Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
"# <!-- TITLE --> [BHP2] - Regression with a Dense Network (DNN) - Advanced code\n",
" <!-- DESC --> More advanced example of DNN network code - 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 with backup and restore of the trained model. \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",
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
"\n",
" - (Retrieve data)\n",
" - (Preparing the data)\n",
" - (Build a model)\n",
" - Train and save the model\n",
" - Restore saved model\n",
" - Evaluate the model\n",
" - Make some predictions\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, 18:39:50\n",
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
"TensorFlow version : 2.0.0\n",
"Keras version : 2.2.4-tf\n"
]
}
],
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
"import os,sys\n",
"\n",
"from IPython.display import display, Markdown\n",
"from importlib import reload\n",
"\n",
"sys.path.append('..')\n",
"import fidle.pwk as ooo\n",
"\n",
"ooo.init()\n",
"os.makedirs('./run/models', mode=0o750, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2 - Retrieve data\n",
"\n",
"### 2.1 - Option 1 : From Keras\n",
"Boston housing is a famous historic dataset, so we can get it directly from [Keras datasets](https://www.tensorflow.org/api_docs/python/tf/keras/datasets) "
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"(x_train, y_train), (x_test, y_test) = keras.datasets.boston_housing.load_data(test_split=0.2, seed=113)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.2 - Option 2 : From a csv file\n",
"More fun !"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2\" ><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",
" <th id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" <th id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" <th id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" <th id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" <th id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_fd7e95a4_58be_11ea_954f_edae4404b4c2row4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f244dda3dd0>"
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Données manquantes : 0 Shape is : (506, 14)\n"
]
}
],
"source": [
"data = pd.read_csv('./data/BostonHousing.csv', header=0)\n",
"\n",
"display(data.head(5).style.format(\"{0:.2f}\"))\n",
"print('Données manquantes : ',data.isna().sum().sum(), ' Shape is : ', data.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 3 - Preparing the data\n",
"### 3.1 - Split data\n",
"We will use 80% of the data for training and 20% for validation. \n",
"x will be input data and y the expected output"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Original data shape was : (506, 14)\n",
"x_train : (354, 13) y_train : (354,)\n",
"x_test : (152, 13) y_test : (152,)\n"
]
}
],
"source": [
"# ---- Split => train, test\n",
"#\n",
"data_train = data.sample(frac=0.7, axis=0)\n",
"data_test = data.drop(data_train.index)\n",
"\n",
"# ---- Split => x,y (medv is price)\n",
"#\n",
"x_train = data_train.drop('medv', axis=1)\n",
"y_train = data_train['medv']\n",
"x_test = data_test.drop('medv', axis=1)\n",
"y_test = data_test['medv']\n",
"\n",
"print('Original data shape was : ',data.shape)\n",
"print('x_train : ',x_train.shape, 'y_train : ',y_train.shape)\n",
"print('x_test : ',x_test.shape, 'y_test : ',y_test.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 3.2 - Data normalization\n",
"**Note :** \n",
" - All input data must be normalized, train and test. \n",
" - To do this we will subtract the mean and divide by the standard deviation. \n",
" - But test data should not be used in any way, even for normalization. \n",
" - The mean and the standard deviation will therefore only be calculated with the train data."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2\" ><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",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col0\" class=\"data row1 col0\" >3.60</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col1\" class=\"data row1 col1\" >12.20</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col2\" class=\"data row1 col2\" >10.86</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col4\" class=\"data row1 col4\" >0.55</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col5\" class=\"data row1 col5\" >6.29</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col6\" class=\"data row1 col6\" >67.90</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col7\" class=\"data row1 col7\" >3.91</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col8\" class=\"data row1 col8\" >9.17</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col9\" class=\"data row1 col9\" >398.77</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col10\" class=\"data row1 col10\" >18.44</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col11\" class=\"data row1 col11\" >360.64</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row1_col12\" class=\"data row1 col12\" >12.66</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col0\" class=\"data row2 col0\" >9.38</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col1\" class=\"data row2 col1\" >24.11</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col2\" class=\"data row2 col2\" >6.78</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col3\" class=\"data row2 col3\" >0.27</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col4\" class=\"data row2 col4\" >0.11</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col5\" class=\"data row2 col5\" >0.70</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col6\" class=\"data row2 col6\" >28.08</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col7\" class=\"data row2 col7\" >2.13</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col8\" class=\"data row2 col8\" >8.53</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col9\" class=\"data row2 col9\" >166.41</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col10\" class=\"data row2 col10\" >2.17</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col11\" class=\"data row2 col11\" >86.73</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row2_col12\" class=\"data row2 col12\" >7.18</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col2\" class=\"data row3 col2\" >0.46</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col5\" class=\"data row3 col5\" >3.86</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col6\" class=\"data row3 col6\" >2.90</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col7\" class=\"data row3 col7\" >1.13</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col9\" class=\"data row3 col9\" >187.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col10\" class=\"data row3 col10\" >12.60</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col11\" class=\"data row3 col11\" >0.32</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row3_col12\" class=\"data row3 col12\" >1.98</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col0\" class=\"data row4 col0\" >0.08</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col2\" class=\"data row4 col2\" >5.15</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col4\" class=\"data row4 col4\" >0.45</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col5\" class=\"data row4 col5\" >5.89</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col6\" class=\"data row4 col6\" >45.18</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col7\" class=\"data row4 col7\" >2.13</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col9\" class=\"data row4 col9\" >277.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col10\" class=\"data row4 col10\" >17.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col11\" class=\"data row4 col11\" >377.55</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row4_col12\" class=\"data row4 col12\" >7.15</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col0\" class=\"data row5 col0\" >0.25</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col2\" class=\"data row5 col2\" >8.56</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col4\" class=\"data row5 col4\" >0.53</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col5\" class=\"data row5 col5\" >6.17</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col6\" class=\"data row5 col6\" >76.50</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col7\" class=\"data row5 col7\" >3.42</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col9\" class=\"data row5 col9\" >311.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col10\" class=\"data row5 col10\" >18.70</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col11\" class=\"data row5 col11\" >392.48</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row5_col12\" class=\"data row5 col12\" >11.17</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col0\" class=\"data row6 col0\" >2.77</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col1\" class=\"data row6 col1\" >20.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col5\" class=\"data row6 col5\" >6.63</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col6\" class=\"data row6 col6\" >93.45</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col7\" class=\"data row6 col7\" >5.29</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col8\" class=\"data row6 col8\" >8.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col9\" class=\"data row6 col9\" >616.75</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col11\" class=\"data row6 col11\" >396.32</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row6_col12\" class=\"data row6 col12\" >17.06</td>\n",
" <th id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col0\" class=\"data row7 col0\" >88.98</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col1\" class=\"data row7 col1\" >100.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col5\" class=\"data row7 col5\" >8.78</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col7\" class=\"data row7 col7\" >12.13</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_fd8631f6_58be_11ea_954f_edae4404b4c2row7_col12\" class=\"data row7 col12\" >36.98</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f24c9def750>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2\" ><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",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col1\" class=\"data row1 col1\" >-0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col3\" class=\"data row1 col3\" >-0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col5\" class=\"data row1 col5\" >-0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col7\" class=\"data row1 col7\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col8\" class=\"data row1 col8\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col11\" class=\"data row1 col11\" >0.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row1_col12\" class=\"data row1 col12\" >0.00</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col0\" class=\"data row3 col0\" >-0.38</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col1\" class=\"data row3 col1\" >-0.51</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col2\" class=\"data row3 col2\" >-1.53</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col3\" class=\"data row3 col3\" >-0.29</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col4\" class=\"data row3 col4\" >-1.45</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col5\" class=\"data row3 col5\" >-3.48</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col6\" class=\"data row3 col6\" >-2.31</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col7\" class=\"data row3 col7\" >-1.30</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col8\" class=\"data row3 col8\" >-0.96</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col9\" class=\"data row3 col9\" >-1.27</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col10\" class=\"data row3 col10\" >-2.69</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col11\" class=\"data row3 col11\" >-4.15</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row3_col12\" class=\"data row3 col12\" >-1.49</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col0\" class=\"data row4 col0\" >-0.38</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col1\" class=\"data row4 col1\" >-0.51</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col2\" class=\"data row4 col2\" >-0.84</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col3\" class=\"data row4 col3\" >-0.29</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col4\" class=\"data row4 col4\" >-0.89</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col5\" class=\"data row4 col5\" >-0.58</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col6\" class=\"data row4 col6\" >-0.81</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col7\" class=\"data row4 col7\" >-0.83</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col8\" class=\"data row4 col8\" >-0.61</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col9\" class=\"data row4 col9\" >-0.73</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col10\" class=\"data row4 col10\" >-0.66</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col11\" class=\"data row4 col11\" >0.19</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row4_col12\" class=\"data row4 col12\" >-0.77</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col0\" class=\"data row5 col0\" >-0.36</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col1\" class=\"data row5 col1\" >-0.51</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col2\" class=\"data row5 col2\" >-0.34</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col3\" class=\"data row5 col3\" >-0.29</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col4\" class=\"data row5 col4\" >-0.14</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col5\" class=\"data row5 col5\" >-0.17</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col6\" class=\"data row5 col6\" >0.31</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col7\" class=\"data row5 col7\" >-0.23</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col8\" class=\"data row5 col8\" >-0.49</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col9\" class=\"data row5 col9\" >-0.53</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col10\" class=\"data row5 col10\" >0.12</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col11\" class=\"data row5 col11\" >0.37</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row5_col12\" class=\"data row5 col12\" >-0.21</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col0\" class=\"data row6 col0\" >-0.09</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col1\" class=\"data row6 col1\" >0.32</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col2\" class=\"data row6 col2\" >1.07</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col3\" class=\"data row6 col3\" >-0.29</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col4\" class=\"data row6 col4\" >0.65</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col5\" class=\"data row6 col5\" >0.48</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col6\" class=\"data row6 col6\" >0.91</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col7\" class=\"data row6 col7\" >0.65</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col8\" class=\"data row6 col8\" >-0.14</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col9\" class=\"data row6 col9\" >1.31</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col10\" class=\"data row6 col10\" >0.81</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col11\" class=\"data row6 col11\" >0.41</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row6_col12\" class=\"data row6 col12\" >0.61</td>\n",
" <th id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col0\" class=\"data row7 col0\" >9.10</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col1\" class=\"data row7 col1\" >3.64</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col2\" class=\"data row7 col2\" >2.49</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col3\" class=\"data row7 col3\" >3.41</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col4\" class=\"data row7 col4\" >2.87</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col5\" class=\"data row7 col5\" >3.57</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col6\" class=\"data row7 col6\" >1.14</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col7\" class=\"data row7 col7\" >3.85</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col8\" class=\"data row7 col8\" >1.74</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col9\" class=\"data row7 col9\" >1.88</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col10\" class=\"data row7 col10\" >1.64</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col11\" class=\"data row7 col11\" >0.42</td>\n",
" <td id=\"T_fd8d1f0c_58be_11ea_954f_edae4404b4c2row7_col12\" class=\"data row7 col12\" >3.38</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f244d9dd150>"
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
"\n",
"mean = x_train.mean()\n",
"std = x_train.std()\n",
"x_train = (x_train - mean) / std\n",
"x_test = (x_test - mean) / std\n",
"\n",
"display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"After normalization :\"))\n",
"\n",
"x_train, y_train = np.array(x_train), np.array(y_train)\n",
"x_test, y_test = np.array(x_test), np.array(y_test)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 4 - Build a model\n",
"More 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": [
"## 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 - Add callback"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"os.makedirs('./run/models', mode=0o750, exist_ok=True)\n",
"save_dir = \"./run/models/best_model.h5\"\n",
"\n",
"savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.3 - 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: 492.8138 - mae: 20.3339 - mse: 492.8138 - val_loss: 407.4318 - val_mae: 18.0155 - val_mse: 407.4319\n",
"354/354 [==============================] - 0s 227us/sample - loss: 270.9110 - mae: 14.4363 - mse: 270.9110 - val_loss: 174.6818 - val_mae: 10.7105 - val_mse: 174.6818\n",
"354/354 [==============================] - 0s 228us/sample - loss: 92.9392 - mae: 7.6230 - mse: 92.9392 - val_loss: 65.1059 - val_mae: 6.0160 - val_mse: 65.1059\n",
"354/354 [==============================] - 0s 217us/sample - loss: 39.6349 - mae: 4.7199 - mse: 39.6349 - val_loss: 39.0192 - val_mae: 4.4194 - val_mse: 39.0192\n",
"354/354 [==============================] - 0s 210us/sample - loss: 25.7522 - mae: 3.6619 - mse: 25.7521 - val_loss: 31.3153 - val_mae: 3.8863 - val_mse: 31.3153\n",
"354/354 [==============================] - 0s 221us/sample - loss: 20.5144 - mae: 3.2484 - mse: 20.5144 - val_loss: 28.4388 - val_mae: 3.6434 - val_mse: 28.4388\n",
"354/354 [==============================] - 0s 227us/sample - loss: 18.2619 - mae: 3.0625 - mse: 18.2619 - val_loss: 25.6375 - val_mae: 3.5123 - val_mse: 25.6375\n",
"354/354 [==============================] - 0s 213us/sample - loss: 16.4484 - mae: 2.8664 - mse: 16.4484 - val_loss: 23.8719 - val_mae: 3.3062 - val_mse: 23.8719\n",
"354/354 [==============================] - 0s 217us/sample - loss: 14.8711 - mae: 2.7510 - mse: 14.8711 - val_loss: 22.3218 - val_mae: 3.2885 - val_mse: 22.3218\n",
"354/354 [==============================] - 0s 169us/sample - loss: 13.9053 - mae: 2.6427 - mse: 13.9053 - val_loss: 22.6876 - val_mae: 3.1905 - val_mse: 22.6876\n",
"354/354 [==============================] - 0s 212us/sample - loss: 13.2405 - mae: 2.5373 - mse: 13.2405 - val_loss: 21.4726 - val_mae: 3.1210 - val_mse: 21.4726\n",
"354/354 [==============================] - 0s 212us/sample - loss: 12.4025 - mae: 2.4540 - mse: 12.4025 - val_loss: 20.1153 - val_mae: 3.1025 - val_mse: 20.1153\n",
"354/354 [==============================] - 0s 161us/sample - loss: 12.1724 - mae: 2.4405 - mse: 12.1724 - val_loss: 20.2576 - val_mae: 3.1057 - val_mse: 20.2576\n",
"354/354 [==============================] - 0s 216us/sample - loss: 11.7212 - mae: 2.3730 - mse: 11.7212 - val_loss: 19.8864 - val_mae: 3.0552 - val_mse: 19.8864\n",
"354/354 [==============================] - 0s 210us/sample - loss: 11.3366 - mae: 2.3673 - mse: 11.3366 - val_loss: 19.0607 - val_mae: 2.9963 - val_mse: 19.0607\n",
"354/354 [==============================] - 0s 221us/sample - loss: 10.8612 - mae: 2.2981 - mse: 10.8612 - val_loss: 18.8568 - val_mae: 2.9460 - val_mse: 18.8568\n",
"354/354 [==============================] - 0s 219us/sample - loss: 10.6142 - mae: 2.2892 - mse: 10.6142 - val_loss: 18.7533 - val_mae: 2.9133 - val_mse: 18.7533\n",
"354/354 [==============================] - 0s 213us/sample - loss: 10.5073 - mae: 2.2551 - mse: 10.5073 - val_loss: 18.3180 - val_mae: 2.9078 - val_mse: 18.3180\n",
"354/354 [==============================] - 0s 167us/sample - loss: 10.4158 - mae: 2.2372 - mse: 10.4158 - val_loss: 18.8145 - val_mae: 2.9186 - val_mse: 18.8145\n",
"354/354 [==============================] - 0s 173us/sample - loss: 9.8233 - mae: 2.1800 - mse: 9.8233 - val_loss: 18.7075 - val_mae: 3.0457 - val_mse: 18.7075\n",
"354/354 [==============================] - 0s 169us/sample - loss: 9.7787 - mae: 2.2096 - mse: 9.7787 - val_loss: 18.5517 - val_mae: 2.8966 - val_mse: 18.5517\n",
"354/354 [==============================] - 0s 223us/sample - loss: 9.5516 - mae: 2.1806 - mse: 9.5516 - val_loss: 17.0947 - val_mae: 2.8382 - val_mse: 17.0947\n",
"354/354 [==============================] - 0s 157us/sample - loss: 9.3722 - mae: 2.1813 - mse: 9.3722 - val_loss: 17.3946 - val_mae: 2.8243 - val_mse: 17.3946\n",
"354/354 [==============================] - 0s 167us/sample - loss: 9.2101 - mae: 2.1159 - mse: 9.2101 - val_loss: 17.5853 - val_mae: 2.7938 - val_mse: 17.5853\n",
"354/354 [==============================] - 0s 208us/sample - loss: 8.9463 - mae: 2.0970 - mse: 8.9463 - val_loss: 16.6825 - val_mae: 2.8262 - val_mse: 16.6825\n",
"354/354 [==============================] - 0s 161us/sample - loss: 9.1902 - mae: 2.1226 - mse: 9.1902 - val_loss: 17.2559 - val_mae: 2.7986 - val_mse: 17.2559\n",
"354/354 [==============================] - 0s 164us/sample - loss: 8.6915 - mae: 2.0817 - mse: 8.6915 - val_loss: 17.2847 - val_mae: 2.7818 - val_mse: 17.2847\n",
"354/354 [==============================] - 0s 169us/sample - loss: 8.6410 - mae: 2.0553 - mse: 8.6410 - val_loss: 16.9470 - val_mae: 2.9064 - val_mse: 16.9470\n",
"354/354 [==============================] - 0s 213us/sample - loss: 8.5536 - mae: 2.0797 - mse: 8.5536 - val_loss: 16.6180 - val_mae: 2.8684 - val_mse: 16.6180\n",
"354/354 [==============================] - 0s 209us/sample - loss: 8.4240 - mae: 2.0782 - mse: 8.4240 - val_loss: 16.1003 - val_mae: 2.8414 - val_mse: 16.1003\n",
"354/354 [==============================] - 0s 172us/sample - loss: 8.2710 - mae: 2.0562 - mse: 8.2710 - val_loss: 16.3428 - val_mae: 2.7119 - val_mse: 16.3428\n",
"354/354 [==============================] - 0s 171us/sample - loss: 8.1119 - mae: 2.0277 - mse: 8.1119 - val_loss: 16.3815 - val_mae: 2.7865 - val_mse: 16.3815\n",
"354/354 [==============================] - 0s 166us/sample - loss: 8.1918 - mae: 2.0308 - mse: 8.1918 - val_loss: 16.2353 - val_mae: 2.7153 - val_mse: 16.2353\n",
"354/354 [==============================] - 0s 218us/sample - loss: 7.9849 - mae: 1.9902 - mse: 7.9849 - val_loss: 15.7380 - val_mae: 2.6690 - val_mse: 15.7380\n",
"354/354 [==============================] - 0s 159us/sample - loss: 7.9413 - mae: 2.0112 - mse: 7.9413 - val_loss: 16.1214 - val_mae: 2.6838 - val_mse: 16.1214\n",
"354/354 [==============================] - 0s 168us/sample - loss: 7.8063 - mae: 1.9897 - mse: 7.8063 - val_loss: 16.3512 - val_mae: 2.6823 - val_mse: 16.3512\n",
"354/354 [==============================] - 0s 169us/sample - loss: 7.7355 - mae: 1.9812 - mse: 7.7355 - val_loss: 16.4847 - val_mae: 2.7186 - val_mse: 16.4847\n",
"354/354 [==============================] - 0s 217us/sample - loss: 7.6815 - mae: 1.9707 - mse: 7.6815 - val_loss: 15.5910 - val_mae: 2.7221 - val_mse: 15.5910\n",
"354/354 [==============================] - 0s 165us/sample - loss: 7.4555 - mae: 1.9477 - mse: 7.4555 - val_loss: 15.7338 - val_mae: 2.7056 - val_mse: 15.7338\n",
"354/354 [==============================] - 0s 216us/sample - loss: 7.5960 - mae: 1.9470 - mse: 7.5960 - val_loss: 15.4743 - val_mae: 2.6696 - val_mse: 15.4743\n",
"354/354 [==============================] - 0s 220us/sample - loss: 6.9951 - mae: 1.9196 - mse: 6.9951 - val_loss: 15.3223 - val_mae: 2.6842 - val_mse: 15.3223\n",
"354/354 [==============================] - 0s 164us/sample - loss: 7.1013 - mae: 1.9189 - mse: 7.1013 - val_loss: 15.5466 - val_mae: 2.7655 - val_mse: 15.5466\n",
"354/354 [==============================] - 0s 173us/sample - loss: 7.0727 - mae: 1.9444 - mse: 7.0727 - val_loss: 16.9088 - val_mae: 2.7190 - val_mse: 16.9088\n",
"354/354 [==============================] - 0s 220us/sample - loss: 7.1573 - mae: 1.9191 - mse: 7.1573 - val_loss: 15.1798 - val_mae: 2.6062 - val_mse: 15.1798\n",
"354/354 [==============================] - 0s 165us/sample - loss: 7.0358 - mae: 1.8749 - mse: 7.0358 - val_loss: 15.3766 - val_mae: 2.7889 - val_mse: 15.3766\n",
"354/354 [==============================] - 0s 210us/sample - loss: 6.9060 - mae: 1.9052 - mse: 6.9060 - val_loss: 15.0909 - val_mae: 2.5988 - val_mse: 15.0909\n",
"354/354 [==============================] - 0s 167us/sample - loss: 6.8635 - mae: 1.9062 - mse: 6.8635 - val_loss: 15.5013 - val_mae: 2.8070 - val_mse: 15.5013\n",
"354/354 [==============================] - 0s 159us/sample - loss: 6.7794 - mae: 1.9122 - mse: 6.7794 - val_loss: 16.2729 - val_mae: 2.7203 - val_mse: 16.2729\n",
"354/354 [==============================] - 0s 159us/sample - loss: 6.3733 - mae: 1.8263 - mse: 6.3733 - val_loss: 15.6572 - val_mae: 2.8380 - val_mse: 15.6572\n",
"354/354 [==============================] - 0s 171us/sample - loss: 6.6483 - mae: 1.8630 - mse: 6.6483 - val_loss: 15.1825 - val_mae: 2.6010 - val_mse: 15.1825\n",
"354/354 [==============================] - 0s 180us/sample - loss: 6.4573 - mae: 1.8512 - mse: 6.4573 - val_loss: 15.6393 - val_mae: 2.6149 - val_mse: 15.6393\n",
"354/354 [==============================] - 0s 211us/sample - loss: 6.3801 - mae: 1.8381 - mse: 6.3801 - val_loss: 14.8845 - val_mae: 2.5834 - val_mse: 14.8845\n",
"354/354 [==============================] - 0s 179us/sample - loss: 6.3297 - mae: 1.8233 - mse: 6.3297 - val_loss: 15.6113 - val_mae: 2.7212 - val_mse: 15.6113\n",
"354/354 [==============================] - 0s 169us/sample - loss: 6.2057 - mae: 1.7945 - mse: 6.2057 - val_loss: 15.7076 - val_mae: 2.6109 - val_mse: 15.7076\n",
"354/354 [==============================] - 0s 215us/sample - loss: 6.2918 - mae: 1.8183 - mse: 6.2918 - val_loss: 14.6338 - val_mae: 2.6111 - val_mse: 14.6338\n",
"354/354 [==============================] - 0s 164us/sample - loss: 6.0562 - mae: 1.7805 - mse: 6.0562 - val_loss: 14.7823 - val_mae: 2.6265 - val_mse: 14.7823\n",
"354/354 [==============================] - 0s 166us/sample - loss: 6.1291 - mae: 1.8176 - mse: 6.1291 - val_loss: 15.0973 - val_mae: 2.6218 - val_mse: 15.0973\n",
"354/354 [==============================] - 0s 171us/sample - loss: 5.7409 - mae: 1.7755 - mse: 5.7409 - val_loss: 15.9924 - val_mae: 2.7079 - val_mse: 15.9924\n",
"354/354 [==============================] - 0s 167us/sample - loss: 6.0236 - mae: 1.7585 - mse: 6.0236 - val_loss: 14.6860 - val_mae: 2.5744 - val_mse: 14.6860\n",
"354/354 [==============================] - 0s 169us/sample - loss: 5.9595 - mae: 1.7907 - mse: 5.9595 - val_loss: 15.0726 - val_mae: 2.6175 - val_mse: 15.0726\n",
"354/354 [==============================] - 0s 216us/sample - loss: 5.7280 - mae: 1.7589 - mse: 5.7280 - val_loss: 14.4822 - val_mae: 2.5480 - val_mse: 14.4822\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.7664 - mae: 1.7767 - mse: 5.7664 - val_loss: 14.6256 - val_mae: 2.5334 - val_mse: 14.6256\n",
"354/354 [==============================] - 0s 162us/sample - loss: 5.5867 - mae: 1.7646 - mse: 5.5867 - val_loss: 16.3896 - val_mae: 2.6416 - val_mse: 16.3896\n",
"354/354 [==============================] - 0s 210us/sample - loss: 5.6291 - mae: 1.7258 - mse: 5.6291 - val_loss: 14.2331 - val_mae: 2.4908 - val_mse: 14.2331\n",
"354/354 [==============================] - 0s 165us/sample - loss: 5.5284 - mae: 1.7099 - mse: 5.5284 - val_loss: 14.3109 - val_mae: 2.5810 - val_mse: 14.3109\n",
"354/354 [==============================] - 0s 172us/sample - loss: 5.2182 - mae: 1.7117 - mse: 5.2182 - val_loss: 15.0785 - val_mae: 2.5368 - val_mse: 15.0785\n",
"354/354 [==============================] - 0s 159us/sample - loss: 5.4204 - mae: 1.7002 - mse: 5.4204 - val_loss: 16.3017 - val_mae: 2.6305 - val_mse: 16.3017\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.4612 - mae: 1.7117 - mse: 5.4612 - val_loss: 15.0867 - val_mae: 2.5165 - val_mse: 15.0867\n",
"354/354 [==============================] - 0s 164us/sample - loss: 5.4129 - mae: 1.7000 - mse: 5.4129 - val_loss: 14.8684 - val_mae: 2.5073 - val_mse: 14.8684\n",
"354/354 [==============================] - 0s 169us/sample - loss: 5.2621 - mae: 1.6623 - mse: 5.2621 - val_loss: 14.6805 - val_mae: 2.5521 - val_mse: 14.6805\n",
"354/354 [==============================] - 0s 166us/sample - loss: 5.1718 - mae: 1.6528 - mse: 5.1718 - val_loss: 14.3739 - val_mae: 2.5512 - val_mse: 14.3739\n",
"354/354 [==============================] - 0s 164us/sample - loss: 4.8794 - mae: 1.6359 - mse: 4.8794 - val_loss: 15.9902 - val_mae: 2.5960 - val_mse: 15.9902\n",
"354/354 [==============================] - 0s 163us/sample - loss: 5.0003 - mae: 1.6338 - mse: 5.0003 - val_loss: 14.3421 - val_mae: 2.6004 - val_mse: 14.3421\n",
"354/354 [==============================] - 0s 169us/sample - loss: 4.9487 - mae: 1.6558 - mse: 4.9487 - val_loss: 15.0409 - val_mae: 2.6790 - val_mse: 15.0409\n",
"354/354 [==============================] - 0s 165us/sample - loss: 4.9659 - mae: 1.6515 - mse: 4.9659 - val_loss: 14.6962 - val_mae: 2.6398 - val_mse: 14.6962\n",
"354/354 [==============================] - 0s 213us/sample - loss: 4.6030 - mae: 1.6493 - mse: 4.6030 - val_loss: 14.1598 - val_mae: 2.4762 - val_mse: 14.1598\n",
"354/354 [==============================] - 0s 163us/sample - loss: 4.8425 - mae: 1.6324 - mse: 4.8425 - val_loss: 14.3428 - val_mae: 2.4559 - val_mse: 14.3428\n",
"354/354 [==============================] - 0s 160us/sample - loss: 4.4911 - mae: 1.5643 - mse: 4.4911 - val_loss: 14.6917 - val_mae: 2.4930 - val_mse: 14.6917\n",
"354/354 [==============================] - 0s 164us/sample - loss: 4.6710 - mae: 1.6011 - mse: 4.6710 - val_loss: 14.8064 - val_mae: 2.5343 - val_mse: 14.8064\n",
"354/354 [==============================] - 0s 214us/sample - loss: 4.7346 - mae: 1.6153 - mse: 4.7346 - val_loss: 13.9854 - val_mae: 2.4285 - val_mse: 13.9854\n",
"354/354 [==============================] - 0s 164us/sample - loss: 4.4532 - mae: 1.5694 - mse: 4.4532 - val_loss: 15.1536 - val_mae: 2.6388 - val_mse: 15.1536\n",
"354/354 [==============================] - 0s 163us/sample - loss: 4.4388 - mae: 1.5643 - mse: 4.4388 - val_loss: 15.7038 - val_mae: 2.5911 - val_mse: 15.7038\n",
"354/354 [==============================] - 0s 165us/sample - loss: 4.4841 - mae: 1.5555 - mse: 4.4841 - val_loss: 14.5639 - val_mae: 2.5436 - val_mse: 14.5639\n",
"354/354 [==============================] - 0s 160us/sample - loss: 4.3242 - mae: 1.5403 - mse: 4.3242 - val_loss: 17.1588 - val_mae: 2.7549 - val_mse: 17.1588\n",
"354/354 [==============================] - 0s 163us/sample - loss: 4.2066 - mae: 1.5217 - mse: 4.2066 - val_loss: 15.1860 - val_mae: 2.5559 - val_mse: 15.1860\n",
"354/354 [==============================] - 0s 157us/sample - loss: 4.1626 - mae: 1.5233 - mse: 4.1626 - val_loss: 14.0627 - val_mae: 2.4766 - val_mse: 14.0627\n",
"354/354 [==============================] - 0s 164us/sample - loss: 4.1595 - mae: 1.5441 - mse: 4.1595 - val_loss: 15.5289 - val_mae: 2.6236 - val_mse: 15.5289\n",
"354/354 [==============================] - 0s 167us/sample - loss: 4.2402 - mae: 1.5440 - mse: 4.2402 - val_loss: 14.3521 - val_mae: 2.4475 - val_mse: 14.3521\n",
"354/354 [==============================] - 0s 167us/sample - loss: 4.0009 - mae: 1.5064 - mse: 4.0009 - val_loss: 15.1365 - val_mae: 2.6158 - val_mse: 15.1365\n",
"354/354 [==============================] - 0s 168us/sample - loss: 4.0595 - mae: 1.4949 - mse: 4.0595 - val_loss: 14.6071 - val_mae: 2.4938 - val_mse: 14.6071\n",
"354/354 [==============================] - 0s 168us/sample - loss: 4.0692 - mae: 1.5074 - mse: 4.0692 - val_loss: 15.0121 - val_mae: 2.5201 - val_mse: 15.0121\n",
"354/354 [==============================] - 0s 167us/sample - loss: 3.9964 - mae: 1.4940 - mse: 3.9964 - val_loss: 15.1498 - val_mae: 2.5384 - val_mse: 15.1498\n",
"354/354 [==============================] - 0s 170us/sample - loss: 3.9493 - mae: 1.5102 - mse: 3.9493 - val_loss: 14.3516 - val_mae: 2.5398 - val_mse: 14.3516\n",
"354/354 [==============================] - 0s 169us/sample - loss: 3.7438 - mae: 1.4719 - mse: 3.7438 - val_loss: 14.2705 - val_mae: 2.4448 - val_mse: 14.2705\n",
"354/354 [==============================] - 0s 162us/sample - loss: 3.7455 - mae: 1.4551 - mse: 3.7455 - val_loss: 14.5044 - val_mae: 2.4705 - val_mse: 14.5044\n",
"354/354 [==============================] - 0s 166us/sample - loss: 3.8153 - mae: 1.4834 - mse: 3.8153 - val_loss: 14.4317 - val_mae: 2.5976 - val_mse: 14.4317\n",
"354/354 [==============================] - 0s 211us/sample - loss: 3.7644 - mae: 1.4647 - mse: 3.7644 - val_loss: 13.9224 - val_mae: 2.3992 - val_mse: 13.9224\n",
"354/354 [==============================] - 0s 170us/sample - loss: 3.7750 - mae: 1.4464 - mse: 3.7750 - val_loss: 15.2701 - val_mae: 2.6804 - val_mse: 15.2701\n",
"354/354 [==============================] - 0s 215us/sample - loss: 3.6751 - mae: 1.4225 - mse: 3.6751 - val_loss: 13.7514 - val_mae: 2.4409 - val_mse: 13.7514\n",
"354/354 [==============================] - 0s 210us/sample - loss: 3.7457 - mae: 1.4496 - mse: 3.7457 - val_loss: 13.6171 - val_mae: 2.4261 - val_mse: 13.6171\n"
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
]
}
],
"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),\n",
" callbacks = [savemodel_callback])"
]
},
{
"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 : 13.6171\n",
"x_test / mae : 2.4261\n",
"x_test / mse : 13.6171\n"
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
]
}
],
"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": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"min( val_mae ) : 2.3992\n"