{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
"\n",
"\n",
"# <!-- TITLE --> [BHP1] - Regression with a Dense Network (DNN)\n",
"<!-- DESC --> A Simple regression with a Dense Neural Network (DNN) - BHPD dataset\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
"## Objectives :\n",
" - Predicts **housing prices** from a set of house features. \n",
" - Understanding the **principle** and the **architecture** of a regression with a **dense neural network** \n",
"\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 : 0.4.2\n",
"Run time : Wednesday 26 February 2020, 18:59:13\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",
"sys.path.append('..')\n",
"import fidle.pwk as ooo\n",
"\n",
"ooo.init()"
]
},
{
"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_b264cb30_58c1_11ea_b1f5_11dce601eea1\" ><caption>Few lines of the dataset :</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> <th class=\"col_heading level0 col13\" >medv</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_b264cb30_58c1_11ea_b1f5_11dce601eea1row4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f5d03dbae10>"
]
},
"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}\").set_caption(\"Few lines of the dataset :\"))\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",
"The dataset is **shuffled** and shared between **learning** and **testing**. \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": [
"# ---- Suffle and 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_b26d1074_58c1_11ea_b1f5_11dce601eea1\" ><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_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col0\" class=\"data row1 col0\" >3.67</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col1\" class=\"data row1 col1\" >9.50</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col2\" class=\"data row1 col2\" >11.09</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col3\" class=\"data row1 col3\" >0.07</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col4\" class=\"data row1 col4\" >0.56</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col5\" class=\"data row1 col5\" >6.28</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col6\" class=\"data row1 col6\" >69.05</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col7\" class=\"data row1 col7\" >3.70</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col8\" class=\"data row1 col8\" >9.73</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col9\" class=\"data row1 col9\" >409.71</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col10\" class=\"data row1 col10\" >18.58</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col11\" class=\"data row1 col11\" >360.94</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row1_col12\" class=\"data row1 col12\" >12.52</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col0\" class=\"data row2 col0\" >8.60</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col1\" class=\"data row2 col1\" >20.88</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col2\" class=\"data row2 col2\" >6.74</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col3\" class=\"data row2 col3\" >0.26</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col4\" class=\"data row2 col4\" >0.11</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col5\" class=\"data row2 col5\" >0.71</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col6\" class=\"data row2 col6\" >27.43</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col7\" class=\"data row2 col7\" >2.04</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col8\" class=\"data row2 col8\" >8.77</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col9\" class=\"data row2 col9\" >170.77</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col10\" class=\"data row2 col10\" >2.09</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col11\" class=\"data row2 col11\" >85.01</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row2_col12\" class=\"data row2 col12\" >7.06</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col2\" class=\"data row3 col2\" >0.46</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col5\" class=\"data row3 col5\" >3.56</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col6\" class=\"data row3 col6\" >2.90</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col7\" class=\"data row3 col7\" >1.13</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col9\" class=\"data row3 col9\" >187.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col10\" class=\"data row3 col10\" >13.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col11\" class=\"data row3 col11\" >0.32</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row3_col12\" class=\"data row3 col12\" >1.92</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col0\" class=\"data row4 col0\" >0.09</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col2\" class=\"data row4 col2\" >5.19</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col5\" class=\"data row4 col5\" >5.90</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col6\" class=\"data row4 col6\" >46.52</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col7\" class=\"data row4 col7\" >2.11</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col9\" class=\"data row4 col9\" >277.50</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col10\" class=\"data row4 col10\" >17.40</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col11\" class=\"data row4 col11\" >376.71</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row4_col12\" class=\"data row4 col12\" >7.21</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col0\" class=\"data row5 col0\" >0.27</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col2\" class=\"data row5 col2\" >9.12</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col4\" class=\"data row5 col4\" >0.54</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col5\" class=\"data row5 col5\" >6.22</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col6\" class=\"data row5 col6\" >76.85</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col7\" class=\"data row5 col7\" >3.17</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col9\" class=\"data row5 col9\" >330.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col10\" class=\"data row5 col10\" >19.10</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col11\" class=\"data row5 col11\" >392.08</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row5_col12\" class=\"data row5 col12\" >11.17</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col0\" class=\"data row6 col0\" >3.69</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col1\" class=\"data row6 col1\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col5\" class=\"data row6 col5\" >6.59</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col6\" class=\"data row6 col6\" >93.55</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col7\" class=\"data row6 col7\" >4.81</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col8\" class=\"data row6 col8\" >24.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col9\" class=\"data row6 col9\" >666.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col11\" class=\"data row6 col11\" >396.90</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row6_col12\" class=\"data row6 col12\" >16.32</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col0\" class=\"data row7 col0\" >88.98</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col1\" class=\"data row7 col1\" >100.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col5\" class=\"data row7 col5\" >8.78</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col7\" class=\"data row7 col7\" >12.13</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_b26d1074_58c1_11ea_b1f5_11dce601eea1row7_col12\" class=\"data row7 col12\" >34.77</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f5d03c07290>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1\" ><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_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col3\" class=\"data row1 col3\" >-0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col6\" class=\"data row1 col6\" >-0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col8\" class=\"data row1 col8\" >-0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col9\" class=\"data row1 col9\" >-0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col11\" class=\"data row1 col11\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row1_col12\" class=\"data row1 col12\" >0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col0\" class=\"data row3 col0\" >-0.43</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col1\" class=\"data row3 col1\" >-0.46</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col2\" class=\"data row3 col2\" >-1.58</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col3\" class=\"data row3 col3\" >-0.28</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col4\" class=\"data row3 col4\" >-1.52</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col5\" class=\"data row3 col5\" >-3.84</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col6\" class=\"data row3 col6\" >-2.41</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col7\" class=\"data row3 col7\" >-1.26</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col8\" class=\"data row3 col8\" >-1.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col9\" class=\"data row3 col9\" >-1.30</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col10\" class=\"data row3 col10\" >-2.66</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col11\" class=\"data row3 col11\" >-4.24</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row3_col12\" class=\"data row3 col12\" >-1.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col0\" class=\"data row4 col0\" >-0.42</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col1\" class=\"data row4 col1\" >-0.46</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col2\" class=\"data row4 col2\" >-0.88</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col3\" class=\"data row4 col3\" >-0.28</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col4\" class=\"data row4 col4\" >-0.88</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col5\" class=\"data row4 col5\" >-0.54</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col6\" class=\"data row4 col6\" >-0.82</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col7\" class=\"data row4 col7\" >-0.78</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col8\" class=\"data row4 col8\" >-0.65</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col9\" class=\"data row4 col9\" >-0.77</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col10\" class=\"data row4 col10\" >-0.56</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col11\" class=\"data row4 col11\" >0.19</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row4_col12\" class=\"data row4 col12\" >-0.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col0\" class=\"data row5 col0\" >-0.40</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col1\" class=\"data row5 col1\" >-0.46</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col2\" class=\"data row5 col2\" >-0.29</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col3\" class=\"data row5 col3\" >-0.28</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col4\" class=\"data row5 col4\" >-0.17</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col5\" class=\"data row5 col5\" >-0.09</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col6\" class=\"data row5 col6\" >0.28</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col7\" class=\"data row5 col7\" >-0.26</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col8\" class=\"data row5 col8\" >-0.54</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col9\" class=\"data row5 col9\" >-0.47</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col10\" class=\"data row5 col10\" >0.25</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col11\" class=\"data row5 col11\" >0.37</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row5_col12\" class=\"data row5 col12\" >-0.19</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col0\" class=\"data row6 col0\" >0.00</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col1\" class=\"data row6 col1\" >-0.46</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col2\" class=\"data row6 col2\" >1.04</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col3\" class=\"data row6 col3\" >-0.28</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col4\" class=\"data row6 col4\" >0.60</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col5\" class=\"data row6 col5\" >0.44</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col6\" class=\"data row6 col6\" >0.89</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col7\" class=\"data row6 col7\" >0.54</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col8\" class=\"data row6 col8\" >1.63</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col9\" class=\"data row6 col9\" >1.50</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col10\" class=\"data row6 col10\" >0.78</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col11\" class=\"data row6 col11\" >0.42</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row6_col12\" class=\"data row6 col12\" >0.54</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col0\" class=\"data row7 col0\" >9.92</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col1\" class=\"data row7 col1\" >4.33</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col2\" class=\"data row7 col2\" >2.47</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col3\" class=\"data row7 col3\" >3.55</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col4\" class=\"data row7 col4\" >2.79</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col5\" class=\"data row7 col5\" >3.53</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col6\" class=\"data row7 col6\" >1.13</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col7\" class=\"data row7 col7\" >4.13</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col8\" class=\"data row7 col8\" >1.63</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col9\" class=\"data row7 col9\" >1.76</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col10\" class=\"data row7 col10\" >1.64</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col11\" class=\"data row7 col11\" >0.42</td>\n",
" <td id=\"T_b273d60c_58c1_11ea_b1f5_11dce601eea1row7_col12\" class=\"data row7 col12\" >3.15</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f5d03a75a50>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1\" ><caption>Few lines of the dataset :</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_b27479ea_58c1_11ea_b1f5_11dce601eea1level0_row0\" class=\"row_heading level0 row0\" >437</th>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col0\" class=\"data row0 col0\" >1.34</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col1\" class=\"data row0 col1\" >-0.46</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col2\" class=\"data row0 col2\" >1.04</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col3\" class=\"data row0 col3\" >-0.28</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col4\" class=\"data row0 col4\" >1.63</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col5\" class=\"data row0 col5\" >-0.18</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col6\" class=\"data row0 col6\" >1.13</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col7\" class=\"data row0 col7\" >-0.88</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col8\" class=\"data row0 col8\" >1.63</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col9\" class=\"data row0 col9\" >1.50</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col10\" class=\"data row0 col10\" >0.78</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col11\" class=\"data row0 col11\" >-4.14</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row0_col12\" class=\"data row0 col12\" >1.97</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1level0_row1\" class=\"row_heading level0 row1\" >163</th>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col0\" class=\"data row1 col0\" >-0.25</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col1\" class=\"data row1 col1\" >-0.46</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col2\" class=\"data row1 col2\" >1.26</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col3\" class=\"data row1 col3\" >3.55</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col4\" class=\"data row1 col4\" >0.43</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col5\" class=\"data row1 col5\" >2.96</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col6\" class=\"data row1 col6\" >0.91</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col7\" class=\"data row1 col7\" >-0.76</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col8\" class=\"data row1 col8\" >-0.54</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col9\" class=\"data row1 col9\" >-0.04</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col10\" class=\"data row1 col10\" >-1.85</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col11\" class=\"data row1 col11\" >0.32</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row1_col12\" class=\"data row1 col12\" >-1.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1level0_row2\" class=\"row_heading level0 row2\" >438</th>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col0\" class=\"data row2 col0\" >1.16</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col1\" class=\"data row2 col1\" >-0.46</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col2\" class=\"data row2 col2\" >1.04</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col3\" class=\"data row2 col3\" >-0.28</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col4\" class=\"data row2 col4\" >1.63</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col5\" class=\"data row2 col5\" >-0.49</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col6\" class=\"data row2 col6\" >0.69</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col7\" class=\"data row2 col7\" >-0.92</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col8\" class=\"data row2 col8\" >1.63</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col9\" class=\"data row2 col9\" >1.50</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col10\" class=\"data row2 col10\" >0.78</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col11\" class=\"data row2 col11\" >-3.43</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row2_col12\" class=\"data row2 col12\" >3.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1level0_row3\" class=\"row_heading level0 row3\" >228</th>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col0\" class=\"data row3 col0\" >-0.39</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col1\" class=\"data row3 col1\" >-0.46</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col2\" class=\"data row3 col2\" >-0.73</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col3\" class=\"data row3 col3\" >-0.28</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col4\" class=\"data row3 col4\" >-0.47</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col5\" class=\"data row3 col5\" >1.98</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col6\" class=\"data row3 col6\" >-1.90</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col7\" class=\"data row3 col7\" >-0.16</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col8\" class=\"data row3 col8\" >-0.20</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col9\" class=\"data row3 col9\" >-0.60</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col10\" class=\"data row3 col10\" >-0.56</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col11\" class=\"data row3 col11\" >0.19</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row3_col12\" class=\"data row3 col12\" >-1.22</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1level0_row4\" class=\"row_heading level0 row4\" >58</th>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col0\" class=\"data row4 col0\" >-0.41</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col1\" class=\"data row4 col1\" >0.74</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col2\" class=\"data row4 col2\" >-0.88</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col3\" class=\"data row4 col3\" >-0.28</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col4\" class=\"data row4 col4\" >-0.92</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col5\" class=\"data row4 col5\" >-0.19</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col6\" class=\"data row4 col6\" >-1.45</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col7\" class=\"data row4 col7\" >2.02</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col8\" class=\"data row4 col8\" >-0.20</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col9\" class=\"data row4 col9\" >-0.74</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col10\" class=\"data row4 col10\" >0.54</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col11\" class=\"data row4 col11\" >0.35</td>\n",
" <td id=\"T_b27479ea_58c1_11ea_b1f5_11dce601eea1row4_col12\" class=\"data row4 col12\" >-0.80</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f5d03a88ad0>"
]
},
"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",
"display(x_train.head(5).style.format(\"{0:.2f}\").set_caption(\"Few lines of the dataset :\"))\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 2ms/sample - loss: 484.1251 - mae: 20.0241 - mse: 484.1250 - val_loss: 336.1387 - val_mae: 16.2959 - val_mse: 336.1387\n",
"Epoch 2/100\n",
"354/354 [==============================] - 0s 174us/sample - loss: 266.9655 - mae: 14.1105 - mse: 266.9655 - val_loss: 115.0929 - val_mae: 8.7476 - val_mse: 115.0929\n",
"Epoch 3/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 96.2638 - mae: 7.6200 - mse: 96.2637 - val_loss: 49.2646 - val_mae: 5.6468 - val_mse: 49.2646\n",
"Epoch 4/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 48.7173 - mae: 5.2081 - mse: 48.7173 - val_loss: 29.1408 - val_mae: 4.2536 - val_mse: 29.1408\n",
"Epoch 5/100\n",
"354/354 [==============================] - 0s 158us/sample - loss: 34.5634 - mae: 4.2277 - mse: 34.5634 - val_loss: 19.6660 - val_mae: 3.4774 - val_mse: 19.6660\n",
"Epoch 6/100\n",
"354/354 [==============================] - 0s 159us/sample - loss: 27.4147 - mae: 3.6886 - mse: 27.4147 - val_loss: 15.2821 - val_mae: 3.0972 - val_mse: 15.2821\n",
"Epoch 7/100\n",
"354/354 [==============================] - 0s 174us/sample - loss: 23.4729 - mae: 3.3722 - mse: 23.4729 - val_loss: 14.0564 - val_mae: 3.0557 - val_mse: 14.0564\n",
"Epoch 8/100\n",
"354/354 [==============================] - 0s 173us/sample - loss: 21.2571 - mae: 3.2020 - mse: 21.2571 - val_loss: 11.8761 - val_mae: 2.7355 - val_mse: 11.8761\n",
"Epoch 9/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 19.0063 - mae: 2.9976 - mse: 19.0063 - val_loss: 10.9934 - val_mae: 2.5965 - val_mse: 10.9934\n",
"Epoch 10/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 17.4507 - mae: 2.8840 - mse: 17.4507 - val_loss: 11.0103 - val_mae: 2.6076 - val_mse: 11.0103\n",
"Epoch 11/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 16.6394 - mae: 2.7956 - mse: 16.6394 - val_loss: 11.3581 - val_mae: 2.6628 - val_mse: 11.3581\n",
"Epoch 12/100\n",
"354/354 [==============================] - 0s 170us/sample - loss: 15.9572 - mae: 2.7332 - mse: 15.9572 - val_loss: 10.0877 - val_mae: 2.4737 - val_mse: 10.0877\n",
"Epoch 13/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 15.1041 - mae: 2.6694 - mse: 15.1041 - val_loss: 9.8434 - val_mae: 2.4656 - val_mse: 9.8434\n",
"Epoch 14/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 14.6978 - mae: 2.6086 - mse: 14.6978 - val_loss: 10.1135 - val_mae: 2.5264 - val_mse: 10.1135\n",
"Epoch 15/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 14.0091 - mae: 2.5725 - mse: 14.0091 - val_loss: 10.3903 - val_mae: 2.5780 - val_mse: 10.3903\n",
"Epoch 16/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 13.4616 - mae: 2.5053 - mse: 13.4616 - val_loss: 10.3176 - val_mae: 2.4783 - val_mse: 10.3176\n",
"Epoch 17/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 13.5475 - mae: 2.5085 - mse: 13.5475 - val_loss: 9.2082 - val_mae: 2.3906 - val_mse: 9.2082\n",
"Epoch 18/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 12.8601 - mae: 2.4609 - mse: 12.8601 - val_loss: 9.4860 - val_mae: 2.4163 - val_mse: 9.4860\n",
"Epoch 19/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 12.5792 - mae: 2.4255 - mse: 12.5792 - val_loss: 9.0692 - val_mae: 2.3991 - val_mse: 9.0692\n",
"Epoch 20/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 12.0823 - mae: 2.3706 - mse: 12.0823 - val_loss: 10.3373 - val_mae: 2.4694 - val_mse: 10.3373\n",
"Epoch 21/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 12.1221 - mae: 2.4267 - mse: 12.1221 - val_loss: 11.3902 - val_mae: 2.6939 - val_mse: 11.3902\n",
"Epoch 22/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 12.0942 - mae: 2.4209 - mse: 12.0942 - val_loss: 9.7398 - val_mae: 2.5079 - val_mse: 9.7398\n",
"Epoch 23/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 11.9156 - mae: 2.3525 - mse: 11.9156 - val_loss: 9.0202 - val_mae: 2.3673 - val_mse: 9.0202\n",
"Epoch 24/100\n",
"354/354 [==============================] - 0s 170us/sample - loss: 11.5616 - mae: 2.3156 - mse: 11.5616 - val_loss: 9.2420 - val_mae: 2.4131 - val_mse: 9.2420\n",
"Epoch 25/100\n",
"354/354 [==============================] - 0s 170us/sample - loss: 11.4663 - mae: 2.3318 - mse: 11.4663 - val_loss: 8.5933 - val_mae: 2.3019 - val_mse: 8.5933\n",
"Epoch 26/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 11.1692 - mae: 2.3122 - mse: 11.1692 - val_loss: 9.0358 - val_mae: 2.3782 - val_mse: 9.0358\n",
"Epoch 27/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 10.8542 - mae: 2.2985 - mse: 10.8542 - val_loss: 10.3299 - val_mae: 2.5953 - val_mse: 10.3299\n",
"Epoch 28/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 11.2191 - mae: 2.3130 - mse: 11.2191 - val_loss: 9.6247 - val_mae: 2.5094 - val_mse: 9.6247\n",
"Epoch 29/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 10.6717 - mae: 2.2560 - mse: 10.6717 - val_loss: 8.8072 - val_mae: 2.3290 - val_mse: 8.8072\n",
"Epoch 30/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 10.4437 - mae: 2.2546 - mse: 10.4437 - val_loss: 9.2847 - val_mae: 2.4407 - val_mse: 9.2847\n",
"Epoch 31/100\n",
"354/354 [==============================] - 0s 173us/sample - loss: 10.4666 - mae: 2.2249 - mse: 10.4666 - val_loss: 8.6262 - val_mae: 2.2938 - val_mse: 8.6262\n",
"Epoch 32/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 10.3629 - mae: 2.1890 - mse: 10.3629 - val_loss: 8.9607 - val_mae: 2.3288 - val_mse: 8.9607\n",
"Epoch 33/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 10.1434 - mae: 2.1984 - mse: 10.1434 - val_loss: 8.6240 - val_mae: 2.2927 - val_mse: 8.6240\n",
"Epoch 34/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 10.2132 - mae: 2.2037 - mse: 10.2132 - val_loss: 8.4775 - val_mae: 2.2752 - val_mse: 8.4775\n",
"Epoch 35/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 9.8354 - mae: 2.1641 - mse: 9.8354 - val_loss: 9.6371 - val_mae: 2.4595 - val_mse: 9.6371\n",
"Epoch 36/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 9.6767 - mae: 2.1508 - mse: 9.6767 - val_loss: 8.4953 - val_mae: 2.2750 - val_mse: 8.4953\n",
"Epoch 37/100\n",
"354/354 [==============================] - 0s 180us/sample - loss: 9.7576 - mae: 2.1357 - mse: 9.7576 - val_loss: 9.7324 - val_mae: 2.4832 - val_mse: 9.7324\n",
"Epoch 38/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 9.5451 - mae: 2.1452 - mse: 9.5451 - val_loss: 8.8310 - val_mae: 2.3376 - val_mse: 8.8310\n",
"Epoch 39/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 9.3114 - mae: 2.1538 - mse: 9.3114 - val_loss: 8.2856 - val_mae: 2.2356 - val_mse: 8.2856\n",
"Epoch 40/100\n",
"354/354 [==============================] - 0s 172us/sample - loss: 9.2859 - mae: 2.1057 - mse: 9.2859 - val_loss: 8.4760 - val_mae: 2.2819 - val_mse: 8.4760\n",
"Epoch 41/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 9.2881 - mae: 2.0987 - mse: 9.2881 - val_loss: 8.6341 - val_mae: 2.3273 - val_mse: 8.6341\n",
"Epoch 42/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 9.3559 - mae: 2.0886 - mse: 9.3558 - val_loss: 8.3617 - val_mae: 2.2688 - val_mse: 8.3617\n",
"Epoch 43/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 8.9381 - mae: 2.0579 - mse: 8.9381 - val_loss: 8.6691 - val_mae: 2.3448 - val_mse: 8.6691\n",
"Epoch 44/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 9.0677 - mae: 2.0760 - mse: 9.0677 - val_loss: 8.2238 - val_mae: 2.2527 - val_mse: 8.2238\n",
"Epoch 45/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 8.8264 - mae: 2.0666 - mse: 8.8264 - val_loss: 9.2551 - val_mae: 2.4063 - val_mse: 9.2551\n",
"Epoch 46/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 8.8939 - mae: 2.0745 - mse: 8.8939 - val_loss: 8.2119 - val_mae: 2.2392 - val_mse: 8.2119\n",
"Epoch 47/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 8.6137 - mae: 2.0361 - mse: 8.6137 - val_loss: 8.3562 - val_mae: 2.2279 - val_mse: 8.3562\n",
"Epoch 48/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 8.4736 - mae: 2.0236 - mse: 8.4736 - val_loss: 8.8436 - val_mae: 2.3515 - val_mse: 8.8436\n",
"Epoch 49/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 8.4834 - mae: 2.0319 - mse: 8.4834 - val_loss: 8.8539 - val_mae: 2.3370 - val_mse: 8.8539\n",
"Epoch 50/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 8.3244 - mae: 2.0070 - mse: 8.3244 - val_loss: 8.7671 - val_mae: 2.3284 - val_mse: 8.7671\n",
"Epoch 51/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 8.4132 - mae: 1.9969 - mse: 8.4132 - val_loss: 9.4366 - val_mae: 2.4190 - val_mse: 9.4366\n",
"Epoch 52/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 8.1615 - mae: 1.9770 - mse: 8.1615 - val_loss: 8.3043 - val_mae: 2.2279 - val_mse: 8.3043\n",
"Epoch 53/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 8.1649 - mae: 1.9975 - mse: 8.1649 - val_loss: 8.0006 - val_mae: 2.2026 - val_mse: 8.0006\n",
"Epoch 54/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 8.0448 - mae: 1.9872 - mse: 8.0448 - val_loss: 7.9690 - val_mae: 2.1947 - val_mse: 7.9690\n",
"Epoch 55/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 7.7326 - mae: 1.9080 - mse: 7.7326 - val_loss: 8.3295 - val_mae: 2.2204 - val_mse: 8.3295\n",
"Epoch 56/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 7.9522 - mae: 1.9201 - mse: 7.9522 - val_loss: 9.0692 - val_mae: 2.3496 - val_mse: 9.0692\n",
"Epoch 57/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 7.7350 - mae: 1.9497 - mse: 7.7350 - val_loss: 8.0150 - val_mae: 2.1911 - val_mse: 8.0150\n",
"Epoch 58/100\n",
"354/354 [==============================] - 0s 175us/sample - loss: 7.7322 - mae: 1.9231 - mse: 7.7322 - val_loss: 8.2910 - val_mae: 2.2175 - val_mse: 8.2910\n",
"Epoch 59/100\n",
"354/354 [==============================] - 0s 172us/sample - loss: 7.2398 - mae: 1.8491 - mse: 7.2398 - val_loss: 8.3501 - val_mae: 2.2351 - val_mse: 8.3501\n",
"Epoch 60/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 7.5678 - mae: 1.9134 - mse: 7.5678 - val_loss: 8.2245 - val_mae: 2.2331 - val_mse: 8.2245\n",
"Epoch 61/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 7.6342 - mae: 1.8999 - mse: 7.6342 - val_loss: 7.8723 - val_mae: 2.1654 - val_mse: 7.8723\n",
"Epoch 62/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 7.4963 - mae: 1.8860 - mse: 7.4963 - val_loss: 10.4746 - val_mae: 2.5301 - val_mse: 10.4746\n",
"Epoch 63/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 7.3665 - mae: 1.8960 - mse: 7.3665 - val_loss: 8.6150 - val_mae: 2.2693 - val_mse: 8.6150\n",
"Epoch 64/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 7.2980 - mae: 1.8948 - mse: 7.2980 - val_loss: 7.9022 - val_mae: 2.1722 - val_mse: 7.9022\n",
"Epoch 65/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 7.1944 - mae: 1.8662 - mse: 7.1944 - val_loss: 8.0582 - val_mae: 2.1951 - val_mse: 8.0582\n",
"Epoch 66/100\n",
"354/354 [==============================] - 0s 168us/sample - loss: 7.3373 - mae: 1.8855 - mse: 7.3373 - val_loss: 9.2201 - val_mae: 2.3749 - val_mse: 9.2201\n",
"Epoch 67/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.9805 - mae: 1.8481 - mse: 6.9805 - val_loss: 8.1570 - val_mae: 2.2094 - val_mse: 8.1570\n",
"Epoch 68/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 7.2658 - mae: 1.8414 - mse: 7.2658 - val_loss: 8.0702 - val_mae: 2.2033 - val_mse: 8.0702\n",
"Epoch 69/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 6.9262 - mae: 1.8546 - mse: 6.9262 - val_loss: 7.7649 - val_mae: 2.1500 - val_mse: 7.7649\n",
"Epoch 70/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 6.9447 - mae: 1.8298 - mse: 6.9447 - val_loss: 7.6659 - val_mae: 2.1385 - val_mse: 7.6659\n",
"Epoch 71/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 6.7163 - mae: 1.8046 - mse: 6.7163 - val_loss: 7.7355 - val_mae: 2.1346 - val_mse: 7.7355\n",
"Epoch 72/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 6.7114 - mae: 1.8155 - mse: 6.7114 - val_loss: 9.6016 - val_mae: 2.3953 - val_mse: 9.6016\n",
"Epoch 73/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.5319 - mae: 1.8392 - mse: 6.5319 - val_loss: 7.7355 - val_mae: 2.1233 - val_mse: 7.7355\n",
"Epoch 74/100\n",
"354/354 [==============================] - 0s 159us/sample - loss: 6.6211 - mae: 1.7914 - mse: 6.6211 - val_loss: 7.6516 - val_mae: 2.1122 - val_mse: 7.6516\n",
"Epoch 75/100\n",
"354/354 [==============================] - 0s 179us/sample - loss: 6.4513 - mae: 1.7749 - mse: 6.4513 - val_loss: 8.9891 - val_mae: 2.3194 - val_mse: 8.9891\n",
"Epoch 76/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 6.4155 - mae: 1.7780 - mse: 6.4155 - val_loss: 7.7146 - val_mae: 2.1223 - val_mse: 7.7146\n",
"Epoch 77/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 6.3207 - mae: 1.7432 - mse: 6.3207 - val_loss: 9.0356 - val_mae: 2.3147 - val_mse: 9.0356\n",
"Epoch 78/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 6.4550 - mae: 1.7727 - mse: 6.4550 - val_loss: 8.8363 - val_mae: 2.2857 - val_mse: 8.8363\n",
"Epoch 79/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 6.0707 - mae: 1.7117 - mse: 6.0707 - val_loss: 9.5024 - val_mae: 2.3944 - val_mse: 9.5024\n",
"Epoch 80/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 6.3308 - mae: 1.7601 - mse: 6.3308 - val_loss: 7.7687 - val_mae: 2.1143 - val_mse: 7.7687\n",
"Epoch 81/100\n",
"354/354 [==============================] - 0s 160us/sample - loss: 6.2252 - mae: 1.7075 - mse: 6.2252 - val_loss: 8.7019 - val_mae: 2.2754 - val_mse: 8.7019\n",
"Epoch 82/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 5.9566 - mae: 1.7185 - mse: 5.9566 - val_loss: 7.8045 - val_mae: 2.1393 - val_mse: 7.8045\n",
"Epoch 83/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 6.2495 - mae: 1.7614 - mse: 6.2495 - val_loss: 9.1345 - val_mae: 2.3059 - val_mse: 9.1345\n",
"Epoch 84/100\n",
"354/354 [==============================] - 0s 189us/sample - loss: 5.8219 - mae: 1.7185 - mse: 5.8219 - val_loss: 8.5579 - val_mae: 2.2543 - val_mse: 8.5579\n",
"Epoch 85/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.1006 - mae: 1.6984 - mse: 6.1006 - val_loss: 7.9770 - val_mae: 2.1743 - val_mse: 7.9770\n",
"Epoch 86/100\n",
"354/354 [==============================] - 0s 172us/sample - loss: 5.9287 - mae: 1.6959 - mse: 5.9287 - val_loss: 8.0875 - val_mae: 2.1725 - val_mse: 8.0875\n",
"Epoch 87/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 5.8128 - mae: 1.7131 - mse: 5.8128 - val_loss: 7.5922 - val_mae: 2.1037 - val_mse: 7.5922\n",
"Epoch 88/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 5.7401 - mae: 1.6510 - mse: 5.7401 - val_loss: 9.2433 - val_mae: 2.3041 - val_mse: 9.2433\n",
"Epoch 89/100\n",
"354/354 [==============================] - 0s 172us/sample - loss: 5.7168 - mae: 1.6733 - mse: 5.7168 - val_loss: 7.7648 - val_mae: 2.1137 - val_mse: 7.7648\n",
"Epoch 90/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 5.5887 - mae: 1.6532 - mse: 5.5887 - val_loss: 7.5993 - val_mae: 2.0686 - val_mse: 7.5993\n",
"Epoch 91/100\n",
"354/354 [==============================] - 0s 176us/sample - loss: 5.7810 - mae: 1.6621 - mse: 5.7810 - val_loss: 7.9927 - val_mae: 2.1467 - val_mse: 7.9927\n",
"Epoch 92/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 5.4544 - mae: 1.6139 - mse: 5.4544 - val_loss: 7.4664 - val_mae: 2.0563 - val_mse: 7.4664\n",
"Epoch 93/100\n",
"354/354 [==============================] - 0s 170us/sample - loss: 5.6756 - mae: 1.6660 - mse: 5.6756 - val_loss: 8.0914 - val_mae: 2.1448 - val_mse: 8.0914\n",
"Epoch 94/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.4885 - mae: 1.6707 - mse: 5.4885 - val_loss: 8.2285 - val_mae: 2.1770 - val_mse: 8.2285\n",
"Epoch 95/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 5.4758 - mae: 1.6645 - mse: 5.4758 - val_loss: 7.8756 - val_mae: 2.1244 - val_mse: 7.8756\n",
"Epoch 96/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 5.3024 - mae: 1.5898 - mse: 5.3024 - val_loss: 8.2820 - val_mae: 2.1636 - val_mse: 8.2820\n",
"Epoch 97/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 5.3396 - mae: 1.6173 - mse: 5.3396 - val_loss: 7.8611 - val_mae: 2.1247 - val_mse: 7.8611\n",
"Epoch 98/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 5.1144 - mae: 1.5921 - mse: 5.1144 - val_loss: 7.7698 - val_mae: 2.0885 - val_mse: 7.7698\n",
"Epoch 99/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 5.4428 - mae: 1.6237 - mse: 5.4428 - val_loss: 7.6558 - val_mae: 2.0697 - val_mse: 7.6558\n",
"Epoch 100/100\n",
"354/354 [==============================] - 0s 170us/sample - loss: 5.0182 - mae: 1.5643 - mse: 5.0182 - val_loss: 8.6139 - val_mae: 2.2045 - val_mse: 8.6139\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 : 8.6139\n",
"x_test / mae : 2.2045\n",
"x_test / mse : 8.6139\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>18.096026</td>\n",
" <td>2.476698</td>\n",
" <td>18.096025</td>\n",
" <td>13.967839</td>\n",
" <td>2.586850</td>\n",
" <td>13.967839</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>54.625965</td>\n",
" <td>2.272933</td>\n",
" <td>54.625960</td>\n",
" <td>34.539291</td>\n",
" <td>1.585967</td>\n",
" <td>34.539293</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>5.018227</td>\n",
" <td>1.564279</td>\n",
" <td>5.018228</td>\n",
" <td>7.466392</td>\n",
" <td>2.056279</td>\n",
" <td>7.466392</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>6.454060</td>\n",
" <td>1.777231</td>\n",
" <td>6.454060</td>\n",
" <td>8.083174</td>\n",
" <td>2.193839</td>\n",
" <td>8.083174</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>8.368772</td>\n",
" <td>2.002227</td>\n",
" <td>8.368773</td>\n",
" <td>8.651632</td>\n",
" <td>2.297827</td>\n",
" <td>8.651632</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>11.280877</td>\n",
" <td>2.313615</td>\n",
" <td>11.280877</td>\n",
" <td>9.527210</td>\n",
" <td>2.424410</td>\n",
" <td>9.527210</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>484.125081</td>\n",
" <td>20.024147</td>\n",
" <td>484.125031</td>\n",
" <td>336.138720</td>\n",
" <td>16.295881</td>\n",
" <td>336.138733</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 18.096026 2.476698 18.096025 13.967839 2.586850 13.967839\n",
"std 54.625965 2.272933 54.625960 34.539291 1.585967 34.539293\n",
"min 5.018227 1.564279 5.018228 7.466392 2.056279 7.466392\n",
"25% 6.454060 1.777231 6.454060 8.083174 2.193839 8.083174\n",
"50% 8.368772 2.002227 8.368773 8.651632 2.297827 8.651632\n",
"75% 11.280877 2.313615 11.280877 9.527210 2.424410 9.527210\n",
"max 484.125081 20.024147 484.125031 336.138720 16.295881 336.138733"
]
},
"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 ) : 2.0563\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\n",
"The data must be normalized with the parameters (mean, std) previously used."
]
},
{
"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 : 11.38 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",
"<img width=\"80px\" src=\"../fidle/img/00-Fidle-logo-01.svg\"></img>"
]
}
],
"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": "3.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 4
}