01-DNN-Regression.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Deep Neural Network (DNN) - BHPD dataset\n",
    "========================================\n",
    "---\n",
    "Introduction au Deep Learning  (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020  \n",
    "\n",
    "## A very simple example of **regression** :\n",
    "\n",
    "Objective is to predicts **housing prices** from a set of house features. \n",
    "\n",
    "The **[Boston Housing Dataset](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html)** consists of price of houses in various places in Boston.  \n",
    "Alongside with price, the dataset also provide information such as Crime, areas of non-retail business in the town,  \n",
    "age of people who own the house and many other attributes...\n",
    "\n",
    "What we're going to do:\n",
    "\n",
    " - Retrieve data\n",
    " - Preparing the data\n",
    " - Build a model\n",
    " - Train the model\n",
    " - Evaluate the result\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1/ Init python stuff"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "IDLE 2020 - Practical Work Module\n",
      "  Version            : 0.2\n",
      "  Run time           : Thursday 30 January 2020, 13:57:24\n",
      "  Matplotlib style   : fidle/talk.mplstyle\n",
      "  TensorFlow version : 2.0.0\n",
      "  Keras version      : 2.2.4-tf\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import os\n",
    "\n",
    "from IPython.display import display, Markdown\n",
    "import fidle.pwk as ooo\n",
    "from importlib import reload\n",
    "\n",
    "ooo.init()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2/ Retrieve data\n",
    "\n",
    "**From Keras :**\n",
    "Boston housing is a famous historic dataset, so we can get it directly from [Keras datasets](https://www.tensorflow.org/api_docs/python/tf/keras/datasets)  "
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "(x_train, y_train), (x_test, y_test) = keras.datasets.boston_housing.load_data(test_split=0.2, seed=113)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**From a csv file :**  \n",
    "More fun !"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "</style><table id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddf\" ><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >crim</th>        <th class=\"col_heading level0 col1\" >zn</th>        <th class=\"col_heading level0 col2\" >indus</th>        <th class=\"col_heading level0 col3\" >chas</th>        <th class=\"col_heading level0 col4\" >nox</th>        <th class=\"col_heading level0 col5\" >rm</th>        <th class=\"col_heading level0 col6\" >age</th>        <th class=\"col_heading level0 col7\" >dis</th>        <th class=\"col_heading level0 col8\" >rad</th>        <th class=\"col_heading level0 col9\" >tax</th>        <th class=\"col_heading level0 col10\" >ptratio</th>        <th class=\"col_heading level0 col11\" >b</th>        <th class=\"col_heading level0 col12\" >lstat</th>        <th class=\"col_heading level0 col13\" >medv</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col0\" class=\"data row0 col0\" >0.01</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col1\" class=\"data row0 col1\" >18.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col2\" class=\"data row0 col2\" >2.31</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col3\" class=\"data row0 col3\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col4\" class=\"data row0 col4\" >0.54</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col5\" class=\"data row0 col5\" >6.58</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col6\" class=\"data row0 col6\" >65.20</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col7\" class=\"data row0 col7\" >4.09</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col8\" class=\"data row0 col8\" >1.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col9\" class=\"data row0 col9\" >296.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col10\" class=\"data row0 col10\" >15.30</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col11\" class=\"data row0 col11\" >396.90</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col12\" class=\"data row0 col12\" >4.98</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col13\" class=\"data row0 col13\" >24.00</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col0\" class=\"data row1 col0\" >0.03</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col2\" class=\"data row1 col2\" >7.07</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col3\" class=\"data row1 col3\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col4\" class=\"data row1 col4\" >0.47</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col5\" class=\"data row1 col5\" >6.42</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col6\" class=\"data row1 col6\" >78.90</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col7\" class=\"data row1 col7\" >4.97</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col8\" class=\"data row1 col8\" >2.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col9\" class=\"data row1 col9\" >242.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col10\" class=\"data row1 col10\" >17.80</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col11\" class=\"data row1 col11\" >396.90</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col12\" class=\"data row1 col12\" >9.14</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col13\" class=\"data row1 col13\" >21.60</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col0\" class=\"data row2 col0\" >0.03</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col1\" class=\"data row2 col1\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col2\" class=\"data row2 col2\" >7.07</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col3\" class=\"data row2 col3\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col4\" class=\"data row2 col4\" >0.47</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col5\" class=\"data row2 col5\" >7.18</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col6\" class=\"data row2 col6\" >61.10</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col7\" class=\"data row2 col7\" >4.97</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col8\" class=\"data row2 col8\" >2.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col9\" class=\"data row2 col9\" >242.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col10\" class=\"data row2 col10\" >17.80</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col11\" class=\"data row2 col11\" >392.83</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col12\" class=\"data row2 col12\" >4.03</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col13\" class=\"data row2 col13\" >34.70</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col0\" class=\"data row3 col0\" >0.03</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col2\" class=\"data row3 col2\" >2.18</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col4\" class=\"data row3 col4\" >0.46</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col5\" class=\"data row3 col5\" >7.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col6\" class=\"data row3 col6\" >45.80</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col7\" class=\"data row3 col7\" >6.06</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col8\" class=\"data row3 col8\" >3.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col9\" class=\"data row3 col9\" >222.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col10\" class=\"data row3 col10\" >18.70</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col11\" class=\"data row3 col11\" >394.63</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col12\" class=\"data row3 col12\" >2.94</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col13\" class=\"data row3 col13\" >33.40</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col0\" class=\"data row4 col0\" >0.07</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col2\" class=\"data row4 col2\" >2.18</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col4\" class=\"data row4 col4\" >0.46</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col5\" class=\"data row4 col5\" >7.15</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col6\" class=\"data row4 col6\" >54.20</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col7\" class=\"data row4 col7\" >6.06</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col8\" class=\"data row4 col8\" >3.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col9\" class=\"data row4 col9\" >222.00</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col10\" class=\"data row4 col10\" >18.70</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col11\" class=\"data row4 col11\" >396.90</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col12\" class=\"data row4 col12\" >5.33</td>\n",
       "                        <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col13\" class=\"data row4 col13\" >36.20</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f66b1797890>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Données manquantes :  0   Shape is :  (506, 14)\n"
     ]
    }
   ],
   "source": [
    "data = pd.read_csv('./data/BostonHousing.csv', header=0)\n",
    "\n",
    "display(data.head(5).style.format(\"{0:.2f}\"))\n",
    "print('Données manquantes : ',data.isna().sum().sum(), '  Shape is : ', data.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3/ Preparing the data\n",
    "### 3.1/ Split data\n",
    "We will use 70% of the data for training and 30% for validation.  \n",
    "x will be input data and y the expected output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original data shape was :  (506, 14)\n",
      "x_train :  (354, 13) y_train :  (354,)\n",
      "x_test  :  (152, 13) y_test  :  (152,)\n"
     ]
    }
   ],
   "source": [
    "# ---- Split => train, test\n",
    "#\n",
    "data_train = data.sample(frac=0.7, axis=0)\n",
    "data_test  = data.drop(data_train.index)\n",
    "\n",
    "# ---- Split => x,y (medv is price)\n",
    "#\n",
    "x_train = data_train.drop('medv',  axis=1)\n",
    "y_train = data_train['medv']\n",
    "x_test  = data_test.drop('medv',   axis=1)\n",
    "y_test  = data_test['medv']\n",
    "\n",
    "print('Original data shape was : ',data.shape)\n",
    "print('x_train : ',x_train.shape, 'y_train : ',y_train.shape)\n",
    "print('x_test  : ',x_test.shape,  'y_test  : ',y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.2/ Data normalization\n",
    "**Note :** \n",
    " - All input data must be normalized, train and test.  \n",
    " - To do this we will subtract the mean and divide by the standard deviation.  \n",
    " - But test data should not be used in any way, even for normalization.  \n",
    " - The mean and the standard deviation will therefore only be calculated with the train data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "</style><table id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddf\" ><caption>Before normalization :</caption><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >crim</th>        <th class=\"col_heading level0 col1\" >zn</th>        <th class=\"col_heading level0 col2\" >indus</th>        <th class=\"col_heading level0 col3\" >chas</th>        <th class=\"col_heading level0 col4\" >nox</th>        <th class=\"col_heading level0 col5\" >rm</th>        <th class=\"col_heading level0 col6\" >age</th>        <th class=\"col_heading level0 col7\" >dis</th>        <th class=\"col_heading level0 col8\" >rad</th>        <th class=\"col_heading level0 col9\" >tax</th>        <th class=\"col_heading level0 col10\" >ptratio</th>        <th class=\"col_heading level0 col11\" >b</th>        <th class=\"col_heading level0 col12\" >lstat</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col0\" class=\"data row1 col0\" >3.69</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col1\" class=\"data row1 col1\" >10.39</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col2\" class=\"data row1 col2\" >11.51</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col3\" class=\"data row1 col3\" >0.07</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col4\" class=\"data row1 col4\" >0.55</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col5\" class=\"data row1 col5\" >6.27</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col6\" class=\"data row1 col6\" >69.52</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col7\" class=\"data row1 col7\" >3.76</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col8\" class=\"data row1 col8\" >9.82</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col9\" class=\"data row1 col9\" >412.81</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col10\" class=\"data row1 col10\" >18.59</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col11\" class=\"data row1 col11\" >358.13</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col12\" class=\"data row1 col12\" >12.80</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col0\" class=\"data row2 col0\" >8.49</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col1\" class=\"data row2 col1\" >22.21</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col2\" class=\"data row2 col2\" >6.94</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col3\" class=\"data row2 col3\" >0.25</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col4\" class=\"data row2 col4\" >0.11</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col5\" class=\"data row2 col5\" >0.68</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col6\" class=\"data row2 col6\" >27.74</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col7\" class=\"data row2 col7\" >2.06</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col8\" class=\"data row2 col8\" >8.83</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col9\" class=\"data row2 col9\" >171.63</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col10\" class=\"data row2 col10\" >2.13</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col11\" class=\"data row2 col11\" >88.80</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col12\" class=\"data row2 col12\" >7.07</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col0\" class=\"data row3 col0\" >0.01</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col2\" class=\"data row3 col2\" >1.21</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col4\" class=\"data row3 col4\" >0.39</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col5\" class=\"data row3 col5\" >3.56</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col6\" class=\"data row3 col6\" >2.90</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col7\" class=\"data row3 col7\" >1.13</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col8\" class=\"data row3 col8\" >1.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col9\" class=\"data row3 col9\" >188.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col10\" class=\"data row3 col10\" >12.60</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col11\" class=\"data row3 col11\" >0.32</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col12\" class=\"data row3 col12\" >1.92</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col0\" class=\"data row4 col0\" >0.08</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col2\" class=\"data row4 col2\" >5.32</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col4\" class=\"data row4 col4\" >0.45</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col5\" class=\"data row4 col5\" >5.88</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col6\" class=\"data row4 col6\" >46.40</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col7\" class=\"data row4 col7\" >2.10</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col8\" class=\"data row4 col8\" >4.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col9\" class=\"data row4 col9\" >279.50</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col10\" class=\"data row4 col10\" >17.40</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col11\" class=\"data row4 col11\" >376.12</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col12\" class=\"data row4 col12\" >7.21</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col0\" class=\"data row5 col0\" >0.25</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col1\" class=\"data row5 col1\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col2\" class=\"data row5 col2\" >9.90</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col3\" class=\"data row5 col3\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col4\" class=\"data row5 col4\" >0.54</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col5\" class=\"data row5 col5\" >6.17</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col6\" class=\"data row5 col6\" >78.80</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col7\" class=\"data row5 col7\" >3.11</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col8\" class=\"data row5 col8\" >5.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col9\" class=\"data row5 col9\" >336.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col10\" class=\"data row5 col10\" >19.10</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col11\" class=\"data row5 col11\" >391.26</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col12\" class=\"data row5 col12\" >12.02</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col0\" class=\"data row6 col0\" >4.18</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col1\" class=\"data row6 col1\" >9.38</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col2\" class=\"data row6 col2\" >18.10</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col3\" class=\"data row6 col3\" >0.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col4\" class=\"data row6 col4\" >0.62</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col5\" class=\"data row6 col5\" >6.60</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col6\" class=\"data row6 col6\" >94.45</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col7\" class=\"data row6 col7\" >5.19</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col8\" class=\"data row6 col8\" >24.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col9\" class=\"data row6 col9\" >666.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col10\" class=\"data row6 col10\" >20.20</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col11\" class=\"data row6 col11\" >396.17</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col12\" class=\"data row6 col12\" >17.25</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col0\" class=\"data row7 col0\" >73.53</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col1\" class=\"data row7 col1\" >100.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col2\" class=\"data row7 col2\" >27.74</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col3\" class=\"data row7 col3\" >1.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col4\" class=\"data row7 col4\" >0.87</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col5\" class=\"data row7 col5\" >8.72</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col6\" class=\"data row7 col6\" >100.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col7\" class=\"data row7 col7\" >10.71</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col8\" class=\"data row7 col8\" >24.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col9\" class=\"data row7 col9\" >711.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col10\" class=\"data row7 col10\" >22.00</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col11\" class=\"data row7 col11\" >396.90</td>\n",
       "                        <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col12\" class=\"data row7 col12\" >36.98</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f66b277cc90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "</style><table id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddf\" ><caption>After normalization :</caption><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >crim</th>        <th class=\"col_heading level0 col1\" >zn</th>        <th class=\"col_heading level0 col2\" >indus</th>        <th class=\"col_heading level0 col3\" >chas</th>        <th class=\"col_heading level0 col4\" >nox</th>        <th class=\"col_heading level0 col5\" >rm</th>        <th class=\"col_heading level0 col6\" >age</th>        <th class=\"col_heading level0 col7\" >dis</th>        <th class=\"col_heading level0 col8\" >rad</th>        <th class=\"col_heading level0 col9\" >tax</th>        <th class=\"col_heading level0 col10\" >ptratio</th>        <th class=\"col_heading level0 col11\" >b</th>        <th class=\"col_heading level0 col12\" >lstat</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col0\" class=\"data row1 col0\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col2\" class=\"data row1 col2\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col3\" class=\"data row1 col3\" >-0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col5\" class=\"data row1 col5\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col6\" class=\"data row1 col6\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col7\" class=\"data row1 col7\" >-0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col8\" class=\"data row1 col8\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col9\" class=\"data row1 col9\" >-0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col10\" class=\"data row1 col10\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col11\" class=\"data row1 col11\" >0.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col12\" class=\"data row1 col12\" >0.00</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col0\" class=\"data row2 col0\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col1\" class=\"data row2 col1\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col2\" class=\"data row2 col2\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col3\" class=\"data row2 col3\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col4\" class=\"data row2 col4\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col5\" class=\"data row2 col5\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col6\" class=\"data row2 col6\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col7\" class=\"data row2 col7\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col8\" class=\"data row2 col8\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col9\" class=\"data row2 col9\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col10\" class=\"data row2 col10\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col11\" class=\"data row2 col11\" >1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col12\" class=\"data row2 col12\" >1.00</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col0\" class=\"data row3 col0\" >-0.43</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col1\" class=\"data row3 col1\" >-0.47</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col2\" class=\"data row3 col2\" >-1.49</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col3\" class=\"data row3 col3\" >-0.27</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col4\" class=\"data row3 col4\" >-1.50</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col5\" class=\"data row3 col5\" >-4.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col6\" class=\"data row3 col6\" >-2.40</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col7\" class=\"data row3 col7\" >-1.28</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col8\" class=\"data row3 col8\" >-1.00</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col9\" class=\"data row3 col9\" >-1.31</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col10\" class=\"data row3 col10\" >-2.81</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col11\" class=\"data row3 col11\" >-4.03</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col12\" class=\"data row3 col12\" >-1.54</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col0\" class=\"data row4 col0\" >-0.42</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col1\" class=\"data row4 col1\" >-0.47</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col2\" class=\"data row4 col2\" >-0.89</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col3\" class=\"data row4 col3\" >-0.27</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col4\" class=\"data row4 col4\" >-0.93</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col5\" class=\"data row4 col5\" >-0.58</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col6\" class=\"data row4 col6\" >-0.83</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col7\" class=\"data row4 col7\" >-0.81</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col8\" class=\"data row4 col8\" >-0.66</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col9\" class=\"data row4 col9\" >-0.78</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col10\" class=\"data row4 col10\" >-0.56</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col11\" class=\"data row4 col11\" >0.20</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col12\" class=\"data row4 col12\" >-0.79</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col0\" class=\"data row5 col0\" >-0.40</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col1\" class=\"data row5 col1\" >-0.47</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col2\" class=\"data row5 col2\" >-0.23</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col3\" class=\"data row5 col3\" >-0.27</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col4\" class=\"data row5 col4\" >-0.14</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col5\" class=\"data row5 col5\" >-0.15</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col6\" class=\"data row5 col6\" >0.33</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col7\" class=\"data row5 col7\" >-0.32</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col8\" class=\"data row5 col8\" >-0.55</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col9\" class=\"data row5 col9\" >-0.45</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col10\" class=\"data row5 col10\" >0.24</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col11\" class=\"data row5 col11\" >0.37</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col12\" class=\"data row5 col12\" >-0.11</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col0\" class=\"data row6 col0\" >0.06</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col1\" class=\"data row6 col1\" >-0.05</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col2\" class=\"data row6 col2\" >0.95</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col3\" class=\"data row6 col3\" >-0.27</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col4\" class=\"data row6 col4\" >0.62</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col5\" class=\"data row6 col5\" >0.49</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col6\" class=\"data row6 col6\" >0.90</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col7\" class=\"data row6 col7\" >0.69</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col8\" class=\"data row6 col8\" >1.61</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col9\" class=\"data row6 col9\" >1.48</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col10\" class=\"data row6 col10\" >0.76</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col11\" class=\"data row6 col11\" >0.43</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col12\" class=\"data row6 col12\" >0.63</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col0\" class=\"data row7 col0\" >8.23</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col1\" class=\"data row7 col1\" >4.04</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col2\" class=\"data row7 col2\" >2.34</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col3\" class=\"data row7 col3\" >3.70</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col4\" class=\"data row7 col4\" >2.82</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col5\" class=\"data row7 col5\" >3.62</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col6\" class=\"data row7 col6\" >1.10</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col7\" class=\"data row7 col7\" >3.37</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col8\" class=\"data row7 col8\" >1.61</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col9\" class=\"data row7 col9\" >1.74</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col10\" class=\"data row7 col10\" >1.60</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col11\" class=\"data row7 col11\" >0.44</td>\n",
       "                        <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col12\" class=\"data row7 col12\" >3.42</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7f66b0230290>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
    "\n",
    "mean = x_train.mean()\n",
    "std  = x_train.std()\n",
    "x_train = (x_train - mean) / std\n",
    "x_test  = (x_test  - mean) / std\n",
    "\n",
    "display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"After normalization :\"))\n",
    "\n",
    "x_train, y_train = np.array(x_train), np.array(y_train)\n",
    "x_test,  y_test  = np.array(x_test),  np.array(y_test)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4/ Build a model\n",
    "About informations about : \n",
    " - [Optimizer](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers)\n",
    " - [Activation](https://www.tensorflow.org/api_docs/python/tf/keras/activations)\n",
    " - [Loss](https://www.tensorflow.org/api_docs/python/tf/keras/losses)\n",
    " - [Metrics](https://www.tensorflow.org/api_docs/python/tf/keras/metrics)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "  def get_model_v1(shape):\n",
    "    \n",
    "    model = keras.models.Sequential()\n",
    "    model.add(keras.layers.Dense(64, activation='relu', input_shape=shape))\n",
    "    model.add(keras.layers.Dense(64, activation='relu'))\n",
    "    model.add(keras.layers.Dense(1))\n",
    "    \n",
    "    model.compile(optimizer = 'rmsprop',\n",
    "                  loss      = 'mse',\n",
    "                  metrics   = ['mae', 'mse'] )\n",
    "    return model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5/ Train the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense (Dense)                (None, 64)                896       \n",
      "_________________________________________________________________\n",
      "dense_1 (Dense)              (None, 64)                4160      \n",
      "_________________________________________________________________\n",
      "dense_2 (Dense)              (None, 1)                 65        \n",
      "=================================================================\n",
      "Total params: 5,121\n",
      "Trainable params: 5,121\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model=get_model_v1( (13,) )\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Let's go :**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 354 samples, validate on 152 samples\n",
      "Epoch 1/100\n",
      "354/354 [==============================] - 1s 2ms/sample - loss: 458.8973 - mae: 19.4424 - mse: 458.8973 - val_loss: 318.9800 - val_mae: 15.9424 - val_mse: 318.9801\n",
      "Epoch 2/100\n",
      "354/354 [==============================] - 0s 229us/sample - loss: 213.7796 - mae: 12.2567 - mse: 213.7796 - val_loss: 101.1658 - val_mae: 8.0594 - val_mse: 101.1658\n",
      "Epoch 3/100\n",
      "354/354 [==============================] - 0s 208us/sample - loss: 72.5785 - mae: 6.2987 - mse: 72.5785 - val_loss: 44.4772 - val_mae: 5.2539 - val_mse: 44.4771\n",
      "Epoch 4/100\n",
      "354/354 [==============================] - 0s 197us/sample - loss: 37.8617 - mae: 4.3850 - mse: 37.8617 - val_loss: 26.7013 - val_mae: 4.0062 - val_mse: 26.7013\n",
      "Epoch 5/100\n",
      "354/354 [==============================] - 0s 213us/sample - loss: 28.4107 - mae: 3.7569 - mse: 28.4106 - val_loss: 22.1095 - val_mae: 3.6372 - val_mse: 22.1095\n",
      "Epoch 6/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 23.1609 - mae: 3.4180 - mse: 23.1609 - val_loss: 23.2152 - val_mae: 3.7587 - val_mse: 23.2152\n",
      "Epoch 7/100\n",
      "354/354 [==============================] - 0s 212us/sample - loss: 20.4846 - mae: 3.2105 - mse: 20.4846 - val_loss: 19.2353 - val_mae: 3.2211 - val_mse: 19.2353\n",
      "Epoch 8/100\n",
      "354/354 [==============================] - 0s 182us/sample - loss: 18.0685 - mae: 3.0027 - mse: 18.0685 - val_loss: 18.5149 - val_mae: 3.1562 - val_mse: 18.5149\n",
      "Epoch 9/100\n",
      "354/354 [==============================] - 0s 192us/sample - loss: 16.9782 - mae: 2.9048 - mse: 16.9782 - val_loss: 17.4633 - val_mae: 2.8894 - val_mse: 17.4633\n",
      "Epoch 10/100\n",
      "354/354 [==============================] - 0s 184us/sample - loss: 15.3535 - mae: 2.7671 - mse: 15.3535 - val_loss: 17.4349 - val_mae: 2.9033 - val_mse: 17.4349\n",
      "Epoch 11/100\n",
      "354/354 [==============================] - 0s 211us/sample - loss: 14.0626 - mae: 2.6465 - mse: 14.0626 - val_loss: 18.2428 - val_mae: 3.0016 - val_mse: 18.2428\n",
      "Epoch 12/100\n",
      "354/354 [==============================] - 0s 213us/sample - loss: 13.5890 - mae: 2.5958 - mse: 13.5890 - val_loss: 16.3660 - val_mae: 2.6599 - val_mse: 16.3660\n",
      "Epoch 13/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 13.0816 - mae: 2.5412 - mse: 13.0816 - val_loss: 16.1545 - val_mae: 2.6357 - val_mse: 16.1545\n",
      "Epoch 14/100\n",
      "354/354 [==============================] - 0s 179us/sample - loss: 12.4630 - mae: 2.4577 - mse: 12.4630 - val_loss: 18.6261 - val_mae: 2.8769 - val_mse: 18.6261\n",
      "Epoch 15/100\n",
      "354/354 [==============================] - 0s 180us/sample - loss: 11.8046 - mae: 2.4121 - mse: 11.8046 - val_loss: 16.6238 - val_mae: 2.6581 - val_mse: 16.6238\n",
      "Epoch 16/100\n",
      "354/354 [==============================] - 0s 203us/sample - loss: 11.5041 - mae: 2.3948 - mse: 11.5042 - val_loss: 19.4839 - val_mae: 2.9697 - val_mse: 19.4839\n",
      "Epoch 17/100\n",
      "354/354 [==============================] - 0s 207us/sample - loss: 11.4561 - mae: 2.4221 - mse: 11.4561 - val_loss: 15.4893 - val_mae: 2.5344 - val_mse: 15.4893\n",
      "Epoch 18/100\n",
      "354/354 [==============================] - 0s 201us/sample - loss: 11.2035 - mae: 2.3512 - mse: 11.2035 - val_loss: 16.1624 - val_mae: 2.6216 - val_mse: 16.1624\n",
      "Epoch 19/100\n",
      "354/354 [==============================] - 0s 205us/sample - loss: 10.8601 - mae: 2.3359 - mse: 10.8601 - val_loss: 16.6674 - val_mae: 2.6028 - val_mse: 16.6674\n",
      "Epoch 20/100\n",
      "354/354 [==============================] - 0s 204us/sample - loss: 10.5051 - mae: 2.2677 - mse: 10.5051 - val_loss: 15.9863 - val_mae: 2.5769 - val_mse: 15.9863\n",
      "Epoch 21/100\n",
      "354/354 [==============================] - 0s 186us/sample - loss: 10.2899 - mae: 2.2877 - mse: 10.2899 - val_loss: 16.1491 - val_mae: 2.5465 - val_mse: 16.1491\n",
      "Epoch 22/100\n",
      "354/354 [==============================] - 0s 197us/sample - loss: 10.1146 - mae: 2.2151 - mse: 10.1146 - val_loss: 16.0190 - val_mae: 2.5167 - val_mse: 16.0190\n",
      "Epoch 23/100\n",
      "354/354 [==============================] - 0s 208us/sample - loss: 10.0647 - mae: 2.2372 - mse: 10.0647 - val_loss: 16.0099 - val_mae: 2.5391 - val_mse: 16.0099\n",
      "Epoch 24/100\n",
      "354/354 [==============================] - 0s 205us/sample - loss: 9.7932 - mae: 2.2132 - mse: 9.7932 - val_loss: 15.0919 - val_mae: 2.4853 - val_mse: 15.0919\n",
      "Epoch 25/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 9.7249 - mae: 2.1589 - mse: 9.7249 - val_loss: 16.0316 - val_mae: 2.5151 - val_mse: 16.0316\n",
      "Epoch 26/100\n",
      "354/354 [==============================] - 0s 208us/sample - loss: 9.4263 - mae: 2.1743 - mse: 9.4263 - val_loss: 14.8897 - val_mae: 2.4844 - val_mse: 14.8897\n",
      "Epoch 27/100\n",
      "354/354 [==============================] - 0s 196us/sample - loss: 9.2317 - mae: 2.1075 - mse: 9.2317 - val_loss: 16.4898 - val_mae: 2.5348 - val_mse: 16.4898\n",
      "Epoch 28/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 8.9923 - mae: 2.1092 - mse: 8.9923 - val_loss: 15.7991 - val_mae: 2.5335 - val_mse: 15.7991\n",
      "Epoch 29/100\n",
      "354/354 [==============================] - 0s 205us/sample - loss: 8.9679 - mae: 2.1287 - mse: 8.9679 - val_loss: 17.9783 - val_mae: 2.6815 - val_mse: 17.9783\n",
      "Epoch 30/100\n",
      "354/354 [==============================] - 0s 189us/sample - loss: 8.9394 - mae: 2.1013 - mse: 8.9394 - val_loss: 16.0569 - val_mae: 2.5941 - val_mse: 16.0569\n",
      "Epoch 31/100\n",
      "354/354 [==============================] - 0s 195us/sample - loss: 8.6655 - mae: 2.0745 - mse: 8.6655 - val_loss: 15.6427 - val_mae: 2.5280 - val_mse: 15.6427\n",
      "Epoch 32/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 8.5800 - mae: 2.0763 - mse: 8.5800 - val_loss: 17.5586 - val_mae: 2.6977 - val_mse: 17.5586\n",
      "Epoch 33/100\n",
      "354/354 [==============================] - 0s 212us/sample - loss: 8.2374 - mae: 2.0580 - mse: 8.2374 - val_loss: 14.9162 - val_mae: 2.4350 - val_mse: 14.9162\n",
      "Epoch 34/100\n",
      "354/354 [==============================] - 0s 203us/sample - loss: 8.1720 - mae: 2.0231 - mse: 8.1720 - val_loss: 15.2634 - val_mae: 2.4622 - val_mse: 15.2634\n",
      "Epoch 35/100\n",
      "354/354 [==============================] - 0s 203us/sample - loss: 8.2398 - mae: 1.9970 - mse: 8.2398 - val_loss: 14.5321 - val_mae: 2.4526 - val_mse: 14.5321\n",
      "Epoch 36/100\n",
      "354/354 [==============================] - 0s 191us/sample - loss: 8.1026 - mae: 2.0228 - mse: 8.1026 - val_loss: 14.5209 - val_mae: 2.4306 - val_mse: 14.5209\n",
      "Epoch 37/100\n",
      "354/354 [==============================] - 0s 189us/sample - loss: 8.0507 - mae: 2.0038 - mse: 8.0507 - val_loss: 14.2053 - val_mae: 2.4105 - val_mse: 14.2053\n",
      "Epoch 38/100\n",
      "354/354 [==============================] - 0s 180us/sample - loss: 7.9693 - mae: 1.9907 - mse: 7.9693 - val_loss: 15.1895 - val_mae: 2.4466 - val_mse: 15.1895\n",
      "Epoch 39/100\n",
      "354/354 [==============================] - 0s 190us/sample - loss: 8.0358 - mae: 1.9684 - mse: 8.0358 - val_loss: 14.1343 - val_mae: 2.4152 - val_mse: 14.1343\n",
      "Epoch 40/100\n",
      "354/354 [==============================] - 0s 187us/sample - loss: 7.5035 - mae: 1.9196 - mse: 7.5035 - val_loss: 17.4994 - val_mae: 2.6633 - val_mse: 17.4994\n",
      "Epoch 41/100\n",
      "354/354 [==============================] - 0s 215us/sample - loss: 7.6546 - mae: 1.9187 - mse: 7.6546 - val_loss: 16.1207 - val_mae: 2.5874 - val_mse: 16.1207\n",
      "Epoch 42/100\n",
      "354/354 [==============================] - 0s 191us/sample - loss: 7.5702 - mae: 1.9474 - mse: 7.5702 - val_loss: 16.0411 - val_mae: 2.5549 - val_mse: 16.0411\n",
      "Epoch 43/100\n",
      "354/354 [==============================] - 0s 199us/sample - loss: 7.2741 - mae: 1.8964 - mse: 7.2741 - val_loss: 18.3190 - val_mae: 2.9024 - val_mse: 18.3190\n",
      "Epoch 44/100\n",
      "354/354 [==============================] - 0s 192us/sample - loss: 7.3155 - mae: 1.9052 - mse: 7.3155 - val_loss: 14.6721 - val_mae: 2.5076 - val_mse: 14.6721\n",
      "Epoch 45/100\n",
      "354/354 [==============================] - 0s 180us/sample - loss: 7.2273 - mae: 1.9336 - mse: 7.2273 - val_loss: 16.3598 - val_mae: 2.6645 - val_mse: 16.3598\n",
      "Epoch 46/100\n",
      "354/354 [==============================] - 0s 175us/sample - loss: 7.0535 - mae: 1.9014 - mse: 7.0535 - val_loss: 12.9086 - val_mae: 2.3502 - val_mse: 12.9086\n",
      "Epoch 47/100\n",
      "354/354 [==============================] - 0s 197us/sample - loss: 7.0074 - mae: 1.8563 - mse: 7.0074 - val_loss: 16.8070 - val_mae: 2.6346 - val_mse: 16.8070\n",
      "Epoch 48/100\n",
      "354/354 [==============================] - 0s 182us/sample - loss: 7.0550 - mae: 1.9165 - mse: 7.0550 - val_loss: 14.6369 - val_mae: 2.3841 - val_mse: 14.6369\n",
      "Epoch 49/100\n",
      "354/354 [==============================] - 0s 194us/sample - loss: 6.8742 - mae: 1.8599 - mse: 6.8742 - val_loss: 13.6704 - val_mae: 2.3694 - val_mse: 13.6704\n",
      "Epoch 50/100\n",
      "354/354 [==============================] - 0s 188us/sample - loss: 6.7243 - mae: 1.8279 - mse: 6.7243 - val_loss: 16.2202 - val_mae: 2.7116 - val_mse: 16.2202\n",
      "Epoch 51/100\n",
      "354/354 [==============================] - 0s 182us/sample - loss: 6.6542 - mae: 1.8333 - mse: 6.6542 - val_loss: 13.2996 - val_mae: 2.4556 - val_mse: 13.2996\n",
      "Epoch 52/100\n",
      "354/354 [==============================] - 0s 185us/sample - loss: 6.6939 - mae: 1.7798 - mse: 6.6939 - val_loss: 12.5869 - val_mae: 2.3476 - val_mse: 12.5869\n",
      "Epoch 53/100\n",
      "354/354 [==============================] - 0s 181us/sample - loss: 6.4587 - mae: 1.7806 - mse: 6.4587 - val_loss: 12.8318 - val_mae: 2.3455 - val_mse: 12.8318\n",
      "Epoch 54/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 6.3607 - mae: 1.8065 - mse: 6.3607 - val_loss: 12.5530 - val_mae: 2.3419 - val_mse: 12.5530\n",
      "Epoch 55/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 6.4998 - mae: 1.7788 - mse: 6.4998 - val_loss: 15.9603 - val_mae: 2.6778 - val_mse: 15.9603\n",
      "Epoch 56/100\n",
      "354/354 [==============================] - 0s 214us/sample - loss: 6.3887 - mae: 1.7788 - mse: 6.3887 - val_loss: 13.8484 - val_mae: 2.3625 - val_mse: 13.8484\n",
      "Epoch 57/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 6.1759 - mae: 1.7890 - mse: 6.1759 - val_loss: 13.8605 - val_mae: 2.4015 - val_mse: 13.8605\n",
      "Epoch 58/100\n",
      "354/354 [==============================] - 0s 196us/sample - loss: 6.0961 - mae: 1.7153 - mse: 6.0961 - val_loss: 12.4883 - val_mae: 2.3339 - val_mse: 12.4883\n",
      "Epoch 59/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 6.1896 - mae: 1.7431 - mse: 6.1896 - val_loss: 14.4011 - val_mae: 2.5137 - val_mse: 14.4011\n",
      "Epoch 60/100\n",
      "354/354 [==============================] - 0s 206us/sample - loss: 5.9512 - mae: 1.7174 - mse: 5.9512 - val_loss: 12.7580 - val_mae: 2.3765 - val_mse: 12.7580\n",
      "Epoch 61/100\n",
      "354/354 [==============================] - 0s 182us/sample - loss: 5.9029 - mae: 1.6871 - mse: 5.9029 - val_loss: 12.7280 - val_mae: 2.3057 - val_mse: 12.7280\n",
      "Epoch 62/100\n",
      "354/354 [==============================] - 0s 217us/sample - loss: 5.8361 - mae: 1.6887 - mse: 5.8361 - val_loss: 12.3790 - val_mae: 2.3095 - val_mse: 12.3790\n",
      "Epoch 63/100\n",
      "354/354 [==============================] - 0s 203us/sample - loss: 5.9223 - mae: 1.6781 - mse: 5.9223 - val_loss: 12.8838 - val_mae: 2.3390 - val_mse: 12.8838\n",
      "Epoch 64/100\n",
      "354/354 [==============================] - 0s 188us/sample - loss: 5.6987 - mae: 1.6582 - mse: 5.6987 - val_loss: 15.2329 - val_mae: 2.5214 - val_mse: 15.2329\n",
      "Epoch 65/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 5.7098 - mae: 1.6895 - mse: 5.7098 - val_loss: 15.4004 - val_mae: 2.6585 - val_mse: 15.4004\n",
      "Epoch 66/100\n",
      "354/354 [==============================] - 0s 217us/sample - loss: 5.6926 - mae: 1.7027 - mse: 5.6926 - val_loss: 13.3976 - val_mae: 2.4128 - val_mse: 13.3976\n",
      "Epoch 67/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 5.5392 - mae: 1.6788 - mse: 5.5392 - val_loss: 12.1396 - val_mae: 2.3543 - val_mse: 12.1396\n",
      "Epoch 68/100\n",
      "354/354 [==============================] - 0s 204us/sample - loss: 5.6455 - mae: 1.6395 - mse: 5.6455 - val_loss: 12.3876 - val_mae: 2.2912 - val_mse: 12.3876\n",
      "Epoch 69/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 5.5486 - mae: 1.6507 - mse: 5.5486 - val_loss: 11.8058 - val_mae: 2.2785 - val_mse: 11.8058\n",
      "Epoch 70/100\n",
      "354/354 [==============================] - 0s 196us/sample - loss: 5.2014 - mae: 1.6158 - mse: 5.2014 - val_loss: 12.3587 - val_mae: 2.3669 - val_mse: 12.3587\n",
      "Epoch 71/100\n",
      "354/354 [==============================] - 0s 206us/sample - loss: 5.3234 - mae: 1.6188 - mse: 5.3234 - val_loss: 12.7164 - val_mae: 2.3158 - val_mse: 12.7164\n",
      "Epoch 72/100\n",
      "354/354 [==============================] - 0s 194us/sample - loss: 5.2484 - mae: 1.6042 - mse: 5.2484 - val_loss: 12.3865 - val_mae: 2.3693 - val_mse: 12.3865\n",
      "Epoch 73/100\n",
      "354/354 [==============================] - 0s 196us/sample - loss: 5.0747 - mae: 1.6102 - mse: 5.0747 - val_loss: 12.4433 - val_mae: 2.3377 - val_mse: 12.4433\n",
      "Epoch 74/100\n",
      "354/354 [==============================] - 0s 211us/sample - loss: 5.0366 - mae: 1.5948 - mse: 5.0366 - val_loss: 12.8354 - val_mae: 2.4892 - val_mse: 12.8354\n",
      "Epoch 75/100\n",
      "354/354 [==============================] - 0s 195us/sample - loss: 5.1710 - mae: 1.6385 - mse: 5.1710 - val_loss: 12.3743 - val_mae: 2.3796 - val_mse: 12.3743\n",
      "Epoch 76/100\n",
      "354/354 [==============================] - 0s 206us/sample - loss: 5.0850 - mae: 1.5859 - mse: 5.0850 - val_loss: 13.4606 - val_mae: 2.4595 - val_mse: 13.4606\n",
      "Epoch 77/100\n",
      "354/354 [==============================] - 0s 197us/sample - loss: 5.0708 - mae: 1.6001 - mse: 5.0708 - val_loss: 13.3754 - val_mae: 2.3588 - val_mse: 13.3754\n",
      "Epoch 78/100\n",
      "354/354 [==============================] - 0s 186us/sample - loss: 4.8250 - mae: 1.5805 - mse: 4.8250 - val_loss: 12.2387 - val_mae: 2.2988 - val_mse: 12.2387\n",
      "Epoch 79/100\n",
      "354/354 [==============================] - 0s 194us/sample - loss: 4.8951 - mae: 1.5868 - mse: 4.8951 - val_loss: 11.8498 - val_mae: 2.3508 - val_mse: 11.8498\n",
      "Epoch 80/100\n",
      "354/354 [==============================] - 0s 183us/sample - loss: 4.9441 - mae: 1.5494 - mse: 4.9441 - val_loss: 13.9550 - val_mae: 2.5396 - val_mse: 13.9550\n",
      "Epoch 81/100\n",
      "354/354 [==============================] - 0s 203us/sample - loss: 4.8870 - mae: 1.5427 - mse: 4.8870 - val_loss: 12.1051 - val_mae: 2.3690 - val_mse: 12.1051\n",
      "Epoch 82/100\n",
      "354/354 [==============================] - 0s 190us/sample - loss: 4.7350 - mae: 1.5419 - mse: 4.7350 - val_loss: 13.7286 - val_mae: 2.5262 - val_mse: 13.7286\n",
      "Epoch 83/100\n",
      "354/354 [==============================] - 0s 238us/sample - loss: 4.9354 - mae: 1.5685 - mse: 4.9354 - val_loss: 12.9193 - val_mae: 2.4904 - val_mse: 12.9193\n",
      "Epoch 84/100\n",
      "354/354 [==============================] - 0s 191us/sample - loss: 4.6636 - mae: 1.5551 - mse: 4.6636 - val_loss: 12.1324 - val_mae: 2.4348 - val_mse: 12.1324\n",
      "Epoch 85/100\n",
      "354/354 [==============================] - 0s 195us/sample - loss: 4.7957 - mae: 1.5276 - mse: 4.7957 - val_loss: 12.3749 - val_mae: 2.3330 - val_mse: 12.3749\n",
      "Epoch 86/100\n",
      "354/354 [==============================] - 0s 204us/sample - loss: 4.6654 - mae: 1.5355 - mse: 4.6654 - val_loss: 11.5430 - val_mae: 2.3188 - val_mse: 11.5430\n",
      "Epoch 87/100\n",
      "354/354 [==============================] - 0s 179us/sample - loss: 4.5632 - mae: 1.5194 - mse: 4.5632 - val_loss: 11.3675 - val_mae: 2.2698 - val_mse: 11.3675\n",
      "Epoch 88/100\n",
      "354/354 [==============================] - 0s 196us/sample - loss: 4.5784 - mae: 1.4623 - mse: 4.5784 - val_loss: 14.0622 - val_mae: 2.4995 - val_mse: 14.0622\n",
      "Epoch 89/100\n",
      "354/354 [==============================] - 0s 205us/sample - loss: 4.4661 - mae: 1.4873 - mse: 4.4661 - val_loss: 12.3719 - val_mae: 2.3247 - val_mse: 12.3719\n",
      "Epoch 90/100\n",
      "354/354 [==============================] - 0s 200us/sample - loss: 4.4662 - mae: 1.5005 - mse: 4.4662 - val_loss: 12.6654 - val_mae: 2.3659 - val_mse: 12.6654\n",
      "Epoch 91/100\n",
      "354/354 [==============================] - 0s 190us/sample - loss: 4.3980 - mae: 1.4574 - mse: 4.3980 - val_loss: 12.4609 - val_mae: 2.3459 - val_mse: 12.4609\n",
      "Epoch 92/100\n",
      "354/354 [==============================] - 0s 192us/sample - loss: 4.5533 - mae: 1.5108 - mse: 4.5533 - val_loss: 12.7677 - val_mae: 2.4253 - val_mse: 12.7677\n",
      "Epoch 93/100\n",
      "354/354 [==============================] - 0s 197us/sample - loss: 4.4988 - mae: 1.4931 - mse: 4.4988 - val_loss: 12.2878 - val_mae: 2.3648 - val_mse: 12.2878\n",
      "Epoch 94/100\n",
      "354/354 [==============================] - 0s 196us/sample - loss: 4.5069 - mae: 1.4879 - mse: 4.5069 - val_loss: 12.9163 - val_mae: 2.4027 - val_mse: 12.9163\n",
      "Epoch 95/100\n",
      "354/354 [==============================] - 0s 192us/sample - loss: 4.2032 - mae: 1.4314 - mse: 4.2032 - val_loss: 11.4810 - val_mae: 2.2678 - val_mse: 11.4810\n",
      "Epoch 96/100\n",
      "354/354 [==============================] - 0s 191us/sample - loss: 4.3565 - mae: 1.4812 - mse: 4.3565 - val_loss: 11.7690 - val_mae: 2.3530 - val_mse: 11.7690\n",
      "Epoch 97/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 4.2132 - mae: 1.4641 - mse: 4.2132 - val_loss: 11.7643 - val_mae: 2.3037 - val_mse: 11.7643\n",
      "Epoch 98/100\n",
      "354/354 [==============================] - 0s 184us/sample - loss: 4.2685 - mae: 1.4209 - mse: 4.2685 - val_loss: 13.5426 - val_mae: 2.4505 - val_mse: 13.5426\n",
      "Epoch 99/100\n",
      "354/354 [==============================] - 0s 193us/sample - loss: 4.2273 - mae: 1.4354 - mse: 4.2273 - val_loss: 11.9713 - val_mae: 2.3091 - val_mse: 11.9713\n",
      "Epoch 100/100\n",
      "354/354 [==============================] - 0s 204us/sample - loss: 4.0932 - mae: 1.4115 - mse: 4.0932 - val_loss: 12.6829 - val_mae: 2.3742 - val_mse: 12.6829\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(x_train,\n",
    "                    y_train,\n",
    "                    epochs          = 100,\n",
    "                    batch_size      = 10,\n",
    "                    verbose         = 1,\n",
    "                    validation_data = (x_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 6/ Evaluate\n",
    "### 6.1/ Model evaluation\n",
    "MAE =  Mean Absolute Error (between the labels and predictions)  \n",
    "A mae equal to 3 represents an average error in prediction of $3k."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_test / loss      : 12.6829\n",
      "x_test / mae       : 2.3742\n",
      "x_test / mse       : 12.6829\n"
     ]
    }
   ],
   "source": [
    "score = model.evaluate(x_test, y_test, verbose=0)\n",
    "\n",
    "print('x_test / loss      : {:5.4f}'.format(score[0]))\n",
    "print('x_test / mae       : {:5.4f}'.format(score[1]))\n",
    "print('x_test / mse       : {:5.4f}'.format(score[2]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6.2/ Training history\n",
    "What was the best result during our training ?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>loss</th>\n",
       "      <th>mae</th>\n",
       "      <th>mse</th>\n",
       "      <th>val_loss</th>\n",
       "      <th>val_mae</th>\n",
       "      <th>val_mse</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>15.358750</td>\n",
       "      <td>2.269137</td>\n",
       "      <td>15.358750</td>\n",
       "      <td>18.906837</td>\n",
       "      <td>2.754277</td>\n",
       "      <td>18.906838</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>49.946002</td>\n",
       "      <td>2.123399</td>\n",
       "      <td>49.945997</td>\n",
       "      <td>31.760275</td>\n",
       "      <td>1.495250</td>\n",
       "      <td>31.760280</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>4.093166</td>\n",
       "      <td>1.411523</td>\n",
       "      <td>4.093166</td>\n",
       "      <td>11.367452</td>\n",
       "      <td>2.267774</td>\n",
       "      <td>11.367453</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>5.073712</td>\n",
       "      <td>1.598796</td>\n",
       "      <td>5.073712</td>\n",
       "      <td>12.645807</td>\n",
       "      <td>2.361604</td>\n",
       "      <td>12.645807</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>6.709099</td>\n",
       "      <td>1.830622</td>\n",
       "      <td>6.709099</td>\n",
       "      <td>14.303193</td>\n",
       "      <td>2.460818</td>\n",
       "      <td>14.303193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>9.500961</td>\n",
       "      <td>2.162759</td>\n",
       "      <td>9.500960</td>\n",
       "      <td>16.156455</td>\n",
       "      <td>2.624831</td>\n",
       "      <td>16.156455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>458.897337</td>\n",
       "      <td>19.442396</td>\n",
       "      <td>458.897278</td>\n",
       "      <td>318.980021</td>\n",
       "      <td>15.942373</td>\n",
       "      <td>318.980072</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             loss         mae         mse    val_loss     val_mae     val_mse\n",
       "count  100.000000  100.000000  100.000000  100.000000  100.000000  100.000000\n",
       "mean    15.358750    2.269137   15.358750   18.906837    2.754277   18.906838\n",
       "std     49.946002    2.123399   49.945997   31.760275    1.495250   31.760280\n",
       "min      4.093166    1.411523    4.093166   11.367452    2.267774   11.367453\n",
       "25%      5.073712    1.598796    5.073712   12.645807    2.361604   12.645807\n",
       "50%      6.709099    1.830622    6.709099   14.303193    2.460818   14.303193\n",
       "75%      9.500961    2.162759    9.500960   16.156455    2.624831   16.156455\n",
       "max    458.897337   19.442396  458.897278  318.980021   15.942373  318.980072"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df=pd.DataFrame(data=history.history)\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "min( val_mae ) : 2.2678\n"
     ]
    }
   ],
   "source": [
    "print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ooo.plot_history(history, plot={'MSE' :['mse', 'val_mse'],\n",
    "                                'MAE' :['mae', 'val_mae'],\n",
    "                                'LOSS':['loss','val_loss']})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 7 - Make a prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "my_data = [ 1.26425925, -0.48522739,  1.0436489 , -0.23112788,  1.37120745,\n",
    "       -2.14308942,  1.13489104, -1.06802005,  1.71189006,  1.57042287,\n",
    "        0.77859951,  0.14769795,  2.7585581 ]\n",
    "real_price = 10.4\n",
    "\n",
    "my_data=np.array(my_data).reshape(1,13)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prédiction : 10.45 K$\n",
      "Reality    : 10.40 K$\n"
     ]
    }
   ],
   "source": [
    "\n",
    "predictions = model.predict( my_data )\n",
    "print(\"Prédiction : {:.2f} K$\".format(predictions[0][0]))\n",
    "print(\"Reality    : {:.2f} K$\".format(real_price))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "That's all folks !"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}