{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "59868c88",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "--2023-03-25 11:54:34--  https://archive.ics.uci.edu/ml/machine-learning-databases/car/car.data\n",
      "Resolving archive.ics.uci.edu (archive.ics.uci.edu)... 128.195.10.252\n",
      "Connecting to archive.ics.uci.edu (archive.ics.uci.edu)|128.195.10.252|:443... connected.\n",
      "HTTP request sent, awaiting response... 206 Partial Content\n",
      "Length: 51867 (51K), 1 remaining [application/x-httpd-php]\n",
      "Saving to: ‘car.data’\n",
      "\n",
      "car.data            100%[+++++++++++++++++++>]  50,65K  --.-KB/s    in 0s      \n",
      "\n",
      "2023-03-25 11:54:35 (16,8 KB/s) - ‘car.data’ saved [51867/51867]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "!wget -c https://archive.ics.uci.edu/ml/machine-learning-databases/car/car.data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "776bf1e2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1728 car.data\r\n"
     ]
    }
   ],
   "source": [
    "!wc -l car.data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a56dee9c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "vhigh,vhigh,2,2,small,low,unacc\n",
      "vhigh,vhigh,2,2,small,med,unacc\n",
      "vhigh,vhigh,2,2,small,high,unacc\n",
      "vhigh,vhigh,2,2,med,low,unacc\n",
      "vhigh,vhigh,2,2,med,med,unacc\n",
      "vhigh,vhigh,2,2,med,high,unacc\n",
      "    576 high\n",
      "    576 low\n",
      "    576 med\n"
     ]
    }
   ],
   "source": [
    "!head -n 6 car.data\n",
    "!cut -f 6 -d \",\" car.data | sort | uniq -c"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "54a43eaa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    192 high\n",
      "    193 low\n",
      "    192 med\n",
      "     96 high\n",
      "     96 low\n",
      "     96 med\n",
      "     96 high\n",
      "     96 low\n",
      "     96 med\n"
     ]
    }
   ],
   "source": [
    "!head -n 288 car.data > car.data.test\n",
    "!head -n 576 car.data | tail -n 288 > car.data.dev\n",
    "!head -n +577 car.data > car.data.train\n",
    "#sprawdzanie podziału ze względu na bezpieczeństwo samochodu\n",
    "!cut -f 6 -d \",\" car.data.train | sort | uniq -c\n",
    "!cut -f 6 -d \",\" car.data.test | sort | uniq -c\n",
    "!cut -f 6 -d \",\" car.data.dev | sort | uniq -c"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}