eainfo to csv Example

eainfo to csv Example.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Demo of how to use the MetadataWizard to convert detailed section to a csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pymdwizard.core import xml_utils"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "fname = r\"C:\\Users\\talbertc\\Downloads\\Woody riparian invasion in Colorado.xml\"\n",
    "md = xml_utils.XMLRecord(fname)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### There's a lot of variablility in how an detailed section can be structured.  \n",
    "This won't work in all cases, multiple domain types in a single atribute, etc."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = ['attrlabl', 'attrdef', 'attrdomv', 'values']\n",
    "\n",
    "rows = []\n",
    "for attr in md.metadata.eainfo.detailed.attr:\n",
    "    attrlabl = attr.attrlabl.text\n",
    "    attrdef = attr.attrdef.text\n",
    "    \n",
    "    attrdomv = attr.xpath('attrdomv', as_list=True)[0].children[0].tag\n",
    "        \n",
    "    if attrdomv == \"rdom\":\n",
    "        minvalue = attr.attrdomv.rdom.rdommin.text\n",
    "        maxvalue = attr.attrdomv.rdom.rdommin.text\n",
    "        values = \"|\".join([minvalue, maxvalue])\n",
    "    elif attrdomv == \"edom\":\n",
    "        values = \"|\".join([attrdomv.edom.edomv.text for attrdomv in attr.xpath('attrdomv', as_list=True)])\n",
    "    elif attrdomv == \"udom\":\n",
    "        values = attr.attrdomv.udom.text\n",
    "        \n",
    "    row = [attrlabl, attrdef, attrdomv, values]\n",
    "    rows.append(row)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>attrlabl</th>\n",
       "      <th>attrdef</th>\n",
       "      <th>attrdomv</th>\n",
       "      <th>values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Site ID</td>\n",
       "      <td>Unique identifier assigned to each site</td>\n",
       "      <td>udom</td>\n",
       "      <td>The unique identifier assigned to each site co...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Latitude</td>\n",
       "      <td>Latitude of the site</td>\n",
       "      <td>rdom</td>\n",
       "      <td>33.1483333333|33.1483333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Longitude</td>\n",
       "      <td>Longitude of the site</td>\n",
       "      <td>rdom</td>\n",
       "      <td>101.887972222|101.887972222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Location description</td>\n",
       "      <td>Description of the location of the site</td>\n",
       "      <td>udom</td>\n",
       "      <td>Descriptions of the site locations are from th...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>River basin</td>\n",
       "      <td>Major river basin in which the site is located</td>\n",
       "      <td>edom</td>\n",
       "      <td>South Platte|upper Arkansas|upper/middle Rio G...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               attrlabl                                         attrdef  \\\n",
       "0               Site ID         Unique identifier assigned to each site   \n",
       "1              Latitude                            Latitude of the site   \n",
       "2             Longitude                           Longitude of the site   \n",
       "3  Location description         Description of the location of the site   \n",
       "4           River basin  Major river basin in which the site is located   \n",
       "\n",
       "  attrdomv                                             values  \n",
       "0     udom  The unique identifier assigned to each site co...  \n",
       "1     rdom                        33.1483333333|33.1483333333  \n",
       "2     rdom                        101.887972222|101.887972222  \n",
       "3     udom  Descriptions of the site locations are from th...  \n",
       "4     edom  South Platte|upper Arkansas|upper/middle Rio G...  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df = pd.DataFrame.from_records(rows, columns=cols)\n",
    "df.to_csv(r\"c:\\temp\\out.csv\", index=False)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}