{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2017-05-24T15:13:43.919016Z",
     "start_time": "2017-05-24T16:13:43.760433+01:00"
    },
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "from IPython.display import display\n",
    "%matplotlib inline\n",
    "plt.rcParams['figure.figsize'] = (20.0, 10.0)\n",
    "\n",
    "rhi_csv = 'tabula-RHI-beneficiaries-non-domestic-individuals-companies.csv'\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2017-05-24T15:17:13.882070Z",
     "start_time": "2017-05-24T16:17:13.811741+01:00"
    },
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Company</th>\n",
       "      <th>Postcode</th>\n",
       "      <th>Type</th>\n",
       "      <th>Capacity (kWth)</th>\n",
       "      <th>Date</th>\n",
       "      <th>Cash</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aaron Newell</td>\n",
       "      <td>BT39</td>\n",
       "      <td>Solid Biomass Boiler</td>\n",
       "      <td>60.0</td>\n",
       "      <td>2015-09-04</td>\n",
       "      <td>19084.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Acheson &amp; Glover Precast Ltd</td>\n",
       "      <td>BT75</td>\n",
       "      <td>Solid Biomass Boiler</td>\n",
       "      <td>99.0</td>\n",
       "      <td>2015-11-06</td>\n",
       "      <td>27600.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Acheson &amp; Glover Precast Ltd</td>\n",
       "      <td>BT75</td>\n",
       "      <td>Solid Biomass Boiler</td>\n",
       "      <td>99.0</td>\n",
       "      <td>2015-11-06</td>\n",
       "      <td>30507.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Acheson &amp; Glover Precast Ltd</td>\n",
       "      <td>BT75</td>\n",
       "      <td>Solid Biomass Boiler</td>\n",
       "      <td>99.0</td>\n",
       "      <td>2015-11-06</td>\n",
       "      <td>34416.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Acheson &amp; Glover Precast Ltd</td>\n",
       "      <td>BT75</td>\n",
       "      <td>Solid Biomass Boiler</td>\n",
       "      <td>99.0</td>\n",
       "      <td>2015-07-13</td>\n",
       "      <td>50543.44</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        Company Postcode                  Type  \\\n",
       "0                  Aaron Newell     BT39  Solid Biomass Boiler   \n",
       "1  Acheson & Glover Precast Ltd     BT75  Solid Biomass Boiler   \n",
       "2  Acheson & Glover Precast Ltd     BT75  Solid Biomass Boiler   \n",
       "3  Acheson & Glover Precast Ltd     BT75  Solid Biomass Boiler   \n",
       "4  Acheson & Glover Precast Ltd     BT75  Solid Biomass Boiler   \n",
       "\n",
       "   Capacity (kWth)       Date      Cash  \n",
       "0             60.0 2015-09-04  19084.69  \n",
       "1             99.0 2015-11-06  27600.66  \n",
       "2             99.0 2015-11-06  30507.19  \n",
       "3             99.0 2015-11-06  34416.23  \n",
       "4             99.0 2015-07-13  50543.44  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "Company                    object\n",
       "Postcode                   object\n",
       "Type                       object\n",
       "Capacity (kWth)           float64\n",
       "Date               datetime64[ns]\n",
       "Cash                      float64\n",
       "dtype: object"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df = pd.read_csv(rhi_csv)\n",
    "df['Date'] = pd.to_datetime(df['Date of\\rApplication'], format='%d/%m/%Y')\n",
    "df['Cash'] = df['Amount of payments\\rmade to 28 February\\r2017 (£)*'].replace('[£,]','', regex=True).astype(float)\n",
    "df.drop(['Date of\\rApplication','Amount of payments\\rmade to 28 February\\r2017 (£)*'], axis=1, inplace=True) \n",
    "df.rename(columns={'Business or\\rInstallation\\rLocation':'Postcode', 'Installation\\rCapacity\\r(kWth)':'Capacity (kWth)','Technology Type':'Type','Name':'Company'}, inplace=True)\n",
    "display(df.head())\n",
    "display(df.dtypes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2017-05-24T15:18:46.613887Z",
     "start_time": "2017-05-24T16:18:46.574273+01:00"
    },
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Company</th>\n",
       "      <th>Postcode</th>\n",
       "      <th>Type</th>\n",
       "      <th>Capacity (kWth)</th>\n",
       "      <th>Date</th>\n",
       "      <th>Cash</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1157</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>(GSHP)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaT</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Company Postcode    Type  Capacity (kWth) Date  Cash\n",
       "1157     NaN      NaN  (GSHP)              NaN  NaT   NaN"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.Postcode.isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2017-05-24T15:19:09.762112Z",
     "start_time": "2017-05-24T16:19:09.744219+01:00"
    },
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "60295840.10000002"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Cash.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [conda root]",
   "language": "python",
   "name": "conda-root-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.3"
  },
  "latex_envs": {
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 0
  },
  "nav_menu": {},
  "toc": {
   "navigate_menu": true,
   "number_sections": true,
   "sideBar": true,
   "threshold": 6,
   "toc_cell": false,
   "toc_section_display": "block",
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}