{
"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 : Friday 24 January 2020, 11:42:30\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_3a6ab490_3e96_11ea_bb15_dba25722cc7a\" ><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_3a6ab490_3e96_11ea_bb15_dba25722cc7alevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7alevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7alevel0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7alevel0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7alevel0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_3a6ab490_3e96_11ea_bb15_dba25722cc7arow4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fc61db614d0>"
]
},
"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 80% of the data for training and 20% 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_3dd46306_3e96_11ea_bb15_dba25722cc7a\" ><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_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col0\" class=\"data row1 col0\" >3.97</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col1\" class=\"data row1 col1\" >10.27</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col2\" class=\"data row1 col2\" >11.51</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col3\" class=\"data row1 col3\" >0.07</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col4\" class=\"data row1 col4\" >0.56</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col5\" class=\"data row1 col5\" >6.26</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col6\" class=\"data row1 col6\" >70.20</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col7\" class=\"data row1 col7\" >3.70</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col8\" class=\"data row1 col8\" >9.88</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col9\" class=\"data row1 col9\" >414.85</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col10\" class=\"data row1 col10\" >18.51</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col11\" class=\"data row1 col11\" >354.34</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow1_col12\" class=\"data row1 col12\" >13.01</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col0\" class=\"data row2 col0\" >9.57</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col1\" class=\"data row2 col1\" >22.19</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col2\" class=\"data row2 col2\" >6.78</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col3\" class=\"data row2 col3\" >0.25</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col4\" class=\"data row2 col4\" >0.12</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col5\" class=\"data row2 col5\" >0.70</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col6\" class=\"data row2 col6\" >27.68</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col7\" class=\"data row2 col7\" >2.07</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col8\" class=\"data row2 col8\" >8.80</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col9\" class=\"data row2 col9\" >169.62</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col10\" class=\"data row2 col10\" >2.13</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col11\" class=\"data row2 col11\" >94.06</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow2_col12\" class=\"data row2 col12\" >7.27</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col2\" class=\"data row3 col2\" >0.74</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col5\" class=\"data row3 col5\" >3.56</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col6\" class=\"data row3 col6\" >2.90</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col7\" class=\"data row3 col7\" >1.13</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col9\" class=\"data row3 col9\" >187.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col10\" class=\"data row3 col10\" >12.60</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col11\" class=\"data row3 col11\" >2.52</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow3_col12\" class=\"data row3 col12\" >1.73</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col0\" class=\"data row4 col0\" >0.09</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col2\" class=\"data row4 col2\" >5.86</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col4\" class=\"data row4 col4\" >0.45</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col5\" class=\"data row4 col5\" >5.88</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col6\" class=\"data row4 col6\" >47.25</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col7\" class=\"data row4 col7\" >2.05</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col9\" class=\"data row4 col9\" >284.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col10\" class=\"data row4 col10\" >17.40</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col11\" class=\"data row4 col11\" >374.49</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow4_col12\" class=\"data row4 col12\" >7.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col0\" class=\"data row5 col0\" >0.29</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col2\" class=\"data row5 col2\" >9.90</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col4\" class=\"data row5 col4\" >0.54</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col5\" class=\"data row5 col5\" >6.19</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col6\" class=\"data row5 col6\" >80.10</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col7\" class=\"data row5 col7\" >3.09</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col9\" class=\"data row5 col9\" >334.50</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col10\" class=\"data row5 col10\" >19.10</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col11\" class=\"data row5 col11\" >390.81</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow5_col12\" class=\"data row5 col12\" >11.73</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col0\" class=\"data row6 col0\" >3.85</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col1\" class=\"data row6 col1\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col5\" class=\"data row6 col5\" >6.59</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col6\" class=\"data row6 col6\" >94.57</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col7\" class=\"data row6 col7\" >4.94</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col8\" class=\"data row6 col8\" >24.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col9\" class=\"data row6 col9\" >666.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col11\" class=\"data row6 col11\" >396.04</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow6_col12\" class=\"data row6 col12\" >17.11</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7alevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col0\" class=\"data row7 col0\" >88.98</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col1\" class=\"data row7 col1\" >95.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col5\" class=\"data row7 col5\" >8.72</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col7\" class=\"data row7 col7\" >12.13</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_3dd46306_3e96_11ea_bb15_dba25722cc7arow7_col12\" class=\"data row7 col12\" >37.97</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fc62513f7d0>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7a\" ><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_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col0\" class=\"data row1 col0\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col2\" class=\"data row1 col2\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col3\" class=\"data row1 col3\" >-0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col5\" class=\"data row1 col5\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col6\" class=\"data row1 col6\" >-0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col7\" class=\"data row1 col7\" >-0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col8\" class=\"data row1 col8\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col9\" class=\"data row1 col9\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col11\" class=\"data row1 col11\" >0.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow1_col12\" class=\"data row1 col12\" >0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col0\" class=\"data row3 col0\" >-0.41</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col1\" class=\"data row3 col1\" >-0.46</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col2\" class=\"data row3 col2\" >-1.59</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col3\" class=\"data row3 col3\" >-0.27</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col4\" class=\"data row3 col4\" >-1.43</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col5\" class=\"data row3 col5\" >-3.87</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col6\" class=\"data row3 col6\" >-2.43</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col7\" class=\"data row3 col7\" >-1.24</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col8\" class=\"data row3 col8\" >-1.01</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col9\" class=\"data row3 col9\" >-1.34</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col10\" class=\"data row3 col10\" >-2.78</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col11\" class=\"data row3 col11\" >-3.74</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow3_col12\" class=\"data row3 col12\" >-1.55</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col0\" class=\"data row4 col0\" >-0.41</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col1\" class=\"data row4 col1\" >-0.46</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col2\" class=\"data row4 col2\" >-0.83</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col3\" class=\"data row4 col3\" >-0.27</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col4\" class=\"data row4 col4\" >-0.91</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col5\" class=\"data row4 col5\" >-0.55</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col6\" class=\"data row4 col6\" >-0.83</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col7\" class=\"data row4 col7\" >-0.80</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col8\" class=\"data row4 col8\" >-0.67</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col9\" class=\"data row4 col9\" >-0.77</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col10\" class=\"data row4 col10\" >-0.52</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col11\" class=\"data row4 col11\" >0.21</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow4_col12\" class=\"data row4 col12\" >-0.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col0\" class=\"data row5 col0\" >-0.38</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col1\" class=\"data row5 col1\" >-0.46</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col2\" class=\"data row5 col2\" >-0.24</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col3\" class=\"data row5 col3\" >-0.27</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col4\" class=\"data row5 col4\" >-0.18</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col5\" class=\"data row5 col5\" >-0.10</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col6\" class=\"data row5 col6\" >0.36</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col7\" class=\"data row5 col7\" >-0.29</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col8\" class=\"data row5 col8\" >-0.55</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col9\" class=\"data row5 col9\" >-0.47</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col10\" class=\"data row5 col10\" >0.28</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col11\" class=\"data row5 col11\" >0.39</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow5_col12\" class=\"data row5 col12\" >-0.18</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col0\" class=\"data row6 col0\" >-0.01</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col1\" class=\"data row6 col1\" >-0.46</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col2\" class=\"data row6 col2\" >0.97</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col3\" class=\"data row6 col3\" >-0.27</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col4\" class=\"data row6 col4\" >0.55</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col5\" class=\"data row6 col5\" >0.49</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col6\" class=\"data row6 col6\" >0.88</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col7\" class=\"data row6 col7\" >0.60</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col8\" class=\"data row6 col8\" >1.60</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col9\" class=\"data row6 col9\" >1.48</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col10\" class=\"data row6 col10\" >0.79</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col11\" class=\"data row6 col11\" >0.44</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow6_col12\" class=\"data row6 col12\" >0.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7alevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col0\" class=\"data row7 col0\" >8.89</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col1\" class=\"data row7 col1\" >3.82</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col2\" class=\"data row7 col2\" >2.39</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col3\" class=\"data row7 col3\" >3.70</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col4\" class=\"data row7 col4\" >2.67</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col5\" class=\"data row7 col5\" >3.55</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col6\" class=\"data row7 col6\" >1.08</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col7\" class=\"data row7 col7\" >4.07</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col8\" class=\"data row7 col8\" >1.60</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col9\" class=\"data row7 col9\" >1.75</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col10\" class=\"data row7 col10\" >1.64</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col11\" class=\"data row7 col11\" >0.45</td>\n",
" <td id=\"T_3dddca22_3e96_11ea_bb15_dba25722cc7arow7_col12\" class=\"data row7 col12\" >3.43</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fc61da1b110>"
]
},
"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": 6,
"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": 7,
"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": 9,
"metadata": {},
"outputs": [],
"source": [
"history = model.fit(x_train,\n",
" y_train,\n",
" epochs = 100,\n",
" batch_size = 10,\n",
" verbose = 0,\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": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"x_test / loss : 14.9185\n",
"x_test / mae : 2.5638\n",
"x_test / mse : 14.9185\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": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"min( val_mae ) : 2.1862\n"
]
}
],
"source": [
"print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
]
},
{
"cell_type": "code",
"execution_count": 12,
"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": [
"reload(ooo)\n",
"ooo.plot_history(history, plot={'MSE' :['mse', 'val_mse'],\n",
" 'MAE' :['mae', 'val_mae'],\n",
" 'LOSS':['loss','val_loss']})"
]
},
{
"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
}