dataset" echo "Test dataset"
wc -l data_test wc -l "data_test"
echo "Dev dataset" echo "Dev dataset"
wc -l data_dev wc -l "data_dev"
echo "Train dataset" echo "Train dataset"
wc -l data_train wc -l "data_train"
fi fi