CoCalc -- Grupo_7

GitHub Repository: robertopucp/1eco35_2022_2
Path: blob/main/Trabajo_grupal/WG4/Grupo_7_jupyter.py
²⁷¹⁴ views
1
{
2
 "cells": [
3
  {
4
   "cell_type": "markdown",
5
   "id": "7c45962c",
6
   "metadata": {},
7
   "source": [
8
    "# ISSUE 4"
9
   ]
10
  },
11
  {
12
   "cell_type": "code",
13
   "execution_count": 230,
14
   "id": "0b84b167",
15
   "metadata": {},
16
   "outputs": [],
17
   "source": [
18
    "import pandas as pd\n",
19
    "import numpy as np\n",
20
    "import scipy.stats as stats\n",
21
    "from scipy.stats import t # t - student \n",
22
    "import os "
23
   ]
24
  },
25
  {
26
   "cell_type": "code",
27
   "execution_count": 231,
28
   "id": "4c56cf77",
29
   "metadata": {},
30
   "outputs": [],
31
   "source": [
32
    "user = os.getlogin()   # Username\n",
33
    "os.chdir(f\"/Users/{user}/Documents\")"
34
   ]
35
  },
36
  {
37
   "cell_type": "code",
38
   "execution_count": 233,
39
   "id": "fef4f8b6",
40
   "metadata": {},
41
   "outputs": [],
42
   "source": [
43
    "cps2012 = pd.read_excel(\"cps2012.xlsx\")"
44
   ]
45
  },
46
  {
47
   "cell_type": "code",
48
   "execution_count": 234,
49
   "id": "b40f0a13",
50
   "metadata": {},
51
   "outputs": [
52
    {
53
     "data": {
54
      "text/html": [
55
       "<div>\n",
56
       "<style scoped>\n",
57
       "    .dataframe tbody tr th:only-of-type {\n",
58
       "        vertical-align: middle;\n",
59
       "    }\n",
60
       "\n",
61
       "    .dataframe tbody tr th {\n",
62
       "        vertical-align: top;\n",
63
       "    }\n",
64
       "\n",
65
       "    .dataframe thead th {\n",
66
       "        text-align: right;\n",
67
       "    }\n",
68
       "</style>\n",
69
       "<table border=\"1\" class=\"dataframe\">\n",
70
       "  <thead>\n",
71
       "    <tr style=\"text-align: right;\">\n",
72
       "      <th></th>\n",
73
       "      <th>year</th>\n",
74
       "      <th>lnw</th>\n",
75
       "      <th>intercept</th>\n",
76
       "      <th>female</th>\n",
77
       "      <th>widowed</th>\n",
78
       "      <th>divorced</th>\n",
79
       "      <th>separated</th>\n",
80
       "      <th>nevermarried</th>\n",
81
       "      <th>hsd08</th>\n",
82
       "      <th>hsd911</th>\n",
83
       "      <th>...</th>\n",
84
       "      <th>so</th>\n",
85
       "      <th>we</th>\n",
86
       "      <th>exp1</th>\n",
87
       "      <th>exp2</th>\n",
88
       "      <th>exp3</th>\n",
89
       "      <th>exp4</th>\n",
90
       "      <th>weight</th>\n",
91
       "      <th>married</th>\n",
92
       "      <th>ne</th>\n",
93
       "      <th>sc</th>\n",
94
       "    </tr>\n",
95
       "  </thead>\n",
96
       "  <tbody>\n",
97
       "    <tr>\n",
98
       "      <th>0</th>\n",
99
       "      <td>2012</td>\n",
100
       "      <td>1.909542</td>\n",
101
       "      <td>1</td>\n",
102
       "      <td>1</td>\n",
103
       "      <td>0</td>\n",
104
       "      <td>0</td>\n",
105
       "      <td>0</td>\n",
106
       "      <td>0</td>\n",
107
       "      <td>0</td>\n",
108
       "      <td>0</td>\n",
109
       "      <td>...</td>\n",
110
       "      <td>0</td>\n",
111
       "      <td>0</td>\n",
112
       "      <td>22.0</td>\n",
113
       "      <td>4.8400</td>\n",
114
       "      <td>10.648000</td>\n",
115
       "      <td>23.425600</td>\n",
116
       "      <td>569.43</td>\n",
117
       "      <td>True</td>\n",
118
       "      <td>True</td>\n",
119
       "      <td>True</td>\n",
120
       "    </tr>\n",
121
       "    <tr>\n",
122
       "      <th>1</th>\n",
123
       "      <td>2012</td>\n",
124
       "      <td>1.365773</td>\n",
125
       "      <td>1</td>\n",
126
       "      <td>1</td>\n",
127
       "      <td>0</td>\n",
128
       "      <td>0</td>\n",
129
       "      <td>0</td>\n",
130
       "      <td>0</td>\n",
131
       "      <td>0</td>\n",
132
       "      <td>1</td>\n",
133
       "      <td>...</td>\n",
134
       "      <td>0</td>\n",
135
       "      <td>0</td>\n",
136
       "      <td>30.0</td>\n",
137
       "      <td>9.0000</td>\n",
138
       "      <td>27.000000</td>\n",
139
       "      <td>81.000000</td>\n",
140
       "      <td>625.96</td>\n",
141
       "      <td>True</td>\n",
142
       "      <td>True</td>\n",
143
       "      <td>False</td>\n",
144
       "    </tr>\n",
145
       "    <tr>\n",
146
       "      <th>2</th>\n",
147
       "      <td>2012</td>\n",
148
       "      <td>2.540223</td>\n",
149
       "      <td>1</td>\n",
150
       "      <td>0</td>\n",
151
       "      <td>0</td>\n",
152
       "      <td>0</td>\n",
153
       "      <td>0</td>\n",
154
       "      <td>0</td>\n",
155
       "      <td>0</td>\n",
156
       "      <td>0</td>\n",
157
       "      <td>...</td>\n",
158
       "      <td>0</td>\n",
159
       "      <td>0</td>\n",
160
       "      <td>19.0</td>\n",
161
       "      <td>3.6100</td>\n",
162
       "      <td>6.859000</td>\n",
163
       "      <td>13.032100</td>\n",
164
       "      <td>264.22</td>\n",
165
       "      <td>True</td>\n",
166
       "      <td>True</td>\n",
167
       "      <td>False</td>\n",
168
       "    </tr>\n",
169
       "    <tr>\n",
170
       "      <th>3</th>\n",
171
       "      <td>2012</td>\n",
172
       "      <td>1.801091</td>\n",
173
       "      <td>1</td>\n",
174
       "      <td>1</td>\n",
175
       "      <td>0</td>\n",
176
       "      <td>0</td>\n",
177
       "      <td>0</td>\n",
178
       "      <td>0</td>\n",
179
       "      <td>0</td>\n",
180
       "      <td>0</td>\n",
181
       "      <td>...</td>\n",
182
       "      <td>0</td>\n",
183
       "      <td>0</td>\n",
184
       "      <td>14.0</td>\n",
185
       "      <td>1.9600</td>\n",
186
       "      <td>2.744000</td>\n",
187
       "      <td>3.841600</td>\n",
188
       "      <td>256.81</td>\n",
189
       "      <td>True</td>\n",
190
       "      <td>True</td>\n",
191
       "      <td>False</td>\n",
192
       "    </tr>\n",
193
       "    <tr>\n",
194
       "      <th>4</th>\n",
195
       "      <td>2012</td>\n",
196
       "      <td>3.349904</td>\n",
197
       "      <td>1</td>\n",
198
       "      <td>0</td>\n",
199
       "      <td>0</td>\n",
200
       "      <td>0</td>\n",
201
       "      <td>0</td>\n",
202
       "      <td>0</td>\n",
203
       "      <td>0</td>\n",
204
       "      <td>0</td>\n",
205
       "      <td>...</td>\n",
206
       "      <td>0</td>\n",
207
       "      <td>0</td>\n",
208
       "      <td>15.0</td>\n",
209
       "      <td>2.2500</td>\n",
210
       "      <td>3.375000</td>\n",
211
       "      <td>5.062500</td>\n",
212
       "      <td>256.81</td>\n",
213
       "      <td>True</td>\n",
214
       "      <td>True</td>\n",
215
       "      <td>False</td>\n",
216
       "    </tr>\n",
217
       "    <tr>\n",
218
       "      <th>...</th>\n",
219
       "      <td>...</td>\n",
220
       "      <td>...</td>\n",
221
       "      <td>...</td>\n",
222
       "      <td>...</td>\n",
223
       "      <td>...</td>\n",
224
       "      <td>...</td>\n",
225
       "      <td>...</td>\n",
226
       "      <td>...</td>\n",
227
       "      <td>...</td>\n",
228
       "      <td>...</td>\n",
229
       "      <td>...</td>\n",
230
       "      <td>...</td>\n",
231
       "      <td>...</td>\n",
232
       "      <td>...</td>\n",
233
       "      <td>...</td>\n",
234
       "      <td>...</td>\n",
235
       "      <td>...</td>\n",
236
       "      <td>...</td>\n",
237
       "      <td>...</td>\n",
238
       "      <td>...</td>\n",
239
       "      <td>...</td>\n",
240
       "    </tr>\n",
241
       "    <tr>\n",
242
       "      <th>103</th>\n",
243
       "      <td>2012</td>\n",
244
       "      <td>2.369075</td>\n",
245
       "      <td>1</td>\n",
246
       "      <td>1</td>\n",
247
       "      <td>0</td>\n",
248
       "      <td>0</td>\n",
249
       "      <td>0</td>\n",
250
       "      <td>1</td>\n",
251
       "      <td>0</td>\n",
252
       "      <td>0</td>\n",
253
       "      <td>...</td>\n",
254
       "      <td>0</td>\n",
255
       "      <td>0</td>\n",
256
       "      <td>18.0</td>\n",
257
       "      <td>3.2400</td>\n",
258
       "      <td>5.832000</td>\n",
259
       "      <td>10.497600</td>\n",
260
       "      <td>491.40</td>\n",
261
       "      <td>False</td>\n",
262
       "      <td>True</td>\n",
263
       "      <td>False</td>\n",
264
       "    </tr>\n",
265
       "    <tr>\n",
266
       "      <th>104</th>\n",
267
       "      <td>2012</td>\n",
268
       "      <td>3.338731</td>\n",
269
       "      <td>1</td>\n",
270
       "      <td>0</td>\n",
271
       "      <td>0</td>\n",
272
       "      <td>0</td>\n",
273
       "      <td>0</td>\n",
274
       "      <td>0</td>\n",
275
       "      <td>0</td>\n",
276
       "      <td>0</td>\n",
277
       "      <td>...</td>\n",
278
       "      <td>0</td>\n",
279
       "      <td>0</td>\n",
280
       "      <td>28.0</td>\n",
281
       "      <td>7.8400</td>\n",
282
       "      <td>21.952000</td>\n",
283
       "      <td>61.465600</td>\n",
284
       "      <td>276.46</td>\n",
285
       "      <td>True</td>\n",
286
       "      <td>True</td>\n",
287
       "      <td>True</td>\n",
288
       "    </tr>\n",
289
       "    <tr>\n",
290
       "      <th>105</th>\n",
291
       "      <td>2012</td>\n",
292
       "      <td>2.225974</td>\n",
293
       "      <td>1</td>\n",
294
       "      <td>0</td>\n",
295
       "      <td>0</td>\n",
296
       "      <td>1</td>\n",
297
       "      <td>0</td>\n",
298
       "      <td>0</td>\n",
299
       "      <td>0</td>\n",
300
       "      <td>0</td>\n",
301
       "      <td>...</td>\n",
302
       "      <td>0</td>\n",
303
       "      <td>0</td>\n",
304
       "      <td>27.0</td>\n",
305
       "      <td>7.2900</td>\n",
306
       "      <td>19.683000</td>\n",
307
       "      <td>53.144100</td>\n",
308
       "      <td>479.96</td>\n",
309
       "      <td>False</td>\n",
310
       "      <td>True</td>\n",
311
       "      <td>False</td>\n",
312
       "    </tr>\n",
313
       "    <tr>\n",
314
       "      <th>106</th>\n",
315
       "      <td>2012</td>\n",
316
       "      <td>2.879901</td>\n",
317
       "      <td>1</td>\n",
318
       "      <td>1</td>\n",
319
       "      <td>0</td>\n",
320
       "      <td>1</td>\n",
321
       "      <td>0</td>\n",
322
       "      <td>0</td>\n",
323
       "      <td>0</td>\n",
324
       "      <td>0</td>\n",
325
       "      <td>...</td>\n",
326
       "      <td>0</td>\n",
327
       "      <td>0</td>\n",
328
       "      <td>20.5</td>\n",
329
       "      <td>4.2025</td>\n",
330
       "      <td>8.615125</td>\n",
331
       "      <td>17.661006</td>\n",
332
       "      <td>479.96</td>\n",
333
       "      <td>False</td>\n",
334
       "      <td>True</td>\n",
335
       "      <td>True</td>\n",
336
       "    </tr>\n",
337
       "    <tr>\n",
338
       "      <th>107</th>\n",
339
       "      <td>2012</td>\n",
340
       "      <td>1.852399</td>\n",
341
       "      <td>1</td>\n",
342
       "      <td>1</td>\n",
343
       "      <td>0</td>\n",
344
       "      <td>0</td>\n",
345
       "      <td>0</td>\n",
346
       "      <td>0</td>\n",
347
       "      <td>0</td>\n",
348
       "      <td>0</td>\n",
349
       "      <td>...</td>\n",
350
       "      <td>0</td>\n",
351
       "      <td>0</td>\n",
352
       "      <td>33.0</td>\n",
353
       "      <td>10.8900</td>\n",
354
       "      <td>35.937000</td>\n",
355
       "      <td>118.592100</td>\n",
356
       "      <td>576.29</td>\n",
357
       "      <td>True</td>\n",
358
       "      <td>True</td>\n",
359
       "      <td>True</td>\n",
360
       "    </tr>\n",
361
       "  </tbody>\n",
362
       "</table>\n",
363
       "<p>108 rows × 24 columns</p>\n",
364
       "</div>"
365
      ],
366
      "text/plain": [
367
       "     year       lnw  intercept  female  widowed  divorced  separated  \\\n",
368
       "0    2012  1.909542          1       1        0         0          0   \n",
369
       "1    2012  1.365773          1       1        0         0          0   \n",
370
       "2    2012  2.540223          1       0        0         0          0   \n",
371
       "3    2012  1.801091          1       1        0         0          0   \n",
372
       "4    2012  3.349904          1       0        0         0          0   \n",
373
       "..    ...       ...        ...     ...      ...       ...        ...   \n",
374
       "103  2012  2.369075          1       1        0         0          0   \n",
375
       "104  2012  3.338731          1       0        0         0          0   \n",
376
       "105  2012  2.225974          1       0        0         1          0   \n",
377
       "106  2012  2.879901          1       1        0         1          0   \n",
378
       "107  2012  1.852399          1       1        0         0          0   \n",
379
       "\n",
380
       "     nevermarried  hsd08  hsd911  ...  so  we  exp1     exp2       exp3  \\\n",
381
       "0               0      0       0  ...   0   0  22.0   4.8400  10.648000   \n",
382
       "1               0      0       1  ...   0   0  30.0   9.0000  27.000000   \n",
383
       "2               0      0       0  ...   0   0  19.0   3.6100   6.859000   \n",
384
       "3               0      0       0  ...   0   0  14.0   1.9600   2.744000   \n",
385
       "4               0      0       0  ...   0   0  15.0   2.2500   3.375000   \n",
386
       "..            ...    ...     ...  ...  ..  ..   ...      ...        ...   \n",
387
       "103             1      0       0  ...   0   0  18.0   3.2400   5.832000   \n",
388
       "104             0      0       0  ...   0   0  28.0   7.8400  21.952000   \n",
389
       "105             0      0       0  ...   0   0  27.0   7.2900  19.683000   \n",
390
       "106             0      0       0  ...   0   0  20.5   4.2025   8.615125   \n",
391
       "107             0      0       0  ...   0   0  33.0  10.8900  35.937000   \n",
392
       "\n",
393
       "           exp4  weight  married    ne     sc  \n",
394
       "0     23.425600  569.43     True  True   True  \n",
395
       "1     81.000000  625.96     True  True  False  \n",
396
       "2     13.032100  264.22     True  True  False  \n",
397
       "3      3.841600  256.81     True  True  False  \n",
398
       "4      5.062500  256.81     True  True  False  \n",
399
       "..          ...     ...      ...   ...    ...  \n",
400
       "103   10.497600  491.40    False  True  False  \n",
401
       "104   61.465600  276.46     True  True   True  \n",
402
       "105   53.144100  479.96    False  True  False  \n",
403
       "106   17.661006  479.96    False  True   True  \n",
404
       "107  118.592100  576.29     True  True   True  \n",
405
       "\n",
406
       "[108 rows x 24 columns]"
407
      ]
408
     },
409
     "execution_count": 234,
410
     "metadata": {},
411
     "output_type": "execute_result"
412
    }
413
   ],
414
   "source": [
415
    "cps2012"
416
   ]
417
  },
418
  {
419
   "cell_type": "code",
420
   "execution_count": 324,
421
   "id": "c26d2e2e",
422
   "metadata": {},
423
   "outputs": [],
424
   "source": [
425
    "ln = cps2012.lnw.values # se convierte a un array \n",
426
    "wei = cps2012.weight.values\n",
427
    "ex1 = cps2012.exp1.values\n",
428
    "ex2 = cps2012.exp2.values\n",
429
    "ex3 = cps2012.exp3.values"
430
   ]
431
  },
432
  {
433
   "cell_type": "code",
434
   "execution_count": 325,
435
   "id": "318f28f2",
436
   "metadata": {},
437
   "outputs": [],
438
   "source": [
439
    "# Generation of data\n",
440
    "\n",
441
    "y = np.log(  ln  ) # lnlnw\n",
442
    "c = np.ones( len( y ) ) # Constant\n",
443
    "x1 = cps2012.female\n",
444
    "x2 = cps2012.widowed\n",
445
    "x3 = cps2012.divorced\n",
446
    "x4 = cps2012.separated\n",
447
    "x5 = cps2012.nevermarried\n",
448
    "xw = np.log( wei )\n",
449
    "x11 = np.log( ex1 )\n",
450
    "x22 = np.log( ex2 ) \n",
451
    "x33 = np.log( ex3 ) \n",
452
    "x12 = np.log( ex1 )*np.log( ex2 )\n",
453
    "x13 = np.log( ex1 )*np.log( ex3 ) \n",
454
    "x23 = np.log( ex2 )*np.log( ex3 ) \n",
455
    "\n",
456
    "columns = [  \"ln_lnw\", \"female\", \"widowed\", \"divorced\", \"separated\",\n",
457
    "          \"nevermarried\", \"weight\", \"exp1\", \"exp2\", \"exp3\", \"(exp1)(exp2)\", \"(exp1)(exp3)\", \"(exp2)(exp3)\" ]\n",
458
    "\n",
459
    "data_val = np.asarray( [ y, x1, x2, x3, x4, x5, xw, x11, x22, x33, x12, x13, x23 ] ).T # se coloca transpuesta para que cada varaible sea una columna \n",
460
    "\n",
461
    "# np.asarray permite crear una matriz a partir de vectores \n",
462
    "\n",
463
    "data = pd.DataFrame(  data_val , columns = columns  )"
464
   ]
465
  },
466
  {
467
   "cell_type": "code",
468
   "execution_count": 326,
469
   "id": "73d42596",
470
   "metadata": {},
471
   "outputs": [
472
    {
473
     "data": {
474
      "text/html": [
475
       "<div>\n",
476
       "<style scoped>\n",
477
       "    .dataframe tbody tr th:only-of-type {\n",
478
       "        vertical-align: middle;\n",
479
       "    }\n",
480
       "\n",
481
       "    .dataframe tbody tr th {\n",
482
       "        vertical-align: top;\n",
483
       "    }\n",
484
       "\n",
485
       "    .dataframe thead th {\n",
486
       "        text-align: right;\n",
487
       "    }\n",
488
       "</style>\n",
489
       "<table border=\"1\" class=\"dataframe\">\n",
490
       "  <thead>\n",
491
       "    <tr style=\"text-align: right;\">\n",
492
       "      <th></th>\n",
493
       "      <th>ln_lnw</th>\n",
494
       "      <th>female</th>\n",
495
       "      <th>widowed</th>\n",
496
       "      <th>divorced</th>\n",
497
       "      <th>separated</th>\n",
498
       "      <th>nevermarried</th>\n",
499
       "      <th>weight</th>\n",
500
       "      <th>exp1</th>\n",
501
       "      <th>exp2</th>\n",
502
       "      <th>exp3</th>\n",
503
       "      <th>(exp1)(exp2)</th>\n",
504
       "      <th>(exp1)(exp3)</th>\n",
505
       "      <th>(exp2)(exp3)</th>\n",
506
       "    </tr>\n",
507
       "  </thead>\n",
508
       "  <tbody>\n",
509
       "    <tr>\n",
510
       "      <th>0</th>\n",
511
       "      <td>0.646864</td>\n",
512
       "      <td>1.0</td>\n",
513
       "      <td>0.0</td>\n",
514
       "      <td>0.0</td>\n",
515
       "      <td>0.0</td>\n",
516
       "      <td>0.0</td>\n",
517
       "      <td>6.344636</td>\n",
518
       "      <td>3.091042</td>\n",
519
       "      <td>1.576915</td>\n",
520
       "      <td>2.365372</td>\n",
521
       "      <td>4.874310</td>\n",
522
       "      <td>7.311466</td>\n",
523
       "      <td>3.729990</td>\n",
524
       "    </tr>\n",
525
       "    <tr>\n",
526
       "      <th>1</th>\n",
527
       "      <td>0.311720</td>\n",
528
       "      <td>1.0</td>\n",
529
       "      <td>0.0</td>\n",
530
       "      <td>0.0</td>\n",
531
       "      <td>0.0</td>\n",
532
       "      <td>0.0</td>\n",
533
       "      <td>6.439286</td>\n",
534
       "      <td>3.401197</td>\n",
535
       "      <td>2.197225</td>\n",
536
       "      <td>3.295837</td>\n",
537
       "      <td>7.473194</td>\n",
538
       "      <td>11.209792</td>\n",
539
       "      <td>7.241694</td>\n",
540
       "    </tr>\n",
541
       "    <tr>\n",
542
       "      <th>2</th>\n",
543
       "      <td>0.932252</td>\n",
544
       "      <td>0.0</td>\n",
545
       "      <td>0.0</td>\n",
546
       "      <td>0.0</td>\n",
547
       "      <td>0.0</td>\n",
548
       "      <td>0.0</td>\n",
549
       "      <td>5.576782</td>\n",
550
       "      <td>2.944439</td>\n",
551
       "      <td>1.283708</td>\n",
552
       "      <td>1.925562</td>\n",
553
       "      <td>3.779799</td>\n",
554
       "      <td>5.669699</td>\n",
555
       "      <td>2.471858</td>\n",
556
       "    </tr>\n",
557
       "    <tr>\n",
558
       "      <th>3</th>\n",
559
       "      <td>0.588392</td>\n",
560
       "      <td>1.0</td>\n",
561
       "      <td>0.0</td>\n",
562
       "      <td>0.0</td>\n",
563
       "      <td>0.0</td>\n",
564
       "      <td>0.0</td>\n",
565
       "      <td>5.548337</td>\n",
566
       "      <td>2.639057</td>\n",
567
       "      <td>0.672944</td>\n",
568
       "      <td>1.009417</td>\n",
569
       "      <td>1.775939</td>\n",
570
       "      <td>2.663909</td>\n",
571
       "      <td>0.679281</td>\n",
572
       "    </tr>\n",
573
       "    <tr>\n",
574
       "      <th>4</th>\n",
575
       "      <td>1.208932</td>\n",
576
       "      <td>0.0</td>\n",
577
       "      <td>0.0</td>\n",
578
       "      <td>0.0</td>\n",
579
       "      <td>0.0</td>\n",
580
       "      <td>0.0</td>\n",
581
       "      <td>5.548337</td>\n",
582
       "      <td>2.708050</td>\n",
583
       "      <td>0.810930</td>\n",
584
       "      <td>1.216395</td>\n",
585
       "      <td>2.196040</td>\n",
586
       "      <td>3.294060</td>\n",
587
       "      <td>0.986412</td>\n",
588
       "    </tr>\n",
589
       "    <tr>\n",
590
       "      <th>...</th>\n",
591
       "      <td>...</td>\n",
592
       "      <td>...</td>\n",
593
       "      <td>...</td>\n",
594
       "      <td>...</td>\n",
595
       "      <td>...</td>\n",
596
       "      <td>...</td>\n",
597
       "      <td>...</td>\n",
598
       "      <td>...</td>\n",
599
       "      <td>...</td>\n",
600
       "      <td>...</td>\n",
601
       "      <td>...</td>\n",
602
       "      <td>...</td>\n",
603
       "      <td>...</td>\n",
604
       "    </tr>\n",
605
       "    <tr>\n",
606
       "      <th>103</th>\n",
607
       "      <td>0.862499</td>\n",
608
       "      <td>1.0</td>\n",
609
       "      <td>0.0</td>\n",
610
       "      <td>0.0</td>\n",
611
       "      <td>0.0</td>\n",
612
       "      <td>1.0</td>\n",
613
       "      <td>6.197258</td>\n",
614
       "      <td>2.890372</td>\n",
615
       "      <td>1.175573</td>\n",
616
       "      <td>1.763360</td>\n",
617
       "      <td>3.397844</td>\n",
618
       "      <td>5.096766</td>\n",
619
       "      <td>2.072959</td>\n",
620
       "    </tr>\n",
621
       "    <tr>\n",
622
       "      <th>104</th>\n",
623
       "      <td>1.205591</td>\n",
624
       "      <td>0.0</td>\n",
625
       "      <td>0.0</td>\n",
626
       "      <td>0.0</td>\n",
627
       "      <td>0.0</td>\n",
628
       "      <td>0.0</td>\n",
629
       "      <td>5.622066</td>\n",
630
       "      <td>3.332205</td>\n",
631
       "      <td>2.059239</td>\n",
632
       "      <td>3.088858</td>\n",
633
       "      <td>6.861805</td>\n",
634
       "      <td>10.292707</td>\n",
635
       "      <td>6.360697</td>\n",
636
       "    </tr>\n",
637
       "    <tr>\n",
638
       "      <th>105</th>\n",
639
       "      <td>0.800195</td>\n",
640
       "      <td>0.0</td>\n",
641
       "      <td>0.0</td>\n",
642
       "      <td>1.0</td>\n",
643
       "      <td>0.0</td>\n",
644
       "      <td>0.0</td>\n",
645
       "      <td>6.173703</td>\n",
646
       "      <td>3.295837</td>\n",
647
       "      <td>1.986504</td>\n",
648
       "      <td>2.979755</td>\n",
649
       "      <td>6.547192</td>\n",
650
       "      <td>9.820787</td>\n",
651
       "      <td>5.919295</td>\n",
652
       "    </tr>\n",
653
       "    <tr>\n",
654
       "      <th>106</th>\n",
655
       "      <td>1.057756</td>\n",
656
       "      <td>1.0</td>\n",
657
       "      <td>0.0</td>\n",
658
       "      <td>1.0</td>\n",
659
       "      <td>0.0</td>\n",
660
       "      <td>0.0</td>\n",
661
       "      <td>6.173703</td>\n",
662
       "      <td>3.020425</td>\n",
663
       "      <td>1.435680</td>\n",
664
       "      <td>2.153519</td>\n",
665
       "      <td>4.336362</td>\n",
666
       "      <td>6.504544</td>\n",
667
       "      <td>3.091764</td>\n",
668
       "    </tr>\n",
669
       "    <tr>\n",
670
       "      <th>107</th>\n",
671
       "      <td>0.616481</td>\n",
672
       "      <td>1.0</td>\n",
673
       "      <td>0.0</td>\n",
674
       "      <td>0.0</td>\n",
675
       "      <td>0.0</td>\n",
676
       "      <td>0.0</td>\n",
677
       "      <td>6.356611</td>\n",
678
       "      <td>3.496508</td>\n",
679
       "      <td>2.387845</td>\n",
680
       "      <td>3.581767</td>\n",
681
       "      <td>8.349118</td>\n",
682
       "      <td>12.523677</td>\n",
683
       "      <td>8.552705</td>\n",
684
       "    </tr>\n",
685
       "  </tbody>\n",
686
       "</table>\n",
687
       "<p>108 rows × 13 columns</p>\n",
688
       "</div>"
689
      ],
690
      "text/plain": [
691
       "       ln_lnw  female  widowed  divorced  separated  nevermarried    weight  \\\n",
692
       "0    0.646864     1.0      0.0       0.0        0.0           0.0  6.344636   \n",
693
       "1    0.311720     1.0      0.0       0.0        0.0           0.0  6.439286   \n",
694
       "2    0.932252     0.0      0.0       0.0        0.0           0.0  5.576782   \n",
695
       "3    0.588392     1.0      0.0       0.0        0.0           0.0  5.548337   \n",
696
       "4    1.208932     0.0      0.0       0.0        0.0           0.0  5.548337   \n",
697
       "..        ...     ...      ...       ...        ...           ...       ...   \n",
698
       "103  0.862499     1.0      0.0       0.0        0.0           1.0  6.197258   \n",
699
       "104  1.205591     0.0      0.0       0.0        0.0           0.0  5.622066   \n",
700
       "105  0.800195     0.0      0.0       1.0        0.0           0.0  6.173703   \n",
701
       "106  1.057756     1.0      0.0       1.0        0.0           0.0  6.173703   \n",
702
       "107  0.616481     1.0      0.0       0.0        0.0           0.0  6.356611   \n",
703
       "\n",
704
       "         exp1      exp2      exp3  (exp1)(exp2)  (exp1)(exp3)  (exp2)(exp3)  \n",
705
       "0    3.091042  1.576915  2.365372      4.874310      7.311466      3.729990  \n",
706
       "1    3.401197  2.197225  3.295837      7.473194     11.209792      7.241694  \n",
707
       "2    2.944439  1.283708  1.925562      3.779799      5.669699      2.471858  \n",
708
       "3    2.639057  0.672944  1.009417      1.775939      2.663909      0.679281  \n",
709
       "4    2.708050  0.810930  1.216395      2.196040      3.294060      0.986412  \n",
710
       "..        ...       ...       ...           ...           ...           ...  \n",
711
       "103  2.890372  1.175573  1.763360      3.397844      5.096766      2.072959  \n",
712
       "104  3.332205  2.059239  3.088858      6.861805     10.292707      6.360697  \n",
713
       "105  3.295837  1.986504  2.979755      6.547192      9.820787      5.919295  \n",
714
       "106  3.020425  1.435680  2.153519      4.336362      6.504544      3.091764  \n",
715
       "107  3.496508  2.387845  3.581767      8.349118     12.523677      8.552705  \n",
716
       "\n",
717
       "[108 rows x 13 columns]"
718
      ]
719
     },
720
     "execution_count": 326,
721
     "metadata": {},
722
     "output_type": "execute_result"
723
    }
724
   ],
725
   "source": [
726
    "data"
727
   ]
728
  },
729
  {
730
   "cell_type": "code",
731
   "execution_count": 328,
732
   "id": "e8ae559c",
733
   "metadata": {},
734
   "outputs": [],
735
   "source": [
736
    "# selecting columns\n",
737
    "X = data.iloc[ : ,1:]\n",
738
    "y = data.ln_lnw\n",
739
    "lista = data.iloc[ : , :7]"
740
   ]
741
  },
742
  {
743
   "cell_type": "code",
744
   "execution_count": 340,
745
   "id": "6e5c0891",
746
   "metadata": {
747
    "scrolled": true
748
   },
749
   "outputs": [],
750
   "source": [
751
    "class OLSRegClass( object ):\n",
752
    "    \n",
753
    "    def __init__( self, X : pd.DataFrame , y : pd.Series , lista, RobustStandardError = True):\n",
754
    "    \n",
755
    "        if not isinstance( X, pd.DataFrame ):\n",
756
    "            raise TypeError( \"X must be a pd.DataFrame.\" )\n",
757
    "\n",
758
    "        if not isinstance( y , pd.Series ):\n",
759
    "            raise TypeError( \"y must be a pd.Series.\" )\n",
760
    "            \n",
761
    "        # asignando atributos de la clase\n",
762
    "        \n",
763
    "        self.X = X\n",
764
    "        self.y = y\n",
765
    "        self.lista = lista\n",
766
    "        self.RobustStandardError = RobustStandardError\n",
767
    "\n",
768
    "        self.X[ 'Intercept' ] = 1\n",
769
    "        # colcondo la columna Intercept en la primera columna \n",
770
    "        \n",
771
    "        cols = self.X.columns.tolist() # nombre de variable a lista \n",
772
    "        new_cols_orders = [cols[ -1 ]] + cols[ 5:-1 ]  # juntamos listas\n",
773
    "\n",
774
    "            \n",
775
    "        # [cols[ -1 ]] la jala la ultima fila , cols[ 0:-1 ]  primera fila hasta la fila 9\n",
776
    "            \n",
777
    "        self.X = self.X.loc[ : , new_cols_orders ] # usamos .loc que filtra por nombre de filas o columnas \n",
778
    "\n",
779
    "        \n",
780
    "        # creando nuevos atributos \n",
781
    "        \n",
782
    "        self.X_np = self.X.values  # Dataframe a multi array\n",
783
    "        self.y_np = y.values.reshape( -1 , 1 ) # de objeto serie a array columna \n",
784
    "        self.lista = self.X.columns.tolist() # nombre de la base de datos como objeto lista\n",
785
    "\n",
786
    "        \n",
787
    "# Creando Métodos #\n",
788
    "\n",
789
    "######################      MÉTODO 1     ###############################################\n",
790
    "    \n",
791
    "    def reg_beta_OLS( self ):\n",
792
    "        # X, y en Matrix, y vector columna respectivamente \n",
793
    "        \n",
794
    "        X_np = self.X_np\n",
795
    "        y_np = self.y_np\n",
796
    "\n",
797
    "        # beta_ols\n",
798
    "        beta_ols = np.linalg.inv( X_np.T @ X_np ) @ ( X_np.T @ y_np )\n",
799
    "\n",
800
    "        # columnas de X\n",
801
    "        index_names = self.lista\n",
802
    "        # Output\n",
803
    "        beta_OLS_output = pd.DataFrame( beta_ols , index = index_names , columns = [ 'Coef.' ] )\n",
804
    "        \n",
805
    "        # Dataframe de coeffientes como atributo \n",
806
    "        \n",
807
    "        self.beta_OLS = beta_OLS_output\n",
808
    "        \n",
809
    "        return beta_OLS_output\n",
810
    "    \n",
811
    "    \n",
812
    "######################      MÉTODO 2     ###############################################\n",
813
    "    \n",
814
    "    def var_stderrors_cfdinterval( self ):\n",
815
    "        \n",
816
    "        ### VARIANZA  ###\n",
817
    "        \n",
818
    "        # Se corre la función beta_OLS que estima el vector de coeficientes\n",
819
    "        self.reg_beta_OLS()\n",
820
    "        \n",
821
    "        # usaremos atributos pero con un nombre más simple\n",
822
    "        X_np = self.X_np\n",
823
    "        y_np = self.y_np\n",
824
    "        listaf = self.lista\n",
825
    "        \n",
826
    "        # beta_ols\n",
827
    "        beta_OLS = self.beta_OLS.values.reshape( - 1, 1 ) # Dataframe a vector columna \n",
828
    "\n",
829
    "        # errors\n",
830
    "        e = y_np - ( X_np @ beta_OLS )\n",
831
    "\n",
832
    "        # error variance\n",
833
    "        N = X_np.shape[ 0 ]\n",
834
    "        total_parameters = X_np.shape[ 1 ]\n",
835
    "        error_var = ( (e.T @ e)[ 0 ] )/( N - total_parameters )\n",
836
    "\n",
837
    "        # Varianza\n",
838
    "        var_OLS =  error_var * np.linalg.inv( X_np.T @ X_np )\n",
839
    "        \n",
840
    "        # asignando output de la función def reg_var_OLS( self ):   como atributo  self.var_OLS\n",
841
    "        index_names = listaf\n",
842
    "        var_OLS_output = pd.DataFrame( var_OLS , index = index_names , columns = index_names )\n",
843
    "        self.var_OLS = var_OLS_output\n",
844
    "\n",
845
    "        \n",
846
    "        ### STANDAR ERRORS  ###\n",
847
    "       \n",
848
    "        # var y beta\n",
849
    "        beta_OLS = self.beta_OLS.values.reshape( -1, 1 )   # -1 significa cualquier número de filas\n",
850
    "        var_OLS  = self.var_OLS.values\n",
851
    "        \n",
852
    "        # standard errors\n",
853
    "        beta_stderror = np.sqrt( np.diag( var_OLS ) )\n",
854
    "        \n",
855
    "        table_data0 = {  \"Std.Err.\" : beta_stderror.ravel()}\n",
856
    "        \n",
857
    "        # defining index names\n",
858
    "        index_names0 = listaf\n",
859
    "        \n",
860
    "        # defining a pandas dataframe \n",
861
    "        beta_se_output = pd.DataFrame( table_data0 , index = index_names0 )\n",
862
    "        self.beta_se = beta_se_output\n",
863
    "\n",
864
    "        ### Confidence interval ###\n",
865
    "        \n",
866
    "        up_bd = beta_OLS.ravel() + 1.96*beta_stderror\n",
867
    "        lw_bd = beta_OLS.ravel() - 1.96*beta_stderror\n",
868
    "        \n",
869
    "        table_data1 = {\"[0.025\"   : lw_bd.ravel(),\n",
870
    "                       \"0.975]\"   : up_bd.ravel()}\n",
871
    "        \n",
872
    "        # defining index names\n",
873
    "        index_names1 = listaf\n",
874
    "        \n",
875
    "        # defining a pandas dataframe \n",
876
    "        confiden_interval_output = pd.DataFrame( table_data1 , index = index_names1 )\n",
877
    "        self_confiden_interval = confiden_interval_output\n",
878
    "        \n",
879
    "        return var_OLS_output, beta_se_output, confiden_interval_output\n",
880
    "    \n",
881
    "    \n",
882
    "######################      MÉTODO 3     ###############################################\n",
883
    "    \n",
884
    "    def robust_var_se_cfdinterval(self):\n",
885
    "    \n",
886
    "        # Se corre la función beta_OLS que estima el vector de coeficientes\n",
887
    "        self.reg_beta_OLS()\n",
888
    "    \n",
889
    "        # usaré atributos pero con un nombre más simple\n",
890
    "        X_np = self.X_np\n",
891
    "        y_np = self.y_np\n",
892
    "        listaf = self.lista\n",
893
    "        \n",
894
    "        beta = np.linalg.inv(X_np.T @ X_np) @ ((X_np.T) @ y )\n",
895
    "        y_est = X_np @ beta\n",
896
    "        n = X_np.shape[0]\n",
897
    "        k = X_np.shape[1] - 1 \n",
898
    "        nk = n - k  \n",
899
    "\n",
900
    "        matrix_robust = np.diag(list( map( lambda x: x**2 , y - y_est)))\n",
901
    "        Var = np.linalg.inv(X_np.T @ X_np) @ X_np.T @ matrix_robust @ X_np @ np.linalg.inv(X_np.T @ X_np)\n",
902
    "        sd = np.sqrt( np.diag(Var) )\n",
903
    "        var = sd**2\n",
904
    "        t_est = np.absolute(beta/sd)\n",
905
    "        lower_bound = beta-1.96*sd\n",
906
    "        upper_bound = beta+1.96*sd\n",
907
    "        SCR = sum(list( map( lambda x: x**2 , y - y_est)   ))\n",
908
    "        SCT = sum(list( map( lambda x: x**2 , y - np.mean(y_est)   )))\n",
909
    "        R2 = 1-SCR/SCT\n",
910
    "        rmse = (SCR/n)**0.5\n",
911
    "        table = pd.DataFrame( {\"ols\": beta , \"standar_error\" : sd , \"Lower_bound\":lower_bound, \"Upper_bound\":upper_bound} ) \n",
912
    "        \n",
913
    "        fit = {\"Root_MSE\":rmse, \"R2\": R2}\n",
914
    "        \n",
915
    "        index_names7 = listaf\n",
916
    "        var_robust_output = pd.DataFrame( Var , index = index_names7 , columns = index_names7 )\n",
917
    "        self.var_robust = var_robust_output\n",
918
    "        \n",
919
    "        \n",
920
    "        return table, fit, var_robust_output\n",
921
    "        \n",
922
    "######################      MÉTODO 4     ###############################################  \n",
923
    "    \n",
924
    "    def R2_rootMSE( self ) :\n",
925
    "        \n",
926
    "        ############\n",
927
    "        ###  R2  ###\n",
928
    "        \n",
929
    "        # Se corre la función beta_OLS_Reg que estima el vector de coeficientes\n",
930
    "        self.reg_beta_OLS()\n",
931
    "        \n",
932
    "        y_est    = self.X_np @ self.beta_OLS   # y estimado\n",
933
    "        error    = self.y_np - y_est           # vector de errores\n",
934
    "        self.SCR = np.sum(np.square(error))    # Suma del Cuadrado de los Residuos\n",
935
    "        SCT      = np.sum(np.square(self.y_np - np.mean(self.X_np) ))  # Suma de Cuadrados Total\n",
936
    "\n",
937
    "        self.R2  = 1 - self.SCR/SCT\n",
938
    "\n",
939
    "                \n",
940
    "        #################\n",
941
    "        ### root MSE  ###\n",
942
    "        \n",
943
    "        for i in error.values:\n",
944
    "            \n",
945
    "            suma = 0\n",
946
    "            suma = np.sqrt( suma + (i**2) / self.X_np.shape[0] )\n",
947
    "            \n",
948
    "        self.rootMSE = suma.tolist()\n",
949
    "        \n",
950
    "        return self.R2, self.rootMSE\n",
951
    "    \n",
952
    "\n",
953
    "######################      MÉTODO 5     ###############################################\n",
954
    "    \n",
955
    "    def output( self ):\n",
956
    "        \n",
957
    "        self.reg_beta_OLS()\n",
958
    "        self.R2_rootMSE()\n",
959
    "        self.var_stderrors_cfdinterval()\n",
960
    "        \n",
961
    "        # var y beta\n",
962
    "        beta_OLS = self.beta_OLS.values.reshape( -1, 1 )   # -1 significa cualquier número de filas\n",
963
    "        var_OLS  = self.var_OLS.values\n",
964
    "        \n",
965
    "        # standard errors\n",
966
    "        beta_stderror = np.sqrt( np.diag( var_OLS ) )\n",
967
    "        \n",
968
    "        # confidence interval\n",
969
    "        up_bd = beta_OLS.ravel() + 1.96*beta_stderror\n",
970
    "        lw_bd = beta_OLS.ravel() - 1.96*beta_stderror\n",
971
    "        \n",
972
    "        table_data2 = {'Coef.'    : beta_OLS.ravel(),\n",
973
    "                       'Std.Err.' : beta_stderror.ravel(),\n",
974
    "                       '[0.025'   : lw_bd.ravel(),\n",
975
    "                       '0.975]'   : up_bd.ravel(),\n",
976
    "                       'R2'       : self.R2,\n",
977
    "                       'rootMSE'  : self.rootMSE}\n",
978
    "        \n",
979
    "        return table_data2"
980
   ]
981
  },
982
  {
983
   "cell_type": "code",
984
   "execution_count": 341,
985
   "id": "abd0335d",
986
   "metadata": {},
987
   "outputs": [
988
    {
989
     "data": {
990
      "text/html": [
991
       "<div>\n",
992
       "<style scoped>\n",
993
       "    .dataframe tbody tr th:only-of-type {\n",
994
       "        vertical-align: middle;\n",
995
       "    }\n",
996
       "\n",
997
       "    .dataframe tbody tr th {\n",
998
       "        vertical-align: top;\n",
999
       "    }\n",
1000
       "\n",
1001
       "    .dataframe thead th {\n",
1002
       "        text-align: right;\n",
1003
       "    }\n",
1004
       "</style>\n",
1005
       "<table border=\"1\" class=\"dataframe\">\n",
1006
       "  <thead>\n",
1007
       "    <tr style=\"text-align: right;\">\n",
1008
       "      <th></th>\n",
1009
       "      <th>Intercept</th>\n",
1010
       "      <th>weight</th>\n",
1011
       "      <th>exp1</th>\n",
1012
       "      <th>exp2</th>\n",
1013
       "      <th>exp3</th>\n",
1014
       "      <th>(exp1)(exp2)</th>\n",
1015
       "      <th>(exp1)(exp3)</th>\n",
1016
       "      <th>(exp2)(exp3)</th>\n",
1017
       "    </tr>\n",
1018
       "  </thead>\n",
1019
       "  <tbody>\n",
1020
       "    <tr>\n",
1021
       "      <th>0</th>\n",
1022
       "      <td>1</td>\n",
1023
       "      <td>6.344636</td>\n",
1024
       "      <td>3.091042</td>\n",
1025
       "      <td>1.576915</td>\n",
1026
       "      <td>2.365372</td>\n",
1027
       "      <td>4.874310</td>\n",
1028
       "      <td>7.311466</td>\n",
1029
       "      <td>3.729990</td>\n",
1030
       "    </tr>\n",
1031
       "    <tr>\n",
1032
       "      <th>1</th>\n",
1033
       "      <td>1</td>\n",
1034
       "      <td>6.439286</td>\n",
1035
       "      <td>3.401197</td>\n",
1036
       "      <td>2.197225</td>\n",
1037
       "      <td>3.295837</td>\n",
1038
       "      <td>7.473194</td>\n",
1039
       "      <td>11.209792</td>\n",
1040
       "      <td>7.241694</td>\n",
1041
       "    </tr>\n",
1042
       "    <tr>\n",
1043
       "      <th>2</th>\n",
1044
       "      <td>1</td>\n",
1045
       "      <td>5.576782</td>\n",
1046
       "      <td>2.944439</td>\n",
1047
       "      <td>1.283708</td>\n",
1048
       "      <td>1.925562</td>\n",
1049
       "      <td>3.779799</td>\n",
1050
       "      <td>5.669699</td>\n",
1051
       "      <td>2.471858</td>\n",
1052
       "    </tr>\n",
1053
       "    <tr>\n",
1054
       "      <th>3</th>\n",
1055
       "      <td>1</td>\n",
1056
       "      <td>5.548337</td>\n",
1057
       "      <td>2.639057</td>\n",
1058
       "      <td>0.672944</td>\n",
1059
       "      <td>1.009417</td>\n",
1060
       "      <td>1.775939</td>\n",
1061
       "      <td>2.663909</td>\n",
1062
       "      <td>0.679281</td>\n",
1063
       "    </tr>\n",
1064
       "    <tr>\n",
1065
       "      <th>4</th>\n",
1066
       "      <td>1</td>\n",
1067
       "      <td>5.548337</td>\n",
1068
       "      <td>2.708050</td>\n",
1069
       "      <td>0.810930</td>\n",
1070
       "      <td>1.216395</td>\n",
1071
       "      <td>2.196040</td>\n",
1072
       "      <td>3.294060</td>\n",
1073
       "      <td>0.986412</td>\n",
1074
       "    </tr>\n",
1075
       "    <tr>\n",
1076
       "      <th>...</th>\n",
1077
       "      <td>...</td>\n",
1078
       "      <td>...</td>\n",
1079
       "      <td>...</td>\n",
1080
       "      <td>...</td>\n",
1081
       "      <td>...</td>\n",
1082
       "      <td>...</td>\n",
1083
       "      <td>...</td>\n",
1084
       "      <td>...</td>\n",
1085
       "    </tr>\n",
1086
       "    <tr>\n",
1087
       "      <th>103</th>\n",
1088
       "      <td>1</td>\n",
1089
       "      <td>6.197258</td>\n",
1090
       "      <td>2.890372</td>\n",
1091
       "      <td>1.175573</td>\n",
1092
       "      <td>1.763360</td>\n",
1093
       "      <td>3.397844</td>\n",
1094
       "      <td>5.096766</td>\n",
1095
       "      <td>2.072959</td>\n",
1096
       "    </tr>\n",
1097
       "    <tr>\n",
1098
       "      <th>104</th>\n",
1099
       "      <td>1</td>\n",
1100
       "      <td>5.622066</td>\n",
1101
       "      <td>3.332205</td>\n",
1102
       "      <td>2.059239</td>\n",
1103
       "      <td>3.088858</td>\n",
1104
       "      <td>6.861805</td>\n",
1105
       "      <td>10.292707</td>\n",
1106
       "      <td>6.360697</td>\n",
1107
       "    </tr>\n",
1108
       "    <tr>\n",
1109
       "      <th>105</th>\n",
1110
       "      <td>1</td>\n",
1111
       "      <td>6.173703</td>\n",
1112
       "      <td>3.295837</td>\n",
1113
       "      <td>1.986504</td>\n",
1114
       "      <td>2.979755</td>\n",
1115
       "      <td>6.547192</td>\n",
1116
       "      <td>9.820787</td>\n",
1117
       "      <td>5.919295</td>\n",
1118
       "    </tr>\n",
1119
       "    <tr>\n",
1120
       "      <th>106</th>\n",
1121
       "      <td>1</td>\n",
1122
       "      <td>6.173703</td>\n",
1123
       "      <td>3.020425</td>\n",
1124
       "      <td>1.435680</td>\n",
1125
       "      <td>2.153519</td>\n",
1126
       "      <td>4.336362</td>\n",
1127
       "      <td>6.504544</td>\n",
1128
       "      <td>3.091764</td>\n",
1129
       "    </tr>\n",
1130
       "    <tr>\n",
1131
       "      <th>107</th>\n",
1132
       "      <td>1</td>\n",
1133
       "      <td>6.356611</td>\n",
1134
       "      <td>3.496508</td>\n",
1135
       "      <td>2.387845</td>\n",
1136
       "      <td>3.581767</td>\n",
1137
       "      <td>8.349118</td>\n",
1138
       "      <td>12.523677</td>\n",
1139
       "      <td>8.552705</td>\n",
1140
       "    </tr>\n",
1141
       "  </tbody>\n",
1142
       "</table>\n",
1143
       "<p>108 rows × 8 columns</p>\n",
1144
       "</div>"
1145
      ],
1146
      "text/plain": [
1147
       "     Intercept    weight      exp1      exp2      exp3  (exp1)(exp2)  \\\n",
1148
       "0            1  6.344636  3.091042  1.576915  2.365372      4.874310   \n",
1149
       "1            1  6.439286  3.401197  2.197225  3.295837      7.473194   \n",
1150
       "2            1  5.576782  2.944439  1.283708  1.925562      3.779799   \n",
1151
       "3            1  5.548337  2.639057  0.672944  1.009417      1.775939   \n",
1152
       "4            1  5.548337  2.708050  0.810930  1.216395      2.196040   \n",
1153
       "..         ...       ...       ...       ...       ...           ...   \n",
1154
       "103          1  6.197258  2.890372  1.175573  1.763360      3.397844   \n",
1155
       "104          1  5.622066  3.332205  2.059239  3.088858      6.861805   \n",
1156
       "105          1  6.173703  3.295837  1.986504  2.979755      6.547192   \n",
1157
       "106          1  6.173703  3.020425  1.435680  2.153519      4.336362   \n",
1158
       "107          1  6.356611  3.496508  2.387845  3.581767      8.349118   \n",
1159
       "\n",
1160
       "     (exp1)(exp3)  (exp2)(exp3)  \n",
1161
       "0        7.311466      3.729990  \n",
1162
       "1       11.209792      7.241694  \n",
1163
       "2        5.669699      2.471858  \n",
1164
       "3        2.663909      0.679281  \n",
1165
       "4        3.294060      0.986412  \n",
1166
       "..            ...           ...  \n",
1167
       "103      5.096766      2.072959  \n",
1168
       "104     10.292707      6.360697  \n",
1169
       "105      9.820787      5.919295  \n",
1170
       "106      6.504544      3.091764  \n",
1171
       "107     12.523677      8.552705  \n",
1172
       "\n",
1173
       "[108 rows x 8 columns]"
1174
      ]
1175
     },
1176
     "execution_count": 341,
1177
     "metadata": {},
1178
     "output_type": "execute_result"
1179
    }
1180
   ],
1181
   "source": [
1182
    "A = OLSRegClass( X, y, lista)\n",
1183
    "\n",
1184
    "# Atributo de las variables \n",
1185
    "\n",
1186
    "A.X"
1187
   ]
1188
  },
1189
  {
1190
   "cell_type": "code",
1191
   "execution_count": 342,
1192
   "id": "471ae9b4",
1193
   "metadata": {},
1194
   "outputs": [
1195
    {
1196
     "data": {
1197
      "text/plain": [
1198
       "0      0.646864\n",
1199
       "1      0.311720\n",
1200
       "2      0.932252\n",
1201
       "3      0.588392\n",
1202
       "4      1.208932\n",
1203
       "         ...   \n",
1204
       "103    0.862499\n",
1205
       "104    1.205591\n",
1206
       "105    0.800195\n",
1207
       "106    1.057756\n",
1208
       "107    0.616481\n",
1209
       "Name: ln_lnw, Length: 108, dtype: float64"
1210
      ]
1211
     },
1212
     "execution_count": 342,
1213
     "metadata": {},
1214
     "output_type": "execute_result"
1215
    }
1216
   ],
1217
   "source": [
1218
    "A.y"
1219
   ]
1220
  },
1221
  {
1222
   "cell_type": "code",
1223
   "execution_count": 343,
1224
   "id": "dac40599",
1225
   "metadata": {
1226
    "scrolled": true
1227
   },
1228
   "outputs": [
1229
    {
1230
     "data": {
1231
      "text/html": [
1232
       "<div>\n",
1233
       "<style scoped>\n",
1234
       "    .dataframe tbody tr th:only-of-type {\n",
1235
       "        vertical-align: middle;\n",
1236
       "    }\n",
1237
       "\n",
1238
       "    .dataframe tbody tr th {\n",
1239
       "        vertical-align: top;\n",
1240
       "    }\n",
1241
       "\n",
1242
       "    .dataframe thead th {\n",
1243
       "        text-align: right;\n",
1244
       "    }\n",
1245
       "</style>\n",
1246
       "<table border=\"1\" class=\"dataframe\">\n",
1247
       "  <thead>\n",
1248
       "    <tr style=\"text-align: right;\">\n",
1249
       "      <th></th>\n",
1250
       "      <th>Coef.</th>\n",
1251
       "    </tr>\n",
1252
       "  </thead>\n",
1253
       "  <tbody>\n",
1254
       "    <tr>\n",
1255
       "      <th>Intercept</th>\n",
1256
       "      <td>3.188650e+12</td>\n",
1257
       "    </tr>\n",
1258
       "    <tr>\n",
1259
       "      <th>weight</th>\n",
1260
       "      <td>2.312000e-01</td>\n",
1261
       "    </tr>\n",
1262
       "    <tr>\n",
1263
       "      <th>exp1</th>\n",
1264
       "      <td>-1.384813e+12</td>\n",
1265
       "    </tr>\n",
1266
       "    <tr>\n",
1267
       "      <th>exp2</th>\n",
1268
       "      <td>-2.030916e+12</td>\n",
1269
       "    </tr>\n",
1270
       "    <tr>\n",
1271
       "      <th>exp3</th>\n",
1272
       "      <td>1.815548e+12</td>\n",
1273
       "    </tr>\n",
1274
       "    <tr>\n",
1275
       "      <th>(exp1)(exp2)</th>\n",
1276
       "      <td>-3.750000e-01</td>\n",
1277
       "    </tr>\n",
1278
       "    <tr>\n",
1279
       "      <th>(exp1)(exp3)</th>\n",
1280
       "      <td>2.109375e-01</td>\n",
1281
       "    </tr>\n",
1282
       "    <tr>\n",
1283
       "      <th>(exp2)(exp3)</th>\n",
1284
       "      <td>4.687500e-02</td>\n",
1285
       "    </tr>\n",
1286
       "  </tbody>\n",
1287
       "</table>\n",
1288
       "</div>"
1289
      ],
1290
      "text/plain": [
1291
       "                     Coef.\n",
1292
       "Intercept     3.188650e+12\n",
1293
       "weight        2.312000e-01\n",
1294
       "exp1         -1.384813e+12\n",
1295
       "exp2         -2.030916e+12\n",
1296
       "exp3          1.815548e+12\n",
1297
       "(exp1)(exp2) -3.750000e-01\n",
1298
       "(exp1)(exp3)  2.109375e-01\n",
1299
       "(exp2)(exp3)  4.687500e-02"
1300
      ]
1301
     },
1302
     "execution_count": 343,
1303
     "metadata": {},
1304
     "output_type": "execute_result"
1305
    }
1306
   ],
1307
   "source": [
1308
    "A.reg_beta_OLS()  # Resultado del método reg OLS"
1309
   ]
1310
  },
1311
  {
1312
   "cell_type": "code",
1313
   "execution_count": 344,
1314
   "id": "42a71d89",
1315
   "metadata": {},
1316
   "outputs": [
1317
    {
1318
     "data": {
1319
      "text/plain": [
1320
       "(                 Intercept    weight          exp1          exp2  \\\n",
1321
       " Intercept     3.508713e+12 -0.168439 -1.522627e+12  4.709794e+11   \n",
1322
       " weight       -2.256574e-01  0.014918  6.099939e-02  3.769984e-03   \n",
1323
       " exp1         -1.523815e+12  0.036070  6.612683e+11 -2.045437e+11   \n",
1324
       " exp2          3.475491e+11  0.020307 -1.516955e+11  3.695393e+11   \n",
1325
       " exp3          1.295141e+12 -0.039286 -5.617959e+11  1.613982e+11   \n",
1326
       " (exp1)(exp2) -6.459732e+11  0.029641  2.805426e+11 -1.479965e+11   \n",
1327
       " (exp1)(exp3) -1.185471e+10 -0.013791  5.148436e+09 -4.881184e+10   \n",
1328
       " (exp2)(exp3)  2.212517e+11 -0.003710 -9.608841e+10  7.373810e+10   \n",
1329
       " \n",
1330
       "                       exp3  (exp1)(exp2)  (exp1)(exp3)  (exp2)(exp3)  \n",
1331
       " Intercept     1.202918e+12 -5.229542e+11 -8.942776e+10  2.193859e+11  \n",
1332
       " weight       -5.413574e-02  3.587093e-02 -1.022241e-02 -7.564230e-03  \n",
1333
       " exp1         -5.224208e+11  2.271161e+11  3.883798e+10 -9.527808e+10  \n",
1334
       " exp2          8.694858e+10 -9.184224e+10 -6.175452e+10  6.126590e+10  \n",
1335
       " exp3          1.472972e+11 -1.040522e+11  4.016546e+10  1.480289e+10  \n",
1336
       " (exp1)(exp2) -1.160764e+11  1.264719e+11 -3.166655e+10 -2.632402e+10  \n",
1337
       " (exp1)(exp3)  6.386791e+10 -4.541265e+10  1.592478e+10  7.175158e+09  \n",
1338
       " (exp2)(exp3)  6.758192e+09 -1.945097e+10  2.593123e+09  5.187095e+09  ,\n",
1339
       "                   Std.Err.\n",
1340
       " Intercept     1.873156e+06\n",
1341
       " weight        1.221379e-01\n",
1342
       " exp1          8.131840e+05\n",
1343
       " exp2          6.078975e+05\n",
1344
       " exp3          3.837932e+05\n",
1345
       " (exp1)(exp2)  3.556289e+05\n",
1346
       " (exp1)(exp3)  1.261934e+05\n",
1347
       " (exp2)(exp3)  7.202149e+04,\n",
1348
       "                     [0.025        0.975]\n",
1349
       " Intercept     3.188646e+12  3.188653e+12\n",
1350
       " weight       -8.190362e-03  4.705903e-01\n",
1351
       " exp1         -1.384815e+12 -1.384811e+12\n",
1352
       " exp2         -2.030917e+12 -2.030915e+12\n",
1353
       " exp3          1.815547e+12  1.815549e+12\n",
1354
       " (exp1)(exp2) -6.970329e+05  6.970322e+05\n",
1355
       " (exp1)(exp3) -2.473389e+05  2.473393e+05\n",
1356
       " (exp2)(exp3) -1.411621e+05  1.411622e+05)"
1357
      ]
1358
     },
1359
     "execution_count": 344,
1360
     "metadata": {},
1361
     "output_type": "execute_result"
1362
    }
1363
   ],
1364
   "source": [
1365
    "A.var_stderrors_cfdinterval() # Matriz de var y cov, sd y confidence interval"
1366
   ]
1367
  },
1368
  {
1369
   "cell_type": "code",
1370
   "execution_count": 345,
1371
   "id": "36e9bd53",
1372
   "metadata": {},
1373
   "outputs": [
1374
    {
1375
     "name": "stderr",
1376
     "output_type": "stream",
1377
     "text": [
1378
      "/var/folders/zl/dwjs19r53hv4ng4wbr0b4srm0000gn/T/ipykernel_42554/3219601434.py:152: RuntimeWarning: invalid value encountered in sqrt\n",
1379
      "  sd = np.sqrt( np.diag(Var) )\n"
1380
     ]
1381
    },
1382
    {
1383
     "data": {
1384
      "text/plain": [
1385
       "(            ols  standar_error  Lower_bound  Upper_bound\n",
1386
       " 0  3.188650e+12            NaN          NaN          NaN\n",
1387
       " 1  2.312000e-01       0.106487     0.022485     0.439915\n",
1388
       " 2 -1.384813e+12            NaN          NaN          NaN\n",
1389
       " 3 -2.030916e+12            NaN          NaN          NaN\n",
1390
       " 4  1.815548e+12            NaN          NaN          NaN\n",
1391
       " 5 -3.750000e-01       0.230666    -0.827105     0.077105\n",
1392
       " 6  2.109375e-01       0.084685     0.044954     0.376921\n",
1393
       " 7  4.687500e-02       0.033553    -0.018889     0.112639,\n",
1394
       " {'Root_MSE': 0.38702207433645885, 'R2': -0.6657433395568355},\n",
1395
       "                  Intercept        weight          exp1          exp2  \\\n",
1396
       " Intercept    -6.761294e+10  5.069708e+09  1.841976e+10  3.265294e+09   \n",
1397
       " weight       -1.705086e-01  1.133951e-02  4.523530e-02  4.516671e-03   \n",
1398
       " exp1          3.542932e+10 -2.201746e+09 -1.090204e+10 -8.479164e+08   \n",
1399
       " exp2          4.109676e+10 -3.229000e+09 -1.081535e+10 -2.044731e+09   \n",
1400
       " exp3         -4.334018e+10  2.886582e+09  1.305646e+10  1.032711e+09   \n",
1401
       " (exp1)(exp2) -3.334106e-01  2.154035e-02  8.960376e-02  7.399946e-03   \n",
1402
       " (exp1)(exp3)  1.562500e-01 -1.001835e-02 -4.223633e-02 -3.082275e-03   \n",
1403
       " (exp2)(exp3)  3.338623e-02 -2.175875e-03 -9.002686e-03 -6.256104e-04   \n",
1404
       " \n",
1405
       "                       exp3  (exp1)(exp2)  (exp1)(exp3)  (exp2)(exp3)  \n",
1406
       " Intercept    -1.649820e+10  1.160032e+10 -3.543179e+09 -2.018624e+09  \n",
1407
       " weight       -4.147033e-02  2.783473e-02 -7.845354e-03 -5.283871e-03  \n",
1408
       " exp1          8.904519e+09 -6.238933e+09  1.802301e+09  1.141336e+09  \n",
1409
       " exp2          1.036568e+10 -7.311260e+09  2.116320e+09  1.257054e+09  \n",
1410
       " exp3         -1.095146e+10  7.266514e+09 -1.855335e+09 -1.435356e+09  \n",
1411
       " (exp1)(exp2) -7.962573e-02  5.320682e-02 -1.522332e-02 -1.006715e-02  \n",
1412
       " (exp1)(exp3)  3.710938e-02 -2.502441e-02  7.171631e-03  4.695892e-03  \n",
1413
       " (exp2)(exp3)  8.071899e-03 -5.294800e-03  1.457214e-03  1.125813e-03  )"
1414
      ]
1415
     },
1416
     "execution_count": 345,
1417
     "metadata": {},
1418
     "output_type": "execute_result"
1419
    }
1420
   ],
1421
   "source": [
1422
    "A.robust_var_se_cfdinterval()  # standar error, confidence interval y matriz de var y cov robusta"
1423
   ]
1424
  },
1425
  {
1426
   "cell_type": "code",
1427
   "execution_count": 346,
1428
   "id": "5d2fb628",
1429
   "metadata": {},
1430
   "outputs": [
1431
    {
1432
     "data": {
1433
      "text/plain": [
1434
       "(Coef.    0.971815\n",
1435
       " dtype: float64,\n",
1436
       " [0.08105753598082706])"
1437
      ]
1438
     },
1439
     "execution_count": 346,
1440
     "metadata": {},
1441
     "output_type": "execute_result"
1442
    }
1443
   ],
1444
   "source": [
1445
    "A.R2_rootMSE() # Hallando el R2"
1446
   ]
1447
  },
1448
  {
1449
   "cell_type": "code",
1450
   "execution_count": 347,
1451
   "id": "b932a9d9",
1452
   "metadata": {},
1453
   "outputs": [
1454
    {
1455
     "data": {
1456
      "text/plain": [
1457
       "{'Coef.': array([ 3.18864960e+12,  2.31199987e-01, -1.38481293e+12, -2.03091591e+12,\n",
1458
       "         1.81554825e+12, -3.75000000e-01,  2.10937500e-01,  4.68750000e-02]),\n",
1459
       " 'Std.Err.': array([1.87315594e+06, 1.22137933e-01, 8.13184046e+05, 6.07897457e+05,\n",
1460
       "        3.83793156e+05, 3.55628858e+05, 1.26193437e+05, 7.20214900e+04]),\n",
1461
       " '[0.025': array([ 3.18864593e+12, -8.19036164e-03, -1.38481452e+12, -2.03091710e+12,\n",
1462
       "         1.81554750e+12, -6.97032936e+05, -2.47338926e+05, -1.41162073e+05]),\n",
1463
       " '0.975]': array([ 3.18865327e+12,  4.70590336e-01, -1.38481133e+12, -2.03091472e+12,\n",
1464
       "         1.81554900e+12,  6.97032186e+05,  2.47339348e+05,  1.41162167e+05]),\n",
1465
       " 'R2': Coef.    0.971815\n",
1466
       " dtype: float64,\n",
1467
       " 'rootMSE': [0.08105753598082706]}"
1468
      ]
1469
     },
1470
     "execution_count": 347,
1471
     "metadata": {},
1472
     "output_type": "execute_result"
1473
    }
1474
   ],
1475
   "source": [
1476
    "A.output() # Método final de resultados"
1477
   ]
1478
  }
1479
 ],
1480
 "metadata": {
1481
  "kernelspec": {
1482
   "display_name": "Python 3 (ipykernel)",
1483
   "language": "python",
1484
   "name": "python3"
1485
  },
1486
  "language_info": {
1487
   "codemirror_mode": {
1488
    "name": "ipython",
1489
    "version": 3
1490
   },
1491
   "file_extension": ".py",
1492
   "mimetype": "text/x-python",
1493
   "name": "python",
1494
   "nbconvert_exporter": "python",
1495
   "pygments_lexer": "ipython3",
1496
   "version": "3.9.12"
1497
  }
1498
 },
1499
 "nbformat": 4,
1500
 "nbformat_minor": 5
1501
}
1502

1503
Product

Resources

Company
