johanvdw/dijle.ipynb

## dijle.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualiseren oorspronkelijke resultaten\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAMYAAAD8CAYAAAAsetuWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nheE4Bfw/CozCjDt/bj4AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f99eb820128>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f99eab5fcc0>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import rasterio\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from rasterio.plot import show\n",
    "%matplotlib inline  \n",
    "\n",
    " \n",
    "\n",
    "v7_old = rasterio.open(\"VegNoEffectsRef/v7\")\n",
    "\n",
    "show((v7_old, 1))\n",
    "\n",
    "\n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Het probleem situeert zich in de zones in het zuidwesten, hier is een zeer hoge mhw/mlw: de vegetatie mag hier helemaal niet voorkomen."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAMYAAAD8CAYAAAAsetuWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f99eaadfd68>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAMYAAAD8CAYAAAAsetuWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f99eab2ca90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f99e725f748>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mhw = rasterio.open(\"Input/GXG/ghg_0_cm.asc\")\n",
    "mlw = rasterio.open(\"Input/GXG/glg_0_cm.asc\")\n",
    "msw = rasterio.open(\"Input/GXG/gvg_0_cm.asc\")\n",
    "soil_code = rasterio.open(\"Input/Bodem/bodemv\")\n",
    "\n",
    "show((mhw, 1))\n",
    "show((soil_code,1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Berekening met nieuwe niche versie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   occurence\n",
      "2      0.62%\n",
      "3      5.72%\n",
      "4      2.37%\n",
      "5      2.27%\n",
      "6      0.06%\n",
      "7     15.82%\n",
      "8     23.74%\n",
      "9      8.97%\n",
      "12     3.33%\n",
      "15     0.17%\n",
      "16     0.22%\n",
      "17     0.82%\n",
      "18    19.33%\n",
      "19     0.03%\n",
      "20     6.20%\n",
      "21    17.88%\n",
      "28     0.05%\n"
     ]
    }
   ],
   "source": [
    "import niche_vlaanderen\n",
    "\n",
    "myniche = niche_vlaanderen.Niche()\n",
    "# set_spatial_context: alle andere grids moeten op exact dezelfde manier liggen.\n",
    "myniche.set_input(\"msw\", \"Input/GXG/gvg_0_cm.asc\", set_spatial_context=True)\n",
    "myniche.set_input(\"mlw\", \"Input/GXG/glg_0_cm.asc\")\n",
    "myniche.set_input(\"mhw\", \"Input/GXG/ghg_0_cm.asc\")\n",
    "myniche.set_input(\"seepage\", \"Input/GXG/kwel_mm_dag.asc\")\n",
    "\n",
    "myniche.set_input(\"management\", \"Input/Beheer/beheer_int\")\n",
    "myniche.set_input(\"soil_code\", \"Input/Bodem/bodemv\")\n",
    "\n",
    "\n",
    "myniche.set_input(\"nitrogen_atmospheric\", \"Input/Atmosf_depositie/depositie_def\")\n",
    "myniche.set_input(\"nitrogen_animal\", \"Input/Bemesting/bemest_dier\")\n",
    "myniche.set_input(\"nitrogen_fertilizer\", \"Input/Bemesting/bemest_kunst\")\n",
    "\n",
    "myniche.set_input(\"inundation_vegetation\", \"Input/Overstromingen/overstr_veg\")\n",
    "myniche.set_input(\"inundation_acidity\", \"Input/Overstromingen/ovrstr_t10_50\")\n",
    "myniche.set_input(\"inundation_nutrient\", \"Input/Overstromingen/ovrstr_t10_50\")\n",
    "\n",
    "myniche.set_input(\"conductivity\", \"Input/Mineraalrijkdom/minrijkdom_\")\n",
    "\n",
    "myniche.set_input(\"rainwater\", \"Input/nullgrid.asc\")\n",
    "\n",
    "\n",
    "\n",
    "myniche.run()\n",
    "\n",
    "myniche.write(\"output2\") # schrijft de nicheresultaten weg in een map \"output\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7f99e7285cc0>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAALMAAAD8CAYAAAA8GpVKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ndrLBxexkg4vZyYb/A6o8qUc2dShBAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f9a2c25bb70>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(myniche._vegetation[7])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "De zone lijkt hier weg te zijn. Kunnen we verder achterhalen wat er juist misgelopen is? In eerste instantie kijken we naar de verschillen tussen beide grids.\n",
    "\n",
    "# Verschilkaart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.colorbar.Colorbar at 0x7f99e7097a90>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAAD8CAYAAACmVULXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f9a2c25ba58>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "old = v7_old.read(1) # de eerste band inlezen\n",
    "diff = old - myniche._vegetation[7]\n",
    "plt.imshow(diff)\n",
    "plt.colorbar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We zien in de nieuwe kaart geen voorspelling meer in het zuidwesten en op enkele losse punten. Opvallend is dat we wél een voorspelling krijgen op een aantal plaatsen langs de spoorweg in het oosten van het gebied.\n",
    "\n",
    "Hieronder kijken we welke waarden van mhw/mlw/msw voorkomen op de plaatsen waar de oorspronkelijke voorspelling de mist inging."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "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>mhw</th>\n",
       "      <th>mlw</th>\n",
       "      <th>msw</th>\n",
       "      <th>soil</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>984.000000</td>\n",
       "      <td>1003.000000</td>\n",
       "      <td>995.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>984.000000</td>\n",
       "      <td>1005.000000</td>\n",
       "      <td>995.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>985.999939</td>\n",
       "      <td>1007.000000</td>\n",
       "      <td>997.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1017.000000</td>\n",
       "      <td>1056.000000</td>\n",
       "      <td>1035.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1068.000000</td>\n",
       "      <td>1108.000000</td>\n",
       "      <td>1086.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1052.000000</td>\n",
       "      <td>1093.000000</td>\n",
       "      <td>1071.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1160.000000</td>\n",
       "      <td>1198.000000</td>\n",
       "      <td>1177.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1200.000000</td>\n",
       "      <td>1239.000000</td>\n",
       "      <td>1218.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1212.000000</td>\n",
       "      <td>1254.000000</td>\n",
       "      <td>1231.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1383.000000</td>\n",
       "      <td>1423.000000</td>\n",
       "      <td>1401.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1411.000000</td>\n",
       "      <td>1453.000000</td>\n",
       "      <td>1430.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>1336.000000</td>\n",
       "      <td>1379.000000</td>\n",
       "      <td>1355.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1298.000000</td>\n",
       "      <td>1342.000000</td>\n",
       "      <td>1318.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>1259.000000</td>\n",
       "      <td>1305.000000</td>\n",
       "      <td>1280.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>1584.000000</td>\n",
       "      <td>1626.000000</td>\n",
       "      <td>1602.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>1535.000000</td>\n",
       "      <td>1578.000000</td>\n",
       "      <td>1554.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>1486.000000</td>\n",
       "      <td>1530.000000</td>\n",
       "      <td>1505.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>1387.000000</td>\n",
       "      <td>1433.000000</td>\n",
       "      <td>1408.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>1756.000000</td>\n",
       "      <td>1799.000000</td>\n",
       "      <td>1775.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>1695.999878</td>\n",
       "      <td>1739.000000</td>\n",
       "      <td>1714.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>1635.000000</td>\n",
       "      <td>1679.999878</td>\n",
       "      <td>1654.000122</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>1576.000000</td>\n",
       "      <td>1620.999878</td>\n",
       "      <td>1596.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>1480.000000</td>\n",
       "      <td>1494.000000</td>\n",
       "      <td>1487.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>1554.000000</td>\n",
       "      <td>1573.000000</td>\n",
       "      <td>1563.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>1710.000000</td>\n",
       "      <td>1753.000122</td>\n",
       "      <td>1728.000122</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>1631.000000</td>\n",
       "      <td>1676.000000</td>\n",
       "      <td>1651.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>1675.000000</td>\n",
       "      <td>1695.000122</td>\n",
       "      <td>1685.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>1748.000000</td>\n",
       "      <td>1774.000000</td>\n",
       "      <td>1761.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>1820.999878</td>\n",
       "      <td>1851.000000</td>\n",
       "      <td>1835.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>1628.000122</td>\n",
       "      <td>1673.000000</td>\n",
       "      <td>1646.999878</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>2081.000000</td>\n",
       "      <td>2123.000000</td>\n",
       "      <td>2098.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>1995.999878</td>\n",
       "      <td>2039.000000</td>\n",
       "      <td>2014.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>2105.000000</td>\n",
       "      <td>2125.000000</td>\n",
       "      <td>2116.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>2157.000000</td>\n",
       "      <td>2184.000000</td>\n",
       "      <td>2170.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>2189.000000</td>\n",
       "      <td>2231.000000</td>\n",
       "      <td>2207.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>2095.000000</td>\n",
       "      <td>2137.000000</td>\n",
       "      <td>2113.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>2001.000000</td>\n",
       "      <td>2044.000000</td>\n",
       "      <td>2018.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>2123.000000</td>\n",
       "      <td>2136.000000</td>\n",
       "      <td>2131.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48</th>\n",
       "      <td>2244.000000</td>\n",
       "      <td>2265.000000</td>\n",
       "      <td>2256.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49</th>\n",
       "      <td>2317.000000</td>\n",
       "      <td>2358.000000</td>\n",
       "      <td>2334.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50</th>\n",
       "      <td>2213.000000</td>\n",
       "      <td>2255.000000</td>\n",
       "      <td>2230.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>51</th>\n",
       "      <td>2109.000000</td>\n",
       "      <td>2152.000000</td>\n",
       "      <td>2127.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52</th>\n",
       "      <td>2006.000000</td>\n",
       "      <td>2049.000000</td>\n",
       "      <td>2024.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53</th>\n",
       "      <td>1902.000000</td>\n",
       "      <td>1945.000122</td>\n",
       "      <td>1920.000122</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54</th>\n",
       "      <td>2460.000000</td>\n",
       "      <td>2500.000000</td>\n",
       "      <td>2477.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>2347.000000</td>\n",
       "      <td>2389.000000</td>\n",
       "      <td>2365.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>56</th>\n",
       "      <td>2235.000000</td>\n",
       "      <td>2277.000000</td>\n",
       "      <td>2252.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>2122.000000</td>\n",
       "      <td>2165.000000</td>\n",
       "      <td>2140.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>2009.000000</td>\n",
       "      <td>2052.000000</td>\n",
       "      <td>2027.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>1895.999878</td>\n",
       "      <td>1939.000000</td>\n",
       "      <td>1914.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>1787.000122</td>\n",
       "      <td>1829.000122</td>\n",
       "      <td>1804.999878</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>2498.000000</td>\n",
       "      <td>2535.000000</td>\n",
       "      <td>2515.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>2498.000000</td>\n",
       "      <td>2537.000000</td>\n",
       "      <td>2515.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>2377.000000</td>\n",
       "      <td>2418.000000</td>\n",
       "      <td>2394.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>2256.000000</td>\n",
       "      <td>2298.000000</td>\n",
       "      <td>2274.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>2135.000000</td>\n",
       "      <td>2177.000000</td>\n",
       "      <td>2152.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>2012.999878</td>\n",
       "      <td>2055.000000</td>\n",
       "      <td>2031.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>1891.000000</td>\n",
       "      <td>1932.000000</td>\n",
       "      <td>1908.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>2533.000000</td>\n",
       "      <td>2570.000000</td>\n",
       "      <td>2550.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>2404.000000</td>\n",
       "      <td>2443.000000</td>\n",
       "      <td>2422.000000</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>70 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            mhw          mlw          msw    soil\n",
       "0    984.000000  1003.000000   995.000000  140000\n",
       "1    984.000000  1005.000000   995.000000  140000\n",
       "2    985.999939  1007.000000   997.000000  140000\n",
       "3   1017.000000  1056.000000  1035.000000  140000\n",
       "4   1068.000000  1108.000000  1086.000000  140000\n",
       "5   1052.000000  1093.000000  1071.000000  140000\n",
       "6   1160.000000  1198.000000  1177.000000  140000\n",
       "7   1200.000000  1239.000000  1218.000000  140000\n",
       "8   1212.000000  1254.000000  1231.000000  140000\n",
       "9   1383.000000  1423.000000  1401.000000  140000\n",
       "10  1411.000000  1453.000000  1430.000000  140000\n",
       "11  1336.000000  1379.000000  1355.000000  140000\n",
       "12  1298.000000  1342.000000  1318.000000  140000\n",
       "13  1259.000000  1305.000000  1280.000000  140000\n",
       "14  1584.000000  1626.000000  1602.000000  140000\n",
       "15  1535.000000  1578.000000  1554.000000  140000\n",
       "16  1486.000000  1530.000000  1505.000000  140000\n",
       "17  1387.000000  1433.000000  1408.000000  140000\n",
       "18  1756.000000  1799.000000  1775.000000  140000\n",
       "19  1695.999878  1739.000000  1714.000000  140000\n",
       "20  1635.000000  1679.999878  1654.000122  140000\n",
       "21  1576.000000  1620.999878  1596.000000  140000\n",
       "22  1480.000000  1494.000000  1487.000000  140000\n",
       "23  1554.000000  1573.000000  1563.000000  140000\n",
       "24  1710.000000  1753.000122  1728.000122  140000\n",
       "25  1631.000000  1676.000000  1651.000000  140000\n",
       "26  1675.000000  1695.000122  1685.000000  140000\n",
       "27  1748.000000  1774.000000  1761.000000  140000\n",
       "28  1820.999878  1851.000000  1835.000000  140000\n",
       "29  1628.000122  1673.000000  1646.999878  140000\n",
       "..          ...          ...          ...     ...\n",
       "40  2081.000000  2123.000000  2098.000000  140000\n",
       "41  1995.999878  2039.000000  2014.000000  140000\n",
       "42  2105.000000  2125.000000  2116.000000  140000\n",
       "43  2157.000000  2184.000000  2170.000000  140000\n",
       "44  2189.000000  2231.000000  2207.000000  140000\n",
       "45  2095.000000  2137.000000  2113.000000  140000\n",
       "46  2001.000000  2044.000000  2018.000000  140000\n",
       "47  2123.000000  2136.000000  2131.000000  140000\n",
       "48  2244.000000  2265.000000  2256.000000  140000\n",
       "49  2317.000000  2358.000000  2334.000000  140000\n",
       "50  2213.000000  2255.000000  2230.000000  140000\n",
       "51  2109.000000  2152.000000  2127.000000  140000\n",
       "52  2006.000000  2049.000000  2024.000000  140000\n",
       "53  1902.000000  1945.000122  1920.000122  140000\n",
       "54  2460.000000  2500.000000  2477.000000  140000\n",
       "55  2347.000000  2389.000000  2365.000000  140000\n",
       "56  2235.000000  2277.000000  2252.000000  140000\n",
       "57  2122.000000  2165.000000  2140.000000  140000\n",
       "58  2009.000000  2052.000000  2027.000000  140000\n",
       "59  1895.999878  1939.000000  1914.000000  140000\n",
       "60  1787.000122  1829.000122  1804.999878  140000\n",
       "61  2498.000000  2535.000000  2515.000000  140000\n",
       "62  2498.000000  2537.000000  2515.000000  140000\n",
       "63  2377.000000  2418.000000  2394.000000  140000\n",
       "64  2256.000000  2298.000000  2274.000000  140000\n",
       "65  2135.000000  2177.000000  2152.000000  140000\n",
       "66  2012.999878  2055.000000  2031.000000  140000\n",
       "67  1891.000000  1932.000000  1908.000000  140000\n",
       "68  2533.000000  2570.000000  2550.000000  140000\n",
       "69  2404.000000  2443.000000  2422.000000  140000\n",
       "\n",
       "[70 rows x 4 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "noveg = np.where(diff>0)\n",
    "mhw_band = mhw.read(1)\n",
    "mlw_band = mlw.read(1)\n",
    "msw_band = msw.read(1)\n",
    "soil_band = soil_code.read(1)\n",
    "\n",
    "df = pd.DataFrame(dict(mhw = mhw_band[noveg], mlw = mlw_band[noveg], msw = msw_band[noveg], soil = soil_band[noveg]))\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Het lijkt geen toeval dat fouten steeds voorkomen bij bodem leem (140000) en mlw > 1000. De nieuwe voorspelling lijkt correct aangezien dit vegetatietype niet kan voorkomen bij mlw > 73 (voor dit bodemtype).\n",
    "\n",
    "Vergelijken we waar nu wél vegetatie voorkomt en in het verleden niet, dan krijgen we onderstaande resultaten"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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>mhw</th>\n",
       "      <th>mlw</th>\n",
       "      <th>msw</th>\n",
       "      <th>soil</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>15.000001</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>1.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     mhw   mlw        msw    soil\n",
       "0   13.0  16.0  15.000001  140000\n",
       "1    4.0   5.0   5.000000   80000\n",
       "2   -0.0  -0.0  -0.000000   80000\n",
       "3   -0.0  -0.0  -0.000000   80000\n",
       "4   -0.0  -0.0  -0.000000   80000\n",
       "5   -0.0  -0.0  -0.000000   80000\n",
       "6   -0.0  -0.0  -0.000000   80000\n",
       "7    0.0   2.0   1.000000   80000\n",
       "8   -0.0  -0.0  -0.000000   80000\n",
       "9    3.0   5.0   5.000000   80000\n",
       "10  -0.0  -0.0  -0.000000   80000\n",
       "11  -0.0  -0.0  -0.000000   80000\n",
       "12   0.0   2.0   2.000000   80000\n",
       "13  -0.0  -0.0  -0.000000   80000\n",
       "14  -0.0  -0.0  -0.000000   80000\n",
       "15  -0.0  -0.0  -0.000000   80000\n",
       "16  -0.0  -0.0  -0.000000   80000\n",
       "17  -0.0   1.0   0.000000   80000\n",
       "18  -0.0  -0.0  -0.000000   80000\n",
       "19  -0.0  -0.0  -0.000000   80000\n",
       "20  -0.0  -0.0  -0.000000   80000\n",
       "21  -0.0  -0.0  -0.000000   80000\n",
       "22  -0.0  -0.0  -0.000000   80000\n",
       "23  -0.0  -0.0  -0.000000   80000\n",
       "24  -0.0  -0.0  -0.000000   80000\n",
       "25  -0.0  -0.0  -0.000000   80000\n",
       "26  -0.0  -0.0  -0.000000   80000\n",
       "27  -0.0  -0.0  -0.000000   80000\n",
       "28  -0.0  -0.0  -0.000000   80000\n",
       "29  -0.0  -0.0  -0.000000   80000\n",
       "30  -0.0  -0.0  -0.000000   80000\n",
       "31  -0.0  -0.0  -0.000000   80000\n",
       "32   1.0   7.0   5.000000   80000"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "noveg = np.where(diff<0)\n",
    "mhw_band = mhw.read(1)\n",
    "mlw_band = mlw.read(1)\n",
    "msw_band = msw.read(1)\n",
    "soil_band = soil_code.read(1)\n",
    "\n",
    "df = pd.DataFrame(dict(mhw = mhw_band[noveg], mlw = mlw_band[noveg], msw = msw_band[noveg], soil = soil_band[noveg]))\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Deze waarden voldoen inderdaad aan de niche tabel, al is het wel erg nat allemaal. Nemen we ook nutrient level en acidity mee."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "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>acidity</th>\n",
       "      <th>acidity_old</th>\n",
       "      <th>mhw</th>\n",
       "      <th>mlw</th>\n",
       "      <th>msw</th>\n",
       "      <th>nutrient_level</th>\n",
       "      <th>nutrient_level_old</th>\n",
       "      <th>soil</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>13.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>15.000001</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    acidity  acidity_old   mhw   mlw        msw  nutrient_level  \\\n",
       "0         3            3  13.0  16.0  15.000001               2   \n",
       "1         3            3   4.0   5.0   5.000000               2   \n",
       "2         3            3  -0.0  -0.0  -0.000000               2   \n",
       "3         3            3  -0.0  -0.0  -0.000000               2   \n",
       "4         3            3  -0.0  -0.0  -0.000000               2   \n",
       "5         3            3  -0.0  -0.0  -0.000000               2   \n",
       "6         3            3  -0.0  -0.0  -0.000000               2   \n",
       "7         3            3   0.0   2.0   1.000000               2   \n",
       "8         3            3  -0.0  -0.0  -0.000000               2   \n",
       "9         3            3   3.0   5.0   5.000000               2   \n",
       "10        3            3  -0.0  -0.0  -0.000000               2   \n",
       "11        3            3  -0.0  -0.0  -0.000000               2   \n",
       "12        3            3   0.0   2.0   2.000000               2   \n",
       "13        3            3  -0.0  -0.0  -0.000000               2   \n",
       "14        3            3  -0.0  -0.0  -0.000000               2   \n",
       "15        3            3  -0.0  -0.0  -0.000000               2   \n",
       "16        3            3  -0.0  -0.0  -0.000000               2   \n",
       "17        3            3  -0.0   1.0   0.000000               2   \n",
       "18        3            3  -0.0  -0.0  -0.000000               2   \n",
       "19        3            3  -0.0  -0.0  -0.000000               2   \n",
       "20        3            3  -0.0  -0.0  -0.000000               2   \n",
       "21        3            3  -0.0  -0.0  -0.000000               2   \n",
       "22        3            3  -0.0  -0.0  -0.000000               2   \n",
       "23        3            3  -0.0  -0.0  -0.000000               2   \n",
       "24        3            3  -0.0  -0.0  -0.000000               2   \n",
       "25        3            3  -0.0  -0.0  -0.000000               2   \n",
       "26        3            3  -0.0  -0.0  -0.000000               2   \n",
       "27        3            3  -0.0  -0.0  -0.000000               2   \n",
       "28        3            3  -0.0  -0.0  -0.000000               2   \n",
       "29        3            3  -0.0  -0.0  -0.000000               2   \n",
       "30        3            3  -0.0  -0.0  -0.000000               2   \n",
       "31        3            3  -0.0  -0.0  -0.000000               2   \n",
       "32        3            3   1.0   7.0   5.000000               2   \n",
       "\n",
       "    nutrient_level_old    soil  \n",
       "0                    1  140000  \n",
       "1                    1   80000  \n",
       "2                    1   80000  \n",
       "3                    1   80000  \n",
       "4                    1   80000  \n",
       "5                    1   80000  \n",
       "6                    1   80000  \n",
       "7                    1   80000  \n",
       "8                    1   80000  \n",
       "9                    1   80000  \n",
       "10                   1   80000  \n",
       "11                   1   80000  \n",
       "12                   1   80000  \n",
       "13                   1   80000  \n",
       "14                   1   80000  \n",
       "15                   1   80000  \n",
       "16                   1   80000  \n",
       "17                   1   80000  \n",
       "18                   1   80000  \n",
       "19                   1   80000  \n",
       "20                   1   80000  \n",
       "21                   1   80000  \n",
       "22                   1   80000  \n",
       "23                   1   80000  \n",
       "24                   1   80000  \n",
       "25                   1   80000  \n",
       "26                   1   80000  \n",
       "27                   1   80000  \n",
       "28                   1   80000  \n",
       "29                   1   80000  \n",
       "30                   1   80000  \n",
       "31                   1   80000  \n",
       "32                   1   80000  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with rasterio.open(\"AbiotiekRef/ph\") as file:\n",
    "    acidity_old = file.read(1)\n",
    "    \n",
    "with rasterio.open(\"AbiotiekRef/trofie\") as file:\n",
    "    nutrient_level_old = file.read(1)\n",
    "    \n",
    "df = pd.DataFrame(dict(mhw = mhw_band[noveg], \n",
    "                       mlw = mlw_band[noveg], \n",
    "                       msw = msw_band[noveg], \n",
    "                       soil = soil_band[noveg], \n",
    "                       acidity_old = acidity_old[noveg],\n",
    "                       acidity = myniche._abiotic[\"acidity\"][noveg],\n",
    "                       nutrient_level = myniche._abiotic[\"nutrient_level\"][noveg],\n",
    "                       nutrient_level_old = nutrient_level_old[noveg]\n",
    "                      ))\n",
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "Dan blijkt dat hier het verschil zit. Bij nutrient_level gelijk aan 1 kan dit vegetatietype immers niet voorkomen. \n",
    "Gaan we verder na waarom het type toch voorkomt moeten we alle factoren van de trofie bekijken.\n",
    "\n",
    "Hiervoor zijn volgende waarden vereist:\n",
    " * msw\n",
    " * soil\n",
    " * nitrogen_atmospheric\n",
    " * nitrogen_fertilizer\n",
    " * nitrogen_animal\n",
    " * management\n",
    " * inundation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    inundation  management        msw  nitrogen_external  soil_code\n",
      "0            0           3  15.000001          25.309130     140000\n",
      "1            0           0   5.000000          17.934238      80000\n",
      "2            0           0  -0.000000          17.934238      80000\n",
      "3            0           0  -0.000000          17.934238      80000\n",
      "4            0           0  -0.000000          17.934238      80000\n",
      "5            0           0  -0.000000          17.934238      80000\n",
      "6            0           0  -0.000000          17.934238      80000\n",
      "7            0           0   1.000000          17.934238      80000\n",
      "8            0           0  -0.000000          17.934238      80000\n",
      "9            0           0   5.000000          17.934238      80000\n",
      "10           0           0  -0.000000          17.934238      80000\n",
      "11           0           0  -0.000000          17.934238      80000\n",
      "12           0           0   2.000000          17.934238      80000\n",
      "13           0           0  -0.000000          17.934238      80000\n",
      "14           0           0  -0.000000          17.934238      80000\n",
      "15           0           0  -0.000000          17.934238      80000\n",
      "16           0           0  -0.000000          17.934238      80000\n",
      "17           0           0   0.000000          17.934238      80000\n",
      "18           0           0  -0.000000          17.934238      80000\n",
      "19           0           0  -0.000000          17.934238      80000\n",
      "20           0           0  -0.000000          17.934238      80000\n",
      "21           0           0  -0.000000          17.934238      80000\n",
      "22           0           0  -0.000000          17.934238      80000\n",
      "23           0           0  -0.000000          17.934238      80000\n",
      "24           0           0  -0.000000          17.934238      80000\n",
      "25           0           0  -0.000000          17.934238      80000\n",
      "26           0           0  -0.000000          17.934238      80000\n",
      "27           0           0  -0.000000          17.934238      80000\n",
      "28           0           0  -0.000000          17.934238      80000\n",
      "29           0           0  -0.000000          17.934238      80000\n",
      "30           0           0  -0.000000          17.934238      80000\n",
      "31           0           0  -0.000000          17.934238      80000\n",
      "32           0           0   5.000000          17.934238      80000\n"
     ]
    }
   ],
   "source": [
    "# df = pd.DataFrame(dict(msw = myniche._inputarray[\"msw\"]))\n",
    "\n",
    "df = pd.DataFrame(\n",
    "    dict(msw = myniche._inputarray[\"msw\"][noveg],\n",
    "     soil_code = myniche._inputarray[\"soil_code\"][noveg],\n",
    "     nitrogen_external = myniche._inputarray[\"nitrogen_atmospheric\"][noveg] + \n",
    "         myniche._inputarray[\"nitrogen_fertilizer\"][noveg]  +\n",
    "         myniche._inputarray[\"nitrogen_animal\"][noveg],\n",
    "     management = myniche._inputarray[\"management\"][noveg],\n",
    "     \n",
    "     inundation = myniche._inputarray[\"inundation_nutrient\"][noveg])\n",
    "    );\n",
    "print(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://github.com/inbo/niche_vlaanderen/blob/master/SystemTables/nitrogen_mineralisation.csv\n",
    "\n",
    "Voor deze invoerwaarden is de stikstofmineralisatie 47 (voor 140000). Beschouwen we de msw echter groter dan 15 dan is de mineralisatie 52.\n",
    "\n",
    "De totale stikstof is hier dus 47+25.3=72.3 of 77.3.\n",
    "\n",
    "Voor de andere punten is de mineralisatie 50 (voor 80000). De totale stikstof is dan  en 50+17.93=67.93. voor msw waarden >5 is het 72.93 .\n",
    "\n",
    "Zoeken we deze waarden op in \n",
    "https://github.com/inbo/niche_vlaanderen/blob/master/SystemTables/lnk_soil_nutrient_level.csv\n",
    "\n",
    "\n",
    "Dan zien we dat het verschil voor het eerste punt verklaard wordt door de waarde 15.00000001 die groter is dan 15, waardoor de trofie tot 2 stijgt.\n",
    "\n",
    "Voor de andere punten lijkt de nieuwe predictie steeds correct 2 te zijn in de nieuwe versie en incorrect 1 in de oude versie."
   ]
  }
 ],
 "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}