|
a |
|
b/Model Buliding/first_notebook.ipynb |
|
|
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 |
] |
|
|
13 |
}, |
|
|
14 |
{ |
|
|
15 |
"cell_type": "code", |
|
|
16 |
"execution_count": 2, |
|
|
17 |
"metadata": {}, |
|
|
18 |
"outputs": [ |
|
|
19 |
{ |
|
|
20 |
"data": { |
|
|
21 |
"text/html": [ |
|
|
22 |
"<div>\n", |
|
|
23 |
"<style scoped>\n", |
|
|
24 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
25 |
" vertical-align: middle;\n", |
|
|
26 |
" }\n", |
|
|
27 |
"\n", |
|
|
28 |
" .dataframe tbody tr th {\n", |
|
|
29 |
" vertical-align: top;\n", |
|
|
30 |
" }\n", |
|
|
31 |
"\n", |
|
|
32 |
" .dataframe thead th {\n", |
|
|
33 |
" text-align: right;\n", |
|
|
34 |
" }\n", |
|
|
35 |
"</style>\n", |
|
|
36 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
37 |
" <thead>\n", |
|
|
38 |
" <tr style=\"text-align: right;\">\n", |
|
|
39 |
" <th></th>\n", |
|
|
40 |
" <th>Pregnancies</th>\n", |
|
|
41 |
" <th>Glucose</th>\n", |
|
|
42 |
" <th>BloodPressure</th>\n", |
|
|
43 |
" <th>SkinThickness</th>\n", |
|
|
44 |
" <th>Insulin</th>\n", |
|
|
45 |
" <th>BMI</th>\n", |
|
|
46 |
" <th>DiabetesPedigreeFunction</th>\n", |
|
|
47 |
" <th>Age</th>\n", |
|
|
48 |
" <th>Outcome</th>\n", |
|
|
49 |
" </tr>\n", |
|
|
50 |
" </thead>\n", |
|
|
51 |
" <tbody>\n", |
|
|
52 |
" <tr>\n", |
|
|
53 |
" <th>0</th>\n", |
|
|
54 |
" <td>6</td>\n", |
|
|
55 |
" <td>148</td>\n", |
|
|
56 |
" <td>72</td>\n", |
|
|
57 |
" <td>35</td>\n", |
|
|
58 |
" <td>0</td>\n", |
|
|
59 |
" <td>33.6</td>\n", |
|
|
60 |
" <td>0.627</td>\n", |
|
|
61 |
" <td>50</td>\n", |
|
|
62 |
" <td>1</td>\n", |
|
|
63 |
" </tr>\n", |
|
|
64 |
" <tr>\n", |
|
|
65 |
" <th>1</th>\n", |
|
|
66 |
" <td>1</td>\n", |
|
|
67 |
" <td>85</td>\n", |
|
|
68 |
" <td>66</td>\n", |
|
|
69 |
" <td>29</td>\n", |
|
|
70 |
" <td>0</td>\n", |
|
|
71 |
" <td>26.6</td>\n", |
|
|
72 |
" <td>0.351</td>\n", |
|
|
73 |
" <td>31</td>\n", |
|
|
74 |
" <td>0</td>\n", |
|
|
75 |
" </tr>\n", |
|
|
76 |
" <tr>\n", |
|
|
77 |
" <th>2</th>\n", |
|
|
78 |
" <td>8</td>\n", |
|
|
79 |
" <td>183</td>\n", |
|
|
80 |
" <td>64</td>\n", |
|
|
81 |
" <td>0</td>\n", |
|
|
82 |
" <td>0</td>\n", |
|
|
83 |
" <td>23.3</td>\n", |
|
|
84 |
" <td>0.672</td>\n", |
|
|
85 |
" <td>32</td>\n", |
|
|
86 |
" <td>1</td>\n", |
|
|
87 |
" </tr>\n", |
|
|
88 |
" <tr>\n", |
|
|
89 |
" <th>3</th>\n", |
|
|
90 |
" <td>1</td>\n", |
|
|
91 |
" <td>89</td>\n", |
|
|
92 |
" <td>66</td>\n", |
|
|
93 |
" <td>23</td>\n", |
|
|
94 |
" <td>94</td>\n", |
|
|
95 |
" <td>28.1</td>\n", |
|
|
96 |
" <td>0.167</td>\n", |
|
|
97 |
" <td>21</td>\n", |
|
|
98 |
" <td>0</td>\n", |
|
|
99 |
" </tr>\n", |
|
|
100 |
" <tr>\n", |
|
|
101 |
" <th>4</th>\n", |
|
|
102 |
" <td>0</td>\n", |
|
|
103 |
" <td>137</td>\n", |
|
|
104 |
" <td>40</td>\n", |
|
|
105 |
" <td>35</td>\n", |
|
|
106 |
" <td>168</td>\n", |
|
|
107 |
" <td>43.1</td>\n", |
|
|
108 |
" <td>2.288</td>\n", |
|
|
109 |
" <td>33</td>\n", |
|
|
110 |
" <td>1</td>\n", |
|
|
111 |
" </tr>\n", |
|
|
112 |
" </tbody>\n", |
|
|
113 |
"</table>\n", |
|
|
114 |
"</div>" |
|
|
115 |
], |
|
|
116 |
"text/plain": [ |
|
|
117 |
" Pregnancies Glucose BloodPressure SkinThickness Insulin BMI \\\n", |
|
|
118 |
"0 6 148 72 35 0 33.6 \n", |
|
|
119 |
"1 1 85 66 29 0 26.6 \n", |
|
|
120 |
"2 8 183 64 0 0 23.3 \n", |
|
|
121 |
"3 1 89 66 23 94 28.1 \n", |
|
|
122 |
"4 0 137 40 35 168 43.1 \n", |
|
|
123 |
"\n", |
|
|
124 |
" DiabetesPedigreeFunction Age Outcome \n", |
|
|
125 |
"0 0.627 50 1 \n", |
|
|
126 |
"1 0.351 31 0 \n", |
|
|
127 |
"2 0.672 32 1 \n", |
|
|
128 |
"3 0.167 21 0 \n", |
|
|
129 |
"4 2.288 33 1 " |
|
|
130 |
] |
|
|
131 |
}, |
|
|
132 |
"execution_count": 2, |
|
|
133 |
"metadata": {}, |
|
|
134 |
"output_type": "execute_result" |
|
|
135 |
} |
|
|
136 |
], |
|
|
137 |
"source": [ |
|
|
138 |
"df_diabetes = pd.read_csv('diabetes.csv')\n", |
|
|
139 |
"df_diabetes.head()" |
|
|
140 |
] |
|
|
141 |
}, |
|
|
142 |
{ |
|
|
143 |
"cell_type": "code", |
|
|
144 |
"execution_count": 7, |
|
|
145 |
"metadata": {}, |
|
|
146 |
"outputs": [ |
|
|
147 |
{ |
|
|
148 |
"data": { |
|
|
149 |
"text/html": [ |
|
|
150 |
"<div>\n", |
|
|
151 |
"<style scoped>\n", |
|
|
152 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
153 |
" vertical-align: middle;\n", |
|
|
154 |
" }\n", |
|
|
155 |
"\n", |
|
|
156 |
" .dataframe tbody tr th {\n", |
|
|
157 |
" vertical-align: top;\n", |
|
|
158 |
" }\n", |
|
|
159 |
"\n", |
|
|
160 |
" .dataframe thead th {\n", |
|
|
161 |
" text-align: right;\n", |
|
|
162 |
" }\n", |
|
|
163 |
"</style>\n", |
|
|
164 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
165 |
" <thead>\n", |
|
|
166 |
" <tr style=\"text-align: right;\">\n", |
|
|
167 |
" <th></th>\n", |
|
|
168 |
" <th>age</th>\n", |
|
|
169 |
" <th>sex</th>\n", |
|
|
170 |
" <th>cp</th>\n", |
|
|
171 |
" <th>trestbps</th>\n", |
|
|
172 |
" <th>chol</th>\n", |
|
|
173 |
" <th>fbs</th>\n", |
|
|
174 |
" <th>restecg</th>\n", |
|
|
175 |
" <th>thalach</th>\n", |
|
|
176 |
" <th>exang</th>\n", |
|
|
177 |
" <th>oldpeak</th>\n", |
|
|
178 |
" <th>slope</th>\n", |
|
|
179 |
" <th>ca</th>\n", |
|
|
180 |
" <th>thal</th>\n", |
|
|
181 |
" <th>target</th>\n", |
|
|
182 |
" </tr>\n", |
|
|
183 |
" </thead>\n", |
|
|
184 |
" <tbody>\n", |
|
|
185 |
" <tr>\n", |
|
|
186 |
" <th>0</th>\n", |
|
|
187 |
" <td>52</td>\n", |
|
|
188 |
" <td>1</td>\n", |
|
|
189 |
" <td>0</td>\n", |
|
|
190 |
" <td>125</td>\n", |
|
|
191 |
" <td>212</td>\n", |
|
|
192 |
" <td>0</td>\n", |
|
|
193 |
" <td>1</td>\n", |
|
|
194 |
" <td>168</td>\n", |
|
|
195 |
" <td>0</td>\n", |
|
|
196 |
" <td>1.0</td>\n", |
|
|
197 |
" <td>2</td>\n", |
|
|
198 |
" <td>2</td>\n", |
|
|
199 |
" <td>3</td>\n", |
|
|
200 |
" <td>0</td>\n", |
|
|
201 |
" </tr>\n", |
|
|
202 |
" <tr>\n", |
|
|
203 |
" <th>1</th>\n", |
|
|
204 |
" <td>53</td>\n", |
|
|
205 |
" <td>1</td>\n", |
|
|
206 |
" <td>0</td>\n", |
|
|
207 |
" <td>140</td>\n", |
|
|
208 |
" <td>203</td>\n", |
|
|
209 |
" <td>1</td>\n", |
|
|
210 |
" <td>0</td>\n", |
|
|
211 |
" <td>155</td>\n", |
|
|
212 |
" <td>1</td>\n", |
|
|
213 |
" <td>3.1</td>\n", |
|
|
214 |
" <td>0</td>\n", |
|
|
215 |
" <td>0</td>\n", |
|
|
216 |
" <td>3</td>\n", |
|
|
217 |
" <td>0</td>\n", |
|
|
218 |
" </tr>\n", |
|
|
219 |
" <tr>\n", |
|
|
220 |
" <th>2</th>\n", |
|
|
221 |
" <td>70</td>\n", |
|
|
222 |
" <td>1</td>\n", |
|
|
223 |
" <td>0</td>\n", |
|
|
224 |
" <td>145</td>\n", |
|
|
225 |
" <td>174</td>\n", |
|
|
226 |
" <td>0</td>\n", |
|
|
227 |
" <td>1</td>\n", |
|
|
228 |
" <td>125</td>\n", |
|
|
229 |
" <td>1</td>\n", |
|
|
230 |
" <td>2.6</td>\n", |
|
|
231 |
" <td>0</td>\n", |
|
|
232 |
" <td>0</td>\n", |
|
|
233 |
" <td>3</td>\n", |
|
|
234 |
" <td>0</td>\n", |
|
|
235 |
" </tr>\n", |
|
|
236 |
" <tr>\n", |
|
|
237 |
" <th>3</th>\n", |
|
|
238 |
" <td>61</td>\n", |
|
|
239 |
" <td>1</td>\n", |
|
|
240 |
" <td>0</td>\n", |
|
|
241 |
" <td>148</td>\n", |
|
|
242 |
" <td>203</td>\n", |
|
|
243 |
" <td>0</td>\n", |
|
|
244 |
" <td>1</td>\n", |
|
|
245 |
" <td>161</td>\n", |
|
|
246 |
" <td>0</td>\n", |
|
|
247 |
" <td>0.0</td>\n", |
|
|
248 |
" <td>2</td>\n", |
|
|
249 |
" <td>1</td>\n", |
|
|
250 |
" <td>3</td>\n", |
|
|
251 |
" <td>0</td>\n", |
|
|
252 |
" </tr>\n", |
|
|
253 |
" <tr>\n", |
|
|
254 |
" <th>4</th>\n", |
|
|
255 |
" <td>62</td>\n", |
|
|
256 |
" <td>0</td>\n", |
|
|
257 |
" <td>0</td>\n", |
|
|
258 |
" <td>138</td>\n", |
|
|
259 |
" <td>294</td>\n", |
|
|
260 |
" <td>1</td>\n", |
|
|
261 |
" <td>1</td>\n", |
|
|
262 |
" <td>106</td>\n", |
|
|
263 |
" <td>0</td>\n", |
|
|
264 |
" <td>1.9</td>\n", |
|
|
265 |
" <td>1</td>\n", |
|
|
266 |
" <td>3</td>\n", |
|
|
267 |
" <td>2</td>\n", |
|
|
268 |
" <td>0</td>\n", |
|
|
269 |
" </tr>\n", |
|
|
270 |
" </tbody>\n", |
|
|
271 |
"</table>\n", |
|
|
272 |
"</div>" |
|
|
273 |
], |
|
|
274 |
"text/plain": [ |
|
|
275 |
" age sex cp trestbps chol fbs restecg thalach exang oldpeak slope \\\n", |
|
|
276 |
"0 52 1 0 125 212 0 1 168 0 1.0 2 \n", |
|
|
277 |
"1 53 1 0 140 203 1 0 155 1 3.1 0 \n", |
|
|
278 |
"2 70 1 0 145 174 0 1 125 1 2.6 0 \n", |
|
|
279 |
"3 61 1 0 148 203 0 1 161 0 0.0 2 \n", |
|
|
280 |
"4 62 0 0 138 294 1 1 106 0 1.9 1 \n", |
|
|
281 |
"\n", |
|
|
282 |
" ca thal target \n", |
|
|
283 |
"0 2 3 0 \n", |
|
|
284 |
"1 0 3 0 \n", |
|
|
285 |
"2 0 3 0 \n", |
|
|
286 |
"3 1 3 0 \n", |
|
|
287 |
"4 3 2 0 " |
|
|
288 |
] |
|
|
289 |
}, |
|
|
290 |
"execution_count": 7, |
|
|
291 |
"metadata": {}, |
|
|
292 |
"output_type": "execute_result" |
|
|
293 |
} |
|
|
294 |
], |
|
|
295 |
"source": [ |
|
|
296 |
"df_heart = pd.read_csv(\"heart_complete.csv\")\n", |
|
|
297 |
"df_heart.head()" |
|
|
298 |
] |
|
|
299 |
}, |
|
|
300 |
{ |
|
|
301 |
"cell_type": "code", |
|
|
302 |
"execution_count": 8, |
|
|
303 |
"metadata": {}, |
|
|
304 |
"outputs": [ |
|
|
305 |
{ |
|
|
306 |
"data": { |
|
|
307 |
"text/html": [ |
|
|
308 |
"<div>\n", |
|
|
309 |
"<style scoped>\n", |
|
|
310 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
311 |
" vertical-align: middle;\n", |
|
|
312 |
" }\n", |
|
|
313 |
"\n", |
|
|
314 |
" .dataframe tbody tr th {\n", |
|
|
315 |
" vertical-align: top;\n", |
|
|
316 |
" }\n", |
|
|
317 |
"\n", |
|
|
318 |
" .dataframe thead th {\n", |
|
|
319 |
" text-align: right;\n", |
|
|
320 |
" }\n", |
|
|
321 |
"</style>\n", |
|
|
322 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
323 |
" <thead>\n", |
|
|
324 |
" <tr style=\"text-align: right;\">\n", |
|
|
325 |
" <th></th>\n", |
|
|
326 |
" <th>Age</th>\n", |
|
|
327 |
" <th>Gender</th>\n", |
|
|
328 |
" <th>Height</th>\n", |
|
|
329 |
" <th>Weight</th>\n", |
|
|
330 |
" <th>BMI</th>\n", |
|
|
331 |
" <th>PhysicalActivityLevel</th>\n", |
|
|
332 |
" <th>ObesityCategory</th>\n", |
|
|
333 |
" </tr>\n", |
|
|
334 |
" </thead>\n", |
|
|
335 |
" <tbody>\n", |
|
|
336 |
" <tr>\n", |
|
|
337 |
" <th>0</th>\n", |
|
|
338 |
" <td>56</td>\n", |
|
|
339 |
" <td>Male</td>\n", |
|
|
340 |
" <td>173.575262</td>\n", |
|
|
341 |
" <td>71.982051</td>\n", |
|
|
342 |
" <td>23.891783</td>\n", |
|
|
343 |
" <td>4</td>\n", |
|
|
344 |
" <td>Normal weight</td>\n", |
|
|
345 |
" </tr>\n", |
|
|
346 |
" <tr>\n", |
|
|
347 |
" <th>1</th>\n", |
|
|
348 |
" <td>69</td>\n", |
|
|
349 |
" <td>Male</td>\n", |
|
|
350 |
" <td>164.127306</td>\n", |
|
|
351 |
" <td>89.959256</td>\n", |
|
|
352 |
" <td>33.395209</td>\n", |
|
|
353 |
" <td>2</td>\n", |
|
|
354 |
" <td>Obese</td>\n", |
|
|
355 |
" </tr>\n", |
|
|
356 |
" <tr>\n", |
|
|
357 |
" <th>2</th>\n", |
|
|
358 |
" <td>46</td>\n", |
|
|
359 |
" <td>Female</td>\n", |
|
|
360 |
" <td>168.072202</td>\n", |
|
|
361 |
" <td>72.930629</td>\n", |
|
|
362 |
" <td>25.817737</td>\n", |
|
|
363 |
" <td>4</td>\n", |
|
|
364 |
" <td>Overweight</td>\n", |
|
|
365 |
" </tr>\n", |
|
|
366 |
" <tr>\n", |
|
|
367 |
" <th>3</th>\n", |
|
|
368 |
" <td>32</td>\n", |
|
|
369 |
" <td>Male</td>\n", |
|
|
370 |
" <td>168.459633</td>\n", |
|
|
371 |
" <td>84.886912</td>\n", |
|
|
372 |
" <td>29.912247</td>\n", |
|
|
373 |
" <td>3</td>\n", |
|
|
374 |
" <td>Overweight</td>\n", |
|
|
375 |
" </tr>\n", |
|
|
376 |
" <tr>\n", |
|
|
377 |
" <th>4</th>\n", |
|
|
378 |
" <td>60</td>\n", |
|
|
379 |
" <td>Male</td>\n", |
|
|
380 |
" <td>183.568568</td>\n", |
|
|
381 |
" <td>69.038945</td>\n", |
|
|
382 |
" <td>20.487903</td>\n", |
|
|
383 |
" <td>3</td>\n", |
|
|
384 |
" <td>Normal weight</td>\n", |
|
|
385 |
" </tr>\n", |
|
|
386 |
" </tbody>\n", |
|
|
387 |
"</table>\n", |
|
|
388 |
"</div>" |
|
|
389 |
], |
|
|
390 |
"text/plain": [ |
|
|
391 |
" Age Gender Height Weight BMI PhysicalActivityLevel \\\n", |
|
|
392 |
"0 56 Male 173.575262 71.982051 23.891783 4 \n", |
|
|
393 |
"1 69 Male 164.127306 89.959256 33.395209 2 \n", |
|
|
394 |
"2 46 Female 168.072202 72.930629 25.817737 4 \n", |
|
|
395 |
"3 32 Male 168.459633 84.886912 29.912247 3 \n", |
|
|
396 |
"4 60 Male 183.568568 69.038945 20.487903 3 \n", |
|
|
397 |
"\n", |
|
|
398 |
" ObesityCategory \n", |
|
|
399 |
"0 Normal weight \n", |
|
|
400 |
"1 Obese \n", |
|
|
401 |
"2 Overweight \n", |
|
|
402 |
"3 Overweight \n", |
|
|
403 |
"4 Normal weight " |
|
|
404 |
] |
|
|
405 |
}, |
|
|
406 |
"execution_count": 8, |
|
|
407 |
"metadata": {}, |
|
|
408 |
"output_type": "execute_result" |
|
|
409 |
} |
|
|
410 |
], |
|
|
411 |
"source": [ |
|
|
412 |
"df_obesity = pd.read_csv(\"obesity_data.csv\")\n", |
|
|
413 |
"df_obesity.head()" |
|
|
414 |
] |
|
|
415 |
}, |
|
|
416 |
{ |
|
|
417 |
"cell_type": "code", |
|
|
418 |
"execution_count": null, |
|
|
419 |
"metadata": {}, |
|
|
420 |
"outputs": [], |
|
|
421 |
"source": [] |
|
|
422 |
} |
|
|
423 |
], |
|
|
424 |
"metadata": { |
|
|
425 |
"kernelspec": { |
|
|
426 |
"display_name": "Python 3.9.18 ('ds_ml')", |
|
|
427 |
"language": "python", |
|
|
428 |
"name": "python3" |
|
|
429 |
}, |
|
|
430 |
"language_info": { |
|
|
431 |
"codemirror_mode": { |
|
|
432 |
"name": "ipython", |
|
|
433 |
"version": 3 |
|
|
434 |
}, |
|
|
435 |
"file_extension": ".py", |
|
|
436 |
"mimetype": "text/x-python", |
|
|
437 |
"name": "python", |
|
|
438 |
"nbconvert_exporter": "python", |
|
|
439 |
"pygments_lexer": "ipython3", |
|
|
440 |
"version": "3.9.18" |
|
|
441 |
}, |
|
|
442 |
"orig_nbformat": 4, |
|
|
443 |
"vscode": { |
|
|
444 |
"interpreter": { |
|
|
445 |
"hash": "bcc4fb5aa31885ae3822c808f45050c24798a2479b24a824a4f952e5682b37fd" |
|
|
446 |
} |
|
|
447 |
} |
|
|
448 |
}, |
|
|
449 |
"nbformat": 4, |
|
|
450 |
"nbformat_minor": 2 |
|
|
451 |
} |