/
09-appendix-a.html
1025 lines (928 loc) · 117 KB
/
09-appendix-a.html
1
2
3
4
5
6
7
8
9
10
11
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
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
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
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
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
362
363
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
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
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
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
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8" />
<title>附錄 A — 新手村逃脫！初心者的 Python 機器學習攻略 1.0.0 documentation</title>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.11.2/css/all.min.css" integrity="sha384-KA6wR/X5RY4zFAHpv/CnoG2UW1uogYfdnP67Uv7eULvTveboZJg0qUpmJZb5VqzN" crossorigin="anonymous">
<link href="_static/css/index.css" rel="stylesheet">
<link rel="stylesheet" href="_static/sphinx-book-theme.css" type="text/css" />
<link rel="stylesheet" href="_static/pygments.css" type="text/css" />
<script id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script>
<script src="_static/sphinx-book-theme.js"></script>
<script src="_static/jquery.js"></script>
<script src="_static/underscore.js"></script>
<script src="_static/doctools.js"></script>
<script src="_static/language_data.js"></script>
<script src="_static/sphinx-book-theme.js"></script>
<script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
<script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/x-mathjax-config">MathJax.Hub.Config({"TeX": {"equationNumbers": {"autoNumber": "AMS", "useLabelIds": true}}, "jax": ["input/TeX", "output/HTML-CSS"], "displayAlign": "left", "tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="prev" title="深度學習入門" href="08-deep-learning.html" />
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="docsearch:language" content="en">
</head>
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
<div class="container-xl">
<div class="row">
<div class="col-12 col-md-3 bd-sidebar site-navigation show" id="site-navigation">
<div class="navbar-brand-box">
<a class="navbar-brand text-wrap" href="index.html">
<h1 class="site-logo" id="site-title">新手村逃脫！初心者的 Python 機器學習攻略 1.0.0 documentation</h1>
</a>
</div>
<form class="bd-search d-flex align-items-center" action="search.html" method="get">
<i class="icon fas fa-search"></i>
<input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" >
</form>
<nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation">
<ul class="nav sidenav_l1">
<li class="">
<a href="00-preface.html">關於本書</a>
</li>
<li class="">
<a href="01-introduction.html">關於視覺化與機器學習</a>
</li>
<li class="">
<a href="02-numpy.html">數列運算</a>
</li>
<li class="">
<a href="03-matplotlib.html">資料探索</a>
</li>
<li class="">
<a href="04-sklearn.html">機器學習入門</a>
</li>
<li class="">
<a href="05-regression.html">數值預測的任務</a>
</li>
<li class="">
<a href="06-classification.html">類別預測的任務</a>
</li>
<li class="">
<a href="07-performance.html">表現的評估</a>
</li>
<li class="">
<a href="08-deep-learning.html">深度學習入門</a>
</li>
<li class="active">
<a href="">附錄 A</a>
</li>
</ul>
</nav>
<!-- To handle the deprecated key -->
<div class="navbar_extra_footer">
Theme by the <a href="https://ebp.jupyterbook.org">Executable Book Project</a>
</div>
</div>
<main class="col py-md-3 pl-md-4 bd-content overflow-auto" role="main">
<div class="row topbar fixed-top container-xl">
<div class="col-12 col-md-3 bd-topbar-whitespace site-navigation show">
</div>
<div class="col pl-2 topbar-main">
<button id="navbar-toggler" class="navbar-toggler ml-0" type="button" data-toggle="collapse"
data-toggle="tooltip" data-placement="bottom" data-target=".site-navigation" aria-controls="navbar-menu"
aria-expanded="true" aria-label="Toggle navigation" aria-controls="site-navigation"
title="Toggle navigation" data-toggle="tooltip" data-placement="left">
<i class="fas fa-bars"></i>
<i class="fas fa-arrow-left"></i>
<i class="fas fa-arrow-up"></i>
</button>
<div class="dropdown-buttons-trigger">
<button id="dropdown-buttons-trigger" class="btn btn-secondary topbarbtn" aria-label="Download this page"><i
class="fas fa-download"></i></button>
<div class="dropdown-buttons">
<!-- ipynb file if we had a myst markdown file -->
<!-- Download raw file -->
<a class="dropdown-buttons" href="_sources/09-appendix-a.ipynb"><button type="button"
class="btn btn-secondary topbarbtn" title="Download source file" data-toggle="tooltip"
data-placement="left">.ipynb</button></a>
<!-- Download PDF via print -->
<button type="button" id="download-print" class="btn btn-secondary topbarbtn" title="Print to PDF"
onClick="window.print()" data-toggle="tooltip" data-placement="left">.pdf</button>
</div>
</div>
<!-- Source interaction buttons -->
<div class="dropdown-buttons-trigger">
<button id="dropdown-buttons-trigger" class="btn btn-secondary topbarbtn"
aria-label="Connect with source repository"><i class="fab fa-github"></i></button>
<div class="dropdown-buttons sourcebuttons">
<a class="repository-button"
href="https://github.com/spatialaudio/nbsphinx"><button type="button" class="btn btn-secondary topbarbtn"
data-toggle="tooltip" data-placement="left" title="Source repository"><i
class="fab fa-github"></i>repository</button></a>
<a class="issues-button"
href="https://github.com/spatialaudio/nbsphinx/issues/new?title=Issue%20on%20page%20%2F09-appendix-a.html&body=Your%20issue%20content%20here."><button
type="button" class="btn btn-secondary topbarbtn" data-toggle="tooltip" data-placement="left"
title="Open an issue"><i class="fas fa-lightbulb"></i>open issue</button></a>
<a class="edit-button" href="https://github.com/spatialaudio/nbsphinx/edit/master/doc/09-appendix-a.ipynb"><button
type="button" class="btn btn-secondary topbarbtn" data-toggle="tooltip" data-placement="left"
title="Edit this page"><i class="fas fa-pencil-alt"></i>suggest edit</button></a>
</div>
</div>
<!-- Full screen (wrap in <a> to have style consistency -->
<a class="full-screen-button"><button type="button" class="btn btn-secondary topbarbtn" data-toggle="tooltip"
data-placement="bottom" onclick="toggleFullScreen()" title="Fullscreen mode"><i
class="fas fa-expand"></i></button></a>
<!-- Launch buttons -->
</div>
<div class="d-none d-md-block col-md-2 bd-toc show">
<nav id="bd-toc-nav">
<ul class="nav section-nav flex-column">
</ul>
</nav>
<div class="tocsection editthispage">
<a href="https://github.com/spatialaudio/nbsphinx/edit/master/doc/09-appendix-a.ipynb">
<i class="fas fa-pencil-alt"></i> Edit this page
</a>
</div>
</div>
</div>
<div id="main-content" class="row">
<div class="col-12 col-md-9 pl-md-3 pr-md-0">
<div>
<style>
/* CSS for nbsphinx extension */
/* remove conflicting styling from Sphinx themes */
div.nbinput.container,
div.nbinput.container div.prompt,
div.nbinput.container div.input_area,
div.nbinput.container div[class*=highlight],
div.nbinput.container div[class*=highlight] pre,
div.nboutput.container,
div.nboutput.container div.prompt,
div.nboutput.container div.output_area,
div.nboutput.container div[class*=highlight],
div.nboutput.container div[class*=highlight] pre {
background: none;
border: none;
padding: 0 0;
margin: 0;
box-shadow: none;
}
/* avoid gaps between output lines */
div.nboutput.container div[class*=highlight] pre {
line-height: normal;
}
/* input/output containers */
div.nbinput.container,
div.nboutput.container {
display: -webkit-flex;
display: flex;
align-items: flex-start;
margin: 0;
width: 100%;
}
@media (max-width: 540px) {
div.nbinput.container,
div.nboutput.container {
flex-direction: column;
}
}
/* input container */
div.nbinput.container {
padding-top: 5px;
}
/* last container */
div.nblast.container {
padding-bottom: 5px;
}
/* input prompt */
div.nbinput.container div.prompt pre {
color: #307FC1;
}
/* output prompt */
div.nboutput.container div.prompt pre {
color: #BF5B3D;
}
/* all prompts */
div.nbinput.container div.prompt,
div.nboutput.container div.prompt {
width: 4.5ex;
padding-top: 5px;
position: relative;
user-select: none;
}
div.nbinput.container div.prompt > div,
div.nboutput.container div.prompt > div {
position: absolute;
right: 0;
margin-right: 0.3ex;
}
@media (max-width: 540px) {
div.nbinput.container div.prompt,
div.nboutput.container div.prompt {
width: unset;
text-align: left;
padding: 0.4em;
}
div.nboutput.container div.prompt.empty {
padding: 0;
}
div.nbinput.container div.prompt > div,
div.nboutput.container div.prompt > div {
position: unset;
}
}
/* disable scrollbars on prompts */
div.nbinput.container div.prompt pre,
div.nboutput.container div.prompt pre {
overflow: hidden;
}
/* input/output area */
div.nbinput.container div.input_area,
div.nboutput.container div.output_area {
-webkit-flex: 1;
flex: 1;
overflow: auto;
}
@media (max-width: 540px) {
div.nbinput.container div.input_area,
div.nboutput.container div.output_area {
width: 100%;
}
}
/* input area */
div.nbinput.container div.input_area {
border: 1px solid #e0e0e0;
border-radius: 2px;
background: #f5f5f5;
}
/* override MathJax center alignment in output cells */
div.nboutput.container div[class*=MathJax] {
text-align: left !important;
}
/* override sphinx.ext.imgmath center alignment in output cells */
div.nboutput.container div.math p {
text-align: left;
}
/* standard error */
div.nboutput.container div.output_area.stderr {
background: #fdd;
}
/* ANSI colors */
.ansi-black-fg { color: #3E424D; }
.ansi-black-bg { background-color: #3E424D; }
.ansi-black-intense-fg { color: #282C36; }
.ansi-black-intense-bg { background-color: #282C36; }
.ansi-red-fg { color: #E75C58; }
.ansi-red-bg { background-color: #E75C58; }
.ansi-red-intense-fg { color: #B22B31; }
.ansi-red-intense-bg { background-color: #B22B31; }
.ansi-green-fg { color: #00A250; }
.ansi-green-bg { background-color: #00A250; }
.ansi-green-intense-fg { color: #007427; }
.ansi-green-intense-bg { background-color: #007427; }
.ansi-yellow-fg { color: #DDB62B; }
.ansi-yellow-bg { background-color: #DDB62B; }
.ansi-yellow-intense-fg { color: #B27D12; }
.ansi-yellow-intense-bg { background-color: #B27D12; }
.ansi-blue-fg { color: #208FFB; }
.ansi-blue-bg { background-color: #208FFB; }
.ansi-blue-intense-fg { color: #0065CA; }
.ansi-blue-intense-bg { background-color: #0065CA; }
.ansi-magenta-fg { color: #D160C4; }
.ansi-magenta-bg { background-color: #D160C4; }
.ansi-magenta-intense-fg { color: #A03196; }
.ansi-magenta-intense-bg { background-color: #A03196; }
.ansi-cyan-fg { color: #60C6C8; }
.ansi-cyan-bg { background-color: #60C6C8; }
.ansi-cyan-intense-fg { color: #258F8F; }
.ansi-cyan-intense-bg { background-color: #258F8F; }
.ansi-white-fg { color: #C5C1B4; }
.ansi-white-bg { background-color: #C5C1B4; }
.ansi-white-intense-fg { color: #A1A6B2; }
.ansi-white-intense-bg { background-color: #A1A6B2; }
.ansi-default-inverse-fg { color: #FFFFFF; }
.ansi-default-inverse-bg { background-color: #000000; }
.ansi-bold { font-weight: bold; }
.ansi-underline { text-decoration: underline; }
div.nbinput.container div.input_area div[class*=highlight] > pre,
div.nboutput.container div.output_area div[class*=highlight] > pre,
div.nboutput.container div.output_area div[class*=highlight].math,
div.nboutput.container div.output_area.rendered_html,
div.nboutput.container div.output_area > div.output_javascript,
div.nboutput.container div.output_area:not(.rendered_html) > img{
padding: 5px;
}
/* fix copybtn overflow problem in chromium (needed for 'sphinx_copybutton') */
div.nbinput.container div.input_area > div[class^='highlight'],
div.nboutput.container div.output_area > div[class^='highlight']{
overflow-y: hidden;
}
/* hide copybtn icon on prompts (needed for 'sphinx_copybutton') */
.prompt a.copybtn {
display: none;
}
/* Some additional styling taken form the Jupyter notebook CSS */
div.rendered_html table {
border: none;
border-collapse: collapse;
border-spacing: 0;
color: black;
font-size: 12px;
table-layout: fixed;
}
div.rendered_html thead {
border-bottom: 1px solid black;
vertical-align: bottom;
}
div.rendered_html tr,
div.rendered_html th,
div.rendered_html td {
text-align: right;
vertical-align: middle;
padding: 0.5em 0.5em;
line-height: normal;
white-space: normal;
max-width: none;
border: none;
}
div.rendered_html th {
font-weight: bold;
}
div.rendered_html tbody tr:nth-child(odd) {
background: #f5f5f5;
}
div.rendered_html tbody tr:hover {
background: rgba(66, 165, 245, 0.2);
}
</style>
<div class="section" id="附錄-A">
<h1>附錄 A<a class="headerlink" href="#附錄-A" title="Permalink to this headline">¶</a></h1>
<p><code class="docutils literal notranslate"><span class="pre">pyvizml.py</span></code></p>
<div class="nbinput nblast docutils container">
<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
</pre></div>
</div>
<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="kn">import</span> <span class="nn">requests</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
<span class="n">__author__</span> <span class="o">=</span> <span class="s1">'{Yao-Jen Kuo}'</span>
<span class="n">__copyright__</span> <span class="o">=</span> <span class="s1">'Copyright </span><span class="si">{2020}</span><span class="s1">, {py-viz-ml-book}'</span>
<span class="n">__license__</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{MIT}</span><span class="s1">'</span>
<span class="n">__version__</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{1}</span><span class="s1">.</span><span class="si">{0}</span><span class="s1">.</span><span class="si">{0}</span><span class="s1">'</span>
<span class="n">__maintainer__</span> <span class="o">=</span> <span class="s1">'{Yao-Jen Kuo}'</span>
<span class="n">__email__</span> <span class="o">=</span> <span class="s1">'{tonykuoyj@gmail.com}'</span>
<span class="k">class</span> <span class="nc">CreateNBAData</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class scrapes NBA.com offical api: data.nba.net.</span>
<span class="sd"> See https://data.nba.net/10s/prod/v1/today.json</span>
<span class="sd"> Args:</span>
<span class="sd"> season_year (int): Use the first year to specify season, e.g. specify 2019 for the 2019-2020 season.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">season_year</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_season_year</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">season_year</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">create_players_df</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the DataFrame of player information.</span>
<span class="sd"> """</span>
<span class="n">request_url</span> <span class="o">=</span> <span class="s2">"https://data.nba.net/prod/v1/</span><span class="si">{}</span><span class="s2">/players.json"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_season_year</span><span class="p">)</span>
<span class="n">resp_dict</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">request_url</span><span class="p">)</span><span class="o">.</span><span class="n">json</span><span class="p">()</span>
<span class="n">players_list</span> <span class="o">=</span> <span class="n">resp_dict</span><span class="p">[</span><span class="s1">'league'</span><span class="p">][</span><span class="s1">'standard'</span><span class="p">]</span>
<span class="n">players_list_dict</span> <span class="o">=</span> <span class="p">[]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Creating players df..."</span><span class="p">)</span>
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">players_list</span><span class="p">:</span>
<span class="n">player_dict</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">p</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="nb">bool</span><span class="p">):</span>
<span class="n">player_dict</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">v</span>
<span class="n">players_list_dict</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">player_dict</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">players_list_dict</span><span class="p">)</span>
<span class="n">filtered_df</span> <span class="o">=</span> <span class="n">df</span><span class="p">[(</span><span class="n">df</span><span class="p">[</span><span class="s1">'isActive'</span><span class="p">])</span> <span class="o">&</span> <span class="p">(</span><span class="n">df</span><span class="p">[</span><span class="s1">'heightMeters'</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">)]</span>
<span class="n">filtered_df</span> <span class="o">=</span> <span class="n">filtered_df</span><span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_person_ids</span> <span class="o">=</span> <span class="n">filtered_df</span><span class="p">[</span><span class="s1">'personId'</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>
<span class="k">return</span> <span class="n">filtered_df</span>
<span class="k">def</span> <span class="nf">create_stats_df</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the DataFrame of player career statistics.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">create_players_df</span><span class="p">()</span>
<span class="n">career_summaries</span> <span class="o">=</span> <span class="p">[]</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Creating player stats df..."</span><span class="p">)</span>
<span class="k">for</span> <span class="n">pid</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_person_ids</span><span class="p">:</span>
<span class="n">request_url</span> <span class="o">=</span> <span class="s2">"https://data.nba.net/prod/v1/</span><span class="si">{}</span><span class="s2">/players/</span><span class="si">{}</span><span class="s2">_profile.json"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_season_year</span><span class="p">,</span> <span class="n">pid</span><span class="p">)</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">request_url</span><span class="p">)</span>
<span class="n">profile_json</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">json</span><span class="p">()</span>
<span class="n">career_summary</span> <span class="o">=</span> <span class="n">profile_json</span><span class="p">[</span><span class="s1">'league'</span><span class="p">][</span><span class="s1">'standard'</span><span class="p">][</span><span class="s1">'stats'</span><span class="p">][</span><span class="s1">'careerSummary'</span><span class="p">]</span>
<span class="n">career_summaries</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">career_summary</span><span class="p">)</span>
<span class="n">stats_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">career_summaries</span><span class="p">)</span>
<span class="n">stats_df</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="s1">'personId'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_person_ids</span><span class="p">)</span>
<span class="k">return</span> <span class="n">stats_df</span>
<span class="k">def</span> <span class="nf">create_player_stats_df</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the DataFrame merged from players_df and stats_df.</span>
<span class="sd"> """</span>
<span class="n">players</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">create_players_df</span><span class="p">()</span>
<span class="n">stats</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">create_stats_df</span><span class="p">()</span>
<span class="n">player_stats</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">players</span><span class="p">,</span> <span class="n">stats</span><span class="p">,</span> <span class="n">left_on</span><span class="o">=</span><span class="s1">'personId'</span><span class="p">,</span> <span class="n">right_on</span><span class="o">=</span><span class="s1">'personId'</span><span class="p">)</span>
<span class="k">return</span> <span class="n">player_stats</span>
<span class="k">class</span> <span class="nc">ImshowSubplots</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class plots 2d-arrays with subplots.</span>
<span class="sd"> Args:</span>
<span class="sd"> rows (int): The number of rows of axes.</span>
<span class="sd"> cols (int): The number of columns of axes.</span>
<span class="sd"> fig_size (tuple): Figure size.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rows</span><span class="p">,</span> <span class="n">cols</span><span class="p">,</span> <span class="n">fig_size</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rows</span> <span class="o">=</span> <span class="n">rows</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cols</span> <span class="o">=</span> <span class="n">cols</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fig_size</span> <span class="o">=</span> <span class="n">fig_size</span>
<span class="k">def</span> <span class="nf">im_show</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">label_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function plots 2d-arrays with subplots.</span>
<span class="sd"> Args:</span>
<span class="sd"> X (ndarray): 2d-arrays.</span>
<span class="sd"> y (ndarray): Labels for 2d-arrays.</span>
<span class="sd"> label_dict (dict): Str labels for y if any.</span>
<span class="sd"> """</span>
<span class="n">n_pics</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rows</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">_cols</span>
<span class="n">first_n_pics</span> <span class="o">=</span> <span class="n">X</span><span class="p">[:</span><span class="n">n_pics</span><span class="p">,</span> <span class="p">:,</span> <span class="p">:]</span>
<span class="n">first_n_labels</span> <span class="o">=</span> <span class="n">y</span><span class="p">[:</span><span class="n">n_pics</span><span class="p">]</span>
<span class="n">fig</span><span class="p">,</span> <span class="n">axes</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_rows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cols</span><span class="p">,</span> <span class="n">figsize</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_fig_size</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_pics</span><span class="p">):</span>
<span class="n">row_idx</span> <span class="o">=</span> <span class="n">i</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rows</span>
<span class="n">col_idx</span> <span class="o">=</span> <span class="n">i</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rows</span>
<span class="n">axes</span><span class="p">[</span><span class="n">row_idx</span><span class="p">,</span> <span class="n">col_idx</span><span class="p">]</span><span class="o">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">first_n_pics</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">cmap</span><span class="o">=</span><span class="s2">"Greys"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">label_dict</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">axes</span><span class="p">[</span><span class="n">row_idx</span><span class="p">,</span> <span class="n">col_idx</span><span class="p">]</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s2">"Label: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">label_dict</span><span class="p">(</span><span class="n">first_n_labels</span><span class="p">[</span><span class="n">i</span><span class="p">])))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">axes</span><span class="p">[</span><span class="n">row_idx</span><span class="p">,</span> <span class="n">col_idx</span><span class="p">]</span><span class="o">.</span><span class="n">set_title</span><span class="p">(</span><span class="s2">"Label: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">first_n_labels</span><span class="p">[</span><span class="n">i</span><span class="p">]))</span>
<span class="n">axes</span><span class="p">[</span><span class="n">row_idx</span><span class="p">,</span> <span class="n">col_idx</span><span class="p">]</span><span class="o">.</span><span class="n">set_xticks</span><span class="p">([])</span>
<span class="n">axes</span><span class="p">[</span><span class="n">row_idx</span><span class="p">,</span> <span class="n">col_idx</span><span class="p">]</span><span class="o">.</span><span class="n">set_yticks</span><span class="p">([])</span>
<span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span><span class="p">()</span>
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="k">class</span> <span class="nc">NormalEquation</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class defines the Normal equation for linear regression.</span>
<span class="sd"> Args:</span>
<span class="sd"> fit_intercept (bool): Whether to add intercept for this model.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fit_intercept</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span> <span class="o">=</span> <span class="n">fit_intercept</span>
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function uses Normal equation to solve for weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_train (ndarray): 2d-array for feature matrix of training data.</span>
<span class="sd"> y_train (ndarray): 1d-array for target vector of training data.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">X_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span> <span class="o">=</span> <span class="n">y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="n">m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">X_train_T</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">)</span>
<span class="n">left_matrix</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">X_train_T</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">)</span>
<span class="n">right_matrix</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">X_train_T</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">)</span>
<span class="n">left_matrix_inv</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">inv</span><span class="p">(</span><span class="n">left_matrix</span><span class="p">)</span>
<span class="n">w</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">left_matrix_inv</span><span class="p">,</span> <span class="n">right_matrix</span><span class="p">)</span>
<span class="n">w_ravel</span> <span class="o">=</span> <span class="n">w</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">=</span> <span class="n">w</span>
<span class="bp">self</span><span class="o">.</span><span class="n">intercept_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">coef_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
<span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_test</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns predicted values with weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_test (ndarray): 2d-array for feature matrix of test data.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span> <span class="o">=</span> <span class="n">X_test</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="n">m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="p">)</span>
<span class="k">return</span> <span class="n">y_pred</span>
<span class="k">class</span> <span class="nc">GradientDescent</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class defines the vanilla gradient descent algorithm for linear regression.</span>
<span class="sd"> Args:</span>
<span class="sd"> fit_intercept (bool): Whether to add intercept for this model.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fit_intercept</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span> <span class="o">=</span> <span class="n">fit_intercept</span>
<span class="k">def</span> <span class="nf">find_gradient</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the gradient given certain model weights.</span>
<span class="sd"> """</span>
<span class="n">y_hat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="p">)</span>
<span class="n">gradient</span> <span class="o">=</span> <span class="p">(</span><span class="mi">2</span><span class="o">/</span><span class="bp">self</span><span class="o">.</span><span class="n">_m</span><span class="p">)</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">T</span><span class="p">,</span> <span class="n">y_hat</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">)</span>
<span class="k">return</span> <span class="n">gradient</span>
<span class="k">def</span> <span class="nf">mean_squared_error</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the mean squared error given certain model weights.</span>
<span class="sd"> """</span>
<span class="n">y_hat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="p">)</span>
<span class="n">mse</span> <span class="o">=</span> <span class="p">((</span><span class="n">y_hat</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">)</span><span class="o">.</span><span class="n">T</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">y_hat</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">))</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span>
<span class="k">return</span> <span class="n">mse</span>
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">epochs</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.001</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function uses vanilla gradient descent to solve for weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_train (ndarray): 2d-array for feature matrix of training data.</span>
<span class="sd"> y_train (ndarray): 1d-array for target vector of training data.</span>
<span class="sd"> epochs (int): The number of iterations to update the model weights.</span>
<span class="sd"> learning_rate (float): The learning rate of gradient descent.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">X_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span> <span class="o">=</span> <span class="n">y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">_m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">n</span><span class="p">)</span>
<span class="n">n_prints</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">print_iter</span> <span class="o">=</span> <span class="n">epochs</span> <span class="o">//</span> <span class="n">n_prints</span>
<span class="n">w_history</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">epochs</span><span class="p">):</span>
<span class="n">current_w</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">w_history</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">current_w</span>
<span class="n">mse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean_squared_error</span><span class="p">()</span>
<span class="n">gradient</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">find_gradient</span><span class="p">()</span>
<span class="k">if</span> <span class="n">i</span> <span class="o">%</span> <span class="n">print_iter</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"epoch: </span><span class="si">{:6}</span><span class="s2"> - loss: </span><span class="si">{:.6f}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">mse</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">-=</span> <span class="n">learning_rate</span><span class="o">*</span><span class="n">gradient</span>
<span class="n">w_ravel</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">intercept_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">coef_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w_history</span> <span class="o">=</span> <span class="n">w_history</span>
<span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_test</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns predicted values with weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_test (ndarray): 2d-array for feature matrix of test data.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span> <span class="o">=</span> <span class="n">X_test</span>
<span class="n">m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="n">m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="p">)</span>
<span class="k">return</span> <span class="n">y_pred</span>
<span class="k">class</span> <span class="nc">AdaGrad</span><span class="p">(</span><span class="n">GradientDescent</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This class defines the Adaptive Gradient Descent algorithm for linear regression.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">epochs</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-06</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">X_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span> <span class="o">=</span> <span class="n">y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">_m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">n</span><span class="p">)</span>
<span class="c1"># 初始化 ssg</span>
<span class="n">ssg</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="n">n_prints</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">print_iter</span> <span class="o">=</span> <span class="n">epochs</span> <span class="o">//</span> <span class="n">n_prints</span>
<span class="n">w_history</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">epochs</span><span class="p">):</span>
<span class="n">current_w</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">w_history</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">current_w</span>
<span class="n">mse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean_squared_error</span><span class="p">()</span>
<span class="n">gradient</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">find_gradient</span><span class="p">()</span>
<span class="n">ssg</span> <span class="o">+=</span> <span class="n">gradient</span><span class="o">**</span><span class="mi">2</span>
<span class="n">ada_grad</span> <span class="o">=</span> <span class="n">gradient</span> <span class="o">/</span> <span class="p">(</span><span class="n">epsilon</span> <span class="o">+</span> <span class="n">ssg</span><span class="o">**</span><span class="mf">0.5</span><span class="p">)</span>
<span class="k">if</span> <span class="n">i</span> <span class="o">%</span> <span class="n">print_iter</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"epoch: </span><span class="si">{:6}</span><span class="s2"> - loss: </span><span class="si">{:.6f}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">mse</span><span class="p">))</span>
<span class="c1"># 以 adaptive gradient 更新 w</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">-=</span> <span class="n">learning_rate</span><span class="o">*</span><span class="n">ada_grad</span>
<span class="n">w_ravel</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">intercept_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">coef_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w_history</span> <span class="o">=</span> <span class="n">w_history</span>
<span class="k">class</span> <span class="nc">LogitReg</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class defines the vanilla descent algorithm for logistic regression.</span>
<span class="sd"> Args:</span>
<span class="sd"> fit_intercept (bool): Whether to add intercept for this model.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fit_intercept</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span> <span class="o">=</span> <span class="n">fit_intercept</span>
<span class="k">def</span> <span class="nf">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the Sigmoid output as a probability given certain model weights.</span>
<span class="sd"> """</span>
<span class="n">X_w</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="p">)</span>
<span class="n">p_hat</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="n">X_w</span><span class="p">))</span>
<span class="k">return</span> <span class="n">p_hat</span>
<span class="k">def</span> <span class="nf">find_gradient</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the gradient given certain model weights.</span>
<span class="sd"> """</span>
<span class="n">m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span>
<span class="n">p_hat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">)</span>
<span class="n">X_train_T</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">)</span>
<span class="n">gradient</span> <span class="o">=</span> <span class="p">(</span><span class="mi">1</span><span class="o">/</span><span class="n">m</span><span class="p">)</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">X_train_T</span><span class="p">,</span> <span class="n">p_hat</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">)</span>
<span class="k">return</span> <span class="n">gradient</span>
<span class="k">def</span> <span class="nf">cross_entropy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-06</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the cross entropy given certain model weights.</span>
<span class="sd"> """</span>
<span class="n">m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span>
<span class="n">p_hat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">)</span>
<span class="n">cost_y1</span> <span class="o">=</span> <span class="o">-</span><span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">p_hat</span> <span class="o">+</span> <span class="n">epsilon</span><span class="p">))</span>
<span class="n">cost_y0</span> <span class="o">=</span> <span class="o">-</span><span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">p_hat</span> <span class="o">+</span> <span class="n">epsilon</span><span class="p">))</span>
<span class="n">cross_entropy</span> <span class="o">=</span> <span class="p">(</span><span class="n">cost_y1</span> <span class="o">+</span> <span class="n">cost_y0</span><span class="p">)</span> <span class="o">/</span> <span class="n">m</span>
<span class="k">return</span> <span class="n">cross_entropy</span>
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">epochs</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.001</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function uses vanilla gradient descent to solve for weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_train (ndarray): 2d-array for feature matrix of training data.</span>
<span class="sd"> y_train (ndarray): 1d-array for target vector of training data.</span>
<span class="sd"> epochs (int): The number of iterations to update the model weights.</span>
<span class="sd"> learning_rate (float): The learning rate of gradient descent.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">X_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span> <span class="o">=</span> <span class="n">y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_m</span> <span class="o">=</span> <span class="n">m</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">_m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">n</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">n</span><span class="p">)</span>
<span class="n">n_prints</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">print_iter</span> <span class="o">=</span> <span class="n">epochs</span> <span class="o">//</span> <span class="n">n_prints</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">epochs</span><span class="p">):</span>
<span class="n">cross_entropy</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cross_entropy</span><span class="p">()</span>
<span class="n">gradient</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">find_gradient</span><span class="p">()</span>
<span class="k">if</span> <span class="n">i</span> <span class="o">%</span> <span class="n">print_iter</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"epoch: </span><span class="si">{:6}</span><span class="s2"> - loss: </span><span class="si">{:.6f}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">cross_entropy</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_w</span> <span class="o">-=</span> <span class="n">learning_rate</span><span class="o">*</span><span class="n">gradient</span>
<span class="n">w_ravel</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_w</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">intercept_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">coef_</span> <span class="o">=</span> <span class="n">w_ravel</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">predict_proba</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_test</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns predicted probability with weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_test (ndarray): 2d-array for feature matrix of test data.</span>
<span class="sd"> """</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">X_test</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fit_intercept</span><span class="p">:</span>
<span class="n">X0</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</span><span class="p">((</span><span class="n">m</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">float</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">X0</span><span class="p">,</span> <span class="n">X_test</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">p_hat_1</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_X_test</span><span class="p">)</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">p_hat_0</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">p_hat_1</span>
<span class="n">proba</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">([</span><span class="n">p_hat_0</span><span class="p">,</span> <span class="n">p_hat_1</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="k">return</span> <span class="n">proba</span>
<span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_test</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns predicted label with weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_test (ndarray): 2d-array for feature matrix of test data.</span>
<span class="sd"> """</span>
<span class="n">proba</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_proba</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">proba</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="k">return</span> <span class="n">y_pred</span>
<span class="k">class</span> <span class="nc">ClfMetrics</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class calculates some of the metrics of classifier including accuracy, precision, recall, f1 according to confusion matrix.</span>
<span class="sd"> Args:</span>
<span class="sd"> y_true (ndarray): 1d-array for true target vector.</span>
<span class="sd"> y_pred (ndarray): 1d-array for predicted target vector.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">y_true</span><span class="p">,</span> <span class="n">y_pred</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_true</span> <span class="o">=</span> <span class="n">y_true</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_pred</span> <span class="o">=</span> <span class="n">y_pred</span>
<span class="k">def</span> <span class="nf">confusion_matrix</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the confusion matrix given true/predicted target vectors.</span>
<span class="sd"> """</span>
<span class="n">n_unique</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">unique</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_y_true</span><span class="p">)</span><span class="o">.</span><span class="n">size</span>
<span class="n">cm</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">n_unique</span><span class="p">,</span> <span class="n">n_unique</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">int</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_unique</span><span class="p">):</span>
<span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_unique</span><span class="p">):</span>
<span class="n">n_obs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_and</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_y_true</span> <span class="o">==</span> <span class="n">i</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_pred</span> <span class="o">==</span> <span class="n">j</span><span class="p">))</span>
<span class="n">cm</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">]</span> <span class="o">=</span> <span class="n">n_obs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tn</span> <span class="o">=</span> <span class="n">cm</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tp</span> <span class="o">=</span> <span class="n">cm</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fn</span> <span class="o">=</span> <span class="n">cm</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fp</span> <span class="o">=</span> <span class="n">cm</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">]</span>
<span class="k">return</span> <span class="n">cm</span>
<span class="k">def</span> <span class="nf">accuracy_score</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the accuracy score given true/predicted target vectors.</span>
<span class="sd"> """</span>
<span class="n">cm</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">confusion_matrix</span><span class="p">()</span>
<span class="n">accuracy</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_tn</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp</span><span class="p">)</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">cm</span><span class="p">)</span>
<span class="k">return</span> <span class="n">accuracy</span>
<span class="k">def</span> <span class="nf">precision_score</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the precision score given true/predicted target vectors.</span>
<span class="sd"> """</span>
<span class="n">precision</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp</span> <span class="o">/</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_tp</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fp</span><span class="p">)</span>
<span class="k">return</span> <span class="n">precision</span>
<span class="k">def</span> <span class="nf">recall_score</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the recall score given true/predicted target vectors.</span>
<span class="sd"> """</span>
<span class="n">recall</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tp</span> <span class="o">/</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_tp</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fn</span><span class="p">)</span>
<span class="k">return</span> <span class="n">recall</span>
<span class="k">def</span> <span class="nf">f1_score</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="mi">1</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the f1 score given true/predicted target vectors.</span>
<span class="sd"> Args:</span>
<span class="sd"> beta (int, float): Can be used to generalize from f1 score to f score.</span>
<span class="sd"> """</span>
<span class="n">precision</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">precision_score</span><span class="p">()</span>
<span class="n">recall</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">recall_score</span><span class="p">()</span>
<span class="n">f1</span> <span class="o">=</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">beta</span><span class="o">**</span><span class="mi">2</span><span class="p">)</span><span class="o">*</span><span class="n">precision</span><span class="o">*</span><span class="n">recall</span> <span class="o">/</span> <span class="p">((</span><span class="n">beta</span><span class="o">**</span><span class="mi">2</span> <span class="o">*</span> <span class="n">precision</span><span class="p">)</span> <span class="o">+</span> <span class="n">recall</span><span class="p">)</span>
<span class="k">return</span> <span class="n">f1</span>
<span class="k">class</span> <span class="nc">DeepLearning</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> This class defines the vanilla optimization of a deep learning model.</span>
<span class="sd"> Args:</span>
<span class="sd"> layer_of_units (list): A list to specify the number of units in each layer.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layer_of_units</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_n_layers</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">layer_of_units</span><span class="p">)</span>
<span class="n">parameters</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="n">parameters</span><span class="p">[</span><span class="s1">'W</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">layer_of_units</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">],</span> <span class="n">layer_of_units</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
<span class="n">parameters</span><span class="p">[</span><span class="s1">'B</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">layer_of_units</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">],</span> <span class="mi">1</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span> <span class="o">=</span> <span class="n">parameters</span>
<span class="k">def</span> <span class="nf">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">Z</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the Sigmoid output.</span>
<span class="sd"> Args:</span>
<span class="sd"> Z (ndarray): The multiplication of weights and output from previous layer.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="mi">1</span><span class="o">/</span><span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="n">Z</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">single_layer_forward_propagation</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">A_previous</span><span class="p">,</span> <span class="n">W_current</span><span class="p">,</span> <span class="n">B_current</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the output of a single layer of forward propagation.</span>
<span class="sd"> Args:</span>
<span class="sd"> A_previous (ndarray): The Sigmoid output from previous layer.</span>
<span class="sd"> W_current (ndarray): The weights of current layer.</span>
<span class="sd"> B_current (ndarray): The bias of current layer.</span>
<span class="sd"> """</span>
<span class="n">Z_current</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">W_current</span><span class="p">,</span> <span class="n">A_previous</span><span class="p">)</span> <span class="o">+</span> <span class="n">B_current</span>
<span class="n">A_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">Z_current</span><span class="p">)</span>
<span class="k">return</span> <span class="n">A_current</span><span class="p">,</span> <span class="n">Z_current</span>
<span class="k">def</span> <span class="nf">forward_propagation</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the output of a complete round of forward propagation.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_m</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">X_train_T</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">T</span>
<span class="n">cache</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">A_current</span> <span class="o">=</span> <span class="n">X_train_T</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="n">A_previous</span> <span class="o">=</span> <span class="n">A_current</span>
<span class="n">W_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"W</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span>
<span class="n">B_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"B</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span>
<span class="n">A_current</span><span class="p">,</span> <span class="n">Z_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">single_layer_forward_propagation</span><span class="p">(</span><span class="n">A_previous</span><span class="p">,</span> <span class="n">W_current</span><span class="p">,</span> <span class="n">B_current</span><span class="p">)</span>
<span class="n">cache</span><span class="p">[</span><span class="s2">"A</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">)]</span> <span class="o">=</span> <span class="n">A_previous</span>
<span class="n">cache</span><span class="p">[</span><span class="s2">"Z</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">Z_current</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache</span> <span class="o">=</span> <span class="n">cache</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_A_current</span> <span class="o">=</span> <span class="n">A_current</span>
<span class="k">def</span> <span class="nf">derivative_sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">Z</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the output of the derivative of Sigmoid function.</span>
<span class="sd"> Args:</span>
<span class="sd"> Z (ndarray): The multiplication of weights, bias and output from previous layer.</span>
<span class="sd"> """</span>
<span class="n">sig</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">Z</span><span class="p">)</span>
<span class="k">return</span> <span class="n">sig</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">sig</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">single_layer_backward_propagation</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dA_current</span><span class="p">,</span> <span class="n">W_current</span><span class="p">,</span> <span class="n">B_current</span><span class="p">,</span> <span class="n">Z_current</span><span class="p">,</span> <span class="n">A_previous</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the output of a single layer of backward propagation.</span>
<span class="sd"> Args:</span>
<span class="sd"> dA_current (ndarray): The output of the derivative of Sigmoid function from previous layer.</span>
<span class="sd"> W_current (ndarray): The weights of current layer.</span>
<span class="sd"> B_current (ndarray): The bias of current layer.</span>
<span class="sd"> Z_current (ndarray): The multiplication of weights, bias and output from previous layer.</span>
<span class="sd"> A_previous (ndarray): The Sigmoid output from previous layer.</span>
<span class="sd"> """</span>
<span class="n">dZ_current</span> <span class="o">=</span> <span class="n">dA_current</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">derivative_sigmoid</span><span class="p">(</span><span class="n">Z_current</span><span class="p">)</span>
<span class="n">dW_current</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">dZ_current</span><span class="p">,</span> <span class="n">A_previous</span><span class="o">.</span><span class="n">T</span><span class="p">)</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span>
<span class="n">dB_current</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">dZ_current</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">keepdims</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span>
<span class="n">dA_previous</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">W_current</span><span class="o">.</span><span class="n">T</span><span class="p">,</span> <span class="n">dZ_current</span><span class="p">)</span>
<span class="k">return</span> <span class="n">dA_previous</span><span class="p">,</span> <span class="n">dW_current</span><span class="p">,</span> <span class="n">dB_current</span>
<span class="k">def</span> <span class="nf">backward_propagation</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function performs a complete round of backward propagation to update weights and bias.</span>
<span class="sd"> """</span>
<span class="n">gradients</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">forward_propagation</span><span class="p">()</span>
<span class="n">Y_hat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_A_current</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">Y_train</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span><span class="p">)</span>
<span class="n">dA_previous</span> <span class="o">=</span> <span class="o">-</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">divide</span><span class="p">(</span><span class="n">Y_train</span><span class="p">,</span> <span class="n">Y_hat</span><span class="p">)</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">divide</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">Y_train</span><span class="p">,</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">Y_hat</span><span class="p">))</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">reversed</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">dl</span><span class="o">.</span><span class="n">_n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)):</span>
<span class="n">dA_current</span> <span class="o">=</span> <span class="n">dA_previous</span>
<span class="n">A_previous</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache</span><span class="p">[</span><span class="s2">"A</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">)]</span>
<span class="n">Z_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache</span><span class="p">[</span><span class="s2">"Z</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="o">+</span><span class="mi">1</span><span class="p">)]</span>
<span class="n">W_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"W</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="o">+</span><span class="mi">1</span><span class="p">)]</span>
<span class="n">B_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"B</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="o">+</span><span class="mi">1</span><span class="p">)]</span>
<span class="n">dA_previous</span><span class="p">,</span> <span class="n">dW_current</span><span class="p">,</span> <span class="n">dB_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">single_layer_backward_propagation</span><span class="p">(</span><span class="n">dA_current</span><span class="p">,</span> <span class="n">W_current</span><span class="p">,</span> <span class="n">B_current</span><span class="p">,</span> <span class="n">Z_current</span><span class="p">,</span> <span class="n">A_previous</span><span class="p">)</span>
<span class="n">gradients</span><span class="p">[</span><span class="s2">"dW</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">dW_current</span>
<span class="n">gradients</span><span class="p">[</span><span class="s2">"dB</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">dB_current</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_gradients</span> <span class="o">=</span> <span class="n">gradients</span>
<span class="k">def</span> <span class="nf">cross_entropy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the cross entropy given weights and bias.</span>
<span class="sd"> """</span>
<span class="n">Y_hat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_A_current</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_Y_hat</span> <span class="o">=</span> <span class="n">Y_hat</span>
<span class="n">Y_train</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span><span class="p">)</span>
<span class="n">ce</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_m</span> <span class="o">*</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">Y_train</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">Y_hat</span><span class="p">)</span><span class="o">.</span><span class="n">T</span><span class="p">)</span> <span class="o">+</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">Y_train</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">Y_hat</span><span class="p">)</span><span class="o">.</span><span class="n">T</span><span class="p">))</span>
<span class="k">return</span> <span class="n">ce</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">accuracy_score</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns the accuracy score given weights and bias.</span>
<span class="sd"> """</span>
<span class="n">p_pred</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_Y_hat</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">p_pred</span> <span class="o">></span> <span class="mf">0.5</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">y_true</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span>
<span class="n">accuracy</span> <span class="o">=</span> <span class="p">(</span><span class="n">y_pred</span> <span class="o">==</span> <span class="n">y_true</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">/</span> <span class="n">y_pred</span><span class="o">.</span><span class="n">size</span>
<span class="k">return</span> <span class="n">accuracy</span>
<span class="k">def</span> <span class="nf">gradient_descent</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function performs vanilla gradient descent to update weights and bias.</span>
<span class="sd"> """</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"W</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">-=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_learning_rate</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_gradients</span><span class="p">[</span><span class="s2">"dW</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"B</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">-=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_learning_rate</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_gradients</span><span class="p">[</span><span class="s2">"dB</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span>
<span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">epochs</span><span class="o">=</span><span class="mi">100000</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.001</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function uses multiple rounds of forward propagations and backward propagations to optimize weights and bias.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_train (ndarray): 2d-array for feature matrix of training data.</span>
<span class="sd"> y_train (ndarray): 1d-array for target vector of training data.</span>
<span class="sd"> epochs (int): The number of iterations to update the model weights.</span>
<span class="sd"> learning_rate (float): The learning rate of gradient descent.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_X_train</span> <span class="o">=</span> <span class="n">X_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_y_train</span> <span class="o">=</span> <span class="n">y_train</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_learning_rate</span> <span class="o">=</span> <span class="n">learning_rate</span>
<span class="n">loss_history</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">accuracy_history</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">n_prints</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">print_iter</span> <span class="o">=</span> <span class="n">epochs</span> <span class="o">//</span> <span class="n">n_prints</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">epochs</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">forward_propagation</span><span class="p">()</span>
<span class="n">ce</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cross_entropy</span><span class="p">()</span>
<span class="n">accuracy</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy_score</span><span class="p">()</span>
<span class="n">loss_history</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ce</span><span class="p">)</span>
<span class="n">accuracy_history</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">accuracy</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">backward_propagation</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gradient_descent</span><span class="p">()</span>
<span class="k">if</span> <span class="n">i</span> <span class="o">%</span> <span class="n">print_iter</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Iteration: </span><span class="si">{:6}</span><span class="s2"> - cost: </span><span class="si">{:.6f}</span><span class="s2"> - accuracy: </span><span class="si">{:.2f}</span><span class="s2">%"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">ce</span><span class="p">,</span> <span class="n">accuracy</span> <span class="o">*</span> <span class="mi">100</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_loss_history</span> <span class="o">=</span> <span class="n">loss_history</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_accuracy_history</span> <span class="o">=</span> <span class="n">accuracy_history</span>
<span class="k">def</span> <span class="nf">predict_proba</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_test</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> This function returns predicted probability for class 1 with weights of this model.</span>
<span class="sd"> Args:</span>
<span class="sd"> X_test (ndarray): 2d-array for feature matrix of test data.</span>
<span class="sd"> """</span>
<span class="n">X_test_T</span> <span class="o">=</span> <span class="n">X_test</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">T</span>
<span class="n">A_current</span> <span class="o">=</span> <span class="n">X_test_T</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="n">A_previous</span> <span class="o">=</span> <span class="n">A_current</span>
<span class="n">W_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"W</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span>
<span class="n">B_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parameters</span><span class="p">[</span><span class="s2">"B</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span>
<span class="n">A_current</span><span class="p">,</span> <span class="n">Z_current</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">single_layer_forward_propagation</span><span class="p">(</span><span class="n">A_previous</span><span class="p">,</span> <span class="n">W_current</span><span class="p">,</span> <span class="n">B_current</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache</span><span class="p">[</span><span class="s2">"A</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span><span class="p">)]</span> <span class="o">=</span> <span class="n">A_previous</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache</span><span class="p">[</span><span class="s2">"Z</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">Z_current</span>
<span class="n">p_hat_1</span> <span class="o">=</span> <span class="n">A_current</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="k">return</span> <span class="n">p_hat_1</span>
<span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">X_test</span><span class="p">):</span>
<span class="n">p_hat_1</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_proba</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
<span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">p_hat_1</span> <span class="o">>=</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
</div>
</div>