03 part 1

create_data.ipynb

@@ -0,0 +1,94 @@
+{
+ "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
+}

dataset_stats.ipynb

@@ -0,0 +1,53 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Załadowanie artefaktu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3. Statystyki\n",
+    "# Wielkość zbioru i podzbiorów\n",
+    "print(f\"Wielkosc zbioru: {len(no_shows)}, podzbiór train: {train_size}, podzbiór test {test_size}.\")\n",
+    "# Opis parametrów\n",
+    "no_shows.describe(include='all')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Rozkład częstości dla klas\n",
+    "no_shows[\"No-show\"].value_counts().plot(kind=\"bar\", title=\"No-show\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Zapisanie statystyk jako artefakt"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}