ium_434765/get_data.sh
s434765 ed16ad4d5c
All checks were successful
s434765-training/pipeline/head This commit looks good
dev data
2021-05-17 19:53:21 +02:00

11 lines
505 B
Bash
Executable File

#!/bin/bash
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"
python3 get_data.py USvideos_modified.csv
fi