{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quickstart"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We download some test data for the 32 tables from the address below and populate the Concept registry."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [],
   "source": [
    "!wget -nc https://physionet.org/static/published-projects/mimic-iv-demo-omop/mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip\n",
    "!unzip -n mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a test instance:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!lamin init --storage ./test-omop --name test-omop --schema omop"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import `omop`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import lamindb as ln\n",
    "import omop as op\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load the data into a Pandas DataFrame:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"./mimic-iv-demo-data-in-the-omop-common-data-model-0.9/1_omop_data_csv/2b_concept.csv\")\n",
    "df.columns = df.columns.str.lower()\n",
    "df.rename(columns={\"concept_class_id\": \"concept_class\"}, inplace=True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Populate the Concept registry:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [],
   "source": [
    "concepts = [op.Concept(**row.to_dict()) for _, row in df.iterrows()]\n",
    "for concept in concepts:\n",
    "    concept.save()\n",
    "op.Concept.df()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Perform validation of new data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "op.Concept.validate([\"Stroke Volume Variation\", \"this concept does not exist\"], field=op.Concept.concept_name)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "lamindb",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}