Add emergency and outpatient data

Using the new scraper!

exploration/.ipynb_checkpoints/MEPS Scraping - Python-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

exploration/.ipynb_checkpoints/MEPS Scraping-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

exploration/MEPS Scraping - Python.ipynb

@@ -0,0 +1,211 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "from html.parser import HTMLParser\n",
+    "from IPython.display import display\n",
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "emergency_data_url = \"http://meps.ahrq.gov/mepsweb/data_stats/download_data_files_results.jsp?cboDataYear=All&cboDataTypeY=2%2CHousehold+Event+File&buttonYearandDataType=Search&cboPufNumber=All&SearchTitle=Emergency+Room+Visits\"\n",
+    "\n",
+    "emergency_page = requests.get(emergency_data_url).text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "collapsed": false,
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['HC-160E',\n",
+       " 'HC-152E',\n",
+       " 'HC-144E',\n",
+       " 'HC-135E',\n",
+       " 'HC-126E',\n",
+       " 'HC-118E',\n",
+       " 'HC-110E',\n",
+       " 'HC-102E',\n",
+       " 'HC-094E',\n",
+       " 'HC-085E',\n",
+       " 'HC-077E',\n",
+       " 'HC-067E',\n",
+       " 'HC-059E',\n",
+       " 'HC-051E',\n",
+       " 'HC-033E',\n",
+       " 'HC-026E',\n",
+       " 'HC-016E',\n",
+       " 'HC-010E']"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class MepsScraper(HTMLParser):\n",
+    "    p = re.compile('HC-[0-9]*[A-Z]?')\n",
+    "    pufs = []\n",
+    "    \n",
+    "    def handle_data(self, data):\n",
+    "        \n",
+    "        if self.p.match(data):\n",
+    "            self.pufs.append(data)\n",
+    "        \n",
+    "meps = MepsScraper()\n",
+    "meps.feed(emergency_page)\n",
+    "display(meps.pufs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['h160e',\n",
+       " 'h152e',\n",
+       " 'h144e',\n",
+       " 'h135e',\n",
+       " 'h126e',\n",
+       " 'h118e',\n",
+       " 'h110e',\n",
+       " 'h102e',\n",
+       " 'h94e',\n",
+       " 'h85e',\n",
+       " 'h77e',\n",
+       " 'h67e',\n",
+       " 'h59e',\n",
+       " 'h51e',\n",
+       " 'h33e',\n",
+       " 'h26e',\n",
+       " 'h16e',\n",
+       " 'h10e']"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "def norm_puf(puf):\n",
+    "    splits = puf.split(\"C-\")\n",
+    "    if splits[1][0] == '0':\n",
+    "        return ''.join([splits[0], splits[1][1:]]).lower()\n",
+    "    else:\n",
+    "        return ''.join(splits).lower()\n",
+    "    \n",
+    "final_pufs = list(map(norm_puf, meps.pufs))\n",
+    "display(final_pufs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": false,
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "puf_url = lambda x: 'http://meps.ahrq.gov/mepsweb/data_files/pufs/' + x + 'ssp.zip'\n",
+    "\n",
+    "puf_urls = list(map(puf_url, final_pufs))\n",
+    "\n",
+    "puf_files = {puf: requests.get(puf_url(puf)) for puf in final_pufs}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Error extracting h26e'"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Error extracting h16e'"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Error extracting h10e'"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from zipfile import ZipFile, BadZipFile\n",
+    "from io import BytesIO\n",
+    "\n",
+    "for key, value in puf_files.items():\n",
+    "    try:\n",
+    "        puf_zip = ZipFile(BytesIO(value.content))\n",
+    "        puf_zip.extractall()\n",
+    "    except BadZipFile:\n",
+    "        display(\"Error extracting {}\".format(key))"
+   ]
+  }
+ ],
+ "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": "3.5.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

exploration/MEPS Scraping.ipynb

@@ -0,0 +1,87 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "library(httr)\n",
+    "library(foreign)\n",
+    "        \n",
+    "download_puf <- function(short_puf) {\n",
+    "    puf_base <- \"http://meps.ahrq.gov/mepsweb/data_files/pufs/\"\n",
+    "    puf_suffix <- \"ssp.zip\"\n",
+    "    \n",
+    "    zip_filename <- paste0(short_puf, \"ssp.zip\")\n",
+    "    filename <- paste0(short_puf, \".ssp\")\n",
+    "    puf_url <- paste0(puf_base, zip_filename)\n",
+    "    download.file(puf_url, zip_filename)\n",
+    "    \n",
+    "    # unzip\n",
+    "    unzip(zip_filename, files = filename)\n",
+    "    saveName <- paste0(short_puf, \".csv\")\n",
+    "\n",
+    "    # read sas file and return as csv file\n",
+    "    mydata <- read.xport(filename)\n",
+    "    write.table(mydata, file = saveName, sep = \",\")\n",
+    "}\n",
+    "\n",
+    "normalize_puf <- function(full_puf) {\n",
+    "    stage_1 <- gsub(\"C-0\", \"\", full_puf)\n",
+    "    stage_2 <- gsub(\"C-\", \"\", stage_1)\n",
+    "    \n",
+    "    tolower(stage_2)\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "ename": "ERROR",
+     "evalue": "Error in lookup.xport(file): file not in SAS transfer format\n",
+     "output_type": "error",
+     "traceback": [
+      "Error in lookup.xport(file): file not in SAS transfer format\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Emergency Visit PUF's\n",
+    "# pufs <- c('HC-160E','HC-152E','HC-144E','HC-135E','HC-126E','HC-118E','HC-110E','HC-102E','HC-094E','HC-085E','HC-077E','HC-067E','HC-059E','HC-051E','HC-033E','HC-026E','HC-016E','HC-010E')\n",
+    "\n",
+    "# Outpatient Visits\n",
+    "pufs <- c('HC-160F','HC-152F','HC-144F','HC-135F','HC-126F','HC-118F','HC-110F','HC-102F','HC-094F','HC-085F','HC-077F','HC-067F','HC-059F','HC-051F','HC-033F','HC-026F','HC-016F','HC-010F')\n",
+    "\n",
+    "puf_downloads = c()\n",
+    "for (puf in pufs) {\n",
+    "    download_puf(normalize_puf(puf))\n",
+    "}"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "R",
+   "language": "R",
+   "name": "ir"
+  },
+  "language_info": {
+   "codemirror_mode": "r",
+   "file_extension": ".r",
+   "mimetype": "text/x-r-source",
+   "name": "R",
+   "pygments_lexer": "r",
+   "version": "3.2.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}