Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
"\n",
"\n",
"# <!-- TITLE --> [BHPD1] - Regression with a Dense Network (DNN)\n",
"<!-- DESC --> Simple example of a regression with the dataset Boston Housing Prices Dataset (BHPD)\n",
12
13
14
15
16
17
18
19
20
21
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
"<!-- 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 Prices 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",
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
84
85
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
"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",
"div .comment{\n",
" font-size:0.8em;\n",
" color:#696969;\n",
"}\n",
"\n",
"\n",
"\n",
"</style>\n",
"\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"<br>**FIDLE 2020 - Practical Work Module**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Version : 2.0.1\n",
"Notebook id : BHPD1\n",
"Run time : Thursday 14 January 2021, 10:57:04\n",
"TensorFlow version : 2.2.0\n",
"Keras version : 2.3.0-tf\n",
"Datasets dir : /home/pjluc/datasets/fidle\n",
"Run dir : ./run\n",
"Update keras cache : False\n"
]
}
],
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
"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 pwk\n",
"\n",
"datasets_dir = pwk.init('BHPD1')"
]
},
{
"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",
"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",
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
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
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_ba065_\" ><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_ba065_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_ba065_row0_col0\" class=\"data row0 col0\" >0.01</td>\n",
" <td id=\"T_ba065_row0_col1\" class=\"data row0 col1\" >18.00</td>\n",
" <td id=\"T_ba065_row0_col2\" class=\"data row0 col2\" >2.31</td>\n",
" <td id=\"T_ba065_row0_col3\" class=\"data row0 col3\" >0.00</td>\n",
" <td id=\"T_ba065_row0_col4\" class=\"data row0 col4\" >0.54</td>\n",
" <td id=\"T_ba065_row0_col5\" class=\"data row0 col5\" >6.58</td>\n",
" <td id=\"T_ba065_row0_col6\" class=\"data row0 col6\" >65.20</td>\n",
" <td id=\"T_ba065_row0_col7\" class=\"data row0 col7\" >4.09</td>\n",
" <td id=\"T_ba065_row0_col8\" class=\"data row0 col8\" >1.00</td>\n",
" <td id=\"T_ba065_row0_col9\" class=\"data row0 col9\" >296.00</td>\n",
" <td id=\"T_ba065_row0_col10\" class=\"data row0 col10\" >15.30</td>\n",
" <td id=\"T_ba065_row0_col11\" class=\"data row0 col11\" >396.90</td>\n",
" <td id=\"T_ba065_row0_col12\" class=\"data row0 col12\" >4.98</td>\n",
" <td id=\"T_ba065_row0_col13\" class=\"data row0 col13\" >24.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_ba065_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_ba065_row1_col0\" class=\"data row1 col0\" >0.03</td>\n",
" <td id=\"T_ba065_row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_ba065_row1_col2\" class=\"data row1 col2\" >7.07</td>\n",
" <td id=\"T_ba065_row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_ba065_row1_col4\" class=\"data row1 col4\" >0.47</td>\n",
" <td id=\"T_ba065_row1_col5\" class=\"data row1 col5\" >6.42</td>\n",
" <td id=\"T_ba065_row1_col6\" class=\"data row1 col6\" >78.90</td>\n",
" <td id=\"T_ba065_row1_col7\" class=\"data row1 col7\" >4.97</td>\n",
" <td id=\"T_ba065_row1_col8\" class=\"data row1 col8\" >2.00</td>\n",
" <td id=\"T_ba065_row1_col9\" class=\"data row1 col9\" >242.00</td>\n",
" <td id=\"T_ba065_row1_col10\" class=\"data row1 col10\" >17.80</td>\n",
" <td id=\"T_ba065_row1_col11\" class=\"data row1 col11\" >396.90</td>\n",
" <td id=\"T_ba065_row1_col12\" class=\"data row1 col12\" >9.14</td>\n",
" <td id=\"T_ba065_row1_col13\" class=\"data row1 col13\" >21.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_ba065_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_ba065_row2_col0\" class=\"data row2 col0\" >0.03</td>\n",
" <td id=\"T_ba065_row2_col1\" class=\"data row2 col1\" >0.00</td>\n",
" <td id=\"T_ba065_row2_col2\" class=\"data row2 col2\" >7.07</td>\n",
" <td id=\"T_ba065_row2_col3\" class=\"data row2 col3\" >0.00</td>\n",
" <td id=\"T_ba065_row2_col4\" class=\"data row2 col4\" >0.47</td>\n",
" <td id=\"T_ba065_row2_col5\" class=\"data row2 col5\" >7.18</td>\n",
" <td id=\"T_ba065_row2_col6\" class=\"data row2 col6\" >61.10</td>\n",
" <td id=\"T_ba065_row2_col7\" class=\"data row2 col7\" >4.97</td>\n",
" <td id=\"T_ba065_row2_col8\" class=\"data row2 col8\" >2.00</td>\n",
" <td id=\"T_ba065_row2_col9\" class=\"data row2 col9\" >242.00</td>\n",
" <td id=\"T_ba065_row2_col10\" class=\"data row2 col10\" >17.80</td>\n",
" <td id=\"T_ba065_row2_col11\" class=\"data row2 col11\" >392.83</td>\n",
" <td id=\"T_ba065_row2_col12\" class=\"data row2 col12\" >4.03</td>\n",
" <td id=\"T_ba065_row2_col13\" class=\"data row2 col13\" >34.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_ba065_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_ba065_row3_col0\" class=\"data row3 col0\" >0.03</td>\n",
" <td id=\"T_ba065_row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_ba065_row3_col2\" class=\"data row3 col2\" >2.18</td>\n",
" <td id=\"T_ba065_row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_ba065_row3_col4\" class=\"data row3 col4\" >0.46</td>\n",
" <td id=\"T_ba065_row3_col5\" class=\"data row3 col5\" >7.00</td>\n",
" <td id=\"T_ba065_row3_col6\" class=\"data row3 col6\" >45.80</td>\n",
" <td id=\"T_ba065_row3_col7\" class=\"data row3 col7\" >6.06</td>\n",
" <td id=\"T_ba065_row3_col8\" class=\"data row3 col8\" >3.00</td>\n",
" <td id=\"T_ba065_row3_col9\" class=\"data row3 col9\" >222.00</td>\n",
" <td id=\"T_ba065_row3_col10\" class=\"data row3 col10\" >18.70</td>\n",
" <td id=\"T_ba065_row3_col11\" class=\"data row3 col11\" >394.63</td>\n",
" <td id=\"T_ba065_row3_col12\" class=\"data row3 col12\" >2.94</td>\n",
" <td id=\"T_ba065_row3_col13\" class=\"data row3 col13\" >33.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_ba065_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_ba065_row4_col0\" class=\"data row4 col0\" >0.07</td>\n",
" <td id=\"T_ba065_row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_ba065_row4_col2\" class=\"data row4 col2\" >2.18</td>\n",
" <td id=\"T_ba065_row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_ba065_row4_col4\" class=\"data row4 col4\" >0.46</td>\n",
" <td id=\"T_ba065_row4_col5\" class=\"data row4 col5\" >7.15</td>\n",
" <td id=\"T_ba065_row4_col6\" class=\"data row4 col6\" >54.20</td>\n",
" <td id=\"T_ba065_row4_col7\" class=\"data row4 col7\" >6.06</td>\n",
" <td id=\"T_ba065_row4_col8\" class=\"data row4 col8\" >3.00</td>\n",
" <td id=\"T_ba065_row4_col9\" class=\"data row4 col9\" >222.00</td>\n",
" <td id=\"T_ba065_row4_col10\" class=\"data row4 col10\" >18.70</td>\n",
" <td id=\"T_ba065_row4_col11\" class=\"data row4 col11\" >396.90</td>\n",
" <td id=\"T_ba065_row4_col12\" class=\"data row4 col12\" >5.33</td>\n",
" <td id=\"T_ba065_row4_col13\" class=\"data row4 col13\" >36.20</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f64eb329f50>"
]
},
"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'{datasets_dir}/BHPD/origine/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",
"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"
]
}
],
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
"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",
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
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
734
735
736
737
738
739
740
741
742
743
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_e5177_\" ><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_e5177_level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_e5177_row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_e5177_row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_e5177_row1_col0\" class=\"data row1 col0\" >3.81</td>\n",
" <td id=\"T_e5177_row1_col1\" class=\"data row1 col1\" >12.47</td>\n",
" <td id=\"T_e5177_row1_col2\" class=\"data row1 col2\" >11.00</td>\n",
" <td id=\"T_e5177_row1_col3\" class=\"data row1 col3\" >0.08</td>\n",
" <td id=\"T_e5177_row1_col4\" class=\"data row1 col4\" >0.55</td>\n",
" <td id=\"T_e5177_row1_col5\" class=\"data row1 col5\" >6.32</td>\n",
" <td id=\"T_e5177_row1_col6\" class=\"data row1 col6\" >67.06</td>\n",
" <td id=\"T_e5177_row1_col7\" class=\"data row1 col7\" >3.86</td>\n",
" <td id=\"T_e5177_row1_col8\" class=\"data row1 col8\" >9.58</td>\n",
" <td id=\"T_e5177_row1_col9\" class=\"data row1 col9\" >406.70</td>\n",
" <td id=\"T_e5177_row1_col10\" class=\"data row1 col10\" >18.35</td>\n",
" <td id=\"T_e5177_row1_col11\" class=\"data row1 col11\" >353.78</td>\n",
" <td id=\"T_e5177_row1_col12\" class=\"data row1 col12\" >12.34</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_e5177_row2_col0\" class=\"data row2 col0\" >9.49</td>\n",
" <td id=\"T_e5177_row2_col1\" class=\"data row2 col1\" >24.98</td>\n",
" <td id=\"T_e5177_row2_col2\" class=\"data row2 col2\" >6.86</td>\n",
" <td id=\"T_e5177_row2_col3\" class=\"data row2 col3\" >0.27</td>\n",
" <td id=\"T_e5177_row2_col4\" class=\"data row2 col4\" >0.12</td>\n",
" <td id=\"T_e5177_row2_col5\" class=\"data row2 col5\" >0.71</td>\n",
" <td id=\"T_e5177_row2_col6\" class=\"data row2 col6\" >29.01</td>\n",
" <td id=\"T_e5177_row2_col7\" class=\"data row2 col7\" >2.14</td>\n",
" <td id=\"T_e5177_row2_col8\" class=\"data row2 col8\" >8.74</td>\n",
" <td id=\"T_e5177_row2_col9\" class=\"data row2 col9\" >169.05</td>\n",
" <td id=\"T_e5177_row2_col10\" class=\"data row2 col10\" >2.18</td>\n",
" <td id=\"T_e5177_row2_col11\" class=\"data row2 col11\" >97.53</td>\n",
" <td id=\"T_e5177_row2_col12\" class=\"data row2 col12\" >7.17</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_e5177_row3_col0\" class=\"data row3 col0\" >0.01</td>\n",
" <td id=\"T_e5177_row3_col1\" class=\"data row3 col1\" >0.00</td>\n",
" <td id=\"T_e5177_row3_col2\" class=\"data row3 col2\" >0.46</td>\n",
" <td id=\"T_e5177_row3_col3\" class=\"data row3 col3\" >0.00</td>\n",
" <td id=\"T_e5177_row3_col4\" class=\"data row3 col4\" >0.39</td>\n",
" <td id=\"T_e5177_row3_col5\" class=\"data row3 col5\" >3.56</td>\n",
" <td id=\"T_e5177_row3_col6\" class=\"data row3 col6\" >2.90</td>\n",
" <td id=\"T_e5177_row3_col7\" class=\"data row3 col7\" >1.13</td>\n",
" <td id=\"T_e5177_row3_col8\" class=\"data row3 col8\" >1.00</td>\n",
" <td id=\"T_e5177_row3_col9\" class=\"data row3 col9\" >187.00</td>\n",
" <td id=\"T_e5177_row3_col10\" class=\"data row3 col10\" >12.60</td>\n",
" <td id=\"T_e5177_row3_col11\" class=\"data row3 col11\" >0.32</td>\n",
" <td id=\"T_e5177_row3_col12\" class=\"data row3 col12\" >1.92</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_e5177_row4_col0\" class=\"data row4 col0\" >0.08</td>\n",
" <td id=\"T_e5177_row4_col1\" class=\"data row4 col1\" >0.00</td>\n",
" <td id=\"T_e5177_row4_col2\" class=\"data row4 col2\" >5.19</td>\n",
" <td id=\"T_e5177_row4_col3\" class=\"data row4 col3\" >0.00</td>\n",
" <td id=\"T_e5177_row4_col4\" class=\"data row4 col4\" >0.45</td>\n",
" <td id=\"T_e5177_row4_col5\" class=\"data row4 col5\" >5.92</td>\n",
" <td id=\"T_e5177_row4_col6\" class=\"data row4 col6\" >39.25</td>\n",
" <td id=\"T_e5177_row4_col7\" class=\"data row4 col7\" >2.11</td>\n",
" <td id=\"T_e5177_row4_col8\" class=\"data row4 col8\" >4.00</td>\n",
" <td id=\"T_e5177_row4_col9\" class=\"data row4 col9\" >281.75</td>\n",
" <td id=\"T_e5177_row4_col10\" class=\"data row4 col10\" >16.90</td>\n",
" <td id=\"T_e5177_row4_col11\" class=\"data row4 col11\" >376.25</td>\n",
" <td id=\"T_e5177_row4_col12\" class=\"data row4 col12\" >6.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_e5177_row5_col0\" class=\"data row5 col0\" >0.27</td>\n",
" <td id=\"T_e5177_row5_col1\" class=\"data row5 col1\" >0.00</td>\n",
" <td id=\"T_e5177_row5_col2\" class=\"data row5 col2\" >8.56</td>\n",
" <td id=\"T_e5177_row5_col3\" class=\"data row5 col3\" >0.00</td>\n",
" <td id=\"T_e5177_row5_col4\" class=\"data row5 col4\" >0.53</td>\n",
" <td id=\"T_e5177_row5_col5\" class=\"data row5 col5\" >6.23</td>\n",
" <td id=\"T_e5177_row5_col6\" class=\"data row5 col6\" >76.80</td>\n",
" <td id=\"T_e5177_row5_col7\" class=\"data row5 col7\" >3.27</td>\n",
" <td id=\"T_e5177_row5_col8\" class=\"data row5 col8\" >5.00</td>\n",
" <td id=\"T_e5177_row5_col9\" class=\"data row5 col9\" >329.50</td>\n",
" <td id=\"T_e5177_row5_col10\" class=\"data row5 col10\" >18.80</td>\n",
" <td id=\"T_e5177_row5_col11\" class=\"data row5 col11\" >391.88</td>\n",
" <td id=\"T_e5177_row5_col12\" class=\"data row5 col12\" >10.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_e5177_row6_col0\" class=\"data row6 col0\" >3.65</td>\n",
" <td id=\"T_e5177_row6_col1\" class=\"data row6 col1\" >12.50</td>\n",
" <td id=\"T_e5177_row6_col2\" class=\"data row6 col2\" >18.10</td>\n",
" <td id=\"T_e5177_row6_col3\" class=\"data row6 col3\" >0.00</td>\n",
" <td id=\"T_e5177_row6_col4\" class=\"data row6 col4\" >0.62</td>\n",
" <td id=\"T_e5177_row6_col5\" class=\"data row6 col5\" >6.68</td>\n",
" <td id=\"T_e5177_row6_col6\" class=\"data row6 col6\" >93.75</td>\n",
" <td id=\"T_e5177_row6_col7\" class=\"data row6 col7\" >5.29</td>\n",
" <td id=\"T_e5177_row6_col8\" class=\"data row6 col8\" >24.00</td>\n",
" <td id=\"T_e5177_row6_col9\" class=\"data row6 col9\" >666.00</td>\n",
" <td id=\"T_e5177_row6_col10\" class=\"data row6 col10\" >20.20</td>\n",
" <td id=\"T_e5177_row6_col11\" class=\"data row6 col11\" >396.38</td>\n",
" <td id=\"T_e5177_row6_col12\" class=\"data row6 col12\" >16.44</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_e5177_level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_e5177_row7_col0\" class=\"data row7 col0\" >88.98</td>\n",
" <td id=\"T_e5177_row7_col1\" class=\"data row7 col1\" >95.00</td>\n",
" <td id=\"T_e5177_row7_col2\" class=\"data row7 col2\" >27.74</td>\n",
" <td id=\"T_e5177_row7_col3\" class=\"data row7 col3\" >1.00</td>\n",
" <td id=\"T_e5177_row7_col4\" class=\"data row7 col4\" >0.87</td>\n",
" <td id=\"T_e5177_row7_col5\" class=\"data row7 col5\" >8.78</td>\n",
" <td id=\"T_e5177_row7_col6\" class=\"data row7 col6\" >100.00</td>\n",
" <td id=\"T_e5177_row7_col7\" class=\"data row7 col7\" >12.13</td>\n",
" <td id=\"T_e5177_row7_col8\" class=\"data row7 col8\" >24.00</td>\n",
" <td id=\"T_e5177_row7_col9\" class=\"data row7 col9\" >711.00</td>\n",
" <td id=\"T_e5177_row7_col10\" class=\"data row7 col10\" >22.00</td>\n",
" <td id=\"T_e5177_row7_col11\" class=\"data row7 col11\" >396.90</td>\n",
" <td id=\"T_e5177_row7_col12\" class=\"data row7 col12\" >37.97</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f64356310d0>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_0f378_\" ><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_0f378_level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_0f378_row0_col0\" class=\"data row0 col0\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col1\" class=\"data row0 col1\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col2\" class=\"data row0 col2\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col3\" class=\"data row0 col3\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col4\" class=\"data row0 col4\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col5\" class=\"data row0 col5\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col6\" class=\"data row0 col6\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col7\" class=\"data row0 col7\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col8\" class=\"data row0 col8\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col9\" class=\"data row0 col9\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col10\" class=\"data row0 col10\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col11\" class=\"data row0 col11\" >354.00</td>\n",
" <td id=\"T_0f378_row0_col12\" class=\"data row0 col12\" >354.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_0f378_row1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
" <td id=\"T_0f378_row1_col2\" class=\"data row1 col2\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_0f378_row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col5\" class=\"data row1 col5\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col6\" class=\"data row1 col6\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col7\" class=\"data row1 col7\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col8\" class=\"data row1 col8\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col9\" class=\"data row1 col9\" >0.00</td>\n",
" <td id=\"T_0f378_row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_0f378_row1_col11\" class=\"data row1 col11\" >-0.00</td>\n",
" <td id=\"T_0f378_row1_col12\" class=\"data row1 col12\" >-0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_0f378_row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" <td id=\"T_0f378_row2_col12\" class=\"data row2 col12\" >1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_0f378_row3_col0\" class=\"data row3 col0\" >-0.40</td>\n",
" <td id=\"T_0f378_row3_col1\" class=\"data row3 col1\" >-0.50</td>\n",
" <td id=\"T_0f378_row3_col2\" class=\"data row3 col2\" >-1.54</td>\n",
" <td id=\"T_0f378_row3_col3\" class=\"data row3 col3\" >-0.30</td>\n",
" <td id=\"T_0f378_row3_col4\" class=\"data row3 col4\" >-1.42</td>\n",
" <td id=\"T_0f378_row3_col5\" class=\"data row3 col5\" >-3.87</td>\n",
" <td id=\"T_0f378_row3_col6\" class=\"data row3 col6\" >-2.21</td>\n",
" <td id=\"T_0f378_row3_col7\" class=\"data row3 col7\" >-1.28</td>\n",
" <td id=\"T_0f378_row3_col8\" class=\"data row3 col8\" >-0.98</td>\n",
" <td id=\"T_0f378_row3_col9\" class=\"data row3 col9\" >-1.30</td>\n",
" <td id=\"T_0f378_row3_col10\" class=\"data row3 col10\" >-2.64</td>\n",
" <td id=\"T_0f378_row3_col11\" class=\"data row3 col11\" >-3.62</td>\n",
" <td id=\"T_0f378_row3_col12\" class=\"data row3 col12\" >-1.45</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_0f378_row4_col0\" class=\"data row4 col0\" >-0.39</td>\n",
" <td id=\"T_0f378_row4_col1\" class=\"data row4 col1\" >-0.50</td>\n",
" <td id=\"T_0f378_row4_col2\" class=\"data row4 col2\" >-0.85</td>\n",
" <td id=\"T_0f378_row4_col3\" class=\"data row4 col3\" >-0.30</td>\n",
" <td id=\"T_0f378_row4_col4\" class=\"data row4 col4\" >-0.89</td>\n",
" <td id=\"T_0f378_row4_col5\" class=\"data row4 col5\" >-0.56</td>\n",
" <td id=\"T_0f378_row4_col6\" class=\"data row4 col6\" >-0.96</td>\n",
" <td id=\"T_0f378_row4_col7\" class=\"data row4 col7\" >-0.82</td>\n",
" <td id=\"T_0f378_row4_col8\" class=\"data row4 col8\" >-0.64</td>\n",
" <td id=\"T_0f378_row4_col9\" class=\"data row4 col9\" >-0.74</td>\n",
" <td id=\"T_0f378_row4_col10\" class=\"data row4 col10\" >-0.67</td>\n",
" <td id=\"T_0f378_row4_col11\" class=\"data row4 col11\" >0.23</td>\n",
" <td id=\"T_0f378_row4_col12\" class=\"data row4 col12\" >-0.78</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_0f378_row5_col0\" class=\"data row5 col0\" >-0.37</td>\n",
" <td id=\"T_0f378_row5_col1\" class=\"data row5 col1\" >-0.50</td>\n",
" <td id=\"T_0f378_row5_col2\" class=\"data row5 col2\" >-0.36</td>\n",
" <td id=\"T_0f378_row5_col3\" class=\"data row5 col3\" >-0.30</td>\n",
" <td id=\"T_0f378_row5_col4\" class=\"data row5 col4\" >-0.18</td>\n",
" <td id=\"T_0f378_row5_col5\" class=\"data row5 col5\" >-0.13</td>\n",
" <td id=\"T_0f378_row5_col6\" class=\"data row5 col6\" >0.34</td>\n",
" <td id=\"T_0f378_row5_col7\" class=\"data row5 col7\" >-0.28</td>\n",
" <td id=\"T_0f378_row5_col8\" class=\"data row5 col8\" >-0.52</td>\n",
" <td id=\"T_0f378_row5_col9\" class=\"data row5 col9\" >-0.46</td>\n",
" <td id=\"T_0f378_row5_col10\" class=\"data row5 col10\" >0.21</td>\n",
" <td id=\"T_0f378_row5_col11\" class=\"data row5 col11\" >0.39</td>\n",
" <td id=\"T_0f378_row5_col12\" class=\"data row5 col12\" >-0.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_0f378_row6_col0\" class=\"data row6 col0\" >-0.02</td>\n",
" <td id=\"T_0f378_row6_col1\" class=\"data row6 col1\" >0.00</td>\n",
" <td id=\"T_0f378_row6_col2\" class=\"data row6 col2\" >1.04</td>\n",
" <td id=\"T_0f378_row6_col3\" class=\"data row6 col3\" >-0.30</td>\n",
" <td id=\"T_0f378_row6_col4\" class=\"data row6 col4\" >0.60</td>\n",
" <td id=\"T_0f378_row6_col5\" class=\"data row6 col5\" >0.50</td>\n",
" <td id=\"T_0f378_row6_col6\" class=\"data row6 col6\" >0.92</td>\n",
" <td id=\"T_0f378_row6_col7\" class=\"data row6 col7\" >0.66</td>\n",
" <td id=\"T_0f378_row6_col8\" class=\"data row6 col8\" >1.65</td>\n",
" <td id=\"T_0f378_row6_col9\" class=\"data row6 col9\" >1.53</td>\n",
" <td id=\"T_0f378_row6_col10\" class=\"data row6 col10\" >0.85</td>\n",
" <td id=\"T_0f378_row6_col11\" class=\"data row6 col11\" >0.44</td>\n",
" <td id=\"T_0f378_row6_col12\" class=\"data row6 col12\" >0.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0f378_level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_0f378_row7_col0\" class=\"data row7 col0\" >8.97</td>\n",
" <td id=\"T_0f378_row7_col1\" class=\"data row7 col1\" >3.30</td>\n",
" <td id=\"T_0f378_row7_col2\" class=\"data row7 col2\" >2.44</td>\n",
" <td id=\"T_0f378_row7_col3\" class=\"data row7 col3\" >3.34</td>\n",
" <td id=\"T_0f378_row7_col4\" class=\"data row7 col4\" >2.70</td>\n",
" <td id=\"T_0f378_row7_col5\" class=\"data row7 col5\" >3.46</td>\n",
" <td id=\"T_0f378_row7_col6\" class=\"data row7 col6\" >1.14</td>\n",
" <td id=\"T_0f378_row7_col7\" class=\"data row7 col7\" >3.86</td>\n",
" <td id=\"T_0f378_row7_col8\" class=\"data row7 col8\" >1.65</td>\n",
" <td id=\"T_0f378_row7_col9\" class=\"data row7 col9\" >1.80</td>\n",
" <td id=\"T_0f378_row7_col10\" class=\"data row7 col10\" >1.68</td>\n",
" <td id=\"T_0f378_row7_col11\" class=\"data row7 col11\" >0.44</td>\n",
" <td id=\"T_0f378_row7_col12\" class=\"data row7 col12\" >3.57</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f64e825c510>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_b130d_\" ><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_b130d_level0_row0\" class=\"row_heading level0 row0\" >473</th>\n",
" <td id=\"T_b130d_row0_col0\" class=\"data row0 col0\" >0.09</td>\n",
" <td id=\"T_b130d_row0_col1\" class=\"data row0 col1\" >-0.50</td>\n",
" <td id=\"T_b130d_row0_col2\" class=\"data row0 col2\" >1.04</td>\n",
" <td id=\"T_b130d_row0_col3\" class=\"data row0 col3\" >-0.30</td>\n",
" <td id=\"T_b130d_row0_col4\" class=\"data row0 col4\" >0.52</td>\n",
" <td id=\"T_b130d_row0_col5\" class=\"data row0 col5\" >0.93</td>\n",
" <td id=\"T_b130d_row0_col6\" class=\"data row0 col6\" >0.02</td>\n",
" <td id=\"T_b130d_row0_col7\" class=\"data row0 col7\" >-0.62</td>\n",
" <td id=\"T_b130d_row0_col8\" class=\"data row0 col8\" >1.65</td>\n",
" <td id=\"T_b130d_row0_col9\" class=\"data row0 col9\" >1.53</td>\n",
" <td id=\"T_b130d_row0_col10\" class=\"data row0 col10\" >0.85</td>\n",
" <td id=\"T_b130d_row0_col11\" class=\"data row0 col11\" >0.21</td>\n",
" <td id=\"T_b130d_row0_col12\" class=\"data row0 col12\" >-0.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b130d_level0_row1\" class=\"row_heading level0 row1\" >232</th>\n",
" <td id=\"T_b130d_row1_col0\" class=\"data row1 col0\" >-0.34</td>\n",
" <td id=\"T_b130d_row1_col1\" class=\"data row1 col1\" >-0.50</td>\n",
" <td id=\"T_b130d_row1_col2\" class=\"data row1 col2\" >-0.70</td>\n",
" <td id=\"T_b130d_row1_col3\" class=\"data row1 col3\" >-0.30</td>\n",
" <td id=\"T_b130d_row1_col4\" class=\"data row1 col4\" >-0.39</td>\n",
" <td id=\"T_b130d_row1_col5\" class=\"data row1 col5\" >2.83</td>\n",
" <td id=\"T_b130d_row1_col6\" class=\"data row1 col6\" >0.22</td>\n",
" <td id=\"T_b130d_row1_col7\" class=\"data row1 col7\" >-0.01</td>\n",
" <td id=\"T_b130d_row1_col8\" class=\"data row1 col8\" >-0.18</td>\n",
" <td id=\"T_b130d_row1_col9\" class=\"data row1 col9\" >-0.59</td>\n",
" <td id=\"T_b130d_row1_col10\" class=\"data row1 col10\" >-0.44</td>\n",
" <td id=\"T_b130d_row1_col11\" class=\"data row1 col11\" >0.33</td>\n",
" <td id=\"T_b130d_row1_col12\" class=\"data row1 col12\" >-1.38</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b130d_level0_row2\" class=\"row_heading level0 row2\" >256</th>\n",
" <td id=\"T_b130d_row2_col0\" class=\"data row2 col0\" >-0.40</td>\n",
" <td id=\"T_b130d_row2_col1\" class=\"data row2 col1\" >3.10</td>\n",
" <td id=\"T_b130d_row2_col2\" class=\"data row2 col2\" >-1.06</td>\n",
" <td id=\"T_b130d_row2_col3\" class=\"data row2 col3\" >-0.30</td>\n",
" <td id=\"T_b130d_row2_col4\" class=\"data row2 col4\" >-1.35</td>\n",
" <td id=\"T_b130d_row2_col5\" class=\"data row2 col5\" >1.59</td>\n",
" <td id=\"T_b130d_row2_col6\" class=\"data row2 col6\" >-1.13</td>\n",
" <td id=\"T_b130d_row2_col7\" class=\"data row2 col7\" >1.15</td>\n",
" <td id=\"T_b130d_row2_col8\" class=\"data row2 col8\" >-0.75</td>\n",
" <td id=\"T_b130d_row2_col9\" class=\"data row2 col9\" >-0.96</td>\n",
" <td id=\"T_b130d_row2_col10\" class=\"data row2 col10\" >-1.13</td>\n",
" <td id=\"T_b130d_row2_col11\" class=\"data row2 col11\" >0.33</td>\n",
" <td id=\"T_b130d_row2_col12\" class=\"data row2 col12\" >-1.29</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b130d_level0_row3\" class=\"row_heading level0 row3\" >425</th>\n",
" <td id=\"T_b130d_row3_col0\" class=\"data row3 col0\" >1.27</td>\n",
" <td id=\"T_b130d_row3_col1\" class=\"data row3 col1\" >-0.50</td>\n",
" <td id=\"T_b130d_row3_col2\" class=\"data row3 col2\" >1.04</td>\n",
" <td id=\"T_b130d_row3_col3\" class=\"data row3 col3\" >-0.30</td>\n",
" <td id=\"T_b130d_row3_col4\" class=\"data row3 col4\" >1.07</td>\n",
" <td id=\"T_b130d_row3_col5\" class=\"data row3 col5\" >-0.59</td>\n",
" <td id=\"T_b130d_row3_col6\" class=\"data row3 col6\" >0.98</td>\n",
" <td id=\"T_b130d_row3_col7\" class=\"data row3 col7\" >-0.91</td>\n",
" <td id=\"T_b130d_row3_col8\" class=\"data row3 col8\" >1.65</td>\n",
" <td id=\"T_b130d_row3_col9\" class=\"data row3 col9\" >1.53</td>\n",
" <td id=\"T_b130d_row3_col10\" class=\"data row3 col10\" >0.85</td>\n",
" <td id=\"T_b130d_row3_col11\" class=\"data row3 col11\" >-3.55</td>\n",
" <td id=\"T_b130d_row3_col12\" class=\"data row3 col12\" >1.68</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_b130d_level0_row4\" class=\"row_heading level0 row4\" >230</th>\n",
" <td id=\"T_b130d_row4_col0\" class=\"data row4 col0\" >-0.34</td>\n",
" <td id=\"T_b130d_row4_col1\" class=\"data row4 col1\" >-0.50</td>\n",
" <td id=\"T_b130d_row4_col2\" class=\"data row4 col2\" >-0.70</td>\n",
" <td id=\"T_b130d_row4_col3\" class=\"data row4 col3\" >-0.30</td>\n",
" <td id=\"T_b130d_row4_col4\" class=\"data row4 col4\" >-0.41</td>\n",
" <td id=\"T_b130d_row4_col5\" class=\"data row4 col5\" >-0.48</td>\n",
" <td id=\"T_b130d_row4_col6\" class=\"data row4 col6\" >0.04</td>\n",
" <td id=\"T_b130d_row4_col7\" class=\"data row4 col7\" >-0.09</td>\n",
" <td id=\"T_b130d_row4_col8\" class=\"data row4 col8\" >-0.18</td>\n",
" <td id=\"T_b130d_row4_col9\" class=\"data row4 col9\" >-0.59</td>\n",
" <td id=\"T_b130d_row4_col10\" class=\"data row4 col10\" >-0.44</td>\n",
" <td id=\"T_b130d_row4_col11\" class=\"data row4 col11\" >0.25</td>\n",
" <td id=\"T_b130d_row4_col12\" class=\"data row4 col12\" >-0.10</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f64eb329f50>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
"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",
"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(32, activation='relu', name='Dense_n1'))\n",
" model.add(keras.layers.Dense(64, activation='relu', name='Dense_n2'))\n",
" model.add(keras.layers.Dense(32, activation='relu', name='Dense_n3'))\n",
" model.add(keras.layers.Dense(1, name='Output'))\n",
" \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",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential_5\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"Dense_n1 (Dense) (None, 32) 448 \n",
"_________________________________________________________________\n",
"Dense_n2 (Dense) (None, 64) 2112 \n",
"_________________________________________________________________\n",
"Dense_n3 (Dense) (None, 32) 2080 \n",
"_________________________________________________________________\n",
"Output (Dense) (None, 1) 33 \n",
"=================================================================\n",
"Total params: 4,673\n",
"Trainable params: 4,673\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"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",
"source": [
"history = model.fit(x_train,\n",
" y_train,\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",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5/5 [==============================] - 0s 2ms/step - loss: 11.9059 - mae: 2.6448 - mse: 11.9059\n",
"x_test / loss : 11.9059\n",
"x_test / mae : 2.6448\n",
"x_test / mse : 11.9059\n"
]
}
],
"score = model.evaluate(x_test, y_test, verbose=1)\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",
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
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
965
966
967
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
996
997
998
999
1000
"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>0</th>\n",
" <td>496.808258</td>\n",
" <td>20.406666</td>\n",
" <td>496.808258</td>\n",
" <td>299.685791</td>\n",
" <td>15.153587</td>\n",
" <td>299.685791</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>162.919540</td>\n",
" <td>10.265703</td>\n",
" <td>162.919540</td>\n",
" <td>65.847511</td>\n",
" <td>6.263887</td>\n",
" <td>65.847511</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>58.518223</td>\n",
" <td>5.800590</td>\n",
" <td>58.518223</td>\n",
" <td>33.691109</td>\n",
" <td>4.296726</td>\n",
" <td>33.691113</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>31.010996</td>\n",
" <td>4.039098</td>\n",
" <td>31.010996</td>\n",
" <td>24.567926</td>\n",
" <td>3.534089</td>\n",
" <td>24.567926</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>23.336550</td>\n",
" <td>3.394345</td>\n",
" <td>23.336550</td>\n",
" <td>21.112747</td>\n",
" <td>3.387527</td>\n",
" <td>21.112747</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>20.368439</td>\n",
" <td>3.112291</td>\n",
" <td>20.368439</td>\n",
" <td>19.033449</td>\n",
" <td>3.166226</td>\n",
" <td>19.033449</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>18.681219</td>\n",
" <td>2.996637</td>\n",
" <td>18.681219</td>\n",
" <td>18.153992</td>\n",
" <td>3.020701</td>\n",
" <td>18.153992</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>17.302563</td>\n",