python_for_analytics

1
{
2
 "cells": [
3
  {
4
   "cell_type": "markdown",
5
   "metadata": {
6
    "id": "ra21eO61q-iI"
7
   },
8
   "source": [
9
    "## Задача\n",
10
    "\n",
11
    "Подобрать такие значения параметров модели, чтобы модель давала верный прогноз по всем случаям."
12
   ]
13
  },
14
  {
15
   "cell_type": "code",
16
   "execution_count": 2,
17
   "metadata": {
18
    "id": "Ptsy6rKbQU95"
19
   },
20
   "outputs": [],
21
   "source": [
22
    "\n",
23
    "import pandas as pd\n",
24
    "import numpy as np\n",
25
    "import seaborn as sns\n",
26
    "import matplotlib.pyplot as plt\n",
27
    "\n",
28
    "\n",
29
    "from ipywidgets import interact, interactive, fixed, interact_manual\n",
30
    "import ipywidgets as widgets\n",
31
    "from IPython.display import display"
32
   ]
33
  },
34
  {
35
   "cell_type": "code",
36
   "execution_count": 4,
37
   "metadata": {
38
    "colab": {
39
     "base_uri": "https://localhost:8080/",
40
     "height": 206
41
    },
42
    "id": "RYKdnp9RDM5b",
43
    "outputId": "3bdfeb7b-0109-43fb-be2b-09dae3101cd2"
44
   },
45
   "outputs": [
46
    {
47
     "data": {
48
      "text/html": [
49
       "<div>\n",
50
       "<style scoped>\n",
51
       "    .dataframe tbody tr th:only-of-type {\n",
52
       "        vertical-align: middle;\n",
53
       "    }\n",
54
       "\n",
55
       "    .dataframe tbody tr th {\n",
56
       "        vertical-align: top;\n",
57
       "    }\n",
58
       "\n",
59
       "    .dataframe thead th {\n",
60
       "        text-align: right;\n",
61
       "    }\n",
62
       "</style>\n",
63
       "<table border=\"1\" class=\"dataframe\">\n",
64
       "  <thead>\n",
65
       "    <tr style=\"text-align: right;\">\n",
66
       "      <th></th>\n",
67
       "      <th>p_1</th>\n",
68
       "      <th>p_2</th>\n",
69
       "      <th>target</th>\n",
70
       "    </tr>\n",
71
       "  </thead>\n",
72
       "  <tbody>\n",
73
       "    <tr>\n",
74
       "      <th>0</th>\n",
75
       "      <td>1.4</td>\n",
76
       "      <td>0.2</td>\n",
77
       "      <td>0</td>\n",
78
       "    </tr>\n",
79
       "    <tr>\n",
80
       "      <th>1</th>\n",
81
       "      <td>1.4</td>\n",
82
       "      <td>0.2</td>\n",
83
       "      <td>0</td>\n",
84
       "    </tr>\n",
85
       "    <tr>\n",
86
       "      <th>2</th>\n",
87
       "      <td>1.3</td>\n",
88
       "      <td>0.2</td>\n",
89
       "      <td>0</td>\n",
90
       "    </tr>\n",
91
       "    <tr>\n",
92
       "      <th>3</th>\n",
93
       "      <td>1.5</td>\n",
94
       "      <td>0.2</td>\n",
95
       "      <td>0</td>\n",
96
       "    </tr>\n",
97
       "    <tr>\n",
98
       "      <th>4</th>\n",
99
       "      <td>1.4</td>\n",
100
       "      <td>0.2</td>\n",
101
       "      <td>0</td>\n",
102
       "    </tr>\n",
103
       "  </tbody>\n",
104
       "</table>\n",
105
       "</div>"
106
      ],
107
      "text/plain": [
108
       "   p_1  p_2  target\n",
109
       "0  1.4  0.2       0\n",
110
       "1  1.4  0.2       0\n",
111
       "2  1.3  0.2       0\n",
112
       "3  1.5  0.2       0\n",
113
       "4  1.4  0.2       0"
114
      ]
115
     },
116
     "execution_count": 4,
117
     "metadata": {},
118
     "output_type": "execute_result"
119
    }
120
   ],
121
   "source": [
122
    "from sklearn.datasets import load_iris\n",
123
    "iris = load_iris()\n",
124
    "data = pd.DataFrame(iris.data[:, 2:], columns=['p_1', 'p_2'])\n",
125
    "data['target'] = iris.target\n",
126
    "data.head()"
127
   ]
128
  },
129
  {
130
   "cell_type": "markdown",
131
   "metadata": {
132
    "id": "UCpi3verrKVR"
133
   },
134
   "source": [
135
    "## Функция для отрисовки границы разделения классов"
136
   ]
137
  },
138
  {
139
   "cell_type": "code",
140
   "execution_count": 3,
141
   "metadata": {
142
    "id": "KzRRCMatgRrr"
143
   },
144
   "outputs": [],
145
   "source": [
146
    "def plot_ex(df, name_x1, name_x2, fun):\n",
147
    "    x_min, x_max = df[name_x1].min() - 5, df[name_x1].max() + 5\n",
148
    "    y_min, y_max = df[name_x2].min() - 5, df[name_x2].max() + 5\n",
149
    "\n",
150
    "    h = .1\n",
151
    "    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n",
152
    "\n",
153
    "    Z = fun(np.c_[xx.ravel(),yy.ravel()])\n",
154
    "    Z = Z.reshape(xx.shape)\n",
155
    "    plt.figure(1, figsize=(7,7))\n",
156
    "    plt.pcolormesh(xx,yy,Z,cmap=plt.cm.Pastel1)\n",
157
    "\n",
158
    "    sns.scatterplot(x=df[name_x1], y=df[name_x2], hue=df['target'], palette=['#00aa00','#0000ff','#aa00aa'])\n",
159
    "    plt.xlabel(name_x1)\n",
160
    "    plt.ylabel(name_x2)\n",
161
    "\n",
162
    "    plt.xlim(xx.min(), xx.max())\n",
163
    "    plt.ylim(yy.min(), yy.max())\n",
164
    "    plt.xticks()\n",
165
    "    plt.show()"
166
   ]
167
  },
168
  {
169
   "cell_type": "markdown",
170
   "metadata": {
171
    "id": "mR8dHXxEtQo4"
172
   },
173
   "source": [
174
    "## Подберём параметры модели"
175
   ]
176
  },
177
  {
178
   "cell_type": "markdown",
179
   "metadata": {
180
    "id": "M5iGSbl1rf7M"
181
   },
182
   "source": [
183
    "![image.png](data:image/png;base64,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)"
184
   ]
185
  },
186
  {
187
   "cell_type": "markdown",
188
   "metadata": {
189
    "id": "L8SmWLQGulVA"
190
   },
191
   "source": [
192
    "### Модель\n",
193
    "Модель состоит из входного слоя с двумя входами (у нас всего 2 признака) и из выходного слоя с тремя нейронами (по одному на каждый класс).\n",
194
    "\n",
195
    "Для выходных нейронов значения определяется формулой\n",
196
    "\n",
197
    "$f_i = w_{1i} x_1 + w_{2i} x_2 + b_i$\n",
198
    "\n",
199
    "где $i$ - номер нейрона\n",
200
    "\n",
201
    "Каждый выходной нейрон отвечает за свой класс\n",
202
    "\n",
203
    "Что бы перевести значения на выходе из нейронов к вероятностям классов испоьзуем функцию softmax, \n",
204
    "\n",
205
    "$softmax(f)_j = \\frac{e^{f_j}}{\\sum_{i=1}^n e^{f_i}}$\n",
206
    "\n",
207
    "\n",
208
    "Итоговый класс определяется максимальной вероятностью\n",
209
    "\n",
210
    "$f(x_1,x_2) = softmax(f_3,f_4,f_5)$\n",
211
    "\n",
212
    "Задача в том, чтобы подобрать такие \n",
213
    "\n",
214
    "$w_{13}$, $w_{23}$,  $b_3$,\n",
215
    "\n",
216
    "$w_{14}$, $w_{24}$,  $b_4$,\n",
217
    "\n",
218
    "$w_{15}$, $w_{25}$,  $b_5$\n",
219
    "\n",
220
    ", что бы модель давала верный прогноз по всем случаям"
221
   ]
222
  },
223
  {
224
   "cell_type": "code",
225
   "execution_count": 4,
226
   "metadata": {
227
    "colab": {
228
     "base_uri": "https://localhost:8080/",
229
     "height": 748,
230
     "referenced_widgets": [
231
      "7a32f06a8ae14f808718848572171a34",
232
      "f091fbcc59284b50997c8c183521b1d7",
233
      "7b869c7a7ddd4c9c92f35b6ad5782e0c",
234
      "e78dbfd37e4946598940610b66647c0e",
235
      "549f1236e7184c98aee4a892607340d9",
236
      "62c78df4e46349f3a65ec3ea90c1483e",
237
      "61743bcfb95b417db05d366a482777c3",
238
      "f52736c43b084be397f11802adf1dcbe",
239
      "650a4521ba344165915d6d862254b746",
240
      "25710d97afb241eeb9cb12aa9acaaacc",
241
      "e1016a271f1e4b349afc87b5415b0d0d",
242
      "d8e0818c29d548a8b292d62159a5f5ca",
243
      "a12a59ae8ddf4bd6915e3b495205f100",
244
      "431f41a6a04044448ebe4002213d9722",
245
      "a07987a3f07143929f7bfeff9e07dbde",
246
      "4f1493c09b774b4188f367159b9d2f7a",
247
      "c001d7b1e174451aaee114a908e4c44b",
248
      "3eb7ba98fcd74befb88a0a28c821d5e9",
249
      "0bd870160e9a4f73860cc43fd76c1867",
250
      "fed4dcee89ee49e6ba1a4ce25cdaa91b",
251
      "5febd1c4562741d0b50c46cf94524cdb",
252
      "2e79740af3b44687baf497f7c26c7af9",
253
      "e9272fb1ebb54eb68677a713093d3bc4",
254
      "8c5888f9dd23441f88335e8d1c5eead7",
255
      "52a55ba7508045a595a6ec49a769f48b",
256
      "4ff41ceaf4e54cf78cb2f1269ca75d3e",
257
      "e817eb8cb6334fe0b0592e3cd91b9de9",
258
      "5de38e9cd3d04a5bbe3d0d0cb07eb30f",
259
      "25d3a421827b4db49db889bb93e1957b",
260
      "1cbb0f5c23be4d728c2ab63a8e745835",
261
      "2f134a00227d437e9869f94fad4785b2"
262
     ]
263
    },
264
    "id": "ABOcMLTwgYFC",
265
    "outputId": "83ce8788-12df-4721-e3a5-d19d90255e23"
266
   },
267
   "outputs": [
268
    {
269
     "data": {
270
      "application/vnd.jupyter.widget-view+json": {
271
       "model_id": "29f64143eb5345f1ba0da54e55fd5c73",
272
       "version_major": 2,
273
       "version_minor": 0
274
      },
275
      "text/plain": [
276
       "interactive(children=(FloatSlider(value=0.0, description='w13', max=10.0, min=-10.0, step=0.05), FloatSlider(v…"
277
      ]
278
     },
279
     "metadata": {},
280
     "output_type": "display_data"
281
    }
282
   ],
283
   "source": [
284
    "# Подбираем значения параметров модели\n",
285
    "# =====================\n",
286
    "\n",
287
    "# функция описывающая работу нашей модели \n",
288
    "# здесь х это массив пар значений признаков\n",
289
    "# вида [[0.1, 0.2]\n",
290
    "#      [1.3, 3.1]\n",
291
    "#      [2.1, 1.2]\n",
292
    "#      ...       ]\n",
293
    "def func(w13, w14, w15, w23, w24, w25, b3, b4, b5):\n",
294
    "\n",
295
    "    def softmax(x):\n",
296
    "        return np.exp(x)/np.sum(np.exp(x))\n",
297
    "\n",
298
    "    def f(x):\n",
299
    "        f3 = w13*x[:,0]+w23*x[:,1]+b3\n",
300
    "        f4 = w14*x[:,0]+w24*x[:,1]+b4\n",
301
    "        f5 = w15*x[:,0]+w25*x[:,1]+b5\n",
302
    "        res = softmax(np.vstack([f3, f4, f5]).T)\n",
303
    "        return  np.argmax(res, axis=1)\n",
304
    "\n",
305
    "    # Сделаем прогноз \n",
306
    "    data['pred'] = f(data[['p_1', 'p_2']].to_numpy())\n",
307
    "\n",
308
    "    # Нарисуем границу разделения классов и выведем результат предсказания\n",
309
    "    plot_ex(data, 'p_1', 'p_2', f)\n",
310
    "    print(f\"Доля верных ответов: {sum(data['target'] == data['pred'])/data.shape[0]}\")\n",
311
    "\n",
312
    "val_range = (-10,10,0.05)\n",
313
    "y=interactive(func, \n",
314
    "              w13=val_range, \n",
315
    "              w14=val_range, \n",
316
    "              w15=val_range, \n",
317
    "              w23=val_range, \n",
318
    "              w24=val_range, \n",
319
    "              w25=val_range, \n",
320
    "              b3=val_range, \n",
321
    "              b4=val_range, \n",
322
    "              b5=val_range\n",
323
    "              )\n",
324
    "display(y)"
325
   ]
326
  },
327
  {
328
   "cell_type": "markdown",
329
   "metadata": {},
330
   "source": [
331
    "![image.png](data:image/png;base64,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)\n",
332
    "Доля верных ответов: 0.96"
333
   ]
334
  },
335
  {
336
   "cell_type": "code",
337
   "execution_count": 5,
338
   "metadata": {
339
    "colab": {
340
     "base_uri": "https://localhost:8080/",
341
     "height": 424
342
    },
343
    "id": "eKislGYQ1VN1",
344
    "outputId": "c08acffb-bf9d-4fc0-9d33-3e5b8377ad86"
345
   },
346
   "outputs": [
347
    {
348
     "data": {
349
      "text/html": [
350
       "<div>\n",
351
       "<style scoped>\n",
352
       "    .dataframe tbody tr th:only-of-type {\n",
353
       "        vertical-align: middle;\n",
354
       "    }\n",
355
       "\n",
356
       "    .dataframe tbody tr th {\n",
357
       "        vertical-align: top;\n",
358
       "    }\n",
359
       "\n",
360
       "    .dataframe thead th {\n",
361
       "        text-align: right;\n",
362
       "    }\n",
363
       "</style>\n",
364
       "<table border=\"1\" class=\"dataframe\">\n",
365
       "  <thead>\n",
366
       "    <tr style=\"text-align: right;\">\n",
367
       "      <th></th>\n",
368
       "      <th>p_1</th>\n",
369
       "      <th>p_2</th>\n",
370
       "      <th>target</th>\n",
371
       "    </tr>\n",
372
       "  </thead>\n",
373
       "  <tbody>\n",
374
       "    <tr>\n",
375
       "      <th>0</th>\n",
376
       "      <td>1.4</td>\n",
377
       "      <td>0.2</td>\n",
378
       "      <td>0</td>\n",
379
       "    </tr>\n",
380
       "    <tr>\n",
381
       "      <th>1</th>\n",
382
       "      <td>1.4</td>\n",
383
       "      <td>0.2</td>\n",
384
       "      <td>0</td>\n",
385
       "    </tr>\n",
386
       "    <tr>\n",
387
       "      <th>2</th>\n",
388
       "      <td>1.3</td>\n",
389
       "      <td>0.2</td>\n",
390
       "      <td>0</td>\n",
391
       "    </tr>\n",
392
       "    <tr>\n",
393
       "      <th>3</th>\n",
394
       "      <td>1.5</td>\n",
395
       "      <td>0.2</td>\n",
396
       "      <td>0</td>\n",
397
       "    </tr>\n",
398
       "    <tr>\n",
399
       "      <th>4</th>\n",
400
       "      <td>1.4</td>\n",
401
       "      <td>0.2</td>\n",
402
       "      <td>0</td>\n",
403
       "    </tr>\n",
404
       "    <tr>\n",
405
       "      <th>...</th>\n",
406
       "      <td>...</td>\n",
407
       "      <td>...</td>\n",
408
       "      <td>...</td>\n",
409
       "    </tr>\n",
410
       "    <tr>\n",
411
       "      <th>145</th>\n",
412
       "      <td>5.2</td>\n",
413
       "      <td>2.3</td>\n",
414
       "      <td>2</td>\n",
415
       "    </tr>\n",
416
       "    <tr>\n",
417
       "      <th>146</th>\n",
418
       "      <td>5.0</td>\n",
419
       "      <td>1.9</td>\n",
420
       "      <td>2</td>\n",
421
       "    </tr>\n",
422
       "    <tr>\n",
423
       "      <th>147</th>\n",
424
       "      <td>5.2</td>\n",
425
       "      <td>2.0</td>\n",
426
       "      <td>2</td>\n",
427
       "    </tr>\n",
428
       "    <tr>\n",
429
       "      <th>148</th>\n",
430
       "      <td>5.4</td>\n",
431
       "      <td>2.3</td>\n",
432
       "      <td>2</td>\n",
433
       "    </tr>\n",
434
       "    <tr>\n",
435
       "      <th>149</th>\n",
436
       "      <td>5.1</td>\n",
437
       "      <td>1.8</td>\n",
438
       "      <td>2</td>\n",
439
       "    </tr>\n",
440
       "  </tbody>\n",
441
       "</table>\n",
442
       "<p>150 rows × 3 columns</p>\n",
443
       "</div>"
444
      ],
445
      "text/plain": [
446
       "     p_1  p_2  target\n",
447
       "0    1.4  0.2       0\n",
448
       "1    1.4  0.2       0\n",
449
       "2    1.3  0.2       0\n",
450
       "3    1.5  0.2       0\n",
451
       "4    1.4  0.2       0\n",
452
       "..   ...  ...     ...\n",
453
       "145  5.2  2.3       2\n",
454
       "146  5.0  1.9       2\n",
455
       "147  5.2  2.0       2\n",
456
       "148  5.4  2.3       2\n",
457
       "149  5.1  1.8       2\n",
458
       "\n",
459
       "[150 rows x 3 columns]"
460
      ]
461
     },
462
     "execution_count": 5,
463
     "metadata": {},
464
     "output_type": "execute_result"
465
    }
466
   ],
467
   "source": [
468
    "data"
469
   ]
470
  },
471
  {
472
   "cell_type": "code",
473
   "execution_count": null,
474
   "metadata": {},
475
   "outputs": [],
476
   "source": []
477
  }
478
 ],
479
 "metadata": {
480
  "colab": {
481
   "provenance": []
482
  },
483
  "kernelspec": {
484
   "display_name": "Python 3 (ipykernel)",
485
   "language": "python",
486
   "name": "python3"
487
  },
488
  "language_info": {
489
   "codemirror_mode": {
490
    "name": "ipython",
491
    "version": 3
492
   },
493
   "file_extension": ".py",
494
   "mimetype": "text/x-python",
495
   "name": "python",
496
   "nbconvert_exporter": "python",
497
   "pygments_lexer": "ipython3",
498
   "version": "3.9.13"
499
  },
500
  "widgets": {
501
   "application/vnd.jupyter.widget-state+json": {
502
    "state": {
503
     "07bc3d5bfe6b45bc84d1fc0d2f24b8d2": {
504
      "model_module": "@jupyter-widgets/controls",
505
      "model_module_version": "1.5.0",
506
      "model_name": "SliderStyleModel",
507
      "state": {
508
       "description_width": ""
509
      }
510
     },
511
     "0a2af2fe04704830addfefc9f7297ad0": {
512
      "model_module": "@jupyter-widgets/base",
513
      "model_module_version": "1.2.0",
514
      "model_name": "LayoutModel",
515
      "state": {}
516
     },
517
     "0e1686ea29af4b19a8d6e74bef4aa3fa": {
518
      "model_module": "@jupyter-widgets/controls",
519
      "model_module_version": "1.5.0",
520
      "model_name": "SliderStyleModel",
521
      "state": {
522
       "description_width": ""
523
      }
524
     },
525
     "155618c82c704af59bf688ad7fe9e6b3": {
526
      "model_module": "@jupyter-widgets/controls",
527
      "model_module_version": "1.5.0",
528
      "model_name": "SliderStyleModel",
529
      "state": {
530
       "description_width": ""
531
      }
532
     },
533
     "1912a8f56ab548bc948c0de776e95e11": {
534
      "model_module": "@jupyter-widgets/controls",
535
      "model_module_version": "1.5.0",
536
      "model_name": "SliderStyleModel",
537
      "state": {
538
       "description_width": ""
539
      }
540
     },
541
     "1f482cf2585f4458978382075d3db743": {
542
      "model_module": "@jupyter-widgets/base",
543
      "model_module_version": "1.2.0",
544
      "model_name": "LayoutModel",
545
      "state": {}
546
     },
547
     "29efe08cd0ed49118b7f42a35f1ac994": {
548
      "model_module": "@jupyter-widgets/controls",
549
      "model_module_version": "1.5.0",
550
      "model_name": "FloatSliderModel",
551
      "state": {
552
       "description": "b5",
553
       "layout": "IPY_MODEL_1f482cf2585f4458978382075d3db743",
554
       "max": 10,
555
       "min": -10,
556
       "step": 0.05,
557
       "style": "IPY_MODEL_3d07a0ce17fa4744a9294a3faee47553"
558
      }
559
     },
560
     "29f64143eb5345f1ba0da54e55fd5c73": {
561
      "model_module": "@jupyter-widgets/controls",
562
      "model_module_version": "1.5.0",
563
      "model_name": "VBoxModel",
564
      "state": {
565
       "_dom_classes": [
566
        "widget-interact"
567
       ],
568
       "children": [
569
        "IPY_MODEL_6f90d49dd6bb415786a969bd89b6e03c",
570
        "IPY_MODEL_915f9b481401401e9c153eb83efb91db",
571
        "IPY_MODEL_6c1cbbfccf2b47c5b928477491263403",
572
        "IPY_MODEL_713504d656434ef3887e0131664bb143",
573
        "IPY_MODEL_85c5e2cdc712461c94fd3b2e72f63964",
574
        "IPY_MODEL_d0948a67f2234fdf9d41932810d9cebd",
575
        "IPY_MODEL_e7752043a50c42ccb438712c91e7f9b1",
576
        "IPY_MODEL_74c42ec140384787b92422d1b66d8b5a",
577
        "IPY_MODEL_a39205c8989e4a0bb134260ed4e52b83",
578
        "IPY_MODEL_b58c8d13a104452fa1f9fb3e7d63a65e"
579
       ],
580
       "layout": "IPY_MODEL_c1cf91f5eeeb4abebbdea6f4fea85596"
581
      }
582
     },
583
     "337a1f7c31684eed918d2347dcf32359": {
584
      "model_module": "@jupyter-widgets/base",
585
      "model_module_version": "1.2.0",
586
      "model_name": "LayoutModel",
587
      "state": {}
588
     },
589
     "39e6abfdffbf4f698020027bc2a956bd": {
590
      "model_module": "@jupyter-widgets/controls",
591
      "model_module_version": "1.5.0",
592
      "model_name": "FloatSliderModel",
593
      "state": {
594
       "description": "w25",
595
       "layout": "IPY_MODEL_81166769dc0148fd992b350cc4ddc2af",
596
       "max": 10,
597
       "min": -10,
598
       "step": 0.05,
599
       "style": "IPY_MODEL_bd7bff60ddce496db35c0ffedf0c8c0e"
600
      }
601
     },
602
     "3d07a0ce17fa4744a9294a3faee47553": {
603
      "model_module": "@jupyter-widgets/controls",
604
      "model_module_version": "1.5.0",
605
      "model_name": "SliderStyleModel",
606
      "state": {
607
       "description_width": ""
608
      }
609
     },
610
     "414361ec6b544ea9845ac69137acbed8": {
611
      "model_module": "@jupyter-widgets/controls",
612
      "model_module_version": "1.5.0",
613
      "model_name": "VBoxModel",
614
      "state": {
615
       "_dom_classes": [
616
        "widget-interact"
617
       ],
618
       "children": [
619
        "IPY_MODEL_8cca14d9ca7249c59b141f40ca6c82b2",
620
        "IPY_MODEL_e626ccb021564e379917206284c199ea",
621
        "IPY_MODEL_6cab12e27c2c48e58e0b485a9a414a4f",
622
        "IPY_MODEL_db31f00372e34d46be671e8c9882c6f0",
623
        "IPY_MODEL_ad2d687310704ee5b82e9330ad31b78e",
624
        "IPY_MODEL_39e6abfdffbf4f698020027bc2a956bd",
625
        "IPY_MODEL_90c1a460982a45bca96cc0091df9fa1d",
626
        "IPY_MODEL_e55ebccdbef64994b88b4ba8b7955759",
627
        "IPY_MODEL_29efe08cd0ed49118b7f42a35f1ac994",
628
        "IPY_MODEL_9c445bd6fb504f11b01f14f8e65f0c40"
629
       ],
630
       "layout": "IPY_MODEL_ea92b0ec02df437a8d7c4589c42bcbb6"
631
      }
632
     },
633
     "414f92d63dd945df83503624e3edd502": {
634
      "model_module": "@jupyter-widgets/controls",
635
      "model_module_version": "1.5.0",
636
      "model_name": "SliderStyleModel",
637
      "state": {
638
       "description_width": ""
639
      }
640
     },
641
     "43a0cbb62a364e7285ab3a31148685fb": {
642
      "model_module": "@jupyter-widgets/controls",
643
      "model_module_version": "1.5.0",
644
      "model_name": "SliderStyleModel",
645
      "state": {
646
       "description_width": ""
647
      }
648
     },
649
     "49666af645624666ae2c6b18a2785c09": {
650
      "model_module": "@jupyter-widgets/controls",
651
      "model_module_version": "1.5.0",
652
      "model_name": "SliderStyleModel",
653
      "state": {
654
       "description_width": ""
655
      }
656
     },
657
     "4b9289b265cd4f77ac25507d9f7c1850": {
658
      "model_module": "@jupyter-widgets/base",
659
      "model_module_version": "1.2.0",
660
      "model_name": "LayoutModel",
661
      "state": {}
662
     },
663
     "50c5a297a91c45f0a8855a98ecb1b9cd": {
664
      "model_module": "@jupyter-widgets/base",
665
      "model_module_version": "1.2.0",
666
      "model_name": "LayoutModel",
667
      "state": {}
668
     },
669
     "65d93739b3c84828a3855670ad8ae8f4": {
670
      "model_module": "@jupyter-widgets/base",
671
      "model_module_version": "1.2.0",
672
      "model_name": "LayoutModel",
673
      "state": {}
674
     },
675
     "6c1cbbfccf2b47c5b928477491263403": {
676
      "model_module": "@jupyter-widgets/controls",
677
      "model_module_version": "1.5.0",
678
      "model_name": "FloatSliderModel",
679
      "state": {
680
       "description": "w15",
681
       "layout": "IPY_MODEL_0a2af2fe04704830addfefc9f7297ad0",
682
       "max": 10,
683
       "min": -10,
684
       "step": 0.05,
685
       "style": "IPY_MODEL_1912a8f56ab548bc948c0de776e95e11",
686
       "value": 0.88
687
      }
688
     },
689
     "6cab12e27c2c48e58e0b485a9a414a4f": {
690
      "model_module": "@jupyter-widgets/controls",
691
      "model_module_version": "1.5.0",
692
      "model_name": "FloatSliderModel",
693
      "state": {
694
       "description": "w15",
695
       "layout": "IPY_MODEL_f4d3a1ec8021435f926656e55e599d45",
696
       "max": 10,
697
       "min": -10,
698
       "step": 0.05,
699
       "style": "IPY_MODEL_43a0cbb62a364e7285ab3a31148685fb"
700
      }
701
     },
702
     "6f90d49dd6bb415786a969bd89b6e03c": {
703
      "model_module": "@jupyter-widgets/controls",
704
      "model_module_version": "1.5.0",
705
      "model_name": "FloatSliderModel",
706
      "state": {
707
       "description": "w13",
708
       "layout": "IPY_MODEL_337a1f7c31684eed918d2347dcf32359",
709
       "max": 10,
710
       "min": -10,
711
       "step": 0.05,
712
       "style": "IPY_MODEL_ec829ef2b5f146d6b11b2a3276b15109",
713
       "value": 0.4
714
      }
715
     },
716
     "700fcfa3b5264168b3f051b6e0667666": {
717
      "model_module": "@jupyter-widgets/controls",
718
      "model_module_version": "1.5.0",
719
      "model_name": "SliderStyleModel",
720
      "state": {
721
       "description_width": ""
722
      }
723
     },
724
     "713504d656434ef3887e0131664bb143": {
725
      "model_module": "@jupyter-widgets/controls",
726
      "model_module_version": "1.5.0",
727
      "model_name": "FloatSliderModel",
728
      "state": {
729
       "description": "w23",
730
       "layout": "IPY_MODEL_fa0efcc96292437999029e83dc4858d2",
731
       "max": 10,
732
       "min": -10,
733
       "step": 0.05,
734
       "style": "IPY_MODEL_94e2c53197a84822bdbfc676c4725e20",
735
       "value": -0.2
736
      }
737
     },
738
     "74c42ec140384787b92422d1b66d8b5a": {
739
      "model_module": "@jupyter-widgets/controls",
740
      "model_module_version": "1.5.0",
741
      "model_name": "FloatSliderModel",
742
      "state": {
743
       "description": "b4",
744
       "layout": "IPY_MODEL_b09f356846604ce5bf0542e47427d417",
745
       "max": 10,
746
       "min": -10,
747
       "step": 0.05,
748
       "style": "IPY_MODEL_0e1686ea29af4b19a8d6e74bef4aa3fa",
749
       "value": 1.2
750
      }
751
     },
752
     "7c910f983d8d4247af31cae419124b8c": {
753
      "model_module": "@jupyter-widgets/controls",
754
      "model_module_version": "1.5.0",
755
      "model_name": "SliderStyleModel",
756
      "state": {
757
       "description_width": ""
758
      }
759
     },
760
     "80474965506d4c0f95e22ca9166bbf77": {
761
      "model_module": "@jupyter-widgets/base",
762
      "model_module_version": "1.2.0",
763
      "model_name": "LayoutModel",
764
      "state": {}
765
     },
766
     "81166769dc0148fd992b350cc4ddc2af": {
767
      "model_module": "@jupyter-widgets/base",
768
      "model_module_version": "1.2.0",
769
      "model_name": "LayoutModel",
770
      "state": {}
771
     },
772
     "83dbc2b6a2e640d48df16538537faad0": {
773
      "model_module": "@jupyter-widgets/base",
774
      "model_module_version": "1.2.0",
775
      "model_name": "LayoutModel",
776
      "state": {}
777
     },
778
     "84d60ad5e3db4fb395724427c1085b29": {
779
      "model_module": "@jupyter-widgets/controls",
780
      "model_module_version": "1.5.0",
781
      "model_name": "SliderStyleModel",
782
      "state": {
783
       "description_width": ""
784
      }
785
     },
786
     "85436f3274d34604a6c1902e08fcdc13": {
787
      "model_module": "@jupyter-widgets/base",
788
      "model_module_version": "1.2.0",
789
      "model_name": "LayoutModel",
790
      "state": {}
791
     },
792
     "85c5e2cdc712461c94fd3b2e72f63964": {
793
      "model_module": "@jupyter-widgets/controls",
794
      "model_module_version": "1.5.0",
795
      "model_name": "FloatSliderModel",
796
      "state": {
797
       "description": "w24",
798
       "layout": "IPY_MODEL_4b9289b265cd4f77ac25507d9f7c1850",
799
       "max": 10,
800
       "min": -10,
801
       "step": 0.05,
802
       "style": "IPY_MODEL_07bc3d5bfe6b45bc84d1fc0d2f24b8d2",
803
       "value": 0.2
804
      }
805
     },
806
     "8cca14d9ca7249c59b141f40ca6c82b2": {
807
      "model_module": "@jupyter-widgets/controls",
808
      "model_module_version": "1.5.0",
809
      "model_name": "FloatSliderModel",
810
      "state": {
811
       "description": "w13",
812
       "layout": "IPY_MODEL_fe3260b880774131893d51ee5e20aed5",
813
       "max": 10,
814
       "min": -10,
815
       "step": 0.05,
816
       "style": "IPY_MODEL_49666af645624666ae2c6b18a2785c09"
817
      }
818
     },
819
     "90c1a460982a45bca96cc0091df9fa1d": {
820
      "model_module": "@jupyter-widgets/controls",
821
      "model_module_version": "1.5.0",
822
      "model_name": "FloatSliderModel",
823
      "state": {
824
       "description": "b3",
825
       "layout": "IPY_MODEL_ec36fdcae4fc4183a8c1b550334fadc7",
826
       "max": 10,
827
       "min": -10,
828
       "step": 0.05,
829
       "style": "IPY_MODEL_7c910f983d8d4247af31cae419124b8c"
830
      }
831
     },
832
     "915f9b481401401e9c153eb83efb91db": {
833
      "model_module": "@jupyter-widgets/controls",
834
      "model_module_version": "1.5.0",
835
      "model_name": "FloatSliderModel",
836
      "state": {
837
       "description": "w14",
838
       "layout": "IPY_MODEL_f4115ec9341e4423a05dd2696bbf1892",
839
       "max": 10,
840
       "min": -10,
841
       "step": 0.05,
842
       "style": "IPY_MODEL_9231c6ba06b5453a9b9eef50464eb7d0",
843
       "value": 0.7
844
      }
845
     },
846
     "9231c6ba06b5453a9b9eef50464eb7d0": {
847
      "model_module": "@jupyter-widgets/controls",
848
      "model_module_version": "1.5.0",
849
      "model_name": "SliderStyleModel",
850
      "state": {
851
       "description_width": ""
852
      }
853
     },
854
     "94e2c53197a84822bdbfc676c4725e20": {
855
      "model_module": "@jupyter-widgets/controls",
856
      "model_module_version": "1.5.0",
857
      "model_name": "SliderStyleModel",
858
      "state": {
859
       "description_width": ""
860
      }
861
     },
862
     "9c445bd6fb504f11b01f14f8e65f0c40": {
863
      "model_module": "@jupyter-widgets/output",
864
      "model_module_version": "1.0.0",
865
      "model_name": "OutputModel",
866
      "state": {
867
       "layout": "IPY_MODEL_f16eec6abe03455ba0822e2070bf1012",
868
       "outputs": [
869
        {
870
         "data": {
871
          "image/png": "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\n",
872
          "text/plain": "<Figure size 700x700 with 1 Axes>"
873
         },
874
         "metadata": {},
875
         "output_type": "display_data"
876
        },
877
        {
878
         "name": "stdout",
879
         "output_type": "stream",
880
         "text": "Доля верных ответов: 0.3333333333333333\n"
881
        }
882
       ]
883
      }
884
     },
885
     "a10857379c414c9a8e9c2f5cfbc0fcf3": {
886
      "model_module": "@jupyter-widgets/controls",
887
      "model_module_version": "1.5.0",
888
      "model_name": "SliderStyleModel",
889
      "state": {
890
       "description_width": ""
891
      }
892
     },
893
     "a39205c8989e4a0bb134260ed4e52b83": {
894
      "model_module": "@jupyter-widgets/controls",
895
      "model_module_version": "1.5.0",
896
      "model_name": "FloatSliderModel",
897
      "state": {
898
       "description": "b5",
899
       "layout": "IPY_MODEL_b9acaaed74ab4313903afd5640a76245",
900
       "max": 10,
901
       "min": -10,
902
       "step": 0.05,
903
       "style": "IPY_MODEL_700fcfa3b5264168b3f051b6e0667666",
904
       "value": -0.1
905
      }
906
     },
907
     "a506917ced68474c948ae51f25eb6915": {
908
      "model_module": "@jupyter-widgets/controls",
909
      "model_module_version": "1.5.0",
910
      "model_name": "SliderStyleModel",
911
      "state": {
912
       "description_width": ""
913
      }
914
     },
915
     "ad2d687310704ee5b82e9330ad31b78e": {
916
      "model_module": "@jupyter-widgets/controls",
917
      "model_module_version": "1.5.0",
918
      "model_name": "FloatSliderModel",
919
      "state": {
920
       "description": "w24",
921
       "layout": "IPY_MODEL_c8807feea161481cae188a4fad394f7b",
922
       "max": 10,
923
       "min": -10,
924
       "step": 0.05,
925
       "style": "IPY_MODEL_a506917ced68474c948ae51f25eb6915"
926
      }
927
     },
928
     "b09f356846604ce5bf0542e47427d417": {
929
      "model_module": "@jupyter-widgets/base",
930
      "model_module_version": "1.2.0",
931
      "model_name": "LayoutModel",
932
      "state": {}
933
     },
934
     "b58c8d13a104452fa1f9fb3e7d63a65e": {
935
      "model_module": "@jupyter-widgets/output",
936
      "model_module_version": "1.0.0",
937
      "model_name": "OutputModel",
938
      "state": {
939
       "layout": "IPY_MODEL_80474965506d4c0f95e22ca9166bbf77",
940
       "outputs": [
941
        {
942
         "data": {
943
          "image/png": "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\n",
944
          "text/plain": "<Figure size 700x700 with 1 Axes>"
945
         },
946
         "metadata": {},
947
         "output_type": "display_data"
948
        },
949
        {
950
         "name": "stdout",
951
         "output_type": "stream",
952
         "text": "Доля верных ответов: 0.96\n"
953
        }
954
       ]
955
      }
956
     },
957
     "b9acaaed74ab4313903afd5640a76245": {
958
      "model_module": "@jupyter-widgets/base",
959
      "model_module_version": "1.2.0",
960
      "model_name": "LayoutModel",
961
      "state": {}
962
     },
963
     "bd7bff60ddce496db35c0ffedf0c8c0e": {
964
      "model_module": "@jupyter-widgets/controls",
965
      "model_module_version": "1.5.0",
966
      "model_name": "SliderStyleModel",
967
      "state": {
968
       "description_width": ""
969
      }
970
     },
971
     "c1cf91f5eeeb4abebbdea6f4fea85596": {
972
      "model_module": "@jupyter-widgets/base",
973
      "model_module_version": "1.2.0",
974
      "model_name": "LayoutModel",
975
      "state": {}
976
     },
977
     "c8807feea161481cae188a4fad394f7b": {
978
      "model_module": "@jupyter-widgets/base",
979
      "model_module_version": "1.2.0",
980
      "model_name": "LayoutModel",
981
      "state": {}
982
     },
983
     "d0948a67f2234fdf9d41932810d9cebd": {
984
      "model_module": "@jupyter-widgets/controls",
985
      "model_module_version": "1.5.0",
986
      "model_name": "FloatSliderModel",
987
      "state": {
988
       "description": "w25",
989
       "layout": "IPY_MODEL_85436f3274d34604a6c1902e08fcdc13",
990
       "max": 10,
991
       "min": -10,
992
       "step": 0.05,
993
       "style": "IPY_MODEL_84d60ad5e3db4fb395724427c1085b29",
994
       "value": 0.5
995
      }
996
     },
997
     "db31f00372e34d46be671e8c9882c6f0": {
998
      "model_module": "@jupyter-widgets/controls",
999
      "model_module_version": "1.5.0",
1000
      "model_name": "FloatSliderModel",
1001
      "state": {
1002
       "description": "w23",
1003
       "layout": "IPY_MODEL_50c5a297a91c45f0a8855a98ecb1b9cd",
1004
       "max": 10,
1005
       "min": -10,
1006
       "step": 0.05,
1007
       "style": "IPY_MODEL_155618c82c704af59bf688ad7fe9e6b3"
1008
      }
1009
     },
1010
     "debde3ac5f764ba2939fe54fb231a5a4": {
1011
      "model_module": "@jupyter-widgets/base",
1012
      "model_module_version": "1.2.0",
1013
      "model_name": "LayoutModel",
1014
      "state": {}
1015
     },
1016
     "e55ebccdbef64994b88b4ba8b7955759": {
1017
      "model_module": "@jupyter-widgets/controls",
1018
      "model_module_version": "1.5.0",
1019
      "model_name": "FloatSliderModel",
1020
      "state": {
1021
       "description": "b4",
1022
       "layout": "IPY_MODEL_debde3ac5f764ba2939fe54fb231a5a4",
1023
       "max": 10,
1024
       "min": -10,
1025
       "step": 0.05,
1026
       "style": "IPY_MODEL_a10857379c414c9a8e9c2f5cfbc0fcf3"
1027
      }
1028
     },
1029
     "e626ccb021564e379917206284c199ea": {
1030
      "model_module": "@jupyter-widgets/controls",
1031
      "model_module_version": "1.5.0",
1032
      "model_name": "FloatSliderModel",
1033
      "state": {
1034
       "description": "w14",
1035
       "layout": "IPY_MODEL_65d93739b3c84828a3855670ad8ae8f4",
1036
       "max": 10,
1037
       "min": -10,
1038
       "step": 0.05,
1039
       "style": "IPY_MODEL_414f92d63dd945df83503624e3edd502"
1040
      }
1041
     },
1042
     "e7752043a50c42ccb438712c91e7f9b1": {
1043
      "model_module": "@jupyter-widgets/controls",
1044
      "model_module_version": "1.5.0",
1045
      "model_name": "FloatSliderModel",
1046
      "state": {
1047
       "description": "b3",
1048
       "layout": "IPY_MODEL_83dbc2b6a2e640d48df16538537faad0",
1049
       "max": 10,
1050
       "min": -10,
1051
       "step": 0.05,
1052
       "style": "IPY_MODEL_f5c322021d154704abd4e5c4e64bdc5e",
1053
       "value": 2.2
1054
      }
1055
     },
1056
     "ea92b0ec02df437a8d7c4589c42bcbb6": {
1057
      "model_module": "@jupyter-widgets/base",
1058
      "model_module_version": "1.2.0",
1059
      "model_name": "LayoutModel",
1060
      "state": {}
1061
     },
1062
     "ec36fdcae4fc4183a8c1b550334fadc7": {
1063
      "model_module": "@jupyter-widgets/base",
1064
      "model_module_version": "1.2.0",
1065
      "model_name": "LayoutModel",
1066
      "state": {}
1067
     },
1068
     "ec829ef2b5f146d6b11b2a3276b15109": {
1069
      "model_module": "@jupyter-widgets/controls",
1070
      "model_module_version": "1.5.0",
1071
      "model_name": "SliderStyleModel",
1072
      "state": {
1073
       "description_width": ""
1074
      }
1075
     },
1076
     "f16eec6abe03455ba0822e2070bf1012": {
1077
      "model_module": "@jupyter-widgets/base",
1078
      "model_module_version": "1.2.0",
1079
      "model_name": "LayoutModel",
1080
      "state": {}
1081
     },
1082
     "f4115ec9341e4423a05dd2696bbf1892": {
1083
      "model_module": "@jupyter-widgets/base",
1084
      "model_module_version": "1.2.0",
1085
      "model_name": "LayoutModel",
1086
      "state": {}
1087
     },
1088
     "f4d3a1ec8021435f926656e55e599d45": {
1089
      "model_module": "@jupyter-widgets/base",
1090
      "model_module_version": "1.2.0",
1091
      "model_name": "LayoutModel",
1092
      "state": {}
1093
     },
1094
     "f5c322021d154704abd4e5c4e64bdc5e": {
1095
      "model_module": "@jupyter-widgets/controls",
1096
      "model_module_version": "1.5.0",
1097
      "model_name": "SliderStyleModel",
1098
      "state": {
1099
       "description_width": ""
1100
      }
1101
     },
1102
     "fa0efcc96292437999029e83dc4858d2": {
1103
      "model_module": "@jupyter-widgets/base",
1104
      "model_module_version": "1.2.0",
1105
      "model_name": "LayoutModel",
1106
      "state": {}
1107
     },
1108
     "fe3260b880774131893d51ee5e20aed5": {
1109
      "model_module": "@jupyter-widgets/base",
1110
      "model_module_version": "1.2.0",
1111
      "model_name": "LayoutModel",
1112
      "state": {}
1113
     }
1114
    },
1115
    "version_major": 2,
1116
    "version_minor": 0
1117
   }
1118
  }
1119
 },
1120
 "nbformat": 4,
1121
 "nbformat_minor": 1
1122
}
1123