{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![Urgences - Image CC0 - pexels.com](img/pexels-pixabay-263402.jpg \"Urgences\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Challenge - [ED Lab Prediction]\n",
    "_Nom à trouver_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Objectif"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ce notebook effectue le pre-processing des données.  \n",
    "Il exploite les données stockées dans la base sqlite, téléchargées à partir de `download_data.py` et les exporte dans un fichier csv à destination de l'entrainement de la data-visualisation l'algorithme."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chargement des données"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sqlite3\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Sqlite connection\n",
    "conn = sqlite3.connect(\"./data/mimic-iv.sqlite\")\n",
    "\n",
    "# Custom lab items classification\n",
    "items = pd.read_csv(\"./config/lab_items.csv\").dropna()\n",
    "items_list = items[\"item_id\"].astype(\"str\").tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Création d'un index pour accélérer les requêtes\n",
    "conn.execute(\"CREATE INDEX IF NOT EXISTS biological_index ON labevents (stay_id, itemid)\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stays dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "metadata": {},
   "outputs": [],
   "source": [
    "stays = pd.read_sql(f\"\"\"\n",
    "    SELECT \n",
    "        s.stay_id,\n",
    "        s.intime intime,\n",
    "        p.gender gender,\n",
    "        p.anchor_age age,\n",
    "        t.temperature,\n",
    "        t.heartrate,\n",
    "        t.resprate,\n",
    "        t.o2sat,\n",
    "        t.sbp,\n",
    "        t.dbp,\n",
    "        t.pain,\n",
    "        t.chiefcomplaint\n",
    "    FROM edstays s\n",
    "    LEFT JOIN patients p\n",
    "        ON p.subject_id = s.subject_id\n",
    "    LEFT Join triage t\n",
    "        ON t.stay_id = s.stay_id\n",
    "\"\"\", conn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 151,
   "metadata": {},
   "outputs": [],
   "source": [
    "# @TODO : include drugs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Writting\n",
    "stays.to_csv(\"./data/features.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Lab dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [],
   "source": [
    "labs = pd.read_sql(f\"\"\"\n",
    "    SELECT \n",
    "        le.stay_id,\n",
    "        le.itemid item_id\n",
    "    FROM labevents le\n",
    "    WHERE le.itemid IN ('{\"','\".join(items_list)}')\n",
    "    GROUP BY\n",
    "        le.stay_id,\n",
    "        le.itemid\n",
    "\"\"\", conn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [],
   "source": [
    "labs_deduplicate = pd.merge(\n",
    "    items[[\"item_id\",\"3\"]].rename(columns={\"3\":\"label\"}),\n",
    "    labs,\n",
    "    left_on=\"item_id\",\n",
    "    right_on=\"item_id\"\n",
    ").drop_duplicates([\"stay_id\", \"label\"])[[\"stay_id\",\"label\"]] \\\n",
    " .reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {},
   "outputs": [],
   "source": [
    "labs_deduplicate_pivot = pd.pivot_table(\n",
    "    labs_deduplicate.assign(value=1),\n",
    "    index=[\"stay_id\"],\n",
    "    columns=[\"label\"],\n",
    "    values=\"value\"\n",
    ").fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "metadata": {},
   "outputs": [],
   "source": [
    "labs_deduplicate_pivot_final = labs_deduplicate_pivot.join(\n",
    "    stays[[\"stay_id\"]].set_index(\"stay_id\"),\n",
    "    how=\"right\"\n",
    ").fillna(0).astype(\"int8\").reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "metadata": {},
   "outputs": [],
   "source": [
    "labs_deduplicate_pivot_final.to_csv(\"./data/labels.csv\")"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "28b293e0c0671e44c7281dde6399c7c7419d3faca031d22494da8635907ada72"
  },
  "kernelspec": {
   "display_name": "Python 3.9.7 ('base')",
   "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": "3.9.7"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}