27 lines
848 B
Bash
27 lines
848 B
Bash
#!/bin/bash
|
|
|
|
pip install kaggle --upgrade
|
|
|
|
kaggle datasets download -d gulczas/spotify-dataset
|
|
|
|
unzip -o spotify-dataset.zip
|
|
|
|
echo "------------------ Shufle ------------------"
|
|
shuf Spotify_Dataset.csv -o shuffled_spotify.csv
|
|
|
|
echo "------------------ Cut off to top $1 rows ------------------"
|
|
head -n $1 shuffled_spotify.csv > cutoff_spotify.csv
|
|
|
|
echo "------------------ Split ------------------"
|
|
total_lines=$(wc -l < cutoff_spotify.csv)
|
|
num_test=$((total_lines / 10))
|
|
num_train=$((total_lines - (num_test * 2)))
|
|
num_validation=$num_test
|
|
|
|
head -n $num_train cutoff_spotify.csv > train.csv
|
|
tail -n $((num_test+num_validation)) cutoff_spotify.csv | head -n $num_test > test.csv
|
|
tail -n $num_validation cutoff_spotify.csv > validation.csv
|
|
|
|
mkdir -p artifacts
|
|
mv Spotify_Dataset.csv cutoff_spotify.csv train.csv validation.csv test.csv artifacts/
|