19 lines
765 B
Bash
19 lines
765 B
Bash
dataset_operation() {
|
|
tail -n +2 imdb-dataset.csv | shuf > imdb-dataset.csv.s
|
|
head -n $CUTOFF imdb-dataset.csv.s > ./imdb-dataset.csv.shuf
|
|
len1=$(cat ./imdb-dataset.csv.shuf | wc -l)
|
|
len2=$(($len1/10))
|
|
len3=$(($len2*2))
|
|
len4=$(($len3+1))
|
|
head -n $len2 imdb-dataset.csv.shuf > imdb-dataset.csv.test
|
|
head -n $len3 imdb-dataset.csv.shuf | tail -n $len2 > imdb-dataset.csv.dev
|
|
tail -n +$len4 imdb-dataset.csv.shuf > imdb-dataset.csv.train
|
|
rm imdb-dataset.csv.shuf
|
|
wc -l imdb-dataset.csv.*
|
|
}
|
|
|
|
kaggle datasets download -d harshitshankhdhar/imdb-dataset-of-top-1000-movies-and-tv-shows
|
|
unzip imdb-dataset-of-top-1000-movies-and-tv-shows.zip
|
|
mv imdb-dataset-of-top-1000-movies-and-tv-shows.zip imdb-dataset.zip
|
|
dataset_operation
|