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 21:39:55 +01:00
parent 00e3446c93
commit 88faffea89
2 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
get_data.sh
View File

@ -5,10 +5,15 @@ if kaggle datasets download -d sgonkaggle/youtube-trend-with-subscriber && unzip
COUNT=$(wc -l "USvideos_modified.csv")
echo "${COUNT}"
head -n -1 "USvideos_modified.csv" | shuf > "data_shuf"
head -n "$1" "data_shuf" > "data_train"
head -n 544 "data_shuf" > "data_test"
head -n 1088 "data_shuf" | tail -n 544 > "data_dev"
head -n +1089 "data_shuf" > "data_train"
echo "Shuffled dataset"
wc -l "data_shuf"
echo "Test dataset"
wc -l "data_test"
echo "Dev dataset"
wc -l "data_dev"
echo "Train dataset"
wc -l "data_train"
python main.py USvideos_modified.csv

8
get_data_simple.sh
View File

@ -5,15 +5,9 @@ if kaggle datasets download -d sgonkaggle/youtube-trend-with-subscriber && unzip
COUNT=$(wc -l "USvideos_modified.csv")
echo "${COUNT}"
head -n -1 "USvideos_modified.csv" | shuf > "data_shuf"
head -n 544 "data_shuf" > "data_test"
head -n 1088 "data_shuf" | tail -n 544 > "data_dev"
head -n +1089 "data_shuf" > "data_train"
head -n "$1" "data_shuf" > "data_train"
echo "Shuffled dataset"
wc -l "data_shuf"
echo "Test dataset"
wc -l "data_test"
echo "Dev dataset"
wc -l "data_dev"
echo "Train dataset"
wc -l "data_train"
fi