{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Facies classification using Machine Learning\n",
    "\n",
    "### aaML Submission\n",
    "\n",
    "### By:\n",
    "\n",
    "[Alexsandro G. Cerqueira](https://github.com/alexleogc),    \n",
    "[Alã de C. Damasceno](https://github.com/aladamasceno)\n",
    "\n",
    "There are tow main notebooks:\n",
    "\n",
    "- Data Analysis and edition\n",
    "- Submission\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from libtools import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Loading the data training data without Shankle well"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "training = pd.read_csv('data-test.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>77.45</td>\n",
       "      <td>0.664</td>\n",
       "      <td>9.9</td>\n",
       "      <td>11.915</td>\n",
       "      <td>4.6</td>\n",
       "      <td>1.000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>78.26</td>\n",
       "      <td>0.661</td>\n",
       "      <td>14.2</td>\n",
       "      <td>12.565</td>\n",
       "      <td>4.1</td>\n",
       "      <td>0.979</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>79.05</td>\n",
       "      <td>0.658</td>\n",
       "      <td>14.8</td>\n",
       "      <td>13.050</td>\n",
       "      <td>3.6</td>\n",
       "      <td>0.957</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>86.10</td>\n",
       "      <td>0.655</td>\n",
       "      <td>13.9</td>\n",
       "      <td>13.115</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0.936</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>74.58</td>\n",
       "      <td>0.647</td>\n",
       "      <td>13.5</td>\n",
       "      <td>13.300</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.915</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS  Label_Form_SH_LM\n",
       "0       3  77.45      0.664       9.9  11.915  4.6   1.000                 1\n",
       "1       3  78.26      0.661      14.2  12.565  4.1   0.979                 1\n",
       "2       3  79.05      0.658      14.8  13.050  3.6   0.957                 1\n",
       "3       3  86.10      0.655      13.9  13.115  3.5   0.936                 1\n",
       "4       3  74.58      0.647      13.5  13.300  3.4   0.915                 1"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3700.000000</td>\n",
       "      <td>3700.000000</td>\n",
       "      <td>3700.000000</td>\n",
       "      <td>3700.000000</td>\n",
       "      <td>3700.000000</td>\n",
       "      <td>2783.000000</td>\n",
       "      <td>3700.000000</td>\n",
       "      <td>3700.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.615676</td>\n",
       "      <td>64.873649</td>\n",
       "      <td>0.663053</td>\n",
       "      <td>4.651677</td>\n",
       "      <td>12.892826</td>\n",
       "      <td>3.805693</td>\n",
       "      <td>0.524125</td>\n",
       "      <td>1.542973</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.475808</td>\n",
       "      <td>30.817166</td>\n",
       "      <td>0.253863</td>\n",
       "      <td>5.109006</td>\n",
       "      <td>6.796219</td>\n",
       "      <td>0.894118</td>\n",
       "      <td>0.287147</td>\n",
       "      <td>0.498217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>10.149000</td>\n",
       "      <td>-0.025949</td>\n",
       "      <td>-21.832000</td>\n",
       "      <td>0.550000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>43.778250</td>\n",
       "      <td>0.502000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>8.350000</td>\n",
       "      <td>3.200000</td>\n",
       "      <td>0.278000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>64.817000</td>\n",
       "      <td>0.645613</td>\n",
       "      <td>4.400000</td>\n",
       "      <td>11.857500</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>0.531000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7.000000</td>\n",
       "      <td>80.322500</td>\n",
       "      <td>0.823000</td>\n",
       "      <td>7.600000</td>\n",
       "      <td>15.750000</td>\n",
       "      <td>4.400000</td>\n",
       "      <td>0.772000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>361.150000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>19.312000</td>\n",
       "      <td>84.400000</td>\n",
       "      <td>8.094000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Facies           GR    ILD_log10     DeltaPHI        PHIND  \\\n",
       "count  3700.000000  3700.000000  3700.000000  3700.000000  3700.000000   \n",
       "mean      4.615676    64.873649     0.663053     4.651677    12.892826   \n",
       "std       2.475808    30.817166     0.253863     5.109006     6.796219   \n",
       "min       1.000000    10.149000    -0.025949   -21.832000     0.550000   \n",
       "25%       2.000000    43.778250     0.502000     1.800000     8.350000   \n",
       "50%       4.000000    64.817000     0.645613     4.400000    11.857500   \n",
       "75%       7.000000    80.322500     0.823000     7.600000    15.750000   \n",
       "max       9.000000   361.150000     1.800000    19.312000    84.400000   \n",
       "\n",
       "                PE       RELPOS  Label_Form_SH_LM  \n",
       "count  2783.000000  3700.000000       3700.000000  \n",
       "mean      3.805693     0.524125          1.542973  \n",
       "std       0.894118     0.287147          0.498217  \n",
       "min       0.200000     0.000000          1.000000  \n",
       "25%       3.200000     0.278000          1.000000  \n",
       "50%       3.600000     0.531000          2.000000  \n",
       "75%       4.400000     0.772000          2.000000  \n",
       "max       8.094000     1.000000          2.000000  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "training = training.fillna(-99999)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Loading the SHANKLE well"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "blind = pd.read_csv('blind.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>98.36</td>\n",
       "      <td>0.642</td>\n",
       "      <td>-0.1</td>\n",
       "      <td>18.685</td>\n",
       "      <td>2.9</td>\n",
       "      <td>1.000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>97.57</td>\n",
       "      <td>0.631</td>\n",
       "      <td>7.9</td>\n",
       "      <td>16.745</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.984</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>98.41</td>\n",
       "      <td>0.615</td>\n",
       "      <td>12.8</td>\n",
       "      <td>14.105</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.968</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>85.92</td>\n",
       "      <td>0.597</td>\n",
       "      <td>13.0</td>\n",
       "      <td>13.385</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.952</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>83.16</td>\n",
       "      <td>0.592</td>\n",
       "      <td>12.3</td>\n",
       "      <td>13.345</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.935</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS  Label_Form_SH_LM\n",
       "0       2  98.36      0.642      -0.1  18.685  2.9   1.000                 1\n",
       "1       2  97.57      0.631       7.9  16.745  3.2   0.984                 1\n",
       "2       2  98.41      0.615      12.8  14.105  3.2   0.968                 1\n",
       "3       2  85.92      0.597      13.0  13.385  3.4   0.952                 1\n",
       "4       2  83.16      0.592      12.3  13.345  3.4   0.935                 1"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blind.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "      <td>449.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.576837</td>\n",
       "      <td>65.431180</td>\n",
       "      <td>0.630831</td>\n",
       "      <td>2.348998</td>\n",
       "      <td>15.741125</td>\n",
       "      <td>3.224944</td>\n",
       "      <td>0.503118</td>\n",
       "      <td>1.342984</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.260688</td>\n",
       "      <td>25.696418</td>\n",
       "      <td>0.241293</td>\n",
       "      <td>6.113543</td>\n",
       "      <td>9.080467</td>\n",
       "      <td>0.732414</td>\n",
       "      <td>0.282082</td>\n",
       "      <td>0.475236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>18.400000</td>\n",
       "      <td>0.093000</td>\n",
       "      <td>-19.900000</td>\n",
       "      <td>2.890000</td>\n",
       "      <td>1.500000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>54.960000</td>\n",
       "      <td>0.425000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>9.150000</td>\n",
       "      <td>2.700000</td>\n",
       "      <td>0.258000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>66.600000</td>\n",
       "      <td>0.620000</td>\n",
       "      <td>2.600000</td>\n",
       "      <td>13.935000</td>\n",
       "      <td>3.100000</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>75.150000</td>\n",
       "      <td>0.817000</td>\n",
       "      <td>6.200000</td>\n",
       "      <td>18.575000</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>0.744000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>242.750000</td>\n",
       "      <td>1.311000</td>\n",
       "      <td>18.600000</td>\n",
       "      <td>55.915000</td>\n",
       "      <td>5.400000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Facies          GR   ILD_log10    DeltaPHI       PHIND          PE  \\\n",
       "count  449.000000  449.000000  449.000000  449.000000  449.000000  449.000000   \n",
       "mean     3.576837   65.431180    0.630831    2.348998   15.741125    3.224944   \n",
       "std      2.260688   25.696418    0.241293    6.113543    9.080467    0.732414   \n",
       "min      1.000000   18.400000    0.093000  -19.900000    2.890000    1.500000   \n",
       "25%      2.000000   54.960000    0.425000    0.100000    9.150000    2.700000   \n",
       "50%      3.000000   66.600000    0.620000    2.600000   13.935000    3.100000   \n",
       "75%      6.000000   75.150000    0.817000    6.200000   18.575000    3.600000   \n",
       "max      8.000000  242.750000    1.311000   18.600000   55.915000    5.400000   \n",
       "\n",
       "           RELPOS  Label_Form_SH_LM  \n",
       "count  449.000000        449.000000  \n",
       "mean     0.503118          1.342984  \n",
       "std      0.282082          0.475236  \n",
       "min      0.010000          1.000000  \n",
       "25%      0.258000          1.000000  \n",
       "50%      0.500000          1.000000  \n",
       "75%      0.744000          2.000000  \n",
       "max      1.000000          2.000000  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blind.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "training_SH = divisao_sh(training)\n",
    "training_LM = divisao_lm(training)\n",
    "\n",
    "blind_SH = divisao_sh(blind)\n",
    "blind_LM = divisao_lm(blind)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>77.45</td>\n",
       "      <td>0.664</td>\n",
       "      <td>9.9</td>\n",
       "      <td>11.915</td>\n",
       "      <td>4.6</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>78.26</td>\n",
       "      <td>0.661</td>\n",
       "      <td>14.2</td>\n",
       "      <td>12.565</td>\n",
       "      <td>4.1</td>\n",
       "      <td>0.979</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>79.05</td>\n",
       "      <td>0.658</td>\n",
       "      <td>14.8</td>\n",
       "      <td>13.050</td>\n",
       "      <td>3.6</td>\n",
       "      <td>0.957</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>86.10</td>\n",
       "      <td>0.655</td>\n",
       "      <td>13.9</td>\n",
       "      <td>13.115</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0.936</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>74.58</td>\n",
       "      <td>0.647</td>\n",
       "      <td>13.5</td>\n",
       "      <td>13.300</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.915</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS\n",
       "0       3  77.45      0.664       9.9  11.915  4.6   1.000\n",
       "1       3  78.26      0.661      14.2  12.565  4.1   0.979\n",
       "2       3  79.05      0.658      14.8  13.050  3.6   0.957\n",
       "3       3  86.10      0.655      13.9  13.115  3.5   0.936\n",
       "4       3  74.58      0.647      13.5  13.300  3.4   0.915"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_SH.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>8</td>\n",
       "      <td>57.02</td>\n",
       "      <td>0.628</td>\n",
       "      <td>11.6</td>\n",
       "      <td>12.090</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>8</td>\n",
       "      <td>43.29</td>\n",
       "      <td>0.702</td>\n",
       "      <td>7.3</td>\n",
       "      <td>6.705</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.981</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>8</td>\n",
       "      <td>36.06</td>\n",
       "      <td>0.762</td>\n",
       "      <td>5.7</td>\n",
       "      <td>4.595</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.963</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>8</td>\n",
       "      <td>46.00</td>\n",
       "      <td>0.823</td>\n",
       "      <td>5.1</td>\n",
       "      <td>4.620</td>\n",
       "      <td>5.5</td>\n",
       "      <td>0.944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>6</td>\n",
       "      <td>60.30</td>\n",
       "      <td>0.915</td>\n",
       "      <td>4.6</td>\n",
       "      <td>5.010</td>\n",
       "      <td>5.6</td>\n",
       "      <td>0.926</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS\n",
       "43       8  57.02      0.628      11.6  12.090  3.5   1.000\n",
       "44       8  43.29      0.702       7.3   6.705  4.0   0.981\n",
       "45       8  36.06      0.762       5.7   4.595  5.0   0.963\n",
       "46       8  46.00      0.823       5.1   4.620  5.5   0.944\n",
       "47       6  60.30      0.915       4.6   5.010  5.6   0.926"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_LM.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>98.36</td>\n",
       "      <td>0.642</td>\n",
       "      <td>-0.1</td>\n",
       "      <td>18.685</td>\n",
       "      <td>2.9</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>97.57</td>\n",
       "      <td>0.631</td>\n",
       "      <td>7.9</td>\n",
       "      <td>16.745</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.984</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>98.41</td>\n",
       "      <td>0.615</td>\n",
       "      <td>12.8</td>\n",
       "      <td>14.105</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>85.92</td>\n",
       "      <td>0.597</td>\n",
       "      <td>13.0</td>\n",
       "      <td>13.385</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>83.16</td>\n",
       "      <td>0.592</td>\n",
       "      <td>12.3</td>\n",
       "      <td>13.345</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.935</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS\n",
       "0       2  98.36      0.642      -0.1  18.685  2.9   1.000\n",
       "1       2  97.57      0.631       7.9  16.745  3.2   0.984\n",
       "2       2  98.41      0.615      12.8  14.105  3.2   0.968\n",
       "3       2  85.92      0.597      13.0  13.385  3.4   0.952\n",
       "4       2  83.16      0.592      12.3  13.345  3.4   0.935"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blind_SH.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>8</td>\n",
       "      <td>46.04</td>\n",
       "      <td>0.645</td>\n",
       "      <td>-17.8</td>\n",
       "      <td>28.075</td>\n",
       "      <td>2.3</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>8</td>\n",
       "      <td>26.73</td>\n",
       "      <td>0.748</td>\n",
       "      <td>-9.0</td>\n",
       "      <td>9.105</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>8</td>\n",
       "      <td>36.50</td>\n",
       "      <td>0.794</td>\n",
       "      <td>0.1</td>\n",
       "      <td>5.945</td>\n",
       "      <td>4.5</td>\n",
       "      <td>0.930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>8</td>\n",
       "      <td>52.24</td>\n",
       "      <td>0.867</td>\n",
       "      <td>4.2</td>\n",
       "      <td>7.395</td>\n",
       "      <td>4.1</td>\n",
       "      <td>0.907</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>6</td>\n",
       "      <td>61.32</td>\n",
       "      <td>0.925</td>\n",
       "      <td>9.4</td>\n",
       "      <td>8.825</td>\n",
       "      <td>3.6</td>\n",
       "      <td>0.884</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS\n",
       "63       8  46.04      0.645     -17.8  28.075  2.3   1.000\n",
       "64       8  26.73      0.748      -9.0   9.105  5.0   0.953\n",
       "65       8  36.50      0.794       0.1   5.945  4.5   0.930\n",
       "66       8  52.24      0.867       4.2   7.395  4.1   0.907\n",
       "67       6  61.32      0.925       9.4   8.825  3.6   0.884"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blind_LM.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "X_SH = training_SH.drop(['Facies'],axis=1)\n",
    "y_SH = training_SH['Facies']\n",
    "\n",
    "X_LM = training_LM.drop(['Facies'],axis=1)\n",
    "y_LM = training_LM['Facies']\n",
    "\n",
    "X_SH_blind = blind_SH.drop(['Facies'],axis=1)\n",
    "y_SH_blind = blind_SH['Facies']\n",
    "\n",
    "X_LM_blind = blind_LM.drop(['Facies'],axis=1)\n",
    "y_LM_blind = blind_LM['Facies']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train_SH, X_test_SH, y_train_SH, y_test_SH = train_test_split(X_SH, y_SH, test_size=0.1)\n",
    "\n",
    "X_train_LM, X_test_LM, y_train_LM, y_test_LM = train_test_split(X_LM, y_LM, test_size=0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import ExtraTreesClassifier\n",
    "from sklearn.metrics import classification_report,confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',\n",
       "           max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "           min_impurity_split=1e-07, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           n_estimators=500, n_jobs=1, oob_score=False, random_state=None,\n",
       "           verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ETC_SH = ExtraTreesClassifier(n_estimators=500, bootstrap=True)\n",
    "ETC_LM = ExtraTreesClassifier(n_estimators=500)\n",
    "\n",
    "ETC_SH.fit(X_train_SH, y_train_SH)\n",
    "ETC_LM.fit(X_train_LM, y_train_LM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 9  1  1  0]\n",
      " [ 0 79  9  0]\n",
      " [ 0 11 59  1]\n",
      " [ 0  0  0  0]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          1       1.00      0.82      0.90        11\n",
      "          2       0.87      0.90      0.88        88\n",
      "          3       0.86      0.83      0.84        71\n",
      "          5       0.00      0.00      0.00         0\n",
      "\n",
      "avg / total       0.87      0.86      0.87       170\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pred_SH = ETC_SH.predict(X_test_SH)\n",
    "print(confusion_matrix(y_test_SH,pred_SH))\n",
    "print(classification_report(y_test_SH,pred_SH))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 0  0  0  1  0  0  0]\n",
      " [ 0 20  1  2  0  2  0]\n",
      " [ 0  0 18  5  1  5  0]\n",
      " [ 0  1  1 40  0  9  0]\n",
      " [ 0  0  1  0 13  2  0]\n",
      " [ 0  0  4  9  1 47  0]\n",
      " [ 0  0  0  0  0  2 16]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          3       0.00      0.00      0.00         1\n",
      "          4       0.95      0.80      0.87        25\n",
      "          5       0.72      0.62      0.67        29\n",
      "          6       0.70      0.78      0.74        51\n",
      "          7       0.87      0.81      0.84        16\n",
      "          8       0.70      0.77      0.73        61\n",
      "          9       1.00      0.89      0.94        18\n",
      "\n",
      "avg / total       0.77      0.77      0.77       201\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pred_LM = ETC_LM.predict(X_test_LM)\n",
    "print(confusion_matrix(y_test_LM,pred_LM))\n",
    "print(classification_report(y_test_LM,pred_LM))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 7 81  1]\n",
      " [ 5 75  9]\n",
      " [ 0 43 74]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          1       0.58      0.08      0.14        89\n",
      "          2       0.38      0.84      0.52        89\n",
      "          3       0.88      0.63      0.74       117\n",
      "\n",
      "avg / total       0.64      0.53      0.49       295\n",
      "\n"
     ]
    }
   ],
   "source": [
    "blind_pred_SH = ETC_SH.predict(X_SH_blind)\n",
    "print(confusion_matrix(y_SH_blind, blind_pred_SH))\n",
    "print(classification_report(y_SH_blind, blind_pred_SH))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 0  0  0  0  0  0  0]\n",
      " [ 0  1  0  5  0  1  0]\n",
      " [ 0  5  3  6  0  5  0]\n",
      " [ 1  1  1 52  0 16  0]\n",
      " [ 0  0  0  1  2 13  1]\n",
      " [ 0  0  0 15  1 23  1]\n",
      " [ 0  0  0  0  0  0  0]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          3       0.00      0.00      0.00         0\n",
      "          4       0.14      0.14      0.14         7\n",
      "          5       0.75      0.16      0.26        19\n",
      "          6       0.66      0.73      0.69        71\n",
      "          7       0.67      0.12      0.20        17\n",
      "          8       0.40      0.57      0.47        40\n",
      "          9       0.00      0.00      0.00         0\n",
      "\n",
      "avg / total       0.58      0.53      0.50       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "blind_pred_LM = ETC_LM.predict(X_LM_blind)\n",
    "print(confusion_matrix(y_LM_blind, blind_pred_LM))\n",
    "print(classification_report(y_LM_blind, blind_pred_LM))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "blind_pred_SH = pd.DataFrame(blind_pred_SH, index=X_SH_blind.index)\n",
    "blind_pred_LM = pd.DataFrame(blind_pred_LM, index=X_LM_blind.index)\n",
    "pred_blind = pd.concat([blind_pred_SH,blind_pred_LM])\n",
    "pred_blind = pred_blind.sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "y_blind = blind['Facies']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 7 81  1  0  0  0  0  0  0]\n",
      " [ 5 75  9  0  0  0  0  0  0]\n",
      " [ 0 43 74  0  0  0  0  0  0]\n",
      " [ 0  0  0  1  0  5  0  1  0]\n",
      " [ 0  0  0  5  3  6  0  5  0]\n",
      " [ 0  0  1  1  1 52  0 16  0]\n",
      " [ 0  0  0  0  0  1  2 13  1]\n",
      " [ 0  0  0  0  0 15  1 23  1]\n",
      " [ 0  0  0  0  0  0  0  0  0]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          1       0.58      0.08      0.14        89\n",
      "          2       0.38      0.84      0.52        89\n",
      "          3       0.87      0.63      0.73       117\n",
      "          4       0.14      0.14      0.14         7\n",
      "          5       0.75      0.16      0.26        19\n",
      "          6       0.66      0.73      0.69        71\n",
      "          7       0.67      0.12      0.20        17\n",
      "          8       0.40      0.57      0.47        40\n",
      "          9       0.00      0.00      0.00         0\n",
      "\n",
      "avg / total       0.62      0.53      0.49       449\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(confusion_matrix(y_blind, pred_blind))\n",
    "print(classification_report(y_blind, pred_blind))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using the complete training data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "training_data = pd.read_csv('training.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>77.45</td>\n",
       "      <td>0.664</td>\n",
       "      <td>9.9</td>\n",
       "      <td>11.915</td>\n",
       "      <td>4.6</td>\n",
       "      <td>1.000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>78.26</td>\n",
       "      <td>0.661</td>\n",
       "      <td>14.2</td>\n",
       "      <td>12.565</td>\n",
       "      <td>4.1</td>\n",
       "      <td>0.979</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>79.05</td>\n",
       "      <td>0.658</td>\n",
       "      <td>14.8</td>\n",
       "      <td>13.050</td>\n",
       "      <td>3.6</td>\n",
       "      <td>0.957</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>86.10</td>\n",
       "      <td>0.655</td>\n",
       "      <td>13.9</td>\n",
       "      <td>13.115</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0.936</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>74.58</td>\n",
       "      <td>0.647</td>\n",
       "      <td>13.5</td>\n",
       "      <td>13.300</td>\n",
       "      <td>3.4</td>\n",
       "      <td>0.915</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Facies     GR  ILD_log10  DeltaPHI   PHIND   PE  RELPOS  Label_Form_SH_LM\n",
       "0       3  77.45      0.664       9.9  11.915  4.6   1.000                 1\n",
       "1       3  78.26      0.661      14.2  12.565  4.1   0.979                 1\n",
       "2       3  79.05      0.658      14.8  13.050  3.6   0.957                 1\n",
       "3       3  86.10      0.655      13.9  13.115  3.5   0.936                 1\n",
       "4       3  74.58      0.647      13.5  13.300  3.4   0.915                 1"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "      <td>4149.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.503254</td>\n",
       "      <td>64.933985</td>\n",
       "      <td>0.659566</td>\n",
       "      <td>4.402484</td>\n",
       "      <td>13.201066</td>\n",
       "      <td>-22098.588517</td>\n",
       "      <td>0.521852</td>\n",
       "      <td>1.521330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.474324</td>\n",
       "      <td>30.302530</td>\n",
       "      <td>0.252703</td>\n",
       "      <td>5.274947</td>\n",
       "      <td>7.132846</td>\n",
       "      <td>41499.330187</td>\n",
       "      <td>0.286644</td>\n",
       "      <td>0.499605</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>10.149000</td>\n",
       "      <td>-0.025949</td>\n",
       "      <td>-21.832000</td>\n",
       "      <td>0.550000</td>\n",
       "      <td>-99999.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>44.730000</td>\n",
       "      <td>0.498000</td>\n",
       "      <td>1.600000</td>\n",
       "      <td>8.500000</td>\n",
       "      <td>2.416000</td>\n",
       "      <td>0.277000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>64.990000</td>\n",
       "      <td>0.639000</td>\n",
       "      <td>4.300000</td>\n",
       "      <td>12.020000</td>\n",
       "      <td>3.300000</td>\n",
       "      <td>0.528000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>79.438000</td>\n",
       "      <td>0.822000</td>\n",
       "      <td>7.500000</td>\n",
       "      <td>16.050000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>0.769000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>361.150000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>19.312000</td>\n",
       "      <td>84.400000</td>\n",
       "      <td>8.094000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Facies           GR    ILD_log10     DeltaPHI        PHIND  \\\n",
       "count  4149.000000  4149.000000  4149.000000  4149.000000  4149.000000   \n",
       "mean      4.503254    64.933985     0.659566     4.402484    13.201066   \n",
       "std       2.474324    30.302530     0.252703     5.274947     7.132846   \n",
       "min       1.000000    10.149000    -0.025949   -21.832000     0.550000   \n",
       "25%       2.000000    44.730000     0.498000     1.600000     8.500000   \n",
       "50%       4.000000    64.990000     0.639000     4.300000    12.020000   \n",
       "75%       6.000000    79.438000     0.822000     7.500000    16.050000   \n",
       "max       9.000000   361.150000     1.800000    19.312000    84.400000   \n",
       "\n",
       "                 PE       RELPOS  Label_Form_SH_LM  \n",
       "count   4149.000000  4149.000000       4149.000000  \n",
       "mean  -22098.588517     0.521852          1.521330  \n",
       "std    41499.330187     0.286644          0.499605  \n",
       "min   -99999.000000     0.000000          1.000000  \n",
       "25%        2.416000     0.277000          1.000000  \n",
       "50%        3.300000     0.528000          2.000000  \n",
       "75%        4.000000     0.769000          2.000000  \n",
       "max        8.094000     1.000000          2.000000  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "training_data_SH = divisao_sh(training_data)\n",
    "training_data_LM = divisao_lm(training_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2.297583</td>\n",
       "      <td>75.003921</td>\n",
       "      <td>0.530210</td>\n",
       "      <td>5.432646</td>\n",
       "      <td>16.700658</td>\n",
       "      <td>-18980.149676</td>\n",
       "      <td>0.511780</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.819513</td>\n",
       "      <td>15.637085</td>\n",
       "      <td>0.160003</td>\n",
       "      <td>6.092309</td>\n",
       "      <td>7.712549</td>\n",
       "      <td>39227.270999</td>\n",
       "      <td>0.287772</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>26.230000</td>\n",
       "      <td>-0.025949</td>\n",
       "      <td>-19.900000</td>\n",
       "      <td>4.397000</td>\n",
       "      <td>-99999.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>64.378000</td>\n",
       "      <td>0.441000</td>\n",
       "      <td>2.792500</td>\n",
       "      <td>11.920000</td>\n",
       "      <td>2.459500</td>\n",
       "      <td>0.261500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>73.680000</td>\n",
       "      <td>0.541205</td>\n",
       "      <td>5.800000</td>\n",
       "      <td>14.793500</td>\n",
       "      <td>3.057500</td>\n",
       "      <td>0.504500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>83.797500</td>\n",
       "      <td>0.633000</td>\n",
       "      <td>9.368500</td>\n",
       "      <td>19.143750</td>\n",
       "      <td>3.365000</td>\n",
       "      <td>0.761500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>221.125000</td>\n",
       "      <td>0.966000</td>\n",
       "      <td>19.257000</td>\n",
       "      <td>84.400000</td>\n",
       "      <td>5.100000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Facies           GR    ILD_log10     DeltaPHI        PHIND  \\\n",
       "count  1986.000000  1986.000000  1986.000000  1986.000000  1986.000000   \n",
       "mean      2.297583    75.003921     0.530210     5.432646    16.700658   \n",
       "std       0.819513    15.637085     0.160003     6.092309     7.712549   \n",
       "min       1.000000    26.230000    -0.025949   -19.900000     4.397000   \n",
       "25%       2.000000    64.378000     0.441000     2.792500    11.920000   \n",
       "50%       2.000000    73.680000     0.541205     5.800000    14.793500   \n",
       "75%       3.000000    83.797500     0.633000     9.368500    19.143750   \n",
       "max       9.000000   221.125000     0.966000    19.257000    84.400000   \n",
       "\n",
       "                 PE       RELPOS  \n",
       "count   1986.000000  1986.000000  \n",
       "mean  -18980.149676     0.511780  \n",
       "std    39227.270999     0.287772  \n",
       "min   -99999.000000     0.000000  \n",
       "25%        2.459500     0.261500  \n",
       "50%        3.057500     0.504500  \n",
       "75%        3.365000     0.761500  \n",
       "max        5.100000     1.000000  "
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_data_SH.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "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>Facies</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>6.528433</td>\n",
       "      <td>55.688079</td>\n",
       "      <td>0.778336</td>\n",
       "      <td>3.456620</td>\n",
       "      <td>9.987847</td>\n",
       "      <td>-24961.843041</td>\n",
       "      <td>0.531098</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.599173</td>\n",
       "      <td>36.858662</td>\n",
       "      <td>0.263687</td>\n",
       "      <td>4.175825</td>\n",
       "      <td>4.628169</td>\n",
       "      <td>43292.673480</td>\n",
       "      <td>0.285358</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>10.149000</td>\n",
       "      <td>-0.019000</td>\n",
       "      <td>-21.832000</td>\n",
       "      <td>0.550000</td>\n",
       "      <td>-99999.000000</td>\n",
       "      <td>0.009000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>32.657500</td>\n",
       "      <td>0.628500</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>6.650000</td>\n",
       "      <td>1.952500</td>\n",
       "      <td>0.290500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>46.923000</td>\n",
       "      <td>0.799000</td>\n",
       "      <td>3.100000</td>\n",
       "      <td>8.992000</td>\n",
       "      <td>3.900000</td>\n",
       "      <td>0.544000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>68.357500</td>\n",
       "      <td>0.941000</td>\n",
       "      <td>5.800500</td>\n",
       "      <td>12.400000</td>\n",
       "      <td>4.600000</td>\n",
       "      <td>0.776000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>361.150000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>19.312000</td>\n",
       "      <td>47.721000</td>\n",
       "      <td>8.094000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Facies           GR    ILD_log10     DeltaPHI        PHIND  \\\n",
       "count  2163.000000  2163.000000  2163.000000  2163.000000  2163.000000   \n",
       "mean      6.528433    55.688079     0.778336     3.456620     9.987847   \n",
       "std       1.599173    36.858662     0.263687     4.175825     4.628169   \n",
       "min       2.000000    10.149000    -0.019000   -21.832000     0.550000   \n",
       "25%       5.000000    32.657500     0.628500     1.100000     6.650000   \n",
       "50%       6.000000    46.923000     0.799000     3.100000     8.992000   \n",
       "75%       8.000000    68.357500     0.941000     5.800500    12.400000   \n",
       "max       9.000000   361.150000     1.800000    19.312000    47.721000   \n",
       "\n",
       "                 PE       RELPOS  \n",
       "count   2163.000000  2163.000000  \n",
       "mean  -24961.843041     0.531098  \n",
       "std    43292.673480     0.285358  \n",
       "min   -99999.000000     0.009000  \n",
       "25%        1.952500     0.290500  \n",
       "50%        3.900000     0.544000  \n",
       "75%        4.600000     0.776000  \n",
       "max        8.094000     1.000000  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_data_LM.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "X_SH = training_data_SH.drop(['Facies'],axis=1)\n",
    "y_SH = training_data_SH['Facies']\n",
    "\n",
    "X_LM = training_data_LM.drop(['Facies'],axis=1)\n",
    "y_LM = training_data_LM['Facies']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "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>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "      <td>1986.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>75.003921</td>\n",
       "      <td>0.530210</td>\n",
       "      <td>5.432646</td>\n",
       "      <td>16.700658</td>\n",
       "      <td>-18980.149676</td>\n",
       "      <td>0.511780</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>15.637085</td>\n",
       "      <td>0.160003</td>\n",
       "      <td>6.092309</td>\n",
       "      <td>7.712549</td>\n",
       "      <td>39227.270999</td>\n",
       "      <td>0.287772</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>26.230000</td>\n",
       "      <td>-0.025949</td>\n",
       "      <td>-19.900000</td>\n",
       "      <td>4.397000</td>\n",
       "      <td>-99999.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>64.378000</td>\n",
       "      <td>0.441000</td>\n",
       "      <td>2.792500</td>\n",
       "      <td>11.920000</td>\n",
       "      <td>2.459500</td>\n",
       "      <td>0.261500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>73.680000</td>\n",
       "      <td>0.541205</td>\n",
       "      <td>5.800000</td>\n",
       "      <td>14.793500</td>\n",
       "      <td>3.057500</td>\n",
       "      <td>0.504500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>83.797500</td>\n",
       "      <td>0.633000</td>\n",
       "      <td>9.368500</td>\n",
       "      <td>19.143750</td>\n",
       "      <td>3.365000</td>\n",
       "      <td>0.761500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>221.125000</td>\n",
       "      <td>0.966000</td>\n",
       "      <td>19.257000</td>\n",
       "      <td>84.400000</td>\n",
       "      <td>5.100000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                GR    ILD_log10     DeltaPHI        PHIND            PE  \\\n",
       "count  1986.000000  1986.000000  1986.000000  1986.000000   1986.000000   \n",
       "mean     75.003921     0.530210     5.432646    16.700658 -18980.149676   \n",
       "std      15.637085     0.160003     6.092309     7.712549  39227.270999   \n",
       "min      26.230000    -0.025949   -19.900000     4.397000 -99999.000000   \n",
       "25%      64.378000     0.441000     2.792500    11.920000      2.459500   \n",
       "50%      73.680000     0.541205     5.800000    14.793500      3.057500   \n",
       "75%      83.797500     0.633000     9.368500    19.143750      3.365000   \n",
       "max     221.125000     0.966000    19.257000    84.400000      5.100000   \n",
       "\n",
       "            RELPOS  \n",
       "count  1986.000000  \n",
       "mean      0.511780  \n",
       "std       0.287772  \n",
       "min       0.000000  \n",
       "25%       0.261500  \n",
       "50%       0.504500  \n",
       "75%       0.761500  \n",
       "max       1.000000  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_SH.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "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>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "      <td>2163.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>55.688079</td>\n",
       "      <td>0.778336</td>\n",
       "      <td>3.456620</td>\n",
       "      <td>9.987847</td>\n",
       "      <td>-24961.843041</td>\n",
       "      <td>0.531098</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>36.858662</td>\n",
       "      <td>0.263687</td>\n",
       "      <td>4.175825</td>\n",
       "      <td>4.628169</td>\n",
       "      <td>43292.673480</td>\n",
       "      <td>0.285358</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10.149000</td>\n",
       "      <td>-0.019000</td>\n",
       "      <td>-21.832000</td>\n",
       "      <td>0.550000</td>\n",
       "      <td>-99999.000000</td>\n",
       "      <td>0.009000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>32.657500</td>\n",
       "      <td>0.628500</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>6.650000</td>\n",
       "      <td>1.952500</td>\n",
       "      <td>0.290500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>46.923000</td>\n",
       "      <td>0.799000</td>\n",
       "      <td>3.100000</td>\n",
       "      <td>8.992000</td>\n",
       "      <td>3.900000</td>\n",
       "      <td>0.544000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>68.357500</td>\n",
       "      <td>0.941000</td>\n",
       "      <td>5.800500</td>\n",
       "      <td>12.400000</td>\n",
       "      <td>4.600000</td>\n",
       "      <td>0.776000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>361.150000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>19.312000</td>\n",
       "      <td>47.721000</td>\n",
       "      <td>8.094000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                GR    ILD_log10     DeltaPHI        PHIND            PE  \\\n",
       "count  2163.000000  2163.000000  2163.000000  2163.000000   2163.000000   \n",
       "mean     55.688079     0.778336     3.456620     9.987847 -24961.843041   \n",
       "std      36.858662     0.263687     4.175825     4.628169  43292.673480   \n",
       "min      10.149000    -0.019000   -21.832000     0.550000 -99999.000000   \n",
       "25%      32.657500     0.628500     1.100000     6.650000      1.952500   \n",
       "50%      46.923000     0.799000     3.100000     8.992000      3.900000   \n",
       "75%      68.357500     0.941000     5.800500    12.400000      4.600000   \n",
       "max     361.150000     1.800000    19.312000    47.721000      8.094000   \n",
       "\n",
       "            RELPOS  \n",
       "count  2163.000000  \n",
       "mean      0.531098  \n",
       "std       0.285358  \n",
       "min       0.009000  \n",
       "25%       0.290500  \n",
       "50%       0.544000  \n",
       "75%       0.776000  \n",
       "max       1.000000  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_LM.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train_SH, X_test_SH, y_train_SH, y_test_SH = train_test_split(X_SH, y_SH, test_size=0.1)\n",
    "\n",
    "X_train_LM, X_test_LM, y_train_LM, y_test_LM = train_test_split(X_LM, y_LM, test_size=0.1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#  Applying  ExtraTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',\n",
       "           max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "           min_impurity_split=1e-07, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           n_estimators=500, n_jobs=1, oob_score=False, random_state=None,\n",
       "           verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ETC_SH = ExtraTreesClassifier(n_estimators=500, bootstrap=True)\n",
    "ETC_LM = ExtraTreesClassifier(n_estimators=500)\n",
    "\n",
    "ETC_SH.fit(X_train_SH, y_train_SH)\n",
    "ETC_LM.fit(X_train_LM, y_train_LM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[15  8  1  0  0  0]\n",
      " [ 3 77  8  0  0  0]\n",
      " [ 0 18 65  0  0  0]\n",
      " [ 0  0  1  0  0  0]\n",
      " [ 0  2  0  0  0  0]\n",
      " [ 0  1  0  0  0  0]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          1       0.83      0.62      0.71        24\n",
      "          2       0.73      0.88      0.79        88\n",
      "          3       0.87      0.78      0.82        83\n",
      "          4       0.00      0.00      0.00         1\n",
      "          5       0.00      0.00      0.00         2\n",
      "          7       0.00      0.00      0.00         1\n",
      "\n",
      "avg / total       0.78      0.79      0.78       199\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pred_SH = ETC_SH.predict(X_test_SH)\n",
    "print(confusion_matrix(y_test_SH,pred_SH))\n",
    "print(classification_report(y_test_SH,pred_SH))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 2  0  1  0  0  0  0  0]\n",
      " [ 1  0  0  0  0  0  0  0]\n",
      " [ 0  0 30  1  3  0  1  0]\n",
      " [ 0  0  1 17  6  0  2  0]\n",
      " [ 0  0  3  2 43  0 10  0]\n",
      " [ 0  0  1  0  0  9  4  1]\n",
      " [ 0  0  1  2  6  0 51  0]\n",
      " [ 0  0  0  0  0  1  2 16]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          2       0.67      0.67      0.67         3\n",
      "          3       0.00      0.00      0.00         1\n",
      "          4       0.81      0.86      0.83        35\n",
      "          5       0.77      0.65      0.71        26\n",
      "          6       0.74      0.74      0.74        58\n",
      "          7       0.90      0.60      0.72        15\n",
      "          8       0.73      0.85      0.78        60\n",
      "          9       0.94      0.84      0.89        19\n",
      "\n",
      "avg / total       0.78      0.77      0.77       217\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pred_LM = ETC_LM.predict(X_test_LM)\n",
    "print(confusion_matrix(y_test_LM,pred_LM))\n",
    "print(classification_report(y_test_LM,pred_LM))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "validation = pd.read_csv('validation_data_nofacies.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "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>Formation</th>\n",
       "      <th>Well Name</th>\n",
       "      <th>Depth</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>NM_M</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.0</td>\n",
       "      <td>66.276</td>\n",
       "      <td>0.630</td>\n",
       "      <td>3.3</td>\n",
       "      <td>10.65</td>\n",
       "      <td>3.591</td>\n",
       "      <td>1</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.5</td>\n",
       "      <td>77.252</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.5</td>\n",
       "      <td>11.95</td>\n",
       "      <td>3.341</td>\n",
       "      <td>1</td>\n",
       "      <td>0.978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.0</td>\n",
       "      <td>82.899</td>\n",
       "      <td>0.566</td>\n",
       "      <td>9.4</td>\n",
       "      <td>13.60</td>\n",
       "      <td>3.064</td>\n",
       "      <td>1</td>\n",
       "      <td>0.956</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.5</td>\n",
       "      <td>80.671</td>\n",
       "      <td>0.593</td>\n",
       "      <td>9.5</td>\n",
       "      <td>13.25</td>\n",
       "      <td>2.977</td>\n",
       "      <td>1</td>\n",
       "      <td>0.933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2810.0</td>\n",
       "      <td>75.971</td>\n",
       "      <td>0.638</td>\n",
       "      <td>8.7</td>\n",
       "      <td>12.35</td>\n",
       "      <td>3.020</td>\n",
       "      <td>1</td>\n",
       "      <td>0.911</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Formation Well Name   Depth      GR  ILD_log10  DeltaPHI  PHIND     PE  \\\n",
       "0     A1 SH    STUART  2808.0  66.276      0.630       3.3  10.65  3.591   \n",
       "1     A1 SH    STUART  2808.5  77.252      0.585       6.5  11.95  3.341   \n",
       "2     A1 SH    STUART  2809.0  82.899      0.566       9.4  13.60  3.064   \n",
       "3     A1 SH    STUART  2809.5  80.671      0.593       9.5  13.25  2.977   \n",
       "4     A1 SH    STUART  2810.0  75.971      0.638       8.7  12.35  3.020   \n",
       "\n",
       "   NM_M  RELPOS  \n",
       "0     1   1.000  \n",
       "1     1   0.978  \n",
       "2     1   0.956  \n",
       "3     1   0.933  \n",
       "4     1   0.911  "
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validation.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "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>Depth</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>NM_M</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>830.000000</td>\n",
       "      <td>830.00000</td>\n",
       "      <td>830.000000</td>\n",
       "      <td>830.000000</td>\n",
       "      <td>830.000000</td>\n",
       "      <td>830.000000</td>\n",
       "      <td>830.000000</td>\n",
       "      <td>830.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2987.070482</td>\n",
       "      <td>57.61173</td>\n",
       "      <td>0.666312</td>\n",
       "      <td>2.851964</td>\n",
       "      <td>11.655277</td>\n",
       "      <td>3.654178</td>\n",
       "      <td>1.678313</td>\n",
       "      <td>0.535807</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>94.391925</td>\n",
       "      <td>27.52774</td>\n",
       "      <td>0.288367</td>\n",
       "      <td>3.442074</td>\n",
       "      <td>5.190236</td>\n",
       "      <td>0.649793</td>\n",
       "      <td>0.467405</td>\n",
       "      <td>0.283062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2808.000000</td>\n",
       "      <td>12.03600</td>\n",
       "      <td>-0.468000</td>\n",
       "      <td>-8.900000</td>\n",
       "      <td>1.855000</td>\n",
       "      <td>2.113000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.013000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2911.625000</td>\n",
       "      <td>36.77325</td>\n",
       "      <td>0.541000</td>\n",
       "      <td>0.411250</td>\n",
       "      <td>7.700000</td>\n",
       "      <td>3.171500</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2993.750000</td>\n",
       "      <td>58.34450</td>\n",
       "      <td>0.675000</td>\n",
       "      <td>2.397500</td>\n",
       "      <td>10.950000</td>\n",
       "      <td>3.515500</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.547500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3055.375000</td>\n",
       "      <td>73.05150</td>\n",
       "      <td>0.850750</td>\n",
       "      <td>4.600000</td>\n",
       "      <td>14.793750</td>\n",
       "      <td>4.191500</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.778000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3160.500000</td>\n",
       "      <td>220.41300</td>\n",
       "      <td>1.507000</td>\n",
       "      <td>16.500000</td>\n",
       "      <td>31.335000</td>\n",
       "      <td>6.321000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Depth         GR   ILD_log10    DeltaPHI       PHIND          PE  \\\n",
       "count   830.000000  830.00000  830.000000  830.000000  830.000000  830.000000   \n",
       "mean   2987.070482   57.61173    0.666312    2.851964   11.655277    3.654178   \n",
       "std      94.391925   27.52774    0.288367    3.442074    5.190236    0.649793   \n",
       "min    2808.000000   12.03600   -0.468000   -8.900000    1.855000    2.113000   \n",
       "25%    2911.625000   36.77325    0.541000    0.411250    7.700000    3.171500   \n",
       "50%    2993.750000   58.34450    0.675000    2.397500   10.950000    3.515500   \n",
       "75%    3055.375000   73.05150    0.850750    4.600000   14.793750    4.191500   \n",
       "max    3160.500000  220.41300    1.507000   16.500000   31.335000    6.321000   \n",
       "\n",
       "             NM_M      RELPOS  \n",
       "count  830.000000  830.000000  \n",
       "mean     1.678313    0.535807  \n",
       "std      0.467405    0.283062  \n",
       "min      1.000000    0.013000  \n",
       "25%      1.000000    0.300000  \n",
       "50%      2.000000    0.547500  \n",
       "75%      2.000000    0.778000  \n",
       "max      2.000000    1.000000  "
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validation.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Making the division between SH and LM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "validation['Label_Form_SH_LM'] = validation.Formation.apply((label_two_groups_formation))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "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>Formation</th>\n",
       "      <th>Well Name</th>\n",
       "      <th>Depth</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>NM_M</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Label_Form_SH_LM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.0</td>\n",
       "      <td>66.276</td>\n",
       "      <td>0.630</td>\n",
       "      <td>3.3</td>\n",
       "      <td>10.65</td>\n",
       "      <td>3.591</td>\n",
       "      <td>1</td>\n",
       "      <td>1.000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.5</td>\n",
       "      <td>77.252</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.5</td>\n",
       "      <td>11.95</td>\n",
       "      <td>3.341</td>\n",
       "      <td>1</td>\n",
       "      <td>0.978</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.0</td>\n",
       "      <td>82.899</td>\n",
       "      <td>0.566</td>\n",
       "      <td>9.4</td>\n",
       "      <td>13.60</td>\n",
       "      <td>3.064</td>\n",
       "      <td>1</td>\n",
       "      <td>0.956</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.5</td>\n",
       "      <td>80.671</td>\n",
       "      <td>0.593</td>\n",
       "      <td>9.5</td>\n",
       "      <td>13.25</td>\n",
       "      <td>2.977</td>\n",
       "      <td>1</td>\n",
       "      <td>0.933</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2810.0</td>\n",
       "      <td>75.971</td>\n",
       "      <td>0.638</td>\n",
       "      <td>8.7</td>\n",
       "      <td>12.35</td>\n",
       "      <td>3.020</td>\n",
       "      <td>1</td>\n",
       "      <td>0.911</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Formation Well Name   Depth      GR  ILD_log10  DeltaPHI  PHIND     PE  \\\n",
       "0     A1 SH    STUART  2808.0  66.276      0.630       3.3  10.65  3.591   \n",
       "1     A1 SH    STUART  2808.5  77.252      0.585       6.5  11.95  3.341   \n",
       "2     A1 SH    STUART  2809.0  82.899      0.566       9.4  13.60  3.064   \n",
       "3     A1 SH    STUART  2809.5  80.671      0.593       9.5  13.25  2.977   \n",
       "4     A1 SH    STUART  2810.0  75.971      0.638       8.7  12.35  3.020   \n",
       "\n",
       "   NM_M  RELPOS  Label_Form_SH_LM  \n",
       "0     1   1.000                 1  \n",
       "1     1   0.978                 1  \n",
       "2     1   0.956                 1  \n",
       "3     1   0.933                 1  \n",
       "4     1   0.911                 1  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validation.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "validation_SH = divisao_sh(validation)\n",
    "validation_LM = divisao_lm(validation)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "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>Formation</th>\n",
       "      <th>Well Name</th>\n",
       "      <th>Depth</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>NM_M</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.0</td>\n",
       "      <td>66.276</td>\n",
       "      <td>0.630</td>\n",
       "      <td>3.3</td>\n",
       "      <td>10.65</td>\n",
       "      <td>3.591</td>\n",
       "      <td>1</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.5</td>\n",
       "      <td>77.252</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.5</td>\n",
       "      <td>11.95</td>\n",
       "      <td>3.341</td>\n",
       "      <td>1</td>\n",
       "      <td>0.978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.0</td>\n",
       "      <td>82.899</td>\n",
       "      <td>0.566</td>\n",
       "      <td>9.4</td>\n",
       "      <td>13.60</td>\n",
       "      <td>3.064</td>\n",
       "      <td>1</td>\n",
       "      <td>0.956</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.5</td>\n",
       "      <td>80.671</td>\n",
       "      <td>0.593</td>\n",
       "      <td>9.5</td>\n",
       "      <td>13.25</td>\n",
       "      <td>2.977</td>\n",
       "      <td>1</td>\n",
       "      <td>0.933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2810.0</td>\n",
       "      <td>75.971</td>\n",
       "      <td>0.638</td>\n",
       "      <td>8.7</td>\n",
       "      <td>12.35</td>\n",
       "      <td>3.020</td>\n",
       "      <td>1</td>\n",
       "      <td>0.911</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Formation Well Name   Depth      GR  ILD_log10  DeltaPHI  PHIND     PE  \\\n",
       "0     A1 SH    STUART  2808.0  66.276      0.630       3.3  10.65  3.591   \n",
       "1     A1 SH    STUART  2808.5  77.252      0.585       6.5  11.95  3.341   \n",
       "2     A1 SH    STUART  2809.0  82.899      0.566       9.4  13.60  3.064   \n",
       "3     A1 SH    STUART  2809.5  80.671      0.593       9.5  13.25  2.977   \n",
       "4     A1 SH    STUART  2810.0  75.971      0.638       8.7  12.35  3.020   \n",
       "\n",
       "   NM_M  RELPOS  \n",
       "0     1   1.000  \n",
       "1     1   0.978  \n",
       "2     1   0.956  \n",
       "3     1   0.933  \n",
       "4     1   0.911  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validation_SH.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "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>Formation</th>\n",
       "      <th>Well Name</th>\n",
       "      <th>Depth</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>NM_M</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>A1 LM</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2829.5</td>\n",
       "      <td>47.345</td>\n",
       "      <td>0.584</td>\n",
       "      <td>7.0</td>\n",
       "      <td>16.30</td>\n",
       "      <td>3.527</td>\n",
       "      <td>2</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>A1 LM</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2830.0</td>\n",
       "      <td>35.733</td>\n",
       "      <td>0.730</td>\n",
       "      <td>6.4</td>\n",
       "      <td>10.20</td>\n",
       "      <td>3.928</td>\n",
       "      <td>2</td>\n",
       "      <td>0.987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>A1 LM</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2830.5</td>\n",
       "      <td>29.327</td>\n",
       "      <td>0.873</td>\n",
       "      <td>2.7</td>\n",
       "      <td>7.85</td>\n",
       "      <td>4.330</td>\n",
       "      <td>2</td>\n",
       "      <td>0.974</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>A1 LM</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2831.0</td>\n",
       "      <td>28.242</td>\n",
       "      <td>0.963</td>\n",
       "      <td>1.4</td>\n",
       "      <td>6.30</td>\n",
       "      <td>4.413</td>\n",
       "      <td>2</td>\n",
       "      <td>0.961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>A1 LM</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2831.5</td>\n",
       "      <td>34.558</td>\n",
       "      <td>1.018</td>\n",
       "      <td>1.8</td>\n",
       "      <td>5.60</td>\n",
       "      <td>4.511</td>\n",
       "      <td>2</td>\n",
       "      <td>0.947</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Formation Well Name   Depth      GR  ILD_log10  DeltaPHI  PHIND     PE  \\\n",
       "43     A1 LM    STUART  2829.5  47.345      0.584       7.0  16.30  3.527   \n",
       "44     A1 LM    STUART  2830.0  35.733      0.730       6.4  10.20  3.928   \n",
       "45     A1 LM    STUART  2830.5  29.327      0.873       2.7   7.85  4.330   \n",
       "46     A1 LM    STUART  2831.0  28.242      0.963       1.4   6.30  4.413   \n",
       "47     A1 LM    STUART  2831.5  34.558      1.018       1.8   5.60  4.511   \n",
       "\n",
       "    NM_M  RELPOS  \n",
       "43     2   1.000  \n",
       "44     2   0.987  \n",
       "45     2   0.974  \n",
       "46     2   0.961  \n",
       "47     2   0.947  "
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validation_LM.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Removing the colums: Formation, Well Name, Depth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "X_val_SH = validation_SH.drop(['Formation','Well Name','Depth','NM_M'], axis=1)\n",
    "X_val_LM = validation_LM.drop(['Formation','Well Name','Depth','NM_M'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "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>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>66.276</td>\n",
       "      <td>0.630</td>\n",
       "      <td>3.3</td>\n",
       "      <td>10.65</td>\n",
       "      <td>3.591</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>77.252</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.5</td>\n",
       "      <td>11.95</td>\n",
       "      <td>3.341</td>\n",
       "      <td>0.978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>82.899</td>\n",
       "      <td>0.566</td>\n",
       "      <td>9.4</td>\n",
       "      <td>13.60</td>\n",
       "      <td>3.064</td>\n",
       "      <td>0.956</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>80.671</td>\n",
       "      <td>0.593</td>\n",
       "      <td>9.5</td>\n",
       "      <td>13.25</td>\n",
       "      <td>2.977</td>\n",
       "      <td>0.933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>75.971</td>\n",
       "      <td>0.638</td>\n",
       "      <td>8.7</td>\n",
       "      <td>12.35</td>\n",
       "      <td>3.020</td>\n",
       "      <td>0.911</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       GR  ILD_log10  DeltaPHI  PHIND     PE  RELPOS\n",
       "0  66.276      0.630       3.3  10.65  3.591   1.000\n",
       "1  77.252      0.585       6.5  11.95  3.341   0.978\n",
       "2  82.899      0.566       9.4  13.60  3.064   0.956\n",
       "3  80.671      0.593       9.5  13.25  2.977   0.933\n",
       "4  75.971      0.638       8.7  12.35  3.020   0.911"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_val_SH.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "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>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>RELPOS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>47.345</td>\n",
       "      <td>0.584</td>\n",
       "      <td>7.0</td>\n",
       "      <td>16.30</td>\n",
       "      <td>3.527</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>35.733</td>\n",
       "      <td>0.730</td>\n",
       "      <td>6.4</td>\n",
       "      <td>10.20</td>\n",
       "      <td>3.928</td>\n",
       "      <td>0.987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>29.327</td>\n",
       "      <td>0.873</td>\n",
       "      <td>2.7</td>\n",
       "      <td>7.85</td>\n",
       "      <td>4.330</td>\n",
       "      <td>0.974</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>28.242</td>\n",
       "      <td>0.963</td>\n",
       "      <td>1.4</td>\n",
       "      <td>6.30</td>\n",
       "      <td>4.413</td>\n",
       "      <td>0.961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>34.558</td>\n",
       "      <td>1.018</td>\n",
       "      <td>1.8</td>\n",
       "      <td>5.60</td>\n",
       "      <td>4.511</td>\n",
       "      <td>0.947</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        GR  ILD_log10  DeltaPHI  PHIND     PE  RELPOS\n",
       "43  47.345      0.584       7.0  16.30  3.527   1.000\n",
       "44  35.733      0.730       6.4  10.20  3.928   0.987\n",
       "45  29.327      0.873       2.7   7.85  4.330   0.974\n",
       "46  28.242      0.963       1.4   6.30  4.413   0.961\n",
       "47  34.558      1.018       1.8   5.60  4.511   0.947"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_val_LM.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pred_val_SH = ETC_SH.predict(X_val_SH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "pred_val_LM =ETC_LM.predict(X_val_LM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pred_val_SH = pd.DataFrame(pred_val_SH, index=X_val_SH.index)\n",
    "pred_val_LM = pd.DataFrame(pred_val_LM, index=X_val_LM.index)\n",
    "pred_val = pd.concat([pred_val_SH,pred_val_LM])\n",
    "pred_val = pred_val.sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>830.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5.356627</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.386239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>6.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                0\n",
       "count  830.000000\n",
       "mean     5.356627\n",
       "std      2.386239\n",
       "min      1.000000\n",
       "25%      3.000000\n",
       "50%      6.000000\n",
       "75%      8.000000\n",
       "max      9.000000"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_val.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "validation['Facies Pred'] = pred_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "validation=validation.drop(['Label_Form_SH_LM'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "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>Formation</th>\n",
       "      <th>Well Name</th>\n",
       "      <th>Depth</th>\n",
       "      <th>GR</th>\n",
       "      <th>ILD_log10</th>\n",
       "      <th>DeltaPHI</th>\n",
       "      <th>PHIND</th>\n",
       "      <th>PE</th>\n",
       "      <th>NM_M</th>\n",
       "      <th>RELPOS</th>\n",
       "      <th>Facies Pred</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.0</td>\n",
       "      <td>66.276</td>\n",
       "      <td>0.630</td>\n",
       "      <td>3.3</td>\n",
       "      <td>10.65</td>\n",
       "      <td>3.591</td>\n",
       "      <td>1</td>\n",
       "      <td>1.000</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2808.5</td>\n",
       "      <td>77.252</td>\n",
       "      <td>0.585</td>\n",
       "      <td>6.5</td>\n",
       "      <td>11.95</td>\n",
       "      <td>3.341</td>\n",
       "      <td>1</td>\n",
       "      <td>0.978</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.0</td>\n",
       "      <td>82.899</td>\n",
       "      <td>0.566</td>\n",
       "      <td>9.4</td>\n",
       "      <td>13.60</td>\n",
       "      <td>3.064</td>\n",
       "      <td>1</td>\n",
       "      <td>0.956</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2809.5</td>\n",
       "      <td>80.671</td>\n",
       "      <td>0.593</td>\n",
       "      <td>9.5</td>\n",
       "      <td>13.25</td>\n",
       "      <td>2.977</td>\n",
       "      <td>1</td>\n",
       "      <td>0.933</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>A1 SH</td>\n",
       "      <td>STUART</td>\n",
       "      <td>2810.0</td>\n",
       "      <td>75.971</td>\n",
       "      <td>0.638</td>\n",
       "      <td>8.7</td>\n",
       "      <td>12.35</td>\n",
       "      <td>3.020</td>\n",
       "      <td>1</td>\n",
       "      <td>0.911</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Formation Well Name   Depth      GR  ILD_log10  DeltaPHI  PHIND     PE  \\\n",
       "0     A1 SH    STUART  2808.0  66.276      0.630       3.3  10.65  3.591   \n",
       "1     A1 SH    STUART  2808.5  77.252      0.585       6.5  11.95  3.341   \n",
       "2     A1 SH    STUART  2809.0  82.899      0.566       9.4  13.60  3.064   \n",
       "3     A1 SH    STUART  2809.5  80.671      0.593       9.5  13.25  2.977   \n",
       "4     A1 SH    STUART  2810.0  75.971      0.638       8.7  12.35  3.020   \n",
       "\n",
       "   NM_M  RELPOS  Facies Pred  \n",
       "0     1   1.000            3  \n",
       "1     1   0.978            3  \n",
       "2     1   0.956            2  \n",
       "3     1   0.933            3  \n",
       "4     1   0.911            3  "
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validation.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "validation.to_csv('Prediction.csv')"
   ]
  },
  {
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}