Hugging Face's logo

Spaces:
kheejay88
/
linear-regression-student-scores
Build error

App Files Community
usernameiskheejay commited on
Commit
adbfffd
·
1 Parent(s): 3657854

fix

Browse files
Files changed (1) hide show
  1. model.ipynb +675 -0
model.ipynb ADDED
@@ -0,0 +1,675 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "metadata": {},
7
+ "outputs": [],
8
+ "source": [
9
+ "import pandas as pd\n",
10
+ "import numpy as np\n",
11
+ "import matplotlib.pyplot as plt\n",
12
+ "import seaborn as sns\n",
13
+ "from sklearn.model_selection import train_test_split\n",
14
+ "from sklearn.linear_model import LinearRegression\n",
15
+ "from sklearn.metrics import mean_squared_error, r2_score"
16
+ ]
17
+ },
18
+ {
19
+ "cell_type": "code",
20
+ "execution_count": 11,
21
+ "metadata": {},
22
+ "outputs": [
23
+ {
24
+ "name": "stdout",
25
+ "output_type": "stream",
26
+ "text": [
27
+ " id first_name last_name email gender \\\n",
28
+ "0 1 Paul Casey paul.casey.1@gslingacademy.com male \n",
29
+ "1 2 Danielle Sandoval danielle.sandoval.2@gslingacademy.com female \n",
30
+ "2 3 Tina Andrews tina.andrews.3@gslingacademy.com female \n",
31
+ "3 4 Tara Clark tara.clark.4@gslingacademy.com female \n",
32
+ "4 5 Anthony Campos anthony.campos.5@gslingacademy.com male \n",
33
+ "\n",
34
+ " part_time_job absence_days extracurricular_activities \\\n",
35
+ "0 False 3 False \n",
36
+ "1 False 2 False \n",
37
+ "2 False 9 True \n",
38
+ "3 False 5 False \n",
39
+ "4 False 5 False \n",
40
+ "\n",
41
+ " weekly_self_study_hours career_aspiration math_score history_score \\\n",
42
+ "0 27 Lawyer 73 81 \n",
43
+ "1 47 Doctor 90 86 \n",
44
+ "2 13 Government Officer 81 97 \n",
45
+ "3 3 Artist 71 74 \n",
46
+ "4 10 Unknown 84 77 \n",
47
+ "\n",
48
+ " physics_score chemistry_score biology_score english_score \\\n",
49
+ "0 93 97 63 80 \n",
50
+ "1 96 100 90 88 \n",
51
+ "2 95 96 65 77 \n",
52
+ "3 88 80 89 63 \n",
53
+ "4 65 65 80 74 \n",
54
+ "\n",
55
+ " geography_score \n",
56
+ "0 87 \n",
57
+ "1 90 \n",
58
+ "2 94 \n",
59
+ "3 86 \n",
60
+ "4 76 \n"
61
+ ]
62
+ }
63
+ ],
64
+ "source": [
65
+ "# Load dataset\n",
66
+ "df = pd.read_csv(\"student-scores.csv\")\n",
67
+ "\n",
68
+ "# Display first few rows\n",
69
+ "print(df.head())\n",
70
+ "# print(df.columns)\n",
71
+ "\n",
72
+ "# Get basic info about the dataset\n",
73
+ "# print(df.info())\n",
74
+ "\n",
75
+ "# Summary statistics\n",
76
+ "# print(df.describe())\n"
77
+ ]
78
+ },
79
+ {
80
+ "cell_type": "code",
81
+ "execution_count": 3,
82
+ "metadata": {},
83
+ "outputs": [],
84
+ "source": [
85
+ "import pandas as pd\n",
86
+ "\n",
87
+ "# Apply one-hot encoding\n",
88
+ "df = pd.get_dummies(df, columns=['career_aspiration'], drop_first=True) # Avoid dummy variable trap\n",
89
+ "\n",
90
+ "# Independent variables (features)\n",
91
+ "X = df[['absence_days', 'weekly_self_study_hours', 'extracurricular_activities', 'part_time_job']]\n",
92
+ "\n",
93
+ "# Include all dummy columns for 'career_aspiration'\n",
94
+ "career_dummies = df.filter(like='career_aspiration_') # Select all dummy variables\n",
95
+ "X = X.join(career_dummies) # Append them to feature set\n",
96
+ "\n",
97
+ "# Dependent variables (multiple target scores)\n",
98
+ "Y = df[['math_score', 'history_score', 'physics_score', 'chemistry_score',\n",
99
+ " 'biology_score', 'english_score', 'geography_score']]"
100
+ ]
101
+ },
102
+ {
103
+ "cell_type": "code",
104
+ "execution_count": 4,
105
+ "metadata": {},
106
+ "outputs": [],
107
+ "source": [
108
+ "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)"
109
+ ]
110
+ },
111
+ {
112
+ "cell_type": "code",
113
+ "execution_count": 5,
114
+ "metadata": {},
115
+ "outputs": [
116
+ {
117
+ "data": {
118
+ "text/html": [
119
+ "<style>#sk-container-id-1 {\n",
120
+ " /* Definition of color scheme common for light and dark mode */\n",
121
+ " --sklearn-color-text: #000;\n",
122
+ " --sklearn-color-text-muted: #666;\n",
123
+ " --sklearn-color-line: gray;\n",
124
+ " /* Definition of color scheme for unfitted estimators */\n",
125
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
126
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
127
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
128
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
129
+ " /* Definition of color scheme for fitted estimators */\n",
130
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
131
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
132
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
133
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
134
+ "\n",
135
+ " /* Specific color for light theme */\n",
136
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
137
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
138
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
139
+ " --sklearn-color-icon: #696969;\n",
140
+ "\n",
141
+ " @media (prefers-color-scheme: dark) {\n",
142
+ " /* Redefinition of color scheme for dark theme */\n",
143
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
144
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
145
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
146
+ " --sklearn-color-icon: #878787;\n",
147
+ " }\n",
148
+ "}\n",
149
+ "\n",
150
+ "#sk-container-id-1 {\n",
151
+ " color: var(--sklearn-color-text);\n",
152
+ "}\n",
153
+ "\n",
154
+ "#sk-container-id-1 pre {\n",
155
+ " padding: 0;\n",
156
+ "}\n",
157
+ "\n",
158
+ "#sk-container-id-1 input.sk-hidden--visually {\n",
159
+ " border: 0;\n",
160
+ " clip: rect(1px 1px 1px 1px);\n",
161
+ " clip: rect(1px, 1px, 1px, 1px);\n",
162
+ " height: 1px;\n",
163
+ " margin: -1px;\n",
164
+ " overflow: hidden;\n",
165
+ " padding: 0;\n",
166
+ " position: absolute;\n",
167
+ " width: 1px;\n",
168
+ "}\n",
169
+ "\n",
170
+ "#sk-container-id-1 div.sk-dashed-wrapped {\n",
171
+ " border: 1px dashed var(--sklearn-color-line);\n",
172
+ " margin: 0 0.4em 0.5em 0.4em;\n",
173
+ " box-sizing: border-box;\n",
174
+ " padding-bottom: 0.4em;\n",
175
+ " background-color: var(--sklearn-color-background);\n",
176
+ "}\n",
177
+ "\n",
178
+ "#sk-container-id-1 div.sk-container {\n",
179
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
180
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
181
+ " so we also need the `!important` here to be able to override the\n",
182
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
183
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
184
+ " display: inline-block !important;\n",
185
+ " position: relative;\n",
186
+ "}\n",
187
+ "\n",
188
+ "#sk-container-id-1 div.sk-text-repr-fallback {\n",
189
+ " display: none;\n",
190
+ "}\n",
191
+ "\n",
192
+ "div.sk-parallel-item,\n",
193
+ "div.sk-serial,\n",
194
+ "div.sk-item {\n",
195
+ " /* draw centered vertical line to link estimators */\n",
196
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
197
+ " background-size: 2px 100%;\n",
198
+ " background-repeat: no-repeat;\n",
199
+ " background-position: center center;\n",
200
+ "}\n",
201
+ "\n",
202
+ "/* Parallel-specific style estimator block */\n",
203
+ "\n",
204
+ "#sk-container-id-1 div.sk-parallel-item::after {\n",
205
+ " content: \"\";\n",
206
+ " width: 100%;\n",
207
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
208
+ " flex-grow: 1;\n",
209
+ "}\n",
210
+ "\n",
211
+ "#sk-container-id-1 div.sk-parallel {\n",
212
+ " display: flex;\n",
213
+ " align-items: stretch;\n",
214
+ " justify-content: center;\n",
215
+ " background-color: var(--sklearn-color-background);\n",
216
+ " position: relative;\n",
217
+ "}\n",
218
+ "\n",
219
+ "#sk-container-id-1 div.sk-parallel-item {\n",
220
+ " display: flex;\n",
221
+ " flex-direction: column;\n",
222
+ "}\n",
223
+ "\n",
224
+ "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
225
+ " align-self: flex-end;\n",
226
+ " width: 50%;\n",
227
+ "}\n",
228
+ "\n",
229
+ "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
230
+ " align-self: flex-start;\n",
231
+ " width: 50%;\n",
232
+ "}\n",
233
+ "\n",
234
+ "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
235
+ " width: 0;\n",
236
+ "}\n",
237
+ "\n",
238
+ "/* Serial-specific style estimator block */\n",
239
+ "\n",
240
+ "#sk-container-id-1 div.sk-serial {\n",
241
+ " display: flex;\n",
242
+ " flex-direction: column;\n",
243
+ " align-items: center;\n",
244
+ " background-color: var(--sklearn-color-background);\n",
245
+ " padding-right: 1em;\n",
246
+ " padding-left: 1em;\n",
247
+ "}\n",
248
+ "\n",
249
+ "\n",
250
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
251
+ "clickable and can be expanded/collapsed.\n",
252
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
253
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
254
+ "*/\n",
255
+ "\n",
256
+ "/* Pipeline and ColumnTransformer style (default) */\n",
257
+ "\n",
258
+ "#sk-container-id-1 div.sk-toggleable {\n",
259
+ " /* Default theme specific background. It is overwritten whether we have a\n",
260
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
261
+ " background-color: var(--sklearn-color-background);\n",
262
+ "}\n",
263
+ "\n",
264
+ "/* Toggleable label */\n",
265
+ "#sk-container-id-1 label.sk-toggleable__label {\n",
266
+ " cursor: pointer;\n",
267
+ " display: flex;\n",
268
+ " width: 100%;\n",
269
+ " margin-bottom: 0;\n",
270
+ " padding: 0.5em;\n",
271
+ " box-sizing: border-box;\n",
272
+ " text-align: center;\n",
273
+ " align-items: start;\n",
274
+ " justify-content: space-between;\n",
275
+ " gap: 0.5em;\n",
276
+ "}\n",
277
+ "\n",
278
+ "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
279
+ " font-size: 0.6rem;\n",
280
+ " font-weight: lighter;\n",
281
+ " color: var(--sklearn-color-text-muted);\n",
282
+ "}\n",
283
+ "\n",
284
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
285
+ " /* Arrow on the left of the label */\n",
286
+ " content: \"▸\";\n",
287
+ " float: left;\n",
288
+ " margin-right: 0.25em;\n",
289
+ " color: var(--sklearn-color-icon);\n",
290
+ "}\n",
291
+ "\n",
292
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
293
+ " color: var(--sklearn-color-text);\n",
294
+ "}\n",
295
+ "\n",
296
+ "/* Toggleable content - dropdown */\n",
297
+ "\n",
298
+ "#sk-container-id-1 div.sk-toggleable__content {\n",
299
+ " max-height: 0;\n",
300
+ " max-width: 0;\n",
301
+ " overflow: hidden;\n",
302
+ " text-align: left;\n",
303
+ " /* unfitted */\n",
304
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
305
+ "}\n",
306
+ "\n",
307
+ "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
308
+ " /* fitted */\n",
309
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
310
+ "}\n",
311
+ "\n",
312
+ "#sk-container-id-1 div.sk-toggleable__content pre {\n",
313
+ " margin: 0.2em;\n",
314
+ " border-radius: 0.25em;\n",
315
+ " color: var(--sklearn-color-text);\n",
316
+ " /* unfitted */\n",
317
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
318
+ "}\n",
319
+ "\n",
320
+ "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
321
+ " /* unfitted */\n",
322
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
323
+ "}\n",
324
+ "\n",
325
+ "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
326
+ " /* Expand drop-down */\n",
327
+ " max-height: 200px;\n",
328
+ " max-width: 100%;\n",
329
+ " overflow: auto;\n",
330
+ "}\n",
331
+ "\n",
332
+ "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
333
+ " content: \"▾\";\n",
334
+ "}\n",
335
+ "\n",
336
+ "/* Pipeline/ColumnTransformer-specific style */\n",
337
+ "\n",
338
+ "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
339
+ " color: var(--sklearn-color-text);\n",
340
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
341
+ "}\n",
342
+ "\n",
343
+ "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
344
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
345
+ "}\n",
346
+ "\n",
347
+ "/* Estimator-specific style */\n",
348
+ "\n",
349
+ "/* Colorize estimator box */\n",
350
+ "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
351
+ " /* unfitted */\n",
352
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
353
+ "}\n",
354
+ "\n",
355
+ "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
356
+ " /* fitted */\n",
357
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
358
+ "}\n",
359
+ "\n",
360
+ "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
361
+ "#sk-container-id-1 div.sk-label label {\n",
362
+ " /* The background is the default theme color */\n",
363
+ " color: var(--sklearn-color-text-on-default-background);\n",
364
+ "}\n",
365
+ "\n",
366
+ "/* On hover, darken the color of the background */\n",
367
+ "#sk-container-id-1 div.sk-label:hover 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
+ "/* Label box, darken color on hover, fitted */\n",
373
+ "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
374
+ " color: var(--sklearn-color-text);\n",
375
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
376
+ "}\n",
377
+ "\n",
378
+ "/* Estimator label */\n",
379
+ "\n",
380
+ "#sk-container-id-1 div.sk-label label {\n",
381
+ " font-family: monospace;\n",
382
+ " font-weight: bold;\n",
383
+ " display: inline-block;\n",
384
+ " line-height: 1.2em;\n",
385
+ "}\n",
386
+ "\n",
387
+ "#sk-container-id-1 div.sk-label-container {\n",
388
+ " text-align: center;\n",
389
+ "}\n",
390
+ "\n",
391
+ "/* Estimator-specific */\n",
392
+ "#sk-container-id-1 div.sk-estimator {\n",
393
+ " font-family: monospace;\n",
394
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
395
+ " border-radius: 0.25em;\n",
396
+ " box-sizing: border-box;\n",
397
+ " margin-bottom: 0.5em;\n",
398
+ " /* unfitted */\n",
399
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
400
+ "}\n",
401
+ "\n",
402
+ "#sk-container-id-1 div.sk-estimator.fitted {\n",
403
+ " /* fitted */\n",
404
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
405
+ "}\n",
406
+ "\n",
407
+ "/* on hover */\n",
408
+ "#sk-container-id-1 div.sk-estimator:hover {\n",
409
+ " /* unfitted */\n",
410
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
411
+ "}\n",
412
+ "\n",
413
+ "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
414
+ " /* fitted */\n",
415
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
416
+ "}\n",
417
+ "\n",
418
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
419
+ "\n",
420
+ "/* Common style for \"i\" and \"?\" */\n",
421
+ "\n",
422
+ ".sk-estimator-doc-link,\n",
423
+ "a:link.sk-estimator-doc-link,\n",
424
+ "a:visited.sk-estimator-doc-link {\n",
425
+ " float: right;\n",
426
+ " font-size: smaller;\n",
427
+ " line-height: 1em;\n",
428
+ " font-family: monospace;\n",
429
+ " background-color: var(--sklearn-color-background);\n",
430
+ " border-radius: 1em;\n",
431
+ " height: 1em;\n",
432
+ " width: 1em;\n",
433
+ " text-decoration: none !important;\n",
434
+ " margin-left: 0.5em;\n",
435
+ " text-align: center;\n",
436
+ " /* unfitted */\n",
437
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
438
+ " color: var(--sklearn-color-unfitted-level-1);\n",
439
+ "}\n",
440
+ "\n",
441
+ ".sk-estimator-doc-link.fitted,\n",
442
+ "a:link.sk-estimator-doc-link.fitted,\n",
443
+ "a:visited.sk-estimator-doc-link.fitted {\n",
444
+ " /* fitted */\n",
445
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
446
+ " color: var(--sklearn-color-fitted-level-1);\n",
447
+ "}\n",
448
+ "\n",
449
+ "/* On hover */\n",
450
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
451
+ ".sk-estimator-doc-link:hover,\n",
452
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
453
+ ".sk-estimator-doc-link:hover {\n",
454
+ " /* unfitted */\n",
455
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
456
+ " color: var(--sklearn-color-background);\n",
457
+ " text-decoration: none;\n",
458
+ "}\n",
459
+ "\n",
460
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
461
+ ".sk-estimator-doc-link.fitted:hover,\n",
462
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
463
+ ".sk-estimator-doc-link.fitted:hover {\n",
464
+ " /* fitted */\n",
465
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
466
+ " color: var(--sklearn-color-background);\n",
467
+ " text-decoration: none;\n",
468
+ "}\n",
469
+ "\n",
470
+ "/* Span, style for the box shown on hovering the info icon */\n",
471
+ ".sk-estimator-doc-link span {\n",
472
+ " display: none;\n",
473
+ " z-index: 9999;\n",
474
+ " position: relative;\n",
475
+ " font-weight: normal;\n",
476
+ " right: .2ex;\n",
477
+ " padding: .5ex;\n",
478
+ " margin: .5ex;\n",
479
+ " width: min-content;\n",
480
+ " min-width: 20ex;\n",
481
+ " max-width: 50ex;\n",
482
+ " color: var(--sklearn-color-text);\n",
483
+ " box-shadow: 2pt 2pt 4pt #999;\n",
484
+ " /* unfitted */\n",
485
+ " background: var(--sklearn-color-unfitted-level-0);\n",
486
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
487
+ "}\n",
488
+ "\n",
489
+ ".sk-estimator-doc-link.fitted span {\n",
490
+ " /* fitted */\n",
491
+ " background: var(--sklearn-color-fitted-level-0);\n",
492
+ " border: var(--sklearn-color-fitted-level-3);\n",
493
+ "}\n",
494
+ "\n",
495
+ ".sk-estimator-doc-link:hover span {\n",
496
+ " display: block;\n",
497
+ "}\n",
498
+ "\n",
499
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
500
+ "\n",
501
+ "#sk-container-id-1 a.estimator_doc_link {\n",
502
+ " float: right;\n",
503
+ " font-size: 1rem;\n",
504
+ " line-height: 1em;\n",
505
+ " font-family: monospace;\n",
506
+ " background-color: var(--sklearn-color-background);\n",
507
+ " border-radius: 1rem;\n",
508
+ " height: 1rem;\n",
509
+ " width: 1rem;\n",
510
+ " text-decoration: none;\n",
511
+ " /* unfitted */\n",
512
+ " color: var(--sklearn-color-unfitted-level-1);\n",
513
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
514
+ "}\n",
515
+ "\n",
516
+ "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
517
+ " /* fitted */\n",
518
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
519
+ " color: var(--sklearn-color-fitted-level-1);\n",
520
+ "}\n",
521
+ "\n",
522
+ "/* On hover */\n",
523
+ "#sk-container-id-1 a.estimator_doc_link:hover {\n",
524
+ " /* unfitted */\n",
525
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
526
+ " color: var(--sklearn-color-background);\n",
527
+ " text-decoration: none;\n",
528
+ "}\n",
529
+ "\n",
530
+ "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
531
+ " /* fitted */\n",
532
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
533
+ "}\n",
534
+ "</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 fitted 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 fitted sk-toggleable__label-arrow\"><div><div>LinearRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" 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 fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>LinearRegression()</pre></div> </div></div></div></div>"
535
+ ],
536
+ "text/plain": [
537
+ "LinearRegression()"
538
+ ]
539
+ },
540
+ "execution_count": 5,
541
+ "metadata": {},
542
+ "output_type": "execute_result"
543
+ }
544
+ ],
545
+ "source": [
546
+ "# Create model\n",
547
+ "model = LinearRegression()\n",
548
+ "\n",
549
+ "# Train model on multiple target variables\n",
550
+ "model.fit(X_train, Y_train)"
551
+ ]
552
+ },
553
+ {
554
+ "cell_type": "code",
555
+ "execution_count": 6,
556
+ "metadata": {},
557
+ "outputs": [
558
+ {
559
+ "name": "stdout",
560
+ "output_type": "stream",
561
+ "text": [
562
+ "Mean Squared Error: 143.86862456643777\n",
563
+ "R-squared Score: 0.1451361868355176\n"
564
+ ]
565
+ }
566
+ ],
567
+ "source": [
568
+ "Y_pred = model.predict(X_test)\n",
569
+ "\n",
570
+ "# Calculate Mean Squared Error (MSE) and R-squared (R²)\n",
571
+ "mse = mean_squared_error(Y_test, Y_pred)\n",
572
+ "r2 = r2_score(Y_test, Y_pred)\n",
573
+ "\n",
574
+ "print(f\"Mean Squared Error: {mse}\")\n",
575
+ "print(f\"R-squared Score: {r2}\")\n"
576
+ ]
577
+ },
578
+ {
579
+ "cell_type": "code",
580
+ "execution_count": 7,
581
+ "metadata": {},
582
+ "outputs": [
583
+ {
584
+ "data": {
585
+ "image/png": "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",
586
+ "text/plain": [
587
+ "<Figure size 640x480 with 1 Axes>"
588
+ ]
589
+ },
590
+ "metadata": {},
591
+ "output_type": "display_data"
592
+ }
593
+ ],
594
+ "source": [
595
+ "plt.scatter(Y_test, Y_pred)\n",
596
+ "plt.xlabel(\"Actual Values\")\n",
597
+ "plt.ylabel(\"Predicted Values\")\n",
598
+ "plt.title(\"Actual vs. Predicted Values\")\n",
599
+ "plt.show()\n"
600
+ ]
601
+ },
602
+ {
603
+ "cell_type": "code",
604
+ "execution_count": 8,
605
+ "metadata": {},
606
+ "outputs": [],
607
+ "source": [
608
+ "import pickle\n",
609
+ "from sklearn.linear_model import LinearRegression\n",
610
+ "\n",
611
+ "# Assuming `model` is the trained model\n",
612
+ "with open('model.pkl', 'wb') as file:\n",
613
+ " pickle.dump(model, file)"
614
+ ]
615
+ },
616
+ {
617
+ "cell_type": "code",
618
+ "execution_count": 9,
619
+ "metadata": {},
620
+ "outputs": [
621
+ {
622
+ "name": "stdout",
623
+ "output_type": "stream",
624
+ "text": [
625
+ "<class 'sklearn.linear_model._base.LinearRegression'>\n"
626
+ ]
627
+ }
628
+ ],
629
+ "source": [
630
+ "with open(\"model.pkl\", \"rb\") as file:\n",
631
+ " model = pickle.load(file)\n",
632
+ "\n",
633
+ "print(type(model))"
634
+ ]
635
+ },
636
+ {
637
+ "cell_type": "code",
638
+ "execution_count": null,
639
+ "metadata": {},
640
+ "outputs": [
641
+ {
642
+ "name": "stdout",
643
+ "output_type": "stream",
644
+ "text": [
645
+ "['absence_days', 'weekly_self_study_hours', 'extracurricular_activities', 'part_time_job', 'career_aspiration_Artist', 'career_aspiration_Banker', 'career_aspiration_Business Owner', 'career_aspiration_Construction Engineer', 'career_aspiration_Designer', 'career_aspiration_Doctor', 'career_aspiration_Game Developer', 'career_aspiration_Government Officer', 'career_aspiration_Lawyer', 'career_aspiration_Real Estate Developer', 'career_aspiration_Scientist', 'career_aspiration_Software Engineer', 'career_aspiration_Stock Investor', 'career_aspiration_Teacher', 'career_aspiration_Unknown', 'career_aspiration_Writer']\n"
646
+ ]
647
+ }
648
+ ],
649
+ "source": [
650
+ "print(X.columns.tolist())"
651
+ ]
652
+ }
653
+ ],
654
+ "metadata": {
655
+ "kernelspec": {
656
+ "display_name": "Python 3",
657
+ "language": "python",
658
+ "name": "python3"
659
+ },
660
+ "language_info": {
661
+ "codemirror_mode": {
662
+ "name": "ipython",
663
+ "version": 3
664
+ },
665
+ "file_extension": ".py",
666
+ "mimetype": "text/x-python",
667
+ "name": "python",
668
+ "nbconvert_exporter": "python",
669
+ "pygments_lexer": "ipython3",
670
+ "version": "3.12.8"
671
+ }
672
+ },
673
+ "nbformat": 4,
674
+ "nbformat_minor": 2
675
+ }