ium_495716/data_download.sh

30 lines
651 B
Bash
Raw Normal View History

2024-03-20 14:48:24 +01:00
#!/bin/bash
figlet "DOWNLOAD DATA"
2024-03-20 16:50:15 +01:00
kaggle datasets download iabhishekofficial/mobile-price-classification --unzip --force
figlet "TESTSET BEFORE ID COLUMN CUT"
head -n 5 test.csv
cut -d',' -f2- test.csv > test_without_id_column.csv
figlet "TESTSET AFTER ID COLUMN CUT"
head -n 5 test_without_id_column.csv
2024-03-20 17:20:48 +01:00
figlet "CUTOFF DATA FROM TRAIN SET"
cutoff="10"
shift "$(($OPTIND - 1))"
if [[ "$1" == "--cutoff" ]]; then
shift
if [[ ! "$1" =~ ^[0-9]+$ ]]; then
echo "Error: cutoff value must be a positive number"
exit 1
fi
cutoff="$1"
fi
head -n "$cutoff" train.csv > cutoff_train.csv
figlet "DISPLAY CUTOFF DATA"
cat cutoff_train.csv