From 877ee10827775427038f44da8610bfd78ea3e0ce Mon Sep 17 00:00:00 2001
From: s464962 <krzrac1@st.amu.edu.pl>
Date: Tue, 26 Mar 2024 22:22:08 +0100
Subject: [PATCH] added create-dataset.sh

---
 create-dataset.sh | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100644 create-dataset.sh

diff --git a/create-dataset.sh b/create-dataset.sh
new file mode 100644
index 0000000..41102c3
--- /dev/null
+++ b/create-dataset.sh
@@ -0,0 +1,29 @@
+#!/bin/bash
+
+pip install kaggle
+
+kaggle datasets download -d syedanwarafridi/vehicle-sales-data
+
+unzip -o vehicle-sales-data.zip
+
+# Tasowanie
+shuf car_prices.csv -o car_prices_shuf.csv
+
+# Podział danych na podzbiory
+total_rows=$(wc -l < car_prices_shuf.csv)
+test_dev_rows=$(( $1 * 2 ))
+
+head -n $1 car_prices_shuf.csv > car_prices_test.csv
+head -n $test_dev_rows car_prices_shuf.csv | tail -n +$(( $1 + 1 )) > car_prices_dev.csv
+tail -n +$(( $test_dev_rows + 1 )) car_prices_shuf.csv > car_prices_train.csv
+
+test_size=$(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"
+
+# Zapis artefaktów
+mkdir -p data
+mv car_prices.csv car_prices_shuf.csv car_prices_test.csv car_prices_dev.csv car_prices_train.csv data/