2023-04-19 19:04:17 +02:00
|
|
|
#!/bin/bash
|
2023-04-19 19:59:47 +02:00
|
|
|
set -e
|
2023-04-19 19:04:17 +02:00
|
|
|
|
2023-04-19 19:59:47 +02:00
|
|
|
# Uwierzytelnianie w Kaggle API za pomocą zmiennych środowiskowych
|
|
|
|
export KAGGLE_USERNAME=$KAGGLE_USERNAME
|
|
|
|
export KAGGLE_KEY=$KAGGLE_KEY
|
2023-04-19 19:37:46 +02:00
|
|
|
|
2023-04-19 19:59:47 +02:00
|
|
|
# Pobieranie i rozpakowywanie danych
|
|
|
|
kaggle datasets download -d iabhishekofficial/mobile-price-classification
|
|
|
|
unzip -o mobile-price-classification.zip
|
2023-04-19 19:37:46 +02:00
|
|
|
|
2023-04-19 19:59:47 +02:00
|
|
|
# Przetwarzanie danych
|
2023-04-19 20:22:15 +02:00
|
|
|
head -n $CUTOFF train.csv > train_cutoff.csv
|
|
|
|
cut -f $CUT --complement -d, train_cutoff.csv > mobile-price-classification.csv
|
2023-04-19 20:19:32 +02:00
|
|
|
|
2023-04-19 19:59:47 +02:00
|
|
|
# Kompresowanie pliku wynikowego
|
2023-04-19 20:22:15 +02:00
|
|
|
gzip -c mobile-price-classification.csv > output.txt.gz
|