-
Notifications
You must be signed in to change notification settings - Fork 42
/
Copy pathexamples.html
480 lines (393 loc) · 58.2 KB
/
examples.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
<!DOCTYPE html>
<html class="writer-html5" lang="en" data-content_root="./">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Usage Examples — MABWiser 2.7.4 documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=80d5e7a1" />
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
<!--[if lt IE 9]>
<script src="_static/js/html5shiv.min.js"></script>
<![endif]-->
<script src="_static/jquery.js?v=5d32c60e"></script>
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="_static/documentation_options.js?v=e8140b17"></script>
<script src="_static/doctools.js?v=888ff710"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="_static/js/theme.js"></script>
<link rel="author" title="About these documents" href="about.html" />
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="Contributing" href="contributing.html" />
<link rel="prev" title="Quick Start" href="quick.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="index.html" class="icon icon-home">
MABWiser
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="about.html">About Multi-Armed Bandits</a></li>
<li class="toctree-l1"><a class="reference internal" href="installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="quick.html">Quick Start</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Usage Examples</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#context-free-mab">Context-Free MAB</a></li>
<li class="toctree-l2"><a class="reference internal" href="#parametric-contextual-mab">Parametric Contextual MAB</a></li>
<li class="toctree-l2"><a class="reference internal" href="#non-parametric-contextual-mab">Non-Parametric Contextual MAB</a></li>
<li class="toctree-l2"><a class="reference internal" href="#parallel-mab">Parallel MAB</a></li>
<li class="toctree-l2"><a class="reference internal" href="#simulator">Simulator</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="contributing.html">Contributing</a></li>
<li class="toctree-l1"><a class="reference internal" href="new_bandit.html">Adding a New Bandit</a></li>
<li class="toctree-l1"><a class="reference internal" href="api.html">MABWiser Public API</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="index.html">MABWiser</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item active">Usage Examples</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/examples.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<section id="usage-examples">
<span id="examples"></span><h1>Usage Examples<a class="headerlink" href="#usage-examples" title="Link to this heading"></a></h1>
<p>The examples below show how to use different bandit policies to make decisions among multiple arms based on their expected rewards.</p>
<p>Conceptually, given a set of historical decisions and their corresponding rewards,
the high-level idea behind MABWiser is to train a model using the <code class="docutils literal notranslate"><span class="pre">fit()</span></code> method to make predictions
about next best decisions using the <code class="docutils literal notranslate"><span class="pre">predict()</span></code> method.</p>
<p>It is possible to retrieve the expected reward of each arm using the <code class="docutils literal notranslate"><span class="pre">predict_expectations()</span></code> method and
online training is available using the <code class="docutils literal notranslate"><span class="pre">partial_fit()</span></code> method.
New arms can be added to the bandits using the <code class="docutils literal notranslate"><span class="pre">add_arm()</span></code> method.
Decisions and rewards data support lists, 1D numpy arrays, and pandas series.
Contexts data supports 2D lists, 2D numpy arrays, pandas series and data frames.</p>
<div class="admonition seealso">
<p class="admonition-title">See also</p>
<p>Additional examples are available in the <a class="reference external" href="https://github.com/fidelity/mabwiser/tree/master/examples">examples folder</a> in the repo.</p>
</div>
<section id="context-free-mab">
<h2>Context-Free MAB<a class="headerlink" href="#context-free-mab" title="Link to this heading"></a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span> <span class="kn">from</span> <span class="nn">mabwiser.mab</span> <span class="kn">import</span> <span class="n">MAB</span><span class="p">,</span> <span class="n">LearningPolicy</span>
<span class="c1">######################################################################################</span>
<span class="c1">#</span>
<span class="c1"># MABWiser</span>
<span class="c1"># Scenario: A/B Testing for Website Layout Design</span>
<span class="c1">#</span>
<span class="c1"># An e-commerce website experiments with 2 different layouts options for their homepage</span>
<span class="c1"># Each layouts decision leads to generating different revenues</span>
<span class="c1">#</span>
<span class="c1"># What should the choice of layouts be based on historical data?</span>
<span class="c1">#</span>
<span class="c1">######################################################################################</span>
<span class="c1"># Arms</span>
<span class="n">options</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">]</span>
<span class="c1"># Historical data of layouts decisions and corresponding rewards</span>
<span class="n">layouts</span> <span class="o">=</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="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">]</span>
<span class="n">revenues</span> <span class="o">=</span> <span class="p">[</span><span class="mi">10</span><span class="p">,</span> <span class="mi">17</span><span class="p">,</span> <span class="mi">22</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">10</span><span class="p">]</span>
<span class="c1"># Arm to features</span>
<span class="n">arm_to_features</span> <span class="o">=</span> <span class="p">{</span><span class="mi">1</span><span class="p">:</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="mi">1</span><span class="p">],</span> <span class="mi">2</span><span class="p">:</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="mi">0</span><span class="p">],</span> <span class="mi">3</span><span class="p">:</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="mi">0</span><span class="p">]}</span>
<span class="c1">###################################</span>
<span class="c1"># Epsilon Greedy Learning Policy</span>
<span class="c1">###################################</span>
<span class="c1"># Epsilon Greedy learning policy with random exploration set to 15%</span>
<span class="n">greedy</span> <span class="o">=</span> <span class="n">MAB</span><span class="p">(</span><span class="n">arms</span><span class="o">=</span><span class="n">options</span><span class="p">,</span>
<span class="n">learning_policy</span><span class="o">=</span><span class="n">LearningPolicy</span><span class="o">.</span><span class="n">EpsilonGreedy</span><span class="p">(</span><span class="n">epsilon</span><span class="o">=</span><span class="mf">0.15</span><span class="p">),</span>
<span class="n">seed</span><span class="o">=</span><span class="mi">123456</span><span class="p">)</span>
<span class="c1"># Learn from previous layouts decisions and revenues generated</span>
<span class="n">greedy</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">decisions</span><span class="o">=</span><span class="n">layouts</span><span class="p">,</span> <span class="n">rewards</span><span class="o">=</span><span class="n">revenues</span><span class="p">)</span>
<span class="c1"># Predict the next best layouts decision</span>
<span class="n">prediction</span> <span class="o">=</span> <span class="n">greedy</span><span class="o">.</span><span class="n">predict</span><span class="p">()</span>
<span class="c1"># Expected revenues of each layouts learnt from historical data based on epsilon greedy policy</span>
<span class="n">expectations</span> <span class="o">=</span> <span class="n">greedy</span><span class="o">.</span><span class="n">predict_expectations</span><span class="p">()</span>
<span class="c1"># Results</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Epsilon Greedy: "</span><span class="p">,</span> <span class="n">prediction</span><span class="p">,</span> <span class="s2">" "</span><span class="p">,</span> <span class="n">expectations</span><span class="p">)</span>
<span class="k">assert</span><span class="p">(</span><span class="n">prediction</span> <span class="o">==</span> <span class="mi">2</span><span class="p">)</span>
<span class="c1"># Additional historical data becomes available which allows online learning</span>
<span class="n">additional_layouts</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">]</span>
<span class="n">additional_revenues</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">19</span><span class="p">]</span>
<span class="c1"># Online updating of the model</span>
<span class="n">greedy</span><span class="o">.</span><span class="n">partial_fit</span><span class="p">(</span><span class="n">additional_layouts</span><span class="p">,</span> <span class="n">additional_revenues</span><span class="p">)</span>
<span class="c1"># Adding a new layout option</span>
<span class="n">greedy</span><span class="o">.</span><span class="n">add_arm</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span>
<span class="c1"># Warm start new arm</span>
<span class="n">greedy</span><span class="o">.</span><span class="n">warm_start</span><span class="p">(</span><span class="n">arm_to_features</span><span class="p">,</span> <span class="n">distance_quantile</span><span class="o">=</span><span class="mf">0.5</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="parametric-contextual-mab">
<h2>Parametric Contextual MAB<a class="headerlink" href="#parametric-contextual-mab" title="Link to this heading"></a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="kn">from</span> <span class="nn">mabwiser.mab</span> <span class="kn">import</span> <span class="n">MAB</span><span class="p">,</span> <span class="n">LearningPolicy</span><span class="p">,</span> <span class="n">NeighborhoodPolicy</span>
<span class="c1">######################################################################################</span>
<span class="c1">#</span>
<span class="c1"># MABWiser</span>
<span class="c1"># Scenario: Advertisement Optimization</span>
<span class="c1">#</span>
<span class="c1"># An e-commerce website needs to solve the problem of which ad to display to online users</span>
<span class="c1"># Each advertisement decision leads to generating different revenues</span>
<span class="c1">#</span>
<span class="c1"># What should the choice of advertisement be given the context of an online user</span>
<span class="c1"># based on customer data such as age, click rate, subscriber?</span>
<span class="c1">#</span>
<span class="c1">######################################################################################</span>
<span class="c1"># Arms</span>
<span class="n">ads</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">]</span>
<span class="c1"># Historical data of ad decisions with corresponding revenues and context information</span>
<span class="n">train_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="s1">'ad'</span><span class="p">:</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="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">5</span><span class="p">],</span>
<span class="s1">'revenues'</span><span class="p">:</span> <span class="p">[</span><span class="mi">10</span><span class="p">,</span> <span class="mi">17</span><span class="p">,</span> <span class="mi">22</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">10</span><span class="p">],</span>
<span class="s1">'age'</span><span class="p">:</span> <span class="p">[</span><span class="mi">22</span><span class="p">,</span> <span class="mi">27</span><span class="p">,</span> <span class="mi">39</span><span class="p">,</span> <span class="mi">48</span><span class="p">,</span> <span class="mi">21</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">19</span><span class="p">,</span> <span class="mi">37</span><span class="p">,</span> <span class="mi">52</span><span class="p">,</span> <span class="mi">26</span><span class="p">,</span> <span class="mi">18</span><span class="p">,</span> <span class="mi">42</span><span class="p">,</span> <span class="mi">55</span><span class="p">,</span> <span class="mi">57</span><span class="p">,</span> <span class="mi">38</span><span class="p">],</span>
<span class="s1">'click_rate'</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">,</span> <span class="mf">0.99</span><span class="p">,</span> <span class="mf">0.68</span><span class="p">,</span> <span class="mf">0.15</span><span class="p">,</span> <span class="mf">0.23</span><span class="p">,</span> <span class="mf">0.75</span><span class="p">,</span> <span class="mf">0.17</span><span class="p">,</span>
<span class="mf">0.33</span><span class="p">,</span> <span class="mf">0.65</span><span class="p">,</span> <span class="mf">0.56</span><span class="p">,</span> <span class="mf">0.22</span><span class="p">,</span> <span class="mf">0.19</span><span class="p">,</span> <span class="mf">0.11</span><span class="p">,</span> <span class="mf">0.83</span><span class="p">],</span>
<span class="s1">'subscriber'</span><span class="p">:</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="mi">1</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="mi">0</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="mi">1</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="mi">1</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="mi">0</span><span class="p">]}</span>
<span class="p">)</span>
<span class="c1"># Arm features for warm start</span>
<span class="n">arm_to_features</span> <span class="o">=</span> <span class="p">{</span><span class="mi">1</span><span class="p">:</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="mi">1</span><span class="p">],</span> <span class="mi">2</span><span class="p">:</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">],</span> <span class="mi">3</span><span class="p">:</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="mf">0.5</span><span class="p">],</span> <span class="mi">4</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.2</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="mi">5</span><span class="p">:</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="mf">0.1</span><span class="p">],</span> <span class="mi">6</span><span class="p">:</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">]}</span>
<span class="c1"># Test data to for new prediction</span>
<span class="n">test_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="s1">'age'</span><span class="p">:</span> <span class="p">[</span><span class="mi">37</span><span class="p">,</span> <span class="mi">52</span><span class="p">],</span> <span class="s1">'click_rate'</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">],</span> <span class="s1">'subscriber'</span><span class="p">:</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="n">test_df_revenue</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="mi">7</span><span class="p">,</span> <span class="mi">13</span><span class="p">])</span>
<span class="c1"># Scale the training and test data</span>
<span class="n">scaler</span> <span class="o">=</span> <span class="n">StandardScaler</span><span class="p">()</span>
<span class="n">train</span> <span class="o">=</span> <span class="n">scaler</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">train_df</span><span class="p">[[</span><span class="s1">'age'</span><span class="p">,</span> <span class="s1">'click_rate'</span><span class="p">,</span> <span class="s1">'subscriber'</span><span class="p">]])</span>
<span class="n">test</span> <span class="o">=</span> <span class="n">scaler</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">test_df</span><span class="p">)</span>
<span class="c1">##################################################</span>
<span class="c1"># Linear Upper Confidence Bound Learning Policy</span>
<span class="c1">##################################################</span>
<span class="c1"># LinUCB learning policy with alpha 1.25 and l2_lambda 1</span>
<span class="n">linucb</span> <span class="o">=</span> <span class="n">MAB</span><span class="p">(</span><span class="n">arms</span><span class="o">=</span><span class="n">ads</span><span class="p">,</span>
<span class="n">learning_policy</span><span class="o">=</span><span class="n">LearningPolicy</span><span class="o">.</span><span class="n">LinUCB</span><span class="p">(</span><span class="n">alpha</span><span class="o">=</span><span class="mf">1.25</span><span class="p">,</span> <span class="n">l2_lambda</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
<span class="c1"># Learn from previous ads shown and revenues generated</span>
<span class="n">linucb</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">decisions</span><span class="o">=</span><span class="n">train_df</span><span class="p">[</span><span class="s1">'ad'</span><span class="p">],</span> <span class="n">rewards</span><span class="o">=</span><span class="n">train_df</span><span class="p">[</span><span class="s1">'revenues'</span><span class="p">],</span> <span class="n">contexts</span><span class="o">=</span><span class="n">train</span><span class="p">)</span>
<span class="c1"># Predict the next best ad to show</span>
<span class="n">prediction</span> <span class="o">=</span> <span class="n">linucb</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Expectation of each ad based on learning from past ad revenues</span>
<span class="n">expectations</span> <span class="o">=</span> <span class="n">linucb</span><span class="o">.</span><span class="n">predict_expectations</span><span class="p">(</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Results</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"LinUCB: "</span><span class="p">,</span> <span class="n">prediction</span><span class="p">,</span> <span class="s2">" "</span><span class="p">,</span> <span class="n">expectations</span><span class="p">)</span>
<span class="k">assert</span><span class="p">(</span><span class="n">prediction</span> <span class="o">==</span> <span class="p">[</span><span class="mi">5</span><span class="p">,</span> <span class="mi">2</span><span class="p">])</span>
<span class="c1"># Online update of model</span>
<span class="n">linucb</span><span class="o">.</span><span class="n">partial_fit</span><span class="p">(</span><span class="n">decisions</span><span class="o">=</span><span class="n">prediction</span><span class="p">,</span> <span class="n">rewards</span><span class="o">=</span><span class="n">test_df_revenue</span><span class="p">,</span> <span class="n">contexts</span><span class="o">=</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Update the model with new arm</span>
<span class="n">linucb</span><span class="o">.</span><span class="n">add_arm</span><span class="p">(</span><span class="mi">6</span><span class="p">)</span>
<span class="c1"># Warm start new arm</span>
<span class="n">linucb</span><span class="o">.</span><span class="n">warm_start</span><span class="p">(</span><span class="n">arm_to_features</span><span class="p">,</span> <span class="n">distance_quantile</span><span class="o">=</span><span class="mf">0.75</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="non-parametric-contextual-mab">
<h2>Non-Parametric Contextual MAB<a class="headerlink" href="#non-parametric-contextual-mab" title="Link to this heading"></a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="kn">from</span> <span class="nn">mabwiser.mab</span> <span class="kn">import</span> <span class="n">MAB</span><span class="p">,</span> <span class="n">LearningPolicy</span><span class="p">,</span> <span class="n">NeighborhoodPolicy</span>
<span class="c1">######################################################################################</span>
<span class="c1">#</span>
<span class="c1"># MABWiser</span>
<span class="c1"># Scenario: Advertisement Optimization</span>
<span class="c1">#</span>
<span class="c1"># An e-commerce website needs to solve the problem of which ad to display to online users</span>
<span class="c1"># Each advertisement decision leads to generating different revenues</span>
<span class="c1">#</span>
<span class="c1"># What should the choice of advertisement be given the context of an online user</span>
<span class="c1"># based on customer data such as age, click rate, subscriber?</span>
<span class="c1">#</span>
<span class="c1">######################################################################################</span>
<span class="c1"># Arms</span>
<span class="n">ads</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">]</span>
<span class="c1"># Historical data of ad decisions with corresponding revenues and context information</span>
<span class="n">train_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="s1">'ad'</span><span class="p">:</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="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">5</span><span class="p">],</span>
<span class="s1">'revenues'</span><span class="p">:</span> <span class="p">[</span><span class="mi">10</span><span class="p">,</span> <span class="mi">17</span><span class="p">,</span> <span class="mi">22</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">9</span><span class="p">,</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">12</span><span class="p">,</span> <span class="mi">10</span><span class="p">],</span>
<span class="s1">'age'</span><span class="p">:</span> <span class="p">[</span><span class="mi">22</span><span class="p">,</span> <span class="mi">27</span><span class="p">,</span> <span class="mi">39</span><span class="p">,</span> <span class="mi">48</span><span class="p">,</span> <span class="mi">21</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">19</span><span class="p">,</span> <span class="mi">37</span><span class="p">,</span> <span class="mi">52</span><span class="p">,</span> <span class="mi">26</span><span class="p">,</span> <span class="mi">18</span><span class="p">,</span> <span class="mi">42</span><span class="p">,</span> <span class="mi">55</span><span class="p">,</span> <span class="mi">57</span><span class="p">,</span> <span class="mi">38</span><span class="p">],</span>
<span class="s1">'click_rate'</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">,</span> <span class="mf">0.99</span><span class="p">,</span> <span class="mf">0.68</span><span class="p">,</span> <span class="mf">0.15</span><span class="p">,</span> <span class="mf">0.23</span><span class="p">,</span> <span class="mf">0.75</span><span class="p">,</span> <span class="mf">0.17</span><span class="p">,</span>
<span class="mf">0.33</span><span class="p">,</span> <span class="mf">0.65</span><span class="p">,</span> <span class="mf">0.56</span><span class="p">,</span> <span class="mf">0.22</span><span class="p">,</span> <span class="mf">0.19</span><span class="p">,</span> <span class="mf">0.11</span><span class="p">,</span> <span class="mf">0.83</span><span class="p">],</span>
<span class="s1">'subscriber'</span><span class="p">:</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="mi">1</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="mi">0</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="mi">1</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="mi">1</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="mi">0</span><span class="p">]}</span>
<span class="p">)</span>
<span class="c1"># Arm features for warm start</span>
<span class="n">arm_to_features</span> <span class="o">=</span> <span class="p">{</span><span class="mi">1</span><span class="p">:</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="mi">1</span><span class="p">],</span> <span class="mi">2</span><span class="p">:</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">],</span> <span class="mi">3</span><span class="p">:</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="mf">0.5</span><span class="p">],</span> <span class="mi">4</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.2</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="mi">5</span><span class="p">:</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="mf">0.1</span><span class="p">],</span> <span class="mi">6</span><span class="p">:</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">]}</span>
<span class="c1"># Test data to for new prediction</span>
<span class="n">test_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="s1">'age'</span><span class="p">:</span> <span class="p">[</span><span class="mi">37</span><span class="p">,</span> <span class="mi">52</span><span class="p">],</span> <span class="s1">'click_rate'</span><span class="p">:</span> <span class="p">[</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">],</span> <span class="s1">'subscriber'</span><span class="p">:</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="n">test_df_revenue</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="mi">7</span><span class="p">,</span> <span class="mi">13</span><span class="p">])</span>
<span class="c1"># Scale the training and test data</span>
<span class="n">scaler</span> <span class="o">=</span> <span class="n">StandardScaler</span><span class="p">()</span>
<span class="n">train</span> <span class="o">=</span> <span class="n">scaler</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">train_df</span><span class="p">[[</span><span class="s1">'age'</span><span class="p">,</span> <span class="s1">'click_rate'</span><span class="p">,</span> <span class="s1">'subscriber'</span><span class="p">]])</span>
<span class="n">test</span> <span class="o">=</span> <span class="n">scaler</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">test_df</span><span class="p">)</span>
<span class="c1">########################################################</span>
<span class="c1"># Radius Neighborhood Policy with UCB1 Learning Policy</span>
<span class="c1">########################################################</span>
<span class="c1"># Radius contextual policy with radius equals to 5 and ucb1 learning with alpha 1.25</span>
<span class="n">radius</span> <span class="o">=</span> <span class="n">MAB</span><span class="p">(</span><span class="n">arms</span><span class="o">=</span><span class="n">ads</span><span class="p">,</span>
<span class="n">learning_policy</span><span class="o">=</span><span class="n">LearningPolicy</span><span class="o">.</span><span class="n">UCB1</span><span class="p">(</span><span class="n">alpha</span><span class="o">=</span><span class="mf">1.25</span><span class="p">),</span>
<span class="n">neighborhood_policy</span><span class="o">=</span><span class="n">NeighborhoodPolicy</span><span class="o">.</span><span class="n">Radius</span><span class="p">(</span><span class="n">radius</span><span class="o">=</span><span class="mi">5</span><span class="p">))</span>
<span class="c1"># Learn from previous ads shown and revenues generated</span>
<span class="n">radius</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">decisions</span><span class="o">=</span><span class="n">train_df</span><span class="p">[</span><span class="s1">'ad'</span><span class="p">],</span> <span class="n">rewards</span><span class="o">=</span><span class="n">train_df</span><span class="p">[</span><span class="s1">'revenues'</span><span class="p">],</span> <span class="n">contexts</span><span class="o">=</span><span class="n">train</span><span class="p">)</span>
<span class="c1"># Predict the next best ad to show</span>
<span class="n">prediction</span> <span class="o">=</span> <span class="n">radius</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Expectation of each ad based on learning from past ad revenues</span>
<span class="n">expectations</span> <span class="o">=</span> <span class="n">radius</span><span class="o">.</span><span class="n">predict_expectations</span><span class="p">(</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Results</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Radius: "</span><span class="p">,</span> <span class="n">prediction</span><span class="p">,</span> <span class="s2">" "</span><span class="p">,</span> <span class="n">expectations</span><span class="p">)</span>
<span class="k">assert</span><span class="p">(</span><span class="n">prediction</span> <span class="o">==</span> <span class="p">[</span><span class="mi">4</span><span class="p">,</span> <span class="mi">4</span><span class="p">])</span>
<span class="c1"># Online update of model</span>
<span class="n">radius</span><span class="o">.</span><span class="n">partial_fit</span><span class="p">(</span><span class="n">decisions</span><span class="o">=</span><span class="n">prediction</span><span class="p">,</span> <span class="n">rewards</span><span class="o">=</span><span class="n">test_df_revenue</span><span class="p">,</span> <span class="n">contexts</span><span class="o">=</span><span class="n">test</span><span class="p">)</span>
<span class="c1"># Updating of the model with new arm</span>
<span class="n">radius</span><span class="o">.</span><span class="n">add_arm</span><span class="p">(</span><span class="mi">6</span><span class="p">)</span>
<span class="c1"># Warm start new arm</span>
<span class="n">radius</span><span class="o">.</span><span class="n">warm_start</span><span class="p">(</span><span class="n">arm_to_features</span><span class="p">,</span> <span class="n">distance_quantile</span><span class="o">=</span><span class="mf">0.75</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="parallel-mab">
<h2>Parallel MAB<a class="headerlink" href="#parallel-mab" title="Link to this heading"></a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">make_classification</span>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">train_test_split</span>
<span class="kn">from</span> <span class="nn">mabwiser.mab</span> <span class="kn">import</span> <span class="n">MAB</span><span class="p">,</span> <span class="n">LearningPolicy</span>
<span class="c1">######################################################################################</span>
<span class="c1">#</span>
<span class="c1"># MABWiser</span>
<span class="c1"># Scenario: Playlist recommendation for music streaming service</span>
<span class="c1">#</span>
<span class="c1"># An online music streaming service wants to recommend a playlist to a user</span>
<span class="c1"># based on a user's listening history and user features. There is a large amount</span>
<span class="c1"># of data available to train this recommender model, which means the parallel</span>
<span class="c1"># functionality in MABWiser can be useful.</span>
<span class="c1">#</span>
<span class="c1">#</span>
<span class="c1">######################################################################################</span>
<span class="c1"># Seed</span>
<span class="n">seed</span> <span class="o">=</span> <span class="mi">111</span>
<span class="c1"># Arms</span>
<span class="n">arms</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">100</span><span class="p">))</span>
<span class="c1"># Historical on user contexts and rewards (i.e. whether a user clicked</span>
<span class="c1"># on the recommended playlist or not)</span>
<span class="n">contexts</span><span class="p">,</span> <span class="n">rewards</span> <span class="o">=</span> <span class="n">make_classification</span><span class="p">(</span><span class="n">n_samples</span><span class="o">=</span><span class="mi">100000</span><span class="p">,</span> <span class="n">n_features</span><span class="o">=</span><span class="mi">200</span><span class="p">,</span>
<span class="n">n_informative</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">weights</span><span class="o">=</span><span class="p">[</span><span class="mf">0.01</span><span class="p">],</span> <span class="n">scale</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
<span class="c1"># Independently simulate the recommended playlist for each event</span>
<span class="n">decisions</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">choice</span><span class="p">(</span><span class="n">arms</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">100000</span><span class="p">)</span>
<span class="c1"># Split data into train and test data sets</span>
<span class="n">contexts_train</span><span class="p">,</span> <span class="n">contexts_test</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">contexts</span><span class="p">,</span> <span class="n">test_size</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="n">seed</span><span class="p">)</span>
<span class="n">rewards_train</span><span class="p">,</span> <span class="n">rewards_test</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">rewards</span><span class="p">,</span> <span class="n">test_size</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="n">seed</span><span class="p">)</span>
<span class="n">decisions_train</span><span class="p">,</span> <span class="n">decisions_test</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">decisions</span><span class="p">,</span> <span class="n">test_size</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="n">seed</span><span class="p">)</span>
<span class="c1">#############################################################################</span>
<span class="c1"># Parallel Radius Neighborhood Policy with UCB1 Learning Policy using 8 Cores</span>
<span class="c1">#############################################################################</span>
<span class="c1"># Radius contextual policy with radius equals to 5 and ucb1 learning with alpha 1.25</span>
<span class="n">radius</span> <span class="o">=</span> <span class="n">MAB</span><span class="p">(</span><span class="n">arms</span><span class="o">=</span><span class="n">ads</span><span class="p">,</span>
<span class="n">learning_policy</span><span class="o">=</span><span class="n">LearningPolicy</span><span class="o">.</span><span class="n">UCB1</span><span class="p">(</span><span class="n">alpha</span><span class="o">=</span><span class="mf">1.25</span><span class="p">),</span>
<span class="n">neighborhood_policy</span><span class="o">=</span><span class="n">NeighborhoodPolicy</span><span class="o">.</span><span class="n">Radius</span><span class="p">(</span><span class="n">radius</span><span class="o">=</span><span class="mi">5</span><span class="p">),</span>
<span class="n">n_jobs</span><span class="o">=</span><span class="mi">8</span><span class="p">)</span>
<span class="c1"># Parallel Training</span>
<span class="c1"># Learn from playlists shown and observed click rewards for each arm</span>
<span class="c1"># In reality, we can scale the data --skipping this step in the toy example here</span>
<span class="n">radius</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">decisions</span><span class="o">=</span><span class="n">decisions_train</span><span class="p">,</span> <span class="n">rewards</span><span class="o">=</span><span class="n">rewards_train</span><span class="p">,</span> <span class="n">contexts</span><span class="o">=</span><span class="n">contexts_train</span><span class="p">)</span>
<span class="c1"># Parallel Testing</span>
<span class="c1"># Predict the next best playlist to recommend</span>
<span class="n">prediction</span> <span class="o">=</span> <span class="n">radius</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">contexts_test</span><span class="p">)</span>
<span class="c1"># Results</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"radius: "</span><span class="p">,</span> <span class="n">prediction</span><span class="p">[:</span><span class="mi">10</span><span class="p">])</span>
</pre></div>
</div>
</section>
<section id="simulator">
<h2>Simulator<a class="headerlink" href="#simulator" title="Link to this heading"></a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">random</span>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="kn">from</span> <span class="nn">mabwiser.mab</span> <span class="kn">import</span> <span class="n">MAB</span><span class="p">,</span> <span class="n">LearningPolicy</span><span class="p">,</span> <span class="n">NeighborhoodPolicy</span>
<span class="kn">from</span> <span class="nn">mabwiser.simulator</span> <span class="kn">import</span> <span class="n">Simulator</span>
<span class="c1">######################################################################################</span>
<span class="c1">#</span>
<span class="c1"># MABWiser</span>
<span class="c1"># Scenario: Hyper-Parameter Tuning using the built-in Simulator capability</span>
<span class="c1">#</span>
<span class="c1">######################################################################################</span>
<span class="c1"># Data</span>
<span class="n">size</span> <span class="o">=</span> <span class="mi">1000</span>
<span class="n">decisions</span> <span class="o">=</span> <span class="p">[</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="p">)]</span>
<span class="n">rewards</span> <span class="o">=</span> <span class="p">[</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1000</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="p">)]</span>
<span class="n">contexts</span> <span class="o">=</span> <span class="p">[[</span><span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">50</span><span class="p">)]</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="p">)]</span>
<span class="c1"># Bandits to simulate</span>
<span class="n">n_jobs</span> <span class="o">=</span> <span class="mi">2</span>
<span class="n">hyper_parameter_tuning</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">radius</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">6</span><span class="p">,</span> <span class="mi">10</span><span class="p">):</span>
<span class="n">hyper_parameter_tuning</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="s1">'Radius'</span><span class="o">+</span><span class="nb">str</span><span class="p">(</span><span class="n">radius</span><span class="p">),</span>
<span class="n">MAB</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="n">LearningPolicy</span><span class="o">.</span><span class="n">UCB1</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span>
<span class="n">NeighborhoodPolicy</span><span class="o">.</span><span class="n">Radius</span><span class="p">(</span><span class="n">radius</span><span class="p">),</span>
<span class="n">n_jobs</span><span class="o">=</span><span class="n">n_jobs</span><span class="p">)))</span>
<span class="c1"># Simulator with given bandits and data</span>
<span class="c1"># The parameters uses standard scaler,</span>
<span class="c1"># Test split size set to 0.5</span>
<span class="c1"># The split is not order dependent, i.e., random split</span>
<span class="c1"># Online training with batch size 10, i.e., bandits will re-train at each batch</span>
<span class="c1"># Offline training can be run with batch_size 0, i.e., no re-training during test phase</span>
<span class="n">sim</span> <span class="o">=</span> <span class="n">Simulator</span><span class="p">(</span><span class="n">hyper_parameter_tuning</span><span class="p">,</span> <span class="n">decisions</span><span class="p">,</span> <span class="n">rewards</span><span class="p">,</span> <span class="n">contexts</span><span class="p">,</span>
<span class="n">scaler</span><span class="o">=</span><span class="n">StandardScaler</span><span class="p">(),</span> <span class="n">test_size</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">is_ordered</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">123456</span><span class="p">)</span>
<span class="c1"># Run the simulator</span>
<span class="n">sim</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="c1"># Save the results with a prefix</span>
<span class="n">sim</span><span class="o">.</span><span class="n">save_results</span><span class="p">(</span><span class="s2">"my_results_"</span><span class="p">)</span>
<span class="c1"># You can probe the fields of the simulator for other statisics</span>
<span class="k">for</span> <span class="n">mab_name</span><span class="p">,</span> <span class="n">mab</span> <span class="ow">in</span> <span class="n">sim</span><span class="o">.</span><span class="n">bandits</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="n">mab_name</span> <span class="o">+</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="p">)</span>
<span class="c1"># Since the simulation is online, print the 'total' stats</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">'Worst Case Scenario:'</span><span class="p">,</span> <span class="n">sim</span><span class="o">.</span><span class="n">bandit_to_arm_to_stats_min</span><span class="p">[</span><span class="n">mab_name</span><span class="p">][</span><span class="s1">'total'</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">'Average Case Scenario:'</span><span class="p">,</span> <span class="n">sim</span><span class="o">.</span><span class="n">bandit_to_arm_to_stats_avg</span><span class="p">[</span><span class="n">mab_name</span><span class="p">][</span><span class="s1">'total'</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">'Best Case Scenario:'</span><span class="p">,</span> <span class="n">sim</span><span class="o">.</span><span class="n">bandit_to_arm_to_stats_max</span><span class="p">[</span><span class="n">mab_name</span><span class="p">][</span><span class="s1">'total'</span><span class="p">],</span> <span class="s2">"</span><span class="se">\n\n</span><span class="s2">"</span><span class="p">)</span>
<span class="c1"># Plot the average case results per every arm for each bandit</span>
<span class="n">sim</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">metric</span><span class="o">=</span><span class="s1">'avg'</span><span class="p">,</span> <span class="n">is_per_arm</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
</pre></div>
</div>
<div class="admonition seealso">
<p class="admonition-title">See also</p>
<p>Additional examples are available in the <a class="reference external" href="https://github.com/fidelity/mabwiser/tree/master/examples">examples folder</a> in the repo.</p>
</div>
</section>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="quick.html" class="btn btn-neutral float-left" title="Quick Start" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="contributing.html" class="btn btn-neutral float-right" title="Contributing" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>© Copyright Copyright (C), FMR LLC.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>