ium_464962/create-dataset.sh

#!/bin/bash

export PATH=$PATH:/root/.local/bindock

pip install kaggle

kaggle datasets download -d syedanwarafridi/vehicle-sales-data

unzip -o vehicle-sales-data.zip

head -n 1 car_prices.csv > car_prices_header.csv
tail -n +2 car_prices.csv | awk -F, '!/,,/' | shuf > car_prices_no_null.csv

total_rows=$(wc -l < car_prices_no_null.csv)
test_dev_rows=$(( $1 * 2 ))

head -n $1 car_prices_no_null.csv > car_prices_test_temp.csv
head -n $test_dev_rows car_prices_no_null.csv | tail -n +$(( $1 + 1 )) > car_prices_dev_temp.csv
tail -n +$(( $test_dev_rows + 1 )) car_prices_no_null.csv > car_prices_train_temp.csv

cat car_prices_header.csv car_prices_test_temp.csv > car_prices_test.csv
cat car_prices_header.csv car_prices_dev_temp.csv > car_prices_dev.csv
cat car_prices_header.csv car_prices_train_temp.csv > car_prices_train.csv

rm car_prices_test_temp.csv car_prices_dev_temp.csv car_prices_train_temp.csv car_prices_no_null.csv car_prices_header.csv

test_size=$(wc -l < car_prices_test.csv)
dev_size=$(wc -l < car_prices_dev.csv)
train_size=$(wc -l < car_prices_train.csv)
echo "Rozmiar zbioru testowego: $test_size"
echo "Rozmiar zbioru deweloperskiego: $dev_size"
echo "Rozmiar zbioru treningowego: $train_size"

mkdir -p data
mv car_prices.csv car_prices_test.csv car_prices_dev.csv car_prices_train.csv data/