{
"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 theses informations : \n",
"\n",
" - CRIM: This is the per capita crime rate by town\n",
" - ZN: This is the proportion of residential land zoned for lots larger than 25,000 sq.ft\n",
" - INDUS: This is the proportion of non-retail business acres per town\n",
" - CHAS: This is the Charles River dummy variable (this is equal to 1 if tract bounds river; 0 otherwise)\n",
" - NOX: This is the nitric oxides concentration (parts per 10 million)\n",
" - RM: This is the average number of rooms per dwelling\n",
" - AGE: This is the proportion of owner-occupied units built prior to 1940\n",
" - DIS: This is the weighted distances to five Boston employment centers\n",
" - RAD: This is the index of accessibility to radial highways\n",
" - TAX: This is the full-value property-tax rate per 10,000 dollars\n",
" - PTRATIO: This is the pupil-teacher ratio by town\n",
" - B: This is calculated as 1000(Bk — 0.63)^2, where Bk is the proportion of people of African American descent by town\n",
" - LSTAT: This is the percentage lower status of the population\n",
" - MEDV: This is the median value of owner-occupied homes in 1000 dollars\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",
"div.todo:before { content:url(data:image/svg+xml;base64,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);\n",
" float:left;\n",
" margin-right:20px;\n",
" margin-top:-20px;\n",
" margin-bottom:20px;\n",
"}\n",
"div.todo{\n",
" font-weight: bold;\n",
" font-size: 1.1em;\n",
" margin-top:40px;\n",
"}\n",
"div.todo ul{\n",
" margin: 0.2em;\n",
"}\n",
"div.todo li{\n",
" margin-left:60px;\n",
" margin-top:0;\n",
" margin-bottom:0;\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 : 0.5.2\n",
"Run time : Tuesday 8 September 2020, 18:58:03\n",
"TensorFlow version : 2.0.0\n",
"Keras version : 2.2.4-tf\n",
"Current place : Fidle at HOME\n",
"Dataset dir : /home/pjluc/datasets\n",
"Update keras cache : Yes\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",
"place, dataset_dir = ooo.init(places={'MyLaptop':'/path/to/datasets'})"
]
},
{
"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": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"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": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3\" ><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_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_75c26e2c_f1f4_11ea_a8d7_dbdf8a821ee3row4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f7591be21d0>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Missing Data : 0 Shape is : (506, 14)\n"
]
}
],
"source": [
"data = pd.read_csv(f'{dataset_dir}/BHPD/BostonHousing.csv', header=0)\n",
"\n",
"display(data.head(5).style.format(\"{0:.2f}\").set_caption(\"Few lines of the dataset :\"))\n",
"print('Missing Data : ',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": 4,
"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": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3\" ><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_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col0\" class=\"data row1 col0\" >3.92</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col1\" class=\"data row1 col1\" >10.43</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col2\" class=\"data row1 col2\" >11.36</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col4\" class=\"data row1 col4\" >0.56</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col5\" class=\"data row1 col5\" >6.27</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col6\" class=\"data row1 col6\" >69.73</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col7\" class=\"data row1 col7\" >3.78</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col8\" class=\"data row1 col8\" >9.67</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col9\" class=\"data row1 col9\" >410.66</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col10\" class=\"data row1 col10\" >18.49</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col11\" class=\"data row1 col11\" >352.04</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row1_col12\" class=\"data row1 col12\" >12.91</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col0\" class=\"data row2 col0\" >9.18</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col1\" class=\"data row2 col1\" >21.83</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col2\" class=\"data row2 col2\" >6.91</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col3\" class=\"data row2 col3\" >0.27</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col4\" class=\"data row2 col4\" >0.12</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col5\" class=\"data row2 col5\" >0.74</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col6\" class=\"data row2 col6\" >28.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col7\" class=\"data row2 col7\" >2.15</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col8\" class=\"data row2 col8\" >8.81</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col9\" class=\"data row2 col9\" >170.66</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col10\" class=\"data row2 col10\" >2.18</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col11\" class=\"data row2 col11\" >97.98</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row2_col12\" class=\"data row2 col12\" >7.34</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col2\" class=\"data row3 col2\" >0.74</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col5\" class=\"data row3 col5\" >3.56</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col6\" class=\"data row3 col6\" >2.90</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col7\" class=\"data row3 col7\" >1.13</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col9\" class=\"data row3 col9\" >187.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col10\" class=\"data row3 col10\" >12.60</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col11\" class=\"data row3 col11\" >0.32</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row3_col12\" class=\"data row3 col12\" >1.73</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col0\" class=\"data row4 col0\" >0.09</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col2\" class=\"data row4 col2\" >5.22</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col4\" class=\"data row4 col4\" >0.45</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col5\" class=\"data row4 col5\" >5.87</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col6\" class=\"data row4 col6\" >47.40</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col7\" class=\"data row4 col7\" >2.08</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col9\" class=\"data row4 col9\" >277.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col10\" class=\"data row4 col10\" >17.33</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col11\" class=\"data row4 col11\" >374.59</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row4_col12\" class=\"data row4 col12\" >7.23</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col0\" class=\"data row5 col0\" >0.29</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col2\" class=\"data row5 col2\" >9.69</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col4\" class=\"data row5 col4\" >0.54</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col5\" class=\"data row5 col5\" >6.18</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col6\" class=\"data row5 col6\" >79.50</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col7\" class=\"data row5 col7\" >3.10</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col9\" class=\"data row5 col9\" >332.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col10\" class=\"data row5 col10\" >19.10</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col11\" class=\"data row5 col11\" >390.84</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row5_col12\" class=\"data row5 col12\" >11.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col0\" class=\"data row6 col0\" >3.85</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col1\" class=\"data row6 col1\" >12.50</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col5\" class=\"data row6 col5\" >6.62</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col6\" class=\"data row6 col6\" >94.30</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col7\" class=\"data row6 col7\" >5.23</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col8\" class=\"data row6 col8\" >24.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col9\" class=\"data row6 col9\" >666.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col11\" class=\"data row6 col11\" >395.63</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row6_col12\" class=\"data row6 col12\" >17.26</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col0\" class=\"data row7 col0\" >88.98</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col1\" class=\"data row7 col1\" >95.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col5\" class=\"data row7 col5\" >8.78</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col7\" class=\"data row7 col7\" >12.13</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_75cb9736_f1f4_11ea_a8d7_dbdf8a821ee3row7_col12\" class=\"data row7 col12\" >37.97</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f760c015bd0>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3\" ><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_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col2\" class=\"data row1 col2\" >-0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col8\" class=\"data row1 col8\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col9\" class=\"data row1 col9\" >-0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col11\" class=\"data row1 col11\" >-0.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row1_col12\" class=\"data row1 col12\" >-0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col0\" class=\"data row3 col0\" >-0.43</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col1\" class=\"data row3 col1\" >-0.48</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col2\" class=\"data row3 col2\" >-1.54</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col3\" class=\"data row3 col3\" >-0.30</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col4\" class=\"data row3 col4\" >-1.42</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col5\" class=\"data row3 col5\" >-3.67</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col6\" class=\"data row3 col6\" >-2.39</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col7\" class=\"data row3 col7\" >-1.23</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col8\" class=\"data row3 col8\" >-0.98</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col9\" class=\"data row3 col9\" >-1.31</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col10\" class=\"data row3 col10\" >-2.70</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col11\" class=\"data row3 col11\" >-3.59</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row3_col12\" class=\"data row3 col12\" >-1.52</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col0\" class=\"data row4 col0\" >-0.42</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col1\" class=\"data row4 col1\" >-0.48</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col2\" class=\"data row4 col2\" >-0.89</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col3\" class=\"data row4 col3\" >-0.30</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col4\" class=\"data row4 col4\" >-0.90</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col5\" class=\"data row4 col5\" >-0.53</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col6\" class=\"data row4 col6\" >-0.80</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col7\" class=\"data row4 col7\" >-0.79</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col8\" class=\"data row4 col8\" >-0.64</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col9\" class=\"data row4 col9\" >-0.78</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col10\" class=\"data row4 col10\" >-0.53</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col11\" class=\"data row4 col11\" >0.23</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row4_col12\" class=\"data row4 col12\" >-0.77</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col0\" class=\"data row5 col0\" >-0.40</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col1\" class=\"data row5 col1\" >-0.48</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col2\" class=\"data row5 col2\" >-0.24</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col3\" class=\"data row5 col3\" >-0.30</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col4\" class=\"data row5 col4\" >-0.17</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col5\" class=\"data row5 col5\" >-0.11</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col6\" class=\"data row5 col6\" >0.35</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col7\" class=\"data row5 col7\" >-0.32</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col8\" class=\"data row5 col8\" >-0.53</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col9\" class=\"data row5 col9\" >-0.46</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col10\" class=\"data row5 col10\" >0.28</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col11\" class=\"data row5 col11\" >0.40</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row5_col12\" class=\"data row5 col12\" >-0.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col0\" class=\"data row6 col0\" >-0.01</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col1\" class=\"data row6 col1\" >0.09</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col2\" class=\"data row6 col2\" >0.98</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col3\" class=\"data row6 col3\" >-0.30</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col4\" class=\"data row6 col4\" >0.57</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col5\" class=\"data row6 col5\" >0.47</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col6\" class=\"data row6 col6\" >0.88</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col7\" class=\"data row6 col7\" >0.68</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col8\" class=\"data row6 col8\" >1.63</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col9\" class=\"data row6 col9\" >1.50</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col10\" class=\"data row6 col10\" >0.79</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col11\" class=\"data row6 col11\" >0.44</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row6_col12\" class=\"data row6 col12\" >0.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col0\" class=\"data row7 col0\" >9.26</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col1\" class=\"data row7 col1\" >3.87</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col2\" class=\"data row7 col2\" >2.37</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col3\" class=\"data row7 col3\" >3.34</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col4\" class=\"data row7 col4\" >2.69</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col5\" class=\"data row7 col5\" >3.41</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col6\" class=\"data row7 col6\" >1.08</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col7\" class=\"data row7 col7\" >3.89</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col8\" class=\"data row7 col8\" >1.63</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col9\" class=\"data row7 col9\" >1.76</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col10\" class=\"data row7 col10\" >1.61</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col11\" class=\"data row7 col11\" >0.46</td>\n",
" <td id=\"T_75d25418_f1f4_11ea_a8d7_dbdf8a821ee3row7_col12\" class=\"data row7 col12\" >3.41</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f758fd31190>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3\" ><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_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3level0_row0\" class=\"row_heading level0 row0\" >186</th>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col0\" class=\"data row0 col0\" >-0.42</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col1\" class=\"data row0 col1\" >-0.48</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col2\" class=\"data row0 col2\" >-1.29</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col3\" class=\"data row0 col3\" >-0.30</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col4\" class=\"data row0 col4\" >-0.60</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col5\" class=\"data row0 col5\" >2.12</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col6\" class=\"data row0 col6\" >-0.58</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col7\" class=\"data row0 col7\" >-0.27</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col8\" class=\"data row0 col8\" >-0.76</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col9\" class=\"data row0 col9\" >-1.28</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col10\" class=\"data row0 col10\" >-0.32</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col11\" class=\"data row0 col11\" >0.41</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row0_col12\" class=\"data row0 col12\" >-1.15</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3level0_row1\" class=\"row_heading level0 row1\" >452</th>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col0\" class=\"data row1 col0\" >0.13</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col1\" class=\"data row1 col1\" >-0.48</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col2\" class=\"data row1 col2\" >0.98</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col3\" class=\"data row1 col3\" >-0.30</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col4\" class=\"data row1 col4\" >1.33</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col5\" class=\"data row1 col5\" >0.04</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col6\" class=\"data row1 col6\" >0.79</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col7\" class=\"data row1 col7\" >-0.66</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col8\" class=\"data row1 col8\" >1.63</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col9\" class=\"data row1 col9\" >1.50</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col10\" class=\"data row1 col10\" >0.79</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col11\" class=\"data row1 col11\" >0.34</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row1_col12\" class=\"data row1 col12\" >0.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3level0_row2\" class=\"row_heading level0 row2\" >465</th>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col0\" class=\"data row2 col0\" >-0.08</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col1\" class=\"data row2 col1\" >-0.48</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col2\" class=\"data row2 col2\" >0.98</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col3\" class=\"data row2 col3\" >-0.30</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col4\" class=\"data row2 col4\" >0.84</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col5\" class=\"data row2 col5\" >-0.69</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col6\" class=\"data row2 col6\" >-0.77</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col7\" class=\"data row2 col7\" >-0.33</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col8\" class=\"data row2 col8\" >1.63</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col9\" class=\"data row2 col9\" >1.50</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col10\" class=\"data row2 col10\" >0.79</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col11\" class=\"data row2 col11\" >-0.18</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row2_col12\" class=\"data row2 col12\" >0.17</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3level0_row3\" class=\"row_heading level0 row3\" >193</th>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col0\" class=\"data row3 col0\" >-0.42</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col1\" class=\"data row3 col1\" >2.27</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col2\" class=\"data row3 col2\" >-1.22</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col3\" class=\"data row3 col3\" >-0.30</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col4\" class=\"data row3 col4\" >-1.34</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col5\" class=\"data row3 col5\" >0.72</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col6\" class=\"data row3 col6\" >-2.14</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col7\" class=\"data row3 col7\" >1.14</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col8\" class=\"data row3 col8\" >-0.98</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col9\" class=\"data row3 col9\" >-0.85</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col10\" class=\"data row3 col10\" >-1.33</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col11\" class=\"data row3 col11\" >0.42</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row3_col12\" class=\"data row3 col12\" >-1.07</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3level0_row4\" class=\"row_heading level0 row4\" >32</th>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col0\" class=\"data row4 col0\" >-0.28</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col1\" class=\"data row4 col1\" >-0.48</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col2\" class=\"data row4 col2\" >-0.47</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col3\" class=\"data row4 col3\" >-0.30</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col4\" class=\"data row4 col4\" >-0.17</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col5\" class=\"data row4 col5\" >-0.43</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col6\" class=\"data row4 col6\" >0.44</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col7\" class=\"data row4 col7\" >0.10</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col8\" class=\"data row4 col8\" >-0.64</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col9\" class=\"data row4 col9\" >-0.61</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col10\" class=\"data row4 col10\" >1.15</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col11\" class=\"data row4 col11\" >-1.22</td>\n",
" <td id=\"T_75d30dae_f1f4_11ea_a8d7_dbdf8a821ee3row4_col12\" class=\"data row4 col12\" >2.02</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f760c0155d0>"
]
},
"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": 6,
"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": 7,
"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>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"model=get_model_v1( (13,) )\n",
"\n",
"model.summary()\n",
"\n",
"img=keras.utils.plot_model( model, to_file='./run/model.png', show_shapes=True, show_layer_names=True, dpi=96)\n",
"display(img)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.2 - Train it"
]
},
{
"cell_type": "code",
"execution_count": 8,
"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: 496.9229 - mae: 20.3398 - mse: 496.9229 - val_loss: 419.5401 - val_mae: 18.4986 - val_mse: 419.5401\n",
"Epoch 2/100\n",
"354/354 [==============================] - 0s 177us/sample - loss: 295.5164 - mae: 14.8616 - mse: 295.5164 - val_loss: 186.6298 - val_mae: 11.5436 - val_mse: 186.6298\n",
"Epoch 3/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 114.9580 - mae: 8.2730 - mse: 114.9580 - val_loss: 59.9437 - val_mae: 5.8003 - val_mse: 59.9437\n",
"Epoch 4/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 51.2817 - mae: 5.2744 - mse: 51.2817 - val_loss: 35.3415 - val_mae: 4.3495 - val_mse: 35.3415\n",
"Epoch 5/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 32.2583 - mae: 4.1435 - mse: 32.2583 - val_loss: 25.3969 - val_mae: 3.6065 - val_mse: 25.3969\n",
"Epoch 6/100\n",
"354/354 [==============================] - 0s 268us/sample - loss: 25.0037 - mae: 3.6255 - mse: 25.0037 - val_loss: 21.0705 - val_mae: 3.3281 - val_mse: 21.0705\n",
"Epoch 7/100\n",
"354/354 [==============================] - 0s 183us/sample - loss: 21.5637 - mae: 3.3349 - mse: 21.5637 - val_loss: 18.8010 - val_mae: 3.0725 - val_mse: 18.8010\n",
"Epoch 8/100\n",
"354/354 [==============================] - 0s 208us/sample - loss: 19.2727 - mae: 3.1629 - mse: 19.2727 - val_loss: 17.3783 - val_mae: 2.8856 - val_mse: 17.3783\n",
"Epoch 9/100\n",
"354/354 [==============================] - 0s 248us/sample - loss: 17.6151 - mae: 2.9420 - mse: 17.6151 - val_loss: 17.7303 - val_mae: 2.9088 - val_mse: 17.7303\n",
"Epoch 10/100\n",
"354/354 [==============================] - 0s 201us/sample - loss: 16.7331 - mae: 2.8489 - mse: 16.7331 - val_loss: 16.6203 - val_mae: 2.8102 - val_mse: 16.6203\n",
"Epoch 11/100\n",
"354/354 [==============================] - 0s 199us/sample - loss: 15.4812 - mae: 2.7647 - mse: 15.4812 - val_loss: 15.9232 - val_mae: 2.8161 - val_mse: 15.9232\n",
"Epoch 12/100\n",
"354/354 [==============================] - 0s 215us/sample - loss: 14.9469 - mae: 2.7133 - mse: 14.9469 - val_loss: 14.7353 - val_mae: 2.7331 - val_mse: 14.7353\n",
"Epoch 13/100\n",
"354/354 [==============================] - 0s 222us/sample - loss: 14.2610 - mae: 2.6598 - mse: 14.2610 - val_loss: 15.5891 - val_mae: 2.7066 - val_mse: 15.5891\n",
"Epoch 14/100\n",
"354/354 [==============================] - 0s 207us/sample - loss: 13.9148 - mae: 2.5804 - mse: 13.9148 - val_loss: 13.8518 - val_mae: 2.6489 - val_mse: 13.8518\n",
"Epoch 15/100\n",
"354/354 [==============================] - 0s 206us/sample - loss: 13.2557 - mae: 2.5414 - mse: 13.2557 - val_loss: 14.0806 - val_mae: 2.6050 - val_mse: 14.0806\n",
"Epoch 16/100\n",
"354/354 [==============================] - 0s 176us/sample - loss: 13.0313 - mae: 2.5098 - mse: 13.0313 - val_loss: 13.0845 - val_mae: 2.5645 - val_mse: 13.0845\n",
"Epoch 17/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 12.6932 - mae: 2.4334 - mse: 12.6932 - val_loss: 12.7918 - val_mae: 2.5210 - val_mse: 12.7918\n",
"Epoch 18/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 12.1471 - mae: 2.3744 - mse: 12.1471 - val_loss: 12.7903 - val_mae: 2.5516 - val_mse: 12.7903\n",
"Epoch 19/100\n",
"354/354 [==============================] - 0s 156us/sample - loss: 11.7664 - mae: 2.3935 - mse: 11.7664 - val_loss: 12.7772 - val_mae: 2.5006 - val_mse: 12.7772\n",
"Epoch 20/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 11.7673 - mae: 2.3442 - mse: 11.7673 - val_loss: 12.2528 - val_mae: 2.4773 - val_mse: 12.2528\n",
"Epoch 21/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 11.5515 - mae: 2.3222 - mse: 11.5515 - val_loss: 11.9364 - val_mae: 2.4422 - val_mse: 11.9364\n",
"Epoch 22/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 11.1944 - mae: 2.2782 - mse: 11.1944 - val_loss: 12.1765 - val_mae: 2.4741 - val_mse: 12.1765\n",
"Epoch 23/100\n",
"354/354 [==============================] - 0s 156us/sample - loss: 10.8719 - mae: 2.2615 - mse: 10.8719 - val_loss: 11.6195 - val_mae: 2.4146 - val_mse: 11.6195\n",
"Epoch 24/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 10.7249 - mae: 2.2482 - mse: 10.7249 - val_loss: 11.6477 - val_mae: 2.4269 - val_mse: 11.6477\n",
"Epoch 25/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 10.4705 - mae: 2.2339 - mse: 10.4705 - val_loss: 11.7473 - val_mae: 2.4594 - val_mse: 11.7473\n",
"Epoch 26/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 10.4140 - mae: 2.2127 - mse: 10.4140 - val_loss: 11.5549 - val_mae: 2.4450 - val_mse: 11.5549\n",
"Epoch 27/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 10.0311 - mae: 2.2345 - mse: 10.0311 - val_loss: 11.6549 - val_mae: 2.3777 - val_mse: 11.6549\n",
"Epoch 28/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 10.0233 - mae: 2.1886 - mse: 10.0233 - val_loss: 11.2612 - val_mae: 2.3638 - val_mse: 11.2612\n",
"Epoch 29/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 9.7396 - mae: 2.1549 - mse: 9.7396 - val_loss: 11.7192 - val_mae: 2.3995 - val_mse: 11.7192\n",
"Epoch 30/100\n",
"354/354 [==============================] - 0s 175us/sample - loss: 9.4578 - mae: 2.1502 - mse: 9.4578 - val_loss: 11.0006 - val_mae: 2.3374 - val_mse: 11.0006\n",
"Epoch 31/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 9.2345 - mae: 2.1387 - mse: 9.2345 - val_loss: 10.8882 - val_mae: 2.3251 - val_mse: 10.8882\n",
"Epoch 32/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 9.4173 - mae: 2.1318 - mse: 9.4173 - val_loss: 11.6230 - val_mae: 2.3616 - val_mse: 11.6230\n",
"Epoch 33/100\n",
"354/354 [==============================] - 0s 187us/sample - loss: 9.1474 - mae: 2.0741 - mse: 9.1474 - val_loss: 10.8005 - val_mae: 2.3326 - val_mse: 10.8005\n",
"Epoch 34/100\n",
"354/354 [==============================] - 0s 182us/sample - loss: 8.7565 - mae: 2.0961 - mse: 8.7565 - val_loss: 10.5611 - val_mae: 2.2676 - val_mse: 10.5611\n",
"Epoch 35/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 8.8445 - mae: 2.0441 - mse: 8.8445 - val_loss: 10.7529 - val_mae: 2.2829 - val_mse: 10.7529\n",
"Epoch 36/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 8.7197 - mae: 2.0306 - mse: 8.7197 - val_loss: 10.5885 - val_mae: 2.3312 - val_mse: 10.5885\n",
"Epoch 37/100\n",
"354/354 [==============================] - 0s 160us/sample - loss: 8.3803 - mae: 1.9988 - mse: 8.3803 - val_loss: 10.4625 - val_mae: 2.2977 - val_mse: 10.4625\n",
"Epoch 38/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 8.1797 - mae: 1.9841 - mse: 8.1797 - val_loss: 10.8993 - val_mae: 2.4313 - val_mse: 10.8993\n",
"Epoch 39/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 8.4897 - mae: 2.0293 - mse: 8.4897 - val_loss: 10.3395 - val_mae: 2.3076 - val_mse: 10.3395\n",
"Epoch 40/100\n",
"354/354 [==============================] - 0s 169us/sample - loss: 8.2173 - mae: 2.0265 - mse: 8.2173 - val_loss: 10.4234 - val_mae: 2.3516 - val_mse: 10.4234\n",
"Epoch 41/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 8.0208 - mae: 1.9914 - mse: 8.0208 - val_loss: 10.1297 - val_mae: 2.2798 - val_mse: 10.1297\n",
"Epoch 42/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 7.9852 - mae: 1.9667 - mse: 7.9852 - val_loss: 10.9296 - val_mae: 2.4653 - val_mse: 10.9296\n",
"Epoch 43/100\n",
"354/354 [==============================] - 0s 167us/sample - loss: 7.8901 - mae: 1.9684 - mse: 7.8901 - val_loss: 10.3993 - val_mae: 2.3660 - val_mse: 10.3993\n",
"Epoch 44/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 7.7134 - mae: 1.9914 - mse: 7.7134 - val_loss: 10.1382 - val_mae: 2.1999 - val_mse: 10.1382\n",
"Epoch 45/100\n",
"354/354 [==============================] - 0s 160us/sample - loss: 7.4651 - mae: 1.8810 - mse: 7.4651 - val_loss: 9.9405 - val_mae: 2.2293 - val_mse: 9.9405\n",
"Epoch 46/100\n",
"354/354 [==============================] - 0s 158us/sample - loss: 7.6525 - mae: 1.9254 - mse: 7.6525 - val_loss: 10.6396 - val_mae: 2.3426 - val_mse: 10.6396\n",
"Epoch 47/100\n",
"354/354 [==============================] - 0s 177us/sample - loss: 7.4940 - mae: 1.9148 - mse: 7.4940 - val_loss: 10.3031 - val_mae: 2.3603 - val_mse: 10.3031\n",
"Epoch 48/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 7.3784 - mae: 1.8920 - mse: 7.3784 - val_loss: 10.3574 - val_mae: 2.2241 - val_mse: 10.3574\n",
"Epoch 49/100\n",
"354/354 [==============================] - 0s 182us/sample - loss: 7.3094 - mae: 1.8977 - mse: 7.3094 - val_loss: 9.6455 - val_mae: 2.1697 - val_mse: 9.6455\n",
"Epoch 50/100\n",
"354/354 [==============================] - 0s 213us/sample - loss: 7.0373 - mae: 1.8537 - mse: 7.0373 - val_loss: 9.9072 - val_mae: 2.2264 - val_mse: 9.9072\n",
"Epoch 51/100\n",
"354/354 [==============================] - 0s 189us/sample - loss: 6.9772 - mae: 1.8815 - mse: 6.9772 - val_loss: 10.8260 - val_mae: 2.3366 - val_mse: 10.8260\n",
"Epoch 52/100\n",
"354/354 [==============================] - 0s 196us/sample - loss: 6.8625 - mae: 1.8743 - mse: 6.8625 - val_loss: 9.8249 - val_mae: 2.2377 - val_mse: 9.8249\n",
"Epoch 53/100\n",
"354/354 [==============================] - 0s 194us/sample - loss: 6.8944 - mae: 1.8752 - mse: 6.8944 - val_loss: 9.6898 - val_mae: 2.1971 - val_mse: 9.6898\n",
"Epoch 54/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 6.7095 - mae: 1.8559 - mse: 6.7095 - val_loss: 10.6151 - val_mae: 2.2746 - val_mse: 10.6151\n",
"Epoch 55/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.7723 - mae: 1.8727 - mse: 6.7723 - val_loss: 10.3318 - val_mae: 2.2836 - val_mse: 10.3318\n",
"Epoch 56/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.5750 - mae: 1.8187 - mse: 6.5750 - val_loss: 10.2085 - val_mae: 2.2743 - val_mse: 10.2085\n",
"Epoch 57/100\n",
"354/354 [==============================] - 0s 155us/sample - loss: 6.6257 - mae: 1.7959 - mse: 6.6257 - val_loss: 10.2118 - val_mae: 2.2346 - val_mse: 10.2118\n",
"Epoch 58/100\n",
"354/354 [==============================] - 0s 153us/sample - loss: 6.2614 - mae: 1.8075 - mse: 6.2614 - val_loss: 9.5504 - val_mae: 2.2475 - val_mse: 9.5504\n",
"Epoch 59/100\n",
"354/354 [==============================] - 0s 152us/sample - loss: 6.4591 - mae: 1.8022 - mse: 6.4591 - val_loss: 9.5048 - val_mae: 2.1846 - val_mse: 9.5048\n",
"Epoch 60/100\n",
"354/354 [==============================] - 0s 151us/sample - loss: 6.2679 - mae: 1.7856 - mse: 6.2679 - val_loss: 9.8863 - val_mae: 2.1472 - val_mse: 9.8863\n",
"Epoch 61/100\n",
"354/354 [==============================] - 0s 172us/sample - loss: 6.1997 - mae: 1.7521 - mse: 6.1997 - val_loss: 9.5469 - val_mae: 2.2168 - val_mse: 9.5469\n",
"Epoch 62/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 5.9001 - mae: 1.7677 - mse: 5.9001 - val_loss: 10.3969 - val_mae: 2.2894 - val_mse: 10.3969\n",
"Epoch 63/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.9727 - mae: 1.7715 - mse: 5.9727 - val_loss: 9.2806 - val_mae: 2.1635 - val_mse: 9.2806\n",
"Epoch 64/100\n",
"354/354 [==============================] - 0s 159us/sample - loss: 5.9357 - mae: 1.7691 - mse: 5.9357 - val_loss: 9.7865 - val_mae: 2.1970 - val_mse: 9.7865\n",
"Epoch 65/100\n",
"354/354 [==============================] - 0s 173us/sample - loss: 5.7502 - mae: 1.7583 - mse: 5.7502 - val_loss: 9.4449 - val_mae: 2.1681 - val_mse: 9.4449\n",
"Epoch 66/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.8152 - mae: 1.7191 - mse: 5.8152 - val_loss: 9.6538 - val_mae: 2.2230 - val_mse: 9.6538\n",
"Epoch 67/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.7099 - mae: 1.7531 - mse: 5.7099 - val_loss: 10.2712 - val_mae: 2.2829 - val_mse: 10.2712\n",
"Epoch 68/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 5.6872 - mae: 1.7396 - mse: 5.6872 - val_loss: 9.8613 - val_mae: 2.2475 - val_mse: 9.8614\n",
"Epoch 69/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 5.5726 - mae: 1.6874 - mse: 5.5726 - val_loss: 9.6871 - val_mae: 2.2940 - val_mse: 9.6871\n",
"Epoch 70/100\n",
"354/354 [==============================] - 0s 160us/sample - loss: 5.6172 - mae: 1.6898 - mse: 5.6172 - val_loss: 9.6192 - val_mae: 2.2869 - val_mse: 9.6192\n",
"Epoch 71/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.2962 - mae: 1.6887 - mse: 5.2962 - val_loss: 11.9677 - val_mae: 2.6445 - val_mse: 11.9677\n",
"Epoch 72/100\n",
"354/354 [==============================] - 0s 157us/sample - loss: 5.4289 - mae: 1.6882 - mse: 5.4289 - val_loss: 9.0920 - val_mae: 2.1635 - val_mse: 9.0920\n",
"Epoch 73/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.3055 - mae: 1.6638 - mse: 5.3055 - val_loss: 9.0646 - val_mae: 2.1701 - val_mse: 9.0646\n",
"Epoch 74/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 5.3235 - mae: 1.6849 - mse: 5.3235 - val_loss: 9.1451 - val_mae: 2.1315 - val_mse: 9.1451\n",
"Epoch 75/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.2496 - mae: 1.6685 - mse: 5.2496 - val_loss: 9.3699 - val_mae: 2.2101 - val_mse: 9.3699\n",
"Epoch 76/100\n",
"354/354 [==============================] - 0s 156us/sample - loss: 5.0007 - mae: 1.6417 - mse: 5.0007 - val_loss: 9.0921 - val_mae: 2.1279 - val_mse: 9.0921\n",
"Epoch 77/100\n",
"354/354 [==============================] - 0s 172us/sample - loss: 5.2315 - mae: 1.6528 - mse: 5.2315 - val_loss: 9.0284 - val_mae: 2.1283 - val_mse: 9.0284\n",
"Epoch 78/100\n",
"354/354 [==============================] - 0s 157us/sample - loss: 5.0492 - mae: 1.6244 - mse: 5.0492 - val_loss: 9.7080 - val_mae: 2.2000 - val_mse: 9.7080\n",
"Epoch 79/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 4.9512 - mae: 1.6168 - mse: 4.9512 - val_loss: 9.3491 - val_mae: 2.2524 - val_mse: 9.3491\n",
"Epoch 80/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 4.8233 - mae: 1.5951 - mse: 4.8233 - val_loss: 10.4702 - val_mae: 2.3727 - val_mse: 10.4702\n",
"Epoch 81/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 4.8356 - mae: 1.6313 - mse: 4.8356 - val_loss: 10.8360 - val_mae: 2.5334 - val_mse: 10.8360\n",
"Epoch 82/100\n",
"354/354 [==============================] - 0s 165us/sample - loss: 4.7664 - mae: 1.5728 - mse: 4.7664 - val_loss: 9.0297 - val_mae: 2.1707 - val_mse: 9.0297\n",
"Epoch 83/100\n",
"354/354 [==============================] - 0s 160us/sample - loss: 4.8996 - mae: 1.5917 - mse: 4.8996 - val_loss: 9.0345 - val_mae: 2.1374 - val_mse: 9.0345\n",
"Epoch 84/100\n",
"354/354 [==============================] - 0s 160us/sample - loss: 4.7986 - mae: 1.6048 - mse: 4.7986 - val_loss: 9.4659 - val_mae: 2.2548 - val_mse: 9.4659\n",
"Epoch 85/100\n",
"354/354 [==============================] - 0s 171us/sample - loss: 4.5527 - mae: 1.5404 - mse: 4.5527 - val_loss: 9.5788 - val_mae: 2.1823 - val_mse: 9.5788\n",
"Epoch 86/100\n",
"354/354 [==============================] - 0s 162us/sample - loss: 4.6033 - mae: 1.5829 - mse: 4.6033 - val_loss: 9.7029 - val_mae: 2.2306 - val_mse: 9.7029\n",
"Epoch 87/100\n",
"354/354 [==============================] - 0s 158us/sample - loss: 4.5717 - mae: 1.5727 - mse: 4.5717 - val_loss: 9.1632 - val_mae: 2.1194 - val_mse: 9.1632\n",
"Epoch 88/100\n",
"354/354 [==============================] - 0s 158us/sample - loss: 4.4614 - mae: 1.5356 - mse: 4.4614 - val_loss: 8.9921 - val_mae: 2.1007 - val_mse: 8.9921\n",
"Epoch 89/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 4.6582 - mae: 1.5248 - mse: 4.6582 - val_loss: 9.0494 - val_mae: 2.1288 - val_mse: 9.0494\n",
"Epoch 90/100\n",
"354/354 [==============================] - 0s 158us/sample - loss: 4.3272 - mae: 1.5289 - mse: 4.3272 - val_loss: 9.8204 - val_mae: 2.3003 - val_mse: 9.8204\n",
"Epoch 91/100\n",
"354/354 [==============================] - 0s 157us/sample - loss: 4.4199 - mae: 1.5274 - mse: 4.4199 - val_loss: 10.0219 - val_mae: 2.2723 - val_mse: 10.0219\n",
"Epoch 92/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 4.3447 - mae: 1.5423 - mse: 4.3447 - val_loss: 11.5811 - val_mae: 2.5490 - val_mse: 11.5811\n",
"Epoch 93/100\n",
"354/354 [==============================] - 0s 163us/sample - loss: 4.3355 - mae: 1.5369 - mse: 4.3355 - val_loss: 8.8431 - val_mae: 2.1337 - val_mse: 8.8431\n",
"Epoch 94/100\n",
"354/354 [==============================] - 0s 156us/sample - loss: 4.3791 - mae: 1.5442 - mse: 4.3791 - val_loss: 9.4194 - val_mae: 2.1541 - val_mse: 9.4194\n",
"Epoch 95/100\n",
"354/354 [==============================] - 0s 157us/sample - loss: 4.3247 - mae: 1.5456 - mse: 4.3247 - val_loss: 8.9440 - val_mae: 2.0844 - val_mse: 8.9440\n",
"Epoch 96/100\n",
"354/354 [==============================] - 0s 164us/sample - loss: 4.2525 - mae: 1.4911 - mse: 4.2525 - val_loss: 9.1399 - val_mae: 2.1911 - val_mse: 9.1399\n",
"Epoch 97/100\n",
"354/354 [==============================] - 0s 161us/sample - loss: 4.2203 - mae: 1.4947 - mse: 4.2203 - val_loss: 9.4216 - val_mae: 2.2468 - val_mse: 9.4216\n",
"Epoch 98/100\n",
"354/354 [==============================] - 0s 158us/sample - loss: 4.0427 - mae: 1.5021 - mse: 4.0427 - val_loss: 9.8772 - val_mae: 2.2684 - val_mse: 9.8772\n",
"Epoch 99/100\n",
"354/354 [==============================] - 0s 156us/sample - loss: 4.1551 - mae: 1.4745 - mse: 4.1551 - val_loss: 9.2742 - val_mae: 2.1680 - val_mse: 9.2742\n",
"Epoch 100/100\n",
"354/354 [==============================] - 0s 166us/sample - loss: 4.1385 - mae: 1.4979 - mse: 4.1385 - val_loss: 9.1496 - val_mae: 2.1970 - val_mse: 9.1496\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": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"x_test / loss : 9.1496\n",
"x_test / mae : 2.1970\n",
"x_test / mse : 9.1496\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": 10,
"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>17.575156</td>\n",
" <td>2.393877</td>\n",
" <td>17.575157</td>\n",
" <td>17.672065</td>\n",
" <td>2.668328</td>\n",
" <td>17.672065</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>57.558606</td>\n",
" <td>2.374958</td>\n",
" <td>57.558606</td>\n",
" <td>44.606822</td>\n",
" <td>1.899542</td>\n",
" <td>44.606823</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>4.042664</td>\n",
" <td>1.474455</td>\n",
" <td>4.042665</td>\n",
" <td>8.843062</td>\n",
" <td>2.084356</td>\n",
" <td>8.843062</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>5.245075</td>\n",
" <td>1.661062</td>\n",
" <td>5.245075</td>\n",
" <td>9.571723</td>\n",
" <td>2.199997</td>\n",
" <td>9.571724</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>7.007228</td>\n",
" <td>1.878118</td>\n",
" <td>7.007228</td>\n",
" <td>10.348436</td>\n",
" <td>2.288131</td>\n",
" <td>10.348436</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>10.428114</td>\n",
" <td>2.234086</td>\n",
" <td>10.428113</td>\n",
" <td>11.670978</td>\n",
" <td>2.460876</td>\n",
" <td>11.670978</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>496.922868</td>\n",
" <td>20.339752</td>\n",
" <td>496.922882</td>\n",
" <td>419.540121</td>\n",
" <td>18.498610</td>\n",
" <td>419.540131</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 17.575156 2.393877 17.575157 17.672065 2.668328 17.672065\n",
"std 57.558606 2.374958 57.558606 44.606822 1.899542 44.606823\n",
"min 4.042664 1.474455 4.042665 8.843062 2.084356 8.843062\n",
"25% 5.245075 1.661062 5.245075 9.571723 2.199997 9.571724\n",
"50% 7.007228 1.878118 7.007228 10.348436 2.288131 10.348436\n",
"75% 10.428114 2.234086 10.428113 11.670978 2.460876 11.670978\n",
"max 496.922868 20.339752 496.922882 419.540121 18.498610 419.540131"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"df=pd.DataFrame(data=history.history)\n",
"df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"min( val_mae ) : 2.0844\n"
]
}
],
"source": [
"print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 576x432 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 576x432 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 576x432 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"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": 13,
"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": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Prediction : 10.66 K$\n",
"Reality : 10.40 K$\n"
]
}
],
"source": [
"\n",
"predictions = model.predict( my_data )\n",
"print(\"Prediction : {:.2f} K$\".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": "3.7.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}