#!/bin/bash
rm USvideos_modified.csv
if kaggle datasets download -d sgonkaggle/youtube-trend-with-subscriber && unzip youtube-trend-with-subscriber.zip; then
    grep -v -e "^$" - USvideos_modified.csv
    COUNT=$(wc -l "USvideos_modified.csv")
    echo "${COUNT}"
    head -n -1 "USvideos_modified.csv" | shuf > "data_shuf"
    head -n 544 "data_shuf" > "data_test"
    head -n 1088 "data_shuf" | tail -n 544 > "data_dev"
    head -n 5441 "data_shuf" | tail -n 4352 > "data_train"
    sed '/^$/d' "data_dev"
    python3 get_data.py USvideos_modified.csv
fi