myawesomepkg 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (27) hide show
  1. myawesomepkg/TSAPY1/1 (A) Working with Numpy Arrays.py +1146 -0
  2. myawesomepkg/TSAPY1/1(B)Aggregation (1).py +319 -0
  3. myawesomepkg/TSAPY1/1(C) Broadcasting .py +328 -0
  4. myawesomepkg/TSAPY1/10-A_Load_stringr.py +77 -0
  5. myawesomepkg/TSAPY1/10-B_Forcats.py +70 -0
  6. myawesomepkg/TSAPY1/2(a) Comparison, Masking And Boolean Logic (1).py +497 -0
  7. myawesomepkg/TSAPY1/2(b)Fancy Indexing.py +594 -0
  8. myawesomepkg/TSAPY1/2(c) Sorting Arrays.py +528 -0
  9. myawesomepkg/TSAPY1/2(d) Structured Array.py +350 -0
  10. myawesomepkg/TSAPY1/3 (A) Handling Missing Data.py +1013 -0
  11. myawesomepkg/TSAPY1/4A_Merge_Joins.py +1209 -0
  12. myawesomepkg/TSAPY1/9A_Dplyr.py +85 -0
  13. myawesomepkg/TSAPY1/9B_Tidyr.py +71 -0
  14. myawesomepkg/TSAPY1/Aggregation_Groupin_Pivot_Filter_Vectorice_Time_Series.py +1999 -0
  15. myawesomepkg/TSAPY1/Combining_Joins.py +1209 -0
  16. myawesomepkg/TSAPY1/Pract3_C.py +482 -0
  17. myawesomepkg/TSAPY1/Pract5_Data_Visualization.py +481 -0
  18. myawesomepkg/TSAPY1/Practical 6.py +860 -0
  19. myawesomepkg/TSAPY1/Print_R.py +123 -0
  20. myawesomepkg/TSAPY1/R_Graph.py +32 -0
  21. myawesomepkg/TSAPY1/Working_Ggplot.py +53 -0
  22. myawesomepkg/TSAPY1/pract3A-B.py +3212 -0
  23. {myawesomepkg-0.1.4.dist-info → myawesomepkg-0.1.6.dist-info}/METADATA +1 -1
  24. myawesomepkg-0.1.6.dist-info/RECORD +47 -0
  25. myawesomepkg-0.1.4.dist-info/RECORD +0 -25
  26. {myawesomepkg-0.1.4.dist-info → myawesomepkg-0.1.6.dist-info}/WHEEL +0 -0
  27. {myawesomepkg-0.1.4.dist-info → myawesomepkg-0.1.6.dist-info}/top_level.txt +0 -0
myawesomepkg/TSAPY1/Practical 6.py ADDED
@@ -0,0 +1,860 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 21,
6
+ "id": "b44241f4-33e7-483e-ad33-770c3738e6b0",
7
+ "metadata": {},
8
+ "outputs": [
9
+ {
10
+ "data": {
11
+ "text/html": [
12
+ "<div>\n",
13
+ "<style scoped>\n",
14
+ " .dataframe tbody tr th:only-of-type {\n",
15
+ " vertical-align: middle;\n",
16
+ " }\n",
17
+ "\n",
18
+ " .dataframe tbody tr th {\n",
19
+ " vertical-align: top;\n",
20
+ " }\n",
21
+ "\n",
22
+ " .dataframe thead th {\n",
23
+ " text-align: right;\n",
24
+ " }\n",
25
+ "</style>\n",
26
+ "<table border=\"1\" class=\"dataframe\">\n",
27
+ " <thead>\n",
28
+ " <tr style=\"text-align: right;\">\n",
29
+ " <th></th>\n",
30
+ " <th>sepal_length</th>\n",
31
+ " <th>sepal_width</th>\n",
32
+ " <th>petal_length</th>\n",
33
+ " <th>petal_width</th>\n",
34
+ " <th>species</th>\n",
35
+ " </tr>\n",
36
+ " </thead>\n",
37
+ " <tbody>\n",
38
+ " <tr>\n",
39
+ " <th>0</th>\n",
40
+ " <td>5.1</td>\n",
41
+ " <td>3.5</td>\n",
42
+ " <td>1.4</td>\n",
43
+ " <td>0.2</td>\n",
44
+ " <td>setosa</td>\n",
45
+ " </tr>\n",
46
+ " <tr>\n",
47
+ " <th>1</th>\n",
48
+ " <td>4.9</td>\n",
49
+ " <td>3.0</td>\n",
50
+ " <td>1.4</td>\n",
51
+ " <td>0.2</td>\n",
52
+ " <td>setosa</td>\n",
53
+ " </tr>\n",
54
+ " <tr>\n",
55
+ " <th>2</th>\n",
56
+ " <td>4.7</td>\n",
57
+ " <td>3.2</td>\n",
58
+ " <td>1.3</td>\n",
59
+ " <td>0.2</td>\n",
60
+ " <td>setosa</td>\n",
61
+ " </tr>\n",
62
+ " <tr>\n",
63
+ " <th>3</th>\n",
64
+ " <td>4.6</td>\n",
65
+ " <td>3.1</td>\n",
66
+ " <td>1.5</td>\n",
67
+ " <td>0.2</td>\n",
68
+ " <td>setosa</td>\n",
69
+ " </tr>\n",
70
+ " <tr>\n",
71
+ " <th>4</th>\n",
72
+ " <td>5.0</td>\n",
73
+ " <td>3.6</td>\n",
74
+ " <td>1.4</td>\n",
75
+ " <td>0.2</td>\n",
76
+ " <td>setosa</td>\n",
77
+ " </tr>\n",
78
+ " </tbody>\n",
79
+ "</table>\n",
80
+ "</div>"
81
+ ],
82
+ "text/plain": [
83
+ " sepal_length sepal_width petal_length petal_width species\n",
84
+ "0 5.1 3.5 1.4 0.2 setosa\n",
85
+ "1 4.9 3.0 1.4 0.2 setosa\n",
86
+ "2 4.7 3.2 1.3 0.2 setosa\n",
87
+ "3 4.6 3.1 1.5 0.2 setosa\n",
88
+ "4 5.0 3.6 1.4 0.2 setosa"
89
+ ]
90
+ },
91
+ "execution_count": 21,
92
+ "metadata": {},
93
+ "output_type": "execute_result"
94
+ }
95
+ ],
96
+ "source": [
97
+ "#Data Representation in Scikit-Learn\n",
98
+ "import seaborn as sns\n",
99
+ "iris = sns.load_dataset('iris')\n",
100
+ "iris.head()"
101
+ ]
102
+ },
103
+ {
104
+ "cell_type": "code",
105
+ "execution_count": 2,
106
+ "id": "29407558-d45a-4444-beb9-0982c5340b41",
107
+ "metadata": {},
108
+ "outputs": [],
109
+ "source": [
110
+ " import matplotlib.pyplot as plt\n",
111
+ " import numpy as np"
112
+ ]
113
+ },
114
+ {
115
+ "cell_type": "code",
116
+ "execution_count": 3,
117
+ "id": "66305114-31af-43da-ac91-dc18e51882ec",
118
+ "metadata": {},
119
+ "outputs": [
120
+ {
121
+ "data": {
122
+ "image/png": "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",
123
+ "text/plain": [
124
+ "<Figure size 640x480 with 1 Axes>"
125
+ ]
126
+ },
127
+ "metadata": {},
128
+ "output_type": "display_data"
129
+ }
130
+ ],
131
+ "source": [
132
+ "# Supervised learning example: Simple linear regression\n",
133
+ "rng = np.random.RandomState(42)\n",
134
+ "x = 10 * rng.rand(50)\n",
135
+ "y = 2 * x - 1 + rng.randn(50)\n",
136
+ "plt.scatter(x, y);"
137
+ ]
138
+ },
139
+ {
140
+ "cell_type": "code",
141
+ "execution_count": 4,
142
+ "id": "83401fbc-f2ef-47b0-849c-477d4e1f95a7",
143
+ "metadata": {},
144
+ "outputs": [
145
+ {
146
+ "data": {
147
+ "text/html": [
148
+ "<style>#sk-container-id-1 {\n",
149
+ " /* Definition of color scheme common for light and dark mode */\n",
150
+ " --sklearn-color-text: #000;\n",
151
+ " --sklearn-color-text-muted: #666;\n",
152
+ " --sklearn-color-line: gray;\n",
153
+ " /* Definition of color scheme for unfitted estimators */\n",
154
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
155
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
156
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
157
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
158
+ " /* Definition of color scheme for fitted estimators */\n",
159
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
160
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
161
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
162
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
163
+ "\n",
164
+ " /* Specific color for light theme */\n",
165
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
166
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
167
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
168
+ " --sklearn-color-icon: #696969;\n",
169
+ "\n",
170
+ " @media (prefers-color-scheme: dark) {\n",
171
+ " /* Redefinition of color scheme for dark theme */\n",
172
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
173
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
174
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
175
+ " --sklearn-color-icon: #878787;\n",
176
+ " }\n",
177
+ "}\n",
178
+ "\n",
179
+ "#sk-container-id-1 {\n",
180
+ " color: var(--sklearn-color-text);\n",
181
+ "}\n",
182
+ "\n",
183
+ "#sk-container-id-1 pre {\n",
184
+ " padding: 0;\n",
185
+ "}\n",
186
+ "\n",
187
+ "#sk-container-id-1 input.sk-hidden--visually {\n",
188
+ " border: 0;\n",
189
+ " clip: rect(1px 1px 1px 1px);\n",
190
+ " clip: rect(1px, 1px, 1px, 1px);\n",
191
+ " height: 1px;\n",
192
+ " margin: -1px;\n",
193
+ " overflow: hidden;\n",
194
+ " padding: 0;\n",
195
+ " position: absolute;\n",
196
+ " width: 1px;\n",
197
+ "}\n",
198
+ "\n",
199
+ "#sk-container-id-1 div.sk-dashed-wrapped {\n",
200
+ " border: 1px dashed var(--sklearn-color-line);\n",
201
+ " margin: 0 0.4em 0.5em 0.4em;\n",
202
+ " box-sizing: border-box;\n",
203
+ " padding-bottom: 0.4em;\n",
204
+ " background-color: var(--sklearn-color-background);\n",
205
+ "}\n",
206
+ "\n",
207
+ "#sk-container-id-1 div.sk-container {\n",
208
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
209
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
210
+ " so we also need the `!important` here to be able to override the\n",
211
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
212
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
213
+ " display: inline-block !important;\n",
214
+ " position: relative;\n",
215
+ "}\n",
216
+ "\n",
217
+ "#sk-container-id-1 div.sk-text-repr-fallback {\n",
218
+ " display: none;\n",
219
+ "}\n",
220
+ "\n",
221
+ "div.sk-parallel-item,\n",
222
+ "div.sk-serial,\n",
223
+ "div.sk-item {\n",
224
+ " /* draw centered vertical line to link estimators */\n",
225
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
226
+ " background-size: 2px 100%;\n",
227
+ " background-repeat: no-repeat;\n",
228
+ " background-position: center center;\n",
229
+ "}\n",
230
+ "\n",
231
+ "/* Parallel-specific style estimator block */\n",
232
+ "\n",
233
+ "#sk-container-id-1 div.sk-parallel-item::after {\n",
234
+ " content: \"\";\n",
235
+ " width: 100%;\n",
236
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
237
+ " flex-grow: 1;\n",
238
+ "}\n",
239
+ "\n",
240
+ "#sk-container-id-1 div.sk-parallel {\n",
241
+ " display: flex;\n",
242
+ " align-items: stretch;\n",
243
+ " justify-content: center;\n",
244
+ " background-color: var(--sklearn-color-background);\n",
245
+ " position: relative;\n",
246
+ "}\n",
247
+ "\n",
248
+ "#sk-container-id-1 div.sk-parallel-item {\n",
249
+ " display: flex;\n",
250
+ " flex-direction: column;\n",
251
+ "}\n",
252
+ "\n",
253
+ "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
254
+ " align-self: flex-end;\n",
255
+ " width: 50%;\n",
256
+ "}\n",
257
+ "\n",
258
+ "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
259
+ " align-self: flex-start;\n",
260
+ " width: 50%;\n",
261
+ "}\n",
262
+ "\n",
263
+ "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
264
+ " width: 0;\n",
265
+ "}\n",
266
+ "\n",
267
+ "/* Serial-specific style estimator block */\n",
268
+ "\n",
269
+ "#sk-container-id-1 div.sk-serial {\n",
270
+ " display: flex;\n",
271
+ " flex-direction: column;\n",
272
+ " align-items: center;\n",
273
+ " background-color: var(--sklearn-color-background);\n",
274
+ " padding-right: 1em;\n",
275
+ " padding-left: 1em;\n",
276
+ "}\n",
277
+ "\n",
278
+ "\n",
279
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
280
+ "clickable and can be expanded/collapsed.\n",
281
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
282
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
283
+ "*/\n",
284
+ "\n",
285
+ "/* Pipeline and ColumnTransformer style (default) */\n",
286
+ "\n",
287
+ "#sk-container-id-1 div.sk-toggleable {\n",
288
+ " /* Default theme specific background. It is overwritten whether we have a\n",
289
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
290
+ " background-color: var(--sklearn-color-background);\n",
291
+ "}\n",
292
+ "\n",
293
+ "/* Toggleable label */\n",
294
+ "#sk-container-id-1 label.sk-toggleable__label {\n",
295
+ " cursor: pointer;\n",
296
+ " display: flex;\n",
297
+ " width: 100%;\n",
298
+ " margin-bottom: 0;\n",
299
+ " padding: 0.5em;\n",
300
+ " box-sizing: border-box;\n",
301
+ " text-align: center;\n",
302
+ " align-items: start;\n",
303
+ " justify-content: space-between;\n",
304
+ " gap: 0.5em;\n",
305
+ "}\n",
306
+ "\n",
307
+ "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
308
+ " font-size: 0.6rem;\n",
309
+ " font-weight: lighter;\n",
310
+ " color: var(--sklearn-color-text-muted);\n",
311
+ "}\n",
312
+ "\n",
313
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
314
+ " /* Arrow on the left of the label */\n",
315
+ " content: \"▸\";\n",
316
+ " float: left;\n",
317
+ " margin-right: 0.25em;\n",
318
+ " color: var(--sklearn-color-icon);\n",
319
+ "}\n",
320
+ "\n",
321
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
322
+ " color: var(--sklearn-color-text);\n",
323
+ "}\n",
324
+ "\n",
325
+ "/* Toggleable content - dropdown */\n",
326
+ "\n",
327
+ "#sk-container-id-1 div.sk-toggleable__content {\n",
328
+ " max-height: 0;\n",
329
+ " max-width: 0;\n",
330
+ " overflow: hidden;\n",
331
+ " text-align: left;\n",
332
+ " /* unfitted */\n",
333
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
334
+ "}\n",
335
+ "\n",
336
+ "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
337
+ " /* fitted */\n",
338
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
339
+ "}\n",
340
+ "\n",
341
+ "#sk-container-id-1 div.sk-toggleable__content pre {\n",
342
+ " margin: 0.2em;\n",
343
+ " border-radius: 0.25em;\n",
344
+ " color: var(--sklearn-color-text);\n",
345
+ " /* unfitted */\n",
346
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
347
+ "}\n",
348
+ "\n",
349
+ "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
350
+ " /* unfitted */\n",
351
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
352
+ "}\n",
353
+ "\n",
354
+ "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
355
+ " /* Expand drop-down */\n",
356
+ " max-height: 200px;\n",
357
+ " max-width: 100%;\n",
358
+ " overflow: auto;\n",
359
+ "}\n",
360
+ "\n",
361
+ "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
362
+ " content: \"▾\";\n",
363
+ "}\n",
364
+ "\n",
365
+ "/* Pipeline/ColumnTransformer-specific style */\n",
366
+ "\n",
367
+ "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
368
+ " color: var(--sklearn-color-text);\n",
369
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
370
+ "}\n",
371
+ "\n",
372
+ "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
373
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
374
+ "}\n",
375
+ "\n",
376
+ "/* Estimator-specific style */\n",
377
+ "\n",
378
+ "/* Colorize estimator box */\n",
379
+ "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
380
+ " /* unfitted */\n",
381
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
382
+ "}\n",
383
+ "\n",
384
+ "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
385
+ " /* fitted */\n",
386
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
387
+ "}\n",
388
+ "\n",
389
+ "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
390
+ "#sk-container-id-1 div.sk-label label {\n",
391
+ " /* The background is the default theme color */\n",
392
+ " color: var(--sklearn-color-text-on-default-background);\n",
393
+ "}\n",
394
+ "\n",
395
+ "/* On hover, darken the color of the background */\n",
396
+ "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
397
+ " color: var(--sklearn-color-text);\n",
398
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
399
+ "}\n",
400
+ "\n",
401
+ "/* Label box, darken color on hover, fitted */\n",
402
+ "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
403
+ " color: var(--sklearn-color-text);\n",
404
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
405
+ "}\n",
406
+ "\n",
407
+ "/* Estimator label */\n",
408
+ "\n",
409
+ "#sk-container-id-1 div.sk-label label {\n",
410
+ " font-family: monospace;\n",
411
+ " font-weight: bold;\n",
412
+ " display: inline-block;\n",
413
+ " line-height: 1.2em;\n",
414
+ "}\n",
415
+ "\n",
416
+ "#sk-container-id-1 div.sk-label-container {\n",
417
+ " text-align: center;\n",
418
+ "}\n",
419
+ "\n",
420
+ "/* Estimator-specific */\n",
421
+ "#sk-container-id-1 div.sk-estimator {\n",
422
+ " font-family: monospace;\n",
423
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
424
+ " border-radius: 0.25em;\n",
425
+ " box-sizing: border-box;\n",
426
+ " margin-bottom: 0.5em;\n",
427
+ " /* unfitted */\n",
428
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
429
+ "}\n",
430
+ "\n",
431
+ "#sk-container-id-1 div.sk-estimator.fitted {\n",
432
+ " /* fitted */\n",
433
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
434
+ "}\n",
435
+ "\n",
436
+ "/* on hover */\n",
437
+ "#sk-container-id-1 div.sk-estimator:hover {\n",
438
+ " /* unfitted */\n",
439
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
440
+ "}\n",
441
+ "\n",
442
+ "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
443
+ " /* fitted */\n",
444
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
445
+ "}\n",
446
+ "\n",
447
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
448
+ "\n",
449
+ "/* Common style for \"i\" and \"?\" */\n",
450
+ "\n",
451
+ ".sk-estimator-doc-link,\n",
452
+ "a:link.sk-estimator-doc-link,\n",
453
+ "a:visited.sk-estimator-doc-link {\n",
454
+ " float: right;\n",
455
+ " font-size: smaller;\n",
456
+ " line-height: 1em;\n",
457
+ " font-family: monospace;\n",
458
+ " background-color: var(--sklearn-color-background);\n",
459
+ " border-radius: 1em;\n",
460
+ " height: 1em;\n",
461
+ " width: 1em;\n",
462
+ " text-decoration: none !important;\n",
463
+ " margin-left: 0.5em;\n",
464
+ " text-align: center;\n",
465
+ " /* unfitted */\n",
466
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
467
+ " color: var(--sklearn-color-unfitted-level-1);\n",
468
+ "}\n",
469
+ "\n",
470
+ ".sk-estimator-doc-link.fitted,\n",
471
+ "a:link.sk-estimator-doc-link.fitted,\n",
472
+ "a:visited.sk-estimator-doc-link.fitted {\n",
473
+ " /* fitted */\n",
474
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
475
+ " color: var(--sklearn-color-fitted-level-1);\n",
476
+ "}\n",
477
+ "\n",
478
+ "/* On hover */\n",
479
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
480
+ ".sk-estimator-doc-link:hover,\n",
481
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
482
+ ".sk-estimator-doc-link:hover {\n",
483
+ " /* unfitted */\n",
484
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
485
+ " color: var(--sklearn-color-background);\n",
486
+ " text-decoration: none;\n",
487
+ "}\n",
488
+ "\n",
489
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
490
+ ".sk-estimator-doc-link.fitted:hover,\n",
491
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
492
+ ".sk-estimator-doc-link.fitted:hover {\n",
493
+ " /* fitted */\n",
494
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
495
+ " color: var(--sklearn-color-background);\n",
496
+ " text-decoration: none;\n",
497
+ "}\n",
498
+ "\n",
499
+ "/* Span, style for the box shown on hovering the info icon */\n",
500
+ ".sk-estimator-doc-link span {\n",
501
+ " display: none;\n",
502
+ " z-index: 9999;\n",
503
+ " position: relative;\n",
504
+ " font-weight: normal;\n",
505
+ " right: .2ex;\n",
506
+ " padding: .5ex;\n",
507
+ " margin: .5ex;\n",
508
+ " width: min-content;\n",
509
+ " min-width: 20ex;\n",
510
+ " max-width: 50ex;\n",
511
+ " color: var(--sklearn-color-text);\n",
512
+ " box-shadow: 2pt 2pt 4pt #999;\n",
513
+ " /* unfitted */\n",
514
+ " background: var(--sklearn-color-unfitted-level-0);\n",
515
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
516
+ "}\n",
517
+ "\n",
518
+ ".sk-estimator-doc-link.fitted span {\n",
519
+ " /* fitted */\n",
520
+ " background: var(--sklearn-color-fitted-level-0);\n",
521
+ " border: var(--sklearn-color-fitted-level-3);\n",
522
+ "}\n",
523
+ "\n",
524
+ ".sk-estimator-doc-link:hover span {\n",
525
+ " display: block;\n",
526
+ "}\n",
527
+ "\n",
528
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
529
+ "\n",
530
+ "#sk-container-id-1 a.estimator_doc_link {\n",
531
+ " float: right;\n",
532
+ " font-size: 1rem;\n",
533
+ " line-height: 1em;\n",
534
+ " font-family: monospace;\n",
535
+ " background-color: var(--sklearn-color-background);\n",
536
+ " border-radius: 1rem;\n",
537
+ " height: 1rem;\n",
538
+ " width: 1rem;\n",
539
+ " text-decoration: none;\n",
540
+ " /* unfitted */\n",
541
+ " color: var(--sklearn-color-unfitted-level-1);\n",
542
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
543
+ "}\n",
544
+ "\n",
545
+ "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
546
+ " /* fitted */\n",
547
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
548
+ " color: var(--sklearn-color-fitted-level-1);\n",
549
+ "}\n",
550
+ "\n",
551
+ "/* On hover */\n",
552
+ "#sk-container-id-1 a.estimator_doc_link:hover {\n",
553
+ " /* unfitted */\n",
554
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
555
+ " color: var(--sklearn-color-background);\n",
556
+ " text-decoration: none;\n",
557
+ "}\n",
558
+ "\n",
559
+ "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
560
+ " /* fitted */\n",
561
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
562
+ "}\n",
563
+ "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\"><div><div>LinearRegression</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.linear_model.LinearRegression.html\">?<span>Documentation for LinearRegression</span></a><span class=\"sk-estimator-doc-link \">i<span>Not fitted</span></span></div></label><div class=\"sk-toggleable__content \"><pre>LinearRegression()</pre></div> </div></div></div></div>"
564
+ ],
565
+ "text/plain": [
566
+ "LinearRegression()"
567
+ ]
568
+ },
569
+ "execution_count": 4,
570
+ "metadata": {},
571
+ "output_type": "execute_result"
572
+ }
573
+ ],
574
+ "source": [
575
+ "from sklearn.linear_model import LinearRegression\n",
576
+ "model = LinearRegression(fit_intercept=True)\n",
577
+ "model"
578
+ ]
579
+ },
580
+ {
581
+ "cell_type": "code",
582
+ "execution_count": 5,
583
+ "id": "d37cfab3-5d76-44c2-a3c3-b7771253afc9",
584
+ "metadata": {},
585
+ "outputs": [
586
+ {
587
+ "data": {
588
+ "text/plain": [
589
+ "(50, 1)"
590
+ ]
591
+ },
592
+ "execution_count": 5,
593
+ "metadata": {},
594
+ "output_type": "execute_result"
595
+ }
596
+ ],
597
+ "source": [
598
+ " X = x[:, np.newaxis]\n",
599
+ " X.shape"
600
+ ]
601
+ },
602
+ {
603
+ "cell_type": "code",
604
+ "execution_count": 7,
605
+ "id": "3ef32ec7-ce44-497e-b2aa-402efcff7adf",
606
+ "metadata": {},
607
+ "outputs": [
608
+ {
609
+ "data": {
610
+ "text/plain": [
611
+ "array([1.9776566])"
612
+ ]
613
+ },
614
+ "execution_count": 7,
615
+ "metadata": {},
616
+ "output_type": "execute_result"
617
+ }
618
+ ],
619
+ "source": [
620
+ "model.fit(X, y)\n",
621
+ "model.coef_"
622
+ ]
623
+ },
624
+ {
625
+ "cell_type": "code",
626
+ "execution_count": 8,
627
+ "id": "e54a1515-4672-4fe6-be81-99a4ac1e3bc5",
628
+ "metadata": {},
629
+ "outputs": [
630
+ {
631
+ "data": {
632
+ "text/plain": [
633
+ "-0.9033107255311164"
634
+ ]
635
+ },
636
+ "execution_count": 8,
637
+ "metadata": {},
638
+ "output_type": "execute_result"
639
+ }
640
+ ],
641
+ "source": [
642
+ "model.intercept_\n",
643
+ "-0.90331072553111635"
644
+ ]
645
+ },
646
+ {
647
+ "cell_type": "code",
648
+ "execution_count": 9,
649
+ "id": "5b98c9f7-b3f8-4c50-ada4-9bbf9bba5a25",
650
+ "metadata": {},
651
+ "outputs": [
652
+ {
653
+ "data": {
654
+ "image/png": "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",
655
+ "text/plain": [
656
+ "<Figure size 640x480 with 1 Axes>"
657
+ ]
658
+ },
659
+ "metadata": {},
660
+ "output_type": "display_data"
661
+ }
662
+ ],
663
+ "source": [
664
+ " xfit = np.linspace(-1, 11)\n",
665
+ " Xfit = xfit[:, np.newaxis]\n",
666
+ " yfit = model.predict(Xfit)\n",
667
+ " plt.scatter(x, y)\n",
668
+ " plt.plot(xfit, yfit);"
669
+ ]
670
+ },
671
+ {
672
+ "cell_type": "code",
673
+ "execution_count": 10,
674
+ "id": "4d3d2915-5b70-4a34-b5ea-a107f70b7f15",
675
+ "metadata": {},
676
+ "outputs": [
677
+ {
678
+ "data": {
679
+ "image/png": "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",
680
+ "text/plain": [
681
+ "<Figure size 800x800 with 100 Axes>"
682
+ ]
683
+ },
684
+ "metadata": {},
685
+ "output_type": "display_data"
686
+ }
687
+ ],
688
+ "source": [
689
+ "# Loading and visualizing the digits data\n",
690
+ "from sklearn.datasets import load_digits\n",
691
+ "digits = load_digits()\n",
692
+ "digits.images.shape\n",
693
+ "import matplotlib.pyplot as plt\n",
694
+ "fig, axes = plt.subplots(10, 10, figsize=(8, 8),\n",
695
+ " subplot_kw={'xticks':[], 'yticks':[]},\n",
696
+ " gridspec_kw=dict(hspace=0.1, wspace=0.1))\n",
697
+ "for i, ax in enumerate(axes.flat):\n",
698
+ " ax.imshow(digits.images[i], cmap='binary', interpolation='nearest')\n",
699
+ " ax.text(0.05, 0.05, str(digits.target[i]),\n",
700
+ " transform=ax.transAxes, color='green')"
701
+ ]
702
+ },
703
+ {
704
+ "cell_type": "code",
705
+ "execution_count": 23,
706
+ "id": "fb9b507e-c733-4f28-aa27-b5391e67cce2",
707
+ "metadata": {},
708
+ "outputs": [],
709
+ "source": [
710
+ " # Hyperparameters and Model Validation\n",
711
+ " from sklearn.datasets import load_iris\n",
712
+ " iris = load_iris()\n",
713
+ " iris = load_iris()\n",
714
+ " X = iris.data\n",
715
+ " y = iris.target"
716
+ ]
717
+ },
718
+ {
719
+ "cell_type": "code",
720
+ "execution_count": 24,
721
+ "id": "2949b52b-5889-4a52-b509-e176a3b4d86e",
722
+ "metadata": {},
723
+ "outputs": [],
724
+ "source": [
725
+ "from sklearn.neighbors import KNeighborsClassifier\n",
726
+ "model = KNeighborsClassifier(n_neighbors=1)"
727
+ ]
728
+ },
729
+ {
730
+ "cell_type": "code",
731
+ "execution_count": 22,
732
+ "id": "af8d07d0-5cda-4273-bda7-ea0b6ef78993",
733
+ "metadata": {},
734
+ "outputs": [
735
+ {
736
+ "data": {
737
+ "text/plain": [
738
+ "1.0"
739
+ ]
740
+ },
741
+ "execution_count": 22,
742
+ "metadata": {},
743
+ "output_type": "execute_result"
744
+ }
745
+ ],
746
+ "source": [
747
+ "from sklearn.metrics import accuracy_score\n",
748
+ "accuracy_score(y, y_model)"
749
+ ]
750
+ },
751
+ {
752
+ "cell_type": "code",
753
+ "execution_count": 18,
754
+ "id": "a76fc5fc-4aed-4d70-8d4e-dbd9ea6c400c",
755
+ "metadata": {},
756
+ "outputs": [
757
+ {
758
+ "name": "stdout",
759
+ "output_type": "stream",
760
+ "text": [
761
+ "Accuracy: 0.9333333333333333\n"
762
+ ]
763
+ }
764
+ ],
765
+ "source": [
766
+ "#Model validation the right way: Holdout sets\n",
767
+ "from sklearn.model_selection import train_test_split\n",
768
+ "from sklearn.linear_model import LogisticRegression # Example model\n",
769
+ "\n",
770
+ "# Example dataset\n",
771
+ "X, y = load_iris(return_X_y=True)\n",
772
+ "\n",
773
+ "# Split the data\n",
774
+ "X1, X2, y1, y2 = train_test_split(X, y, random_state=0, train_size=0.5)\n",
775
+ "\n",
776
+ "# Model\n",
777
+ "model = LogisticRegression()\n",
778
+ "model.fit(X1, y1)\n",
779
+ "\n",
780
+ "# Prediction\n",
781
+ "y2_model = model.predict(X2)\n",
782
+ "\n",
783
+ "# Evaluation\n",
784
+ "acc = accuracy_score(y2, y2_model)\n",
785
+ "print(\"Accuracy:\", acc)\n"
786
+ ]
787
+ },
788
+ {
789
+ "cell_type": "code",
790
+ "execution_count": 27,
791
+ "id": "1752312c-9a4a-44b4-bb8b-2c84906bf358",
792
+ "metadata": {},
793
+ "outputs": [],
794
+ "source": [
795
+ "# Feature Engineering\n",
796
+ "data = [\n",
797
+ " {'price': 850000, 'rooms': 4, 'neighborhood': 'Queen Anne'},\n",
798
+ " {'price': 700000, 'rooms': 3, 'neighborhood': 'Fremont'},\n",
799
+ " {'price': 650000, 'rooms': 3, 'neighborhood': 'Wallingford'},\n",
800
+ " {'price': 600000, 'rooms': 2, 'neighborhood': 'Fremont'}\n",
801
+ "]"
802
+ ]
803
+ },
804
+ {
805
+ "cell_type": "code",
806
+ "execution_count": 28,
807
+ "id": "0d41a31a-1e1e-4f1a-8258-06f44a2528ad",
808
+ "metadata": {},
809
+ "outputs": [
810
+ {
811
+ "data": {
812
+ "text/plain": [
813
+ "array([[ 0, 1, 0, 850000, 4],\n",
814
+ " [ 1, 0, 0, 700000, 3],\n",
815
+ " [ 0, 0, 1, 650000, 3],\n",
816
+ " [ 1, 0, 0, 600000, 2]])"
817
+ ]
818
+ },
819
+ "execution_count": 28,
820
+ "metadata": {},
821
+ "output_type": "execute_result"
822
+ }
823
+ ],
824
+ "source": [
825
+ "from sklearn.feature_extraction import DictVectorizer\n",
826
+ "vec = DictVectorizer(sparse=False, dtype=int)\n",
827
+ "vec.fit_transform(data)"
828
+ ]
829
+ },
830
+ {
831
+ "cell_type": "code",
832
+ "execution_count": null,
833
+ "id": "5ac7053a-8a00-49b7-bf4d-6d3e1373686e",
834
+ "metadata": {},
835
+ "outputs": [],
836
+ "source": []
837
+ }
838
+ ],
839
+ "metadata": {
840
+ "kernelspec": {
841
+ "display_name": "Python 3 (ipykernel)",
842
+ "language": "python",
843
+ "name": "python3"
844
+ },
845
+ "language_info": {
846
+ "codemirror_mode": {
847
+ "name": "ipython",
848
+ "version": 3
849
+ },
850
+ "file_extension": ".py",
851
+ "mimetype": "text/x-python",
852
+ "name": "python",
853
+ "nbconvert_exporter": "python",
854
+ "pygments_lexer": "ipython3",
855
+ "version": "3.12.0"
856
+ }
857
+ },
858
+ "nbformat": 4,
859
+ "nbformat_minor": 5
860
+ }