{
"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": [
"## Step 1 - Import and init"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>\n",
"\n",
"div.warn { \n",
" background-color: #fcf2f2;\n",
" border-color: #dFb5b4;\n",
" border-left: 5px solid #dfb5b4;\n",
" padding: 0.5em;\n",
" font-weight: bold;\n",
" font-size: 1.1em;;\n",
" }\n",
"\n",
"\n",
"\n",
"div.nota { \n",
" background-color: #DAFFDE;\n",
" border-left: 5px solid #92CC99;\n",
" padding: 0.5em;\n",
" }\n",
"\n",
"\n",
"\n",
"</style>\n",
"\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"FIDLE 2020 - Practical Work Module\n",
"Version : 0.2.8\n",
"Run time : Saturday 15 February 2020, 12:38:00\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,sys\n",
"\n",
"from IPython.display import display, Markdown\n",
"from importlib import reload\n",
"\n",
"sys.path.append('..')\n",
"import fidle.pwk as ooo\n",
"\n",
"ooo.init()\n",
"os.makedirs('./run/models', mode=0o750, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2 - Retrieve data\n",
"\n",
"### 2.1 - Option 1 : 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": [
"### 2.2 - Option 2 : 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_9eb52d06_4fe7_11ea_bfba_2f4388d94826\" ><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_9eb52d06_4fe7_11ea_bfba_2f4388d94826level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_9eb52d06_4fe7_11ea_bfba_2f4388d94826row4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f7b6c0c8050>"
]
},
"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": [
"## Step 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_9ebc7b06_4fe7_11ea_bfba_2f4388d94826\" ><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_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col0\" class=\"data row1 col0\" >3.73</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col1\" class=\"data row1 col1\" >10.85</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col2\" class=\"data row1 col2\" >11.11</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col4\" class=\"data row1 col4\" >0.55</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col5\" class=\"data row1 col5\" >6.26</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col6\" class=\"data row1 col6\" >69.55</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col7\" class=\"data row1 col7\" >3.86</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col8\" class=\"data row1 col8\" >9.69</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col9\" class=\"data row1 col9\" >410.44</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col10\" class=\"data row1 col10\" >18.56</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col11\" class=\"data row1 col11\" >355.37</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row1_col12\" class=\"data row1 col12\" >12.98</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col0\" class=\"data row2 col0\" >8.61</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col1\" class=\"data row2 col1\" >22.71</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col2\" class=\"data row2 col2\" >6.86</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col3\" class=\"data row2 col3\" >0.27</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col4\" class=\"data row2 col4\" >0.11</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col5\" class=\"data row2 col5\" >0.67</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col6\" class=\"data row2 col6\" >27.52</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col7\" class=\"data row2 col7\" >2.17</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col8\" class=\"data row2 col8\" >8.79</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col9\" class=\"data row2 col9\" >170.55</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col10\" class=\"data row2 col10\" >2.07</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col11\" class=\"data row2 col11\" >93.33</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row2_col12\" class=\"data row2 col12\" >7.13</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col2\" class=\"data row3 col2\" >0.74</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col5\" class=\"data row3 col5\" >3.56</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col6\" class=\"data row3 col6\" >6.50</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col7\" class=\"data row3 col7\" >1.17</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col9\" class=\"data row3 col9\" >187.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col10\" class=\"data row3 col10\" >12.60</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col11\" class=\"data row3 col11\" >0.32</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row3_col12\" class=\"data row3 col12\" >1.92</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col0\" class=\"data row4 col0\" >0.08</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col2\" class=\"data row4 col2\" >5.19</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col4\" class=\"data row4 col4\" >0.45</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col5\" class=\"data row4 col5\" >5.89</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col6\" class=\"data row4 col6\" >47.45</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col7\" class=\"data row4 col7\" >2.07</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col9\" class=\"data row4 col9\" >279.50</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col10\" class=\"data row4 col10\" >17.40</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col11\" class=\"data row4 col11\" >374.59</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row4_col12\" class=\"data row4 col12\" >7.46</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col0\" class=\"data row5 col0\" >0.25</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col2\" class=\"data row5 col2\" >9.12</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col4\" class=\"data row5 col4\" >0.53</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col5\" class=\"data row5 col5\" >6.17</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col6\" class=\"data row5 col6\" >78.50</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col7\" class=\"data row5 col7\" >3.32</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col9\" class=\"data row5 col9\" >330.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col10\" class=\"data row5 col10\" >19.05</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col11\" class=\"data row5 col11\" >391.30</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row5_col12\" class=\"data row5 col12\" >11.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col0\" class=\"data row6 col0\" >3.99</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col1\" class=\"data row6 col1\" >12.50</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col5\" class=\"data row6 col5\" >6.55</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col6\" class=\"data row6 col6\" >94.38</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col7\" class=\"data row6 col7\" >5.27</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col8\" class=\"data row6 col8\" >24.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col9\" class=\"data row6 col9\" >666.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col11\" class=\"data row6 col11\" >396.21</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row6_col12\" class=\"data row6 col12\" >17.27</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col0\" class=\"data row7 col0\" >73.53</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col1\" class=\"data row7 col1\" >95.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col5\" class=\"data row7 col5\" >8.78</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col7\" class=\"data row7 col7\" >12.13</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_9ebc7b06_4fe7_11ea_bfba_2f4388d94826row7_col12\" class=\"data row7 col12\" >36.98</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f7af2b97cd0>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826\" ><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_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col6\" class=\"data row1 col6\" >-0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col8\" class=\"data row1 col8\" >-0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col11\" class=\"data row1 col11\" >0.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row1_col12\" class=\"data row1 col12\" >-0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col0\" class=\"data row3 col0\" >-0.43</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col1\" class=\"data row3 col1\" >-0.48</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col2\" class=\"data row3 col2\" >-1.51</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col3\" class=\"data row3 col3\" >-0.29</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col4\" class=\"data row3 col4\" >-1.48</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col5\" class=\"data row3 col5\" >-4.03</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col6\" class=\"data row3 col6\" >-2.29</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col7\" class=\"data row3 col7\" >-1.24</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col8\" class=\"data row3 col8\" >-0.99</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col9\" class=\"data row3 col9\" >-1.31</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col10\" class=\"data row3 col10\" >-2.88</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col11\" class=\"data row3 col11\" >-3.80</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row3_col12\" class=\"data row3 col12\" >-1.55</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col0\" class=\"data row4 col0\" >-0.42</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col1\" class=\"data row4 col1\" >-0.48</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col2\" class=\"data row4 col2\" >-0.86</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col3\" class=\"data row4 col3\" >-0.29</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col4\" class=\"data row4 col4\" >-0.88</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col5\" class=\"data row4 col5\" >-0.56</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col6\" class=\"data row4 col6\" >-0.80</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col7\" class=\"data row4 col7\" >-0.83</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col8\" class=\"data row4 col8\" >-0.65</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col9\" class=\"data row4 col9\" >-0.77</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col10\" class=\"data row4 col10\" >-0.56</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col11\" class=\"data row4 col11\" >0.21</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row4_col12\" class=\"data row4 col12\" >-0.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col0\" class=\"data row5 col0\" >-0.40</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col1\" class=\"data row5 col1\" >-0.48</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col2\" class=\"data row5 col2\" >-0.29</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col3\" class=\"data row5 col3\" >-0.29</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col4\" class=\"data row5 col4\" >-0.21</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col5\" class=\"data row5 col5\" >-0.13</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col6\" class=\"data row5 col6\" >0.33</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col7\" class=\"data row5 col7\" >-0.25</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col8\" class=\"data row5 col8\" >-0.53</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col9\" class=\"data row5 col9\" >-0.47</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col10\" class=\"data row5 col10\" >0.24</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col11\" class=\"data row5 col11\" >0.39</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row5_col12\" class=\"data row5 col12\" >-0.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col0\" class=\"data row6 col0\" >0.03</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col1\" class=\"data row6 col1\" >0.07</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col2\" class=\"data row6 col2\" >1.02</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col3\" class=\"data row6 col3\" >-0.29</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col4\" class=\"data row6 col4\" >0.63</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col5\" class=\"data row6 col5\" >0.44</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col6\" class=\"data row6 col6\" >0.90</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col7\" class=\"data row6 col7\" >0.65</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col8\" class=\"data row6 col8\" >1.63</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col9\" class=\"data row6 col9\" >1.50</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col10\" class=\"data row6 col10\" >0.80</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col11\" class=\"data row6 col11\" >0.44</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row6_col12\" class=\"data row6 col12\" >0.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col0\" class=\"data row7 col0\" >8.11</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col1\" class=\"data row7 col1\" >3.71</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col2\" class=\"data row7 col2\" >2.42</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col3\" class=\"data row7 col3\" >3.48</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col4\" class=\"data row7 col4\" >2.81</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col5\" class=\"data row7 col5\" >3.77</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col6\" class=\"data row7 col6\" >1.11</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col7\" class=\"data row7 col7\" >3.81</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col8\" class=\"data row7 col8\" >1.63</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col9\" class=\"data row7 col9\" >1.76</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col10\" class=\"data row7 col10\" >1.67</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col11\" class=\"data row7 col11\" >0.44</td>\n",
" <td id=\"T_9ec335cc_4fe7_11ea_bfba_2f4388d94826row7_col12\" class=\"data row7 col12\" >3.36</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f7af238e790>"
]
},
"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": [
"## Step 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.Input(shape, name=\"InputLayer\"))\n",
" model.add(keras.layers.Dense(64, activation='relu', name='Dense_n1'))\n",
" model.add(keras.layers.Dense(64, activation='relu', name='Dense_n2'))\n",
" model.add(keras.layers.Dense(1, name='Output'))\n",
" \n",
" model.compile(optimizer = 'rmsprop',\n",
" loss = 'mse',\n",
" metrics = ['mae', 'mse'] )\n",
" return model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 5 - Train the model\n",
"### 5.1 - Get it"
]
},
{
"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_n1 (Dense) (None, 64) 896 \n",
"_________________________________________________________________\n",
"Dense_n2 (Dense) (None, 64) 4160 \n",
"_________________________________________________________________\n",
"Output (Dense) (None, 1) 65 \n",
"=================================================================\n",
"Total params: 5,121\n",
"Trainable params: 5,121\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<IPython.core.display.Image object>"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model=get_model_v1( (13,) )\n",
"\n",
"model.summary()\n",
"keras.utils.plot_model( model, to_file='./run/model.png', show_shapes=True, show_layer_names=True, dpi=96)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.2 - Train it"
]
},
{
"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 3ms/sample - loss: 418.8435 - mae: 18.6926 - mse: 418.8436 - val_loss: 363.6250 - val_mae: 17.0712 - val_mse: 363.6249\n",
"Epoch 2/100\n",
"354/354 [==============================] - 0s 280us/sample - loss: 185.7644 - mae: 11.5769 - mse: 185.7644 - val_loss: 130.8274 - val_mae: 9.1964 - val_mse: 130.8273\n",
"Epoch 3/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 63.7021 - mae: 6.1090 - mse: 63.7021 - val_loss: 54.9533 - val_mae: 5.5778 - val_mse: 54.9533\n",
"Epoch 4/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 33.5469 - mae: 4.2459 - mse: 33.5469 - val_loss: 38.7432 - val_mae: 4.5027 - val_mse: 38.7432\n",
"Epoch 5/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 25.0842 - mae: 3.5697 - mse: 25.0842 - val_loss: 31.9627 - val_mae: 3.9794 - val_mse: 31.9627\n",
"Epoch 6/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 20.9567 - mae: 3.2382 - mse: 20.9567 - val_loss: 30.0260 - val_mae: 3.7664 - val_mse: 30.0260\n",
"Epoch 7/100\n",
"354/354 [==============================] - 0s 275us/sample - loss: 18.9505 - mae: 3.0151 - mse: 18.9505 - val_loss: 23.8960 - val_mae: 3.3547 - val_mse: 23.8960\n",
"Epoch 8/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 17.1925 - mae: 2.8789 - mse: 17.1925 - val_loss: 22.9789 - val_mae: 3.1954 - val_mse: 22.9789\n",
"Epoch 9/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 15.8211 - mae: 2.7289 - mse: 15.8211 - val_loss: 20.5825 - val_mae: 3.1199 - val_mse: 20.5825\n",
"Epoch 10/100\n",
"354/354 [==============================] - 0s 274us/sample - loss: 15.0976 - mae: 2.6753 - mse: 15.0976 - val_loss: 21.2327 - val_mae: 3.0570 - val_mse: 21.2327\n",
"Epoch 11/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 14.0510 - mae: 2.5988 - mse: 14.0510 - val_loss: 18.8729 - val_mae: 2.9371 - val_mse: 18.8729\n",
"Epoch 12/100\n",
"354/354 [==============================] - 0s 278us/sample - loss: 13.9241 - mae: 2.5217 - mse: 13.9241 - val_loss: 18.5040 - val_mae: 2.8935 - val_mse: 18.5040\n",
"Epoch 13/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 13.2203 - mae: 2.4659 - mse: 13.2203 - val_loss: 17.7626 - val_mae: 2.8627 - val_mse: 17.7626\n",
"Epoch 14/100\n",
"354/354 [==============================] - 0s 277us/sample - loss: 13.0399 - mae: 2.4507 - mse: 13.0399 - val_loss: 18.7882 - val_mae: 2.8812 - val_mse: 18.7882\n",
"Epoch 15/100\n",
"354/354 [==============================] - 0s 274us/sample - loss: 12.7152 - mae: 2.3897 - mse: 12.7152 - val_loss: 17.5327 - val_mae: 2.7973 - val_mse: 17.5327\n",
"Epoch 16/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 12.4044 - mae: 2.3936 - mse: 12.4044 - val_loss: 18.3104 - val_mae: 2.8215 - val_mse: 18.3104\n",
"Epoch 17/100\n",
"354/354 [==============================] - 0s 280us/sample - loss: 12.0216 - mae: 2.3488 - mse: 12.0216 - val_loss: 16.1507 - val_mae: 2.7517 - val_mse: 16.1507\n",
"Epoch 18/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 11.9575 - mae: 2.3477 - mse: 11.9575 - val_loss: 15.5722 - val_mae: 2.6895 - val_mse: 15.5722\n",
"Epoch 19/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 11.7747 - mae: 2.3273 - mse: 11.7747 - val_loss: 15.7311 - val_mae: 2.6832 - val_mse: 15.7311\n",
"Epoch 20/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 11.6233 - mae: 2.3188 - mse: 11.6233 - val_loss: 16.9861 - val_mae: 2.7485 - val_mse: 16.9861\n",
"Epoch 21/100\n",
"354/354 [==============================] - 0s 275us/sample - loss: 11.3040 - mae: 2.2359 - mse: 11.3040 - val_loss: 20.0885 - val_mae: 3.0260 - val_mse: 20.0885\n",
"Epoch 22/100\n",
"354/354 [==============================] - 0s 267us/sample - loss: 11.5525 - mae: 2.2839 - mse: 11.5525 - val_loss: 16.2819 - val_mae: 2.6818 - val_mse: 16.2819\n",
"Epoch 23/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 10.9328 - mae: 2.2393 - mse: 10.9328 - val_loss: 14.8984 - val_mae: 2.6211 - val_mse: 14.8984\n",
"Epoch 24/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 10.6702 - mae: 2.2566 - mse: 10.6702 - val_loss: 15.2297 - val_mae: 2.5943 - val_mse: 15.2297\n",
"Epoch 25/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 10.6099 - mae: 2.2306 - mse: 10.6099 - val_loss: 14.0894 - val_mae: 2.5234 - val_mse: 14.0894\n",
"Epoch 26/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 10.5236 - mae: 2.1899 - mse: 10.5236 - val_loss: 16.2054 - val_mae: 2.6445 - val_mse: 16.2054\n",
"Epoch 27/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 10.3134 - mae: 2.1293 - mse: 10.3134 - val_loss: 14.1194 - val_mae: 2.5172 - val_mse: 14.1194\n",
"Epoch 28/100\n",
"354/354 [==============================] - 0s 252us/sample - loss: 10.1060 - mae: 2.1281 - mse: 10.1060 - val_loss: 15.9710 - val_mae: 2.6624 - val_mse: 15.9710\n",
"Epoch 29/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 10.3668 - mae: 2.1627 - mse: 10.3668 - val_loss: 14.1934 - val_mae: 2.4820 - val_mse: 14.1934\n",
"Epoch 30/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 9.9118 - mae: 2.0982 - mse: 9.9118 - val_loss: 14.3858 - val_mae: 2.4987 - val_mse: 14.3858\n",
"Epoch 31/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 9.8766 - mae: 2.0939 - mse: 9.8766 - val_loss: 13.8227 - val_mae: 2.5071 - val_mse: 13.8227\n",
"Epoch 32/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 9.8629 - mae: 2.1158 - mse: 9.8629 - val_loss: 13.7714 - val_mae: 2.4909 - val_mse: 13.7714\n",
"Epoch 33/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 9.7673 - mae: 2.0776 - mse: 9.7673 - val_loss: 13.6226 - val_mae: 2.4226 - val_mse: 13.6226\n",
"Epoch 34/100\n",
"354/354 [==============================] - 0s 269us/sample - loss: 9.9778 - mae: 2.1046 - mse: 9.9778 - val_loss: 13.7940 - val_mae: 2.4524 - val_mse: 13.7940\n",
"Epoch 35/100\n",
"354/354 [==============================] - 0s 269us/sample - loss: 9.5368 - mae: 2.0359 - mse: 9.5368 - val_loss: 14.8796 - val_mae: 2.7218 - val_mse: 14.8796\n",
"Epoch 36/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 9.6137 - mae: 2.0622 - mse: 9.6137 - val_loss: 13.3884 - val_mae: 2.4377 - val_mse: 13.3884\n",
"Epoch 37/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 9.0956 - mae: 2.0223 - mse: 9.0956 - val_loss: 14.0526 - val_mae: 2.4567 - val_mse: 14.0526\n",
"Epoch 38/100\n",
"354/354 [==============================] - 0s 269us/sample - loss: 9.1988 - mae: 2.0116 - mse: 9.1988 - val_loss: 13.9418 - val_mae: 2.4329 - val_mse: 13.9418\n",
"Epoch 39/100\n",
"354/354 [==============================] - 0s 267us/sample - loss: 9.2909 - mae: 2.0380 - mse: 9.2909 - val_loss: 12.7459 - val_mae: 2.4097 - val_mse: 12.7459\n",
"Epoch 40/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 9.0192 - mae: 2.0256 - mse: 9.0192 - val_loss: 14.2976 - val_mae: 2.4998 - val_mse: 14.2976\n",
"Epoch 41/100\n",
"354/354 [==============================] - 0s 281us/sample - loss: 8.7552 - mae: 1.9830 - mse: 8.7552 - val_loss: 14.4870 - val_mae: 2.4739 - val_mse: 14.4870\n",
"Epoch 42/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 8.8108 - mae: 1.9751 - mse: 8.8108 - val_loss: 12.7398 - val_mae: 2.4317 - val_mse: 12.7398\n",
"Epoch 43/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 8.6617 - mae: 1.9931 - mse: 8.6617 - val_loss: 15.7144 - val_mae: 2.5868 - val_mse: 15.7144\n",
"Epoch 44/100\n",
"354/354 [==============================] - 0s 274us/sample - loss: 8.6111 - mae: 1.9638 - mse: 8.6111 - val_loss: 12.5787 - val_mae: 2.3649 - val_mse: 12.5787\n",
"Epoch 45/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 8.3551 - mae: 1.9166 - mse: 8.3551 - val_loss: 12.4471 - val_mae: 2.3693 - val_mse: 12.4471\n",
"Epoch 46/100\n",
"354/354 [==============================] - 0s 266us/sample - loss: 8.3524 - mae: 1.9671 - mse: 8.3524 - val_loss: 14.4275 - val_mae: 2.4847 - val_mse: 14.4275\n",
"Epoch 47/100\n",
"354/354 [==============================] - 0s 274us/sample - loss: 8.4545 - mae: 1.9071 - mse: 8.4545 - val_loss: 13.2229 - val_mae: 2.4060 - val_mse: 13.2229\n",
"Epoch 48/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 8.5690 - mae: 1.9217 - mse: 8.5690 - val_loss: 13.4104 - val_mae: 2.3992 - val_mse: 13.4104\n",
"Epoch 49/100\n",
"354/354 [==============================] - 0s 278us/sample - loss: 8.1166 - mae: 1.9338 - mse: 8.1166 - val_loss: 14.6198 - val_mae: 2.5067 - val_mse: 14.6198\n",
"Epoch 50/100\n",
"354/354 [==============================] - 0s 249us/sample - loss: 8.1556 - mae: 1.8854 - mse: 8.1556 - val_loss: 13.2502 - val_mae: 2.4204 - val_mse: 13.2502\n",
"Epoch 51/100\n",
"354/354 [==============================] - 0s 266us/sample - loss: 8.1675 - mae: 1.8848 - mse: 8.1675 - val_loss: 13.0517 - val_mae: 2.4092 - val_mse: 13.0517\n",
"Epoch 52/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 7.8965 - mae: 1.8619 - mse: 7.8965 - val_loss: 12.2905 - val_mae: 2.4068 - val_mse: 12.2905\n",
"Epoch 53/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 7.7485 - mae: 1.8806 - mse: 7.7485 - val_loss: 14.3344 - val_mae: 2.4619 - val_mse: 14.3344\n",
"Epoch 54/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 7.8410 - mae: 1.8223 - mse: 7.8410 - val_loss: 12.4339 - val_mae: 2.3516 - val_mse: 12.4339\n",
"Epoch 55/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 7.7763 - mae: 1.8629 - mse: 7.7763 - val_loss: 12.4900 - val_mae: 2.3219 - val_mse: 12.4900\n",
"Epoch 56/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 7.7260 - mae: 1.8532 - mse: 7.7260 - val_loss: 12.1347 - val_mae: 2.4580 - val_mse: 12.1347\n",
"Epoch 57/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 7.7718 - mae: 1.8427 - mse: 7.7718 - val_loss: 12.2219 - val_mae: 2.3501 - val_mse: 12.2219\n",
"Epoch 58/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 7.4303 - mae: 1.8239 - mse: 7.4303 - val_loss: 14.0691 - val_mae: 2.4818 - val_mse: 14.0691\n",
"Epoch 59/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 7.4273 - mae: 1.8028 - mse: 7.4273 - val_loss: 11.7311 - val_mae: 2.3401 - val_mse: 11.7311\n",
"Epoch 60/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 7.5121 - mae: 1.8147 - mse: 7.5121 - val_loss: 11.3120 - val_mae: 2.2758 - val_mse: 11.3120\n",
"Epoch 61/100\n",
"354/354 [==============================] - 0s 264us/sample - loss: 7.2880 - mae: 1.8049 - mse: 7.2880 - val_loss: 11.9505 - val_mae: 2.3743 - val_mse: 11.9505\n",
"Epoch 62/100\n",
"354/354 [==============================] - 0s 267us/sample - loss: 7.4047 - mae: 1.8147 - mse: 7.4047 - val_loss: 11.3717 - val_mae: 2.3193 - val_mse: 11.3717\n",
"Epoch 63/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 7.1160 - mae: 1.8047 - mse: 7.1160 - val_loss: 11.4990 - val_mae: 2.3168 - val_mse: 11.4990\n",
"Epoch 64/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 7.2246 - mae: 1.7902 - mse: 7.2246 - val_loss: 11.6231 - val_mae: 2.3270 - val_mse: 11.6231\n",
"Epoch 65/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 7.2051 - mae: 1.7780 - mse: 7.2051 - val_loss: 11.8574 - val_mae: 2.3124 - val_mse: 11.8574\n",
"Epoch 66/100\n",
"354/354 [==============================] - 0s 275us/sample - loss: 7.2065 - mae: 1.7675 - mse: 7.2065 - val_loss: 11.4090 - val_mae: 2.2963 - val_mse: 11.4090\n",
"Epoch 67/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 6.8474 - mae: 1.7266 - mse: 6.8474 - val_loss: 12.4625 - val_mae: 2.3632 - val_mse: 12.4625\n",
"Epoch 68/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 6.9649 - mae: 1.7497 - mse: 6.9649 - val_loss: 12.4027 - val_mae: 2.4041 - val_mse: 12.4027\n",
"Epoch 69/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 7.0694 - mae: 1.7344 - mse: 7.0694 - val_loss: 12.8411 - val_mae: 2.4197 - val_mse: 12.8411\n",
"Epoch 70/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 6.6178 - mae: 1.6949 - mse: 6.6178 - val_loss: 10.8244 - val_mae: 2.2712 - val_mse: 10.8244\n",
"Epoch 71/100\n",
"354/354 [==============================] - 0s 265us/sample - loss: 6.5987 - mae: 1.7189 - mse: 6.5987 - val_loss: 11.3479 - val_mae: 2.2654 - val_mse: 11.3479\n",
"Epoch 72/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 6.6659 - mae: 1.7367 - mse: 6.6659 - val_loss: 13.3760 - val_mae: 2.5578 - val_mse: 13.3760\n",
"Epoch 73/100\n",
"354/354 [==============================] - 0s 267us/sample - loss: 6.7449 - mae: 1.7191 - mse: 6.7449 - val_loss: 10.6301 - val_mae: 2.2385 - val_mse: 10.6301\n",
"Epoch 74/100\n",
"354/354 [==============================] - 0s 269us/sample - loss: 6.4514 - mae: 1.7079 - mse: 6.4514 - val_loss: 11.2719 - val_mae: 2.4001 - val_mse: 11.2719\n",
"Epoch 75/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 6.4869 - mae: 1.6759 - mse: 6.4869 - val_loss: 12.1220 - val_mae: 2.3984 - val_mse: 12.1220\n",
"Epoch 76/100\n",
"354/354 [==============================] - 0s 274us/sample - loss: 6.5897 - mae: 1.6894 - mse: 6.5897 - val_loss: 11.1440 - val_mae: 2.2544 - val_mse: 11.1440\n",
"Epoch 77/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 6.4586 - mae: 1.6888 - mse: 6.4586 - val_loss: 12.3773 - val_mae: 2.3903 - val_mse: 12.3773\n",
"Epoch 78/100\n",
"354/354 [==============================] - 0s 273us/sample - loss: 6.4341 - mae: 1.7145 - mse: 6.4341 - val_loss: 11.4619 - val_mae: 2.3918 - val_mse: 11.4619\n",
"Epoch 79/100\n",
"354/354 [==============================] - 0s 274us/sample - loss: 6.3822 - mae: 1.6900 - mse: 6.3822 - val_loss: 12.2106 - val_mae: 2.3721 - val_mse: 12.2106\n",
"Epoch 80/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 6.1874 - mae: 1.6462 - mse: 6.1874 - val_loss: 10.5171 - val_mae: 2.2212 - val_mse: 10.5171\n",
"Epoch 81/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 6.2406 - mae: 1.6560 - mse: 6.2406 - val_loss: 11.1654 - val_mae: 2.2688 - val_mse: 11.1654\n",
"Epoch 82/100\n",
"354/354 [==============================] - 0s 277us/sample - loss: 6.1431 - mae: 1.6326 - mse: 6.1431 - val_loss: 10.5330 - val_mae: 2.2102 - val_mse: 10.5330\n",
"Epoch 83/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 6.0614 - mae: 1.6425 - mse: 6.0614 - val_loss: 11.1468 - val_mae: 2.3205 - val_mse: 11.1468\n",
"Epoch 84/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 5.9098 - mae: 1.6575 - mse: 5.9098 - val_loss: 10.3323 - val_mae: 2.2447 - val_mse: 10.3323\n",
"Epoch 85/100\n",
"354/354 [==============================] - 0s 262us/sample - loss: 5.8809 - mae: 1.6603 - mse: 5.8809 - val_loss: 12.0661 - val_mae: 2.3902 - val_mse: 12.0661\n",
"Epoch 86/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 5.9024 - mae: 1.6258 - mse: 5.9024 - val_loss: 10.2668 - val_mae: 2.2403 - val_mse: 10.2668\n",
"Epoch 87/100\n",
"354/354 [==============================] - 0s 267us/sample - loss: 5.9340 - mae: 1.6283 - mse: 5.9340 - val_loss: 10.3232 - val_mae: 2.2364 - val_mse: 10.3232\n",
"Epoch 88/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 5.7561 - mae: 1.6597 - mse: 5.7561 - val_loss: 11.0334 - val_mae: 2.3103 - val_mse: 11.0334\n",
"Epoch 89/100\n",
"354/354 [==============================] - 0s 278us/sample - loss: 5.7652 - mae: 1.6276 - mse: 5.7652 - val_loss: 10.5884 - val_mae: 2.2664 - val_mse: 10.5884\n",
"Epoch 90/100\n",
"354/354 [==============================] - 0s 265us/sample - loss: 5.7276 - mae: 1.6284 - mse: 5.7276 - val_loss: 10.8470 - val_mae: 2.3210 - val_mse: 10.8470\n",
"Epoch 91/100\n",
"354/354 [==============================] - 0s 264us/sample - loss: 5.6704 - mae: 1.5802 - mse: 5.6704 - val_loss: 10.5757 - val_mae: 2.2699 - val_mse: 10.5757\n",
"Epoch 92/100\n",
"354/354 [==============================] - 0s 277us/sample - loss: 5.6099 - mae: 1.5911 - mse: 5.6099 - val_loss: 12.4091 - val_mae: 2.4405 - val_mse: 12.4091\n",
"Epoch 93/100\n",
"354/354 [==============================] - 0s 265us/sample - loss: 5.4673 - mae: 1.5880 - mse: 5.4673 - val_loss: 9.5978 - val_mae: 2.1851 - val_mse: 9.5978\n",
"Epoch 94/100\n",
"354/354 [==============================] - 0s 267us/sample - loss: 5.3195 - mae: 1.5474 - mse: 5.3195 - val_loss: 11.3653 - val_mae: 2.3870 - val_mse: 11.3653\n",
"Epoch 95/100\n",
"354/354 [==============================] - 0s 271us/sample - loss: 5.2298 - mae: 1.5350 - mse: 5.2298 - val_loss: 11.4847 - val_mae: 2.4010 - val_mse: 11.4847\n",
"Epoch 96/100\n",
"354/354 [==============================] - 0s 270us/sample - loss: 5.3535 - mae: 1.5478 - mse: 5.3535 - val_loss: 11.1203 - val_mae: 2.3284 - val_mse: 11.1203\n",
"Epoch 97/100\n",
"354/354 [==============================] - 0s 269us/sample - loss: 5.2177 - mae: 1.5622 - mse: 5.2177 - val_loss: 11.1940 - val_mae: 2.3487 - val_mse: 11.1940\n",
"Epoch 98/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 5.3019 - mae: 1.5416 - mse: 5.3019 - val_loss: 10.6022 - val_mae: 2.2977 - val_mse: 10.6022\n",
"Epoch 99/100\n",
"354/354 [==============================] - 0s 272us/sample - loss: 5.0745 - mae: 1.5318 - mse: 5.0745 - val_loss: 9.1810 - val_mae: 2.1663 - val_mse: 9.1810\n",
"Epoch 100/100\n",
"354/354 [==============================] - 0s 276us/sample - loss: 4.9694 - mae: 1.5170 - mse: 4.9694 - val_loss: 12.8575 - val_mae: 2.7038 - val_mse: 12.8575\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": [
"## Step 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 : 12.8575\n",
"x_test / mae : 2.7038\n",
"x_test / mse : 12.8575\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>15.538406</td>\n",
" <td>2.299461</td>\n",
" <td>15.538407</td>\n",
" <td>19.231753</td>\n",
" <td>2.775025</td>\n",
" <td>19.231753</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>44.914352</td>\n",
" <td>2.003585</td>\n",
" <td>44.914356</td>\n",
" <td>37.177478</td>\n",
" <td>1.657639</td>\n",
" <td>37.177476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>4.969428</td>\n",
" <td>1.516992</td>\n",
" <td>4.969429</td>\n",
" <td>9.180952</td>\n",
" <td>2.166264</td>\n",
" <td>9.180954</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>6.479793</td>\n",
" <td>1.693636</td>\n",
" <td>6.479793</td>\n",
" <td>11.448713</td>\n",
" <td>2.328062</td>\n",
" <td>11.448714</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>8.136086</td>\n",
" <td>1.885107</td>\n",
" <td>8.136086</td>\n",
" <td>12.954600</td>\n",
" <td>2.421493</td>\n",
" <td>12.954600</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>10.545197</td>\n",
" <td>2.200065</td>\n",
" <td>10.545198</td>\n",
" <td>15.315346</td>\n",
" <td>2.648960</td>\n",
" <td>15.315347</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>418.843522</td>\n",
" <td>18.692585</td>\n",
" <td>418.843567</td>\n",
" <td>363.624954</td>\n",
" <td>17.071243</td>\n",
" <td>363.624939</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 15.538406 2.299461 15.538407 19.231753 2.775025 19.231753\n",
"std 44.914352 2.003585 44.914356 37.177478 1.657639 37.177476\n",
"min 4.969428 1.516992 4.969429 9.180952 2.166264 9.180954\n",
"25% 6.479793 1.693636 6.479793 11.448713 2.328062 11.448714\n",
"50% 8.136086 1.885107 8.136086 12.954600 2.421493 12.954600\n",
"75% 10.545197 2.200065 10.545198 15.315346 2.648960 15.315347\n",
"max 418.843522 18.692585 418.843567 363.624954 17.071243 363.624939"
]
},
"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 ) : 2.1663\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 : 8.13 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
}