{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "procedures = pd.read_csv('medicare_procedure_data.tsv', sep='\\t')\n",
    "\n",
    "procedures.to_csv('data/procedures.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "specialties = pd.read_csv('nucc_taxonomy_190.csv')\n",
    "\n",
    "def code_to_specialty(code):\n",
    "    if len(specialties[specialties['Code'] == code]) > 0:\n",
    "        specialty = list(specialties[specialties['Code'] == code]['Grouping'])[0]\n",
    "        return specialty\n",
    "    else:\n",
    "        return \"Unknown\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "providers = pd.read_csv('nppes_npi_registry_with_specialties.csv', usecols=['NPI', 'Healthcare Provider Taxonomy Code_1', 'Primary phone number'])\\\n",
    "              .rename(columns={'Healthcare Provider Taxonomy Code_1':'specialty_code'})\\\n",
    "              .assign(specialty=lambda df: code_to_specialty(df['specialty_code']))\\\n",
    "              .drop('specialty_code')\n",
    "\n",
    "providers.to_csv('data/physicians.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "grouping = providers.groupby('specialty_code')['NPI'].count()\\\n",
    "    .reset_index()\\\n",
    "    .assign(specialty=grouping.specialty_code.apply(code_to_specialty)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}