{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install kaggle\n",
    "!pip install pandas\n",
    "!pip install seaborn\n",
    "!pip install torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1 Pobranie zbioru\n",
    "!kaggle datasets download -d joniarroba/noshowappointments"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!unzip -o noshowappointments.zip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "no_shows=pd.read_csv('KaggleV2-May-2016.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Wyczyszczenie zbioru\n",
    "# Usunięcie negatywnego wieku\n",
    "no_shows = no_shows.drop(no_shows[no_shows[\"Age\"] < 0].index)\n",
    "\n",
    "# Usunięcie niewiadomego wieku (zależy od zastosowania)\n",
    "# no_shows = no_shows.drop(no_shows[no_shows[\"Age\"] == 0].index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Normalizacja danych\n",
    "\n",
    "# Usunięcie kolumn PatientId oraz AppointmentID\n",
    "no_shows.drop([\"PatientId\", \"AppointmentID\"], inplace=True, axis=1)\n",
    "\n",
    "# Zmiena wartości kolumny No-show z Yes/No na wartość boolowską\n",
    "no_shows[\"No-show\"] = no_shows[\"No-show\"].map({'Yes': 1, 'No': 0})\n",
    "\n",
    "# Normalizacja kolumny Age\n",
    "no_shows[\"Age\"]=(no_shows[\"Age\"]-no_shows[\"Age\"].min())/(no_shows[\"Age\"].max()-no_shows[\"Age\"].min())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Zapisanie wyników jako artefakt"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}