|
a |
|
b/LUNG_CANCER_logistic_regression.ipynb |
|
|
1 |
{ |
|
|
2 |
"cells": [ |
|
|
3 |
{ |
|
|
4 |
"cell_type": "markdown", |
|
|
5 |
"metadata": {}, |
|
|
6 |
"source": [ |
|
|
7 |
"Lung_cancer: Logistic regression\n", |
|
|
8 |
"---\n", |
|
|
9 |
"---" |
|
|
10 |
] |
|
|
11 |
}, |
|
|
12 |
{ |
|
|
13 |
"cell_type": "markdown", |
|
|
14 |
"metadata": {}, |
|
|
15 |
"source": [ |
|
|
16 |
"<a id='imporp'></a>\n", |
|
|
17 |
"## Importing Packages\n", |
|
|
18 |
"---" |
|
|
19 |
] |
|
|
20 |
}, |
|
|
21 |
{ |
|
|
22 |
"cell_type": "code", |
|
|
23 |
"execution_count": 2, |
|
|
24 |
"metadata": {}, |
|
|
25 |
"outputs": [], |
|
|
26 |
"source": [ |
|
|
27 |
"## Basic packages\n", |
|
|
28 |
"import numpy as np\n", |
|
|
29 |
"import pandas as pd\n", |
|
|
30 |
"\n", |
|
|
31 |
"\n", |
|
|
32 |
"## Graphing packages\n", |
|
|
33 |
"import seaborn as sns\n", |
|
|
34 |
"import matplotlib.pyplot as plt\n", |
|
|
35 |
"plt.style.use('fivethirtyeight')\n", |
|
|
36 |
"\n", |
|
|
37 |
"## Scikit learn and Statsmodel packages\n", |
|
|
38 |
"from sklearn.linear_model import LogisticRegression, LinearRegression\n", |
|
|
39 |
"import statsmodels.api as sm\n", |
|
|
40 |
"from sklearn.metrics import confusion_matrix\n", |
|
|
41 |
"## Operating system dependent functionality\n", |
|
|
42 |
"import os\n", |
|
|
43 |
"import statsmodels.api as st \n", |
|
|
44 |
"#from pandas.stats.api import ols\n", |
|
|
45 |
"## Lines of code needed to make sure graph(s) appear in notebook, and check versions of packages\n", |
|
|
46 |
"%matplotlib inline\n", |
|
|
47 |
"#%load_ext watermark\n", |
|
|
48 |
"#%config InlineBackend.figure_format = 'retina'\n", |
|
|
49 |
"#%watermark -v -d -a 'Delta Analytics' -p scikit-learn,matplotlib,numpy,pandas" |
|
|
50 |
] |
|
|
51 |
}, |
|
|
52 |
{ |
|
|
53 |
"cell_type": "markdown", |
|
|
54 |
"metadata": {}, |
|
|
55 |
"source": [ |
|
|
56 |
"<a id='rds'></a>\n", |
|
|
57 |
"## Reading the dataset\n", |
|
|
58 |
"---\n", |
|
|
59 |
"we are using Lung_Cancer dataset" |
|
|
60 |
] |
|
|
61 |
}, |
|
|
62 |
{ |
|
|
63 |
"cell_type": "code", |
|
|
64 |
"execution_count": 3, |
|
|
65 |
"metadata": {}, |
|
|
66 |
"outputs": [ |
|
|
67 |
{ |
|
|
68 |
"data": { |
|
|
69 |
"text/html": [ |
|
|
70 |
"<div>\n", |
|
|
71 |
"<style scoped>\n", |
|
|
72 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
73 |
" vertical-align: middle;\n", |
|
|
74 |
" }\n", |
|
|
75 |
"\n", |
|
|
76 |
" .dataframe tbody tr th {\n", |
|
|
77 |
" vertical-align: top;\n", |
|
|
78 |
" }\n", |
|
|
79 |
"\n", |
|
|
80 |
" .dataframe thead th {\n", |
|
|
81 |
" text-align: right;\n", |
|
|
82 |
" }\n", |
|
|
83 |
"</style>\n", |
|
|
84 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
85 |
" <thead>\n", |
|
|
86 |
" <tr style=\"text-align: right;\">\n", |
|
|
87 |
" <th></th>\n", |
|
|
88 |
" <th>patient_id</th>\n", |
|
|
89 |
" <th>age</th>\n", |
|
|
90 |
" <th>gender</th>\n", |
|
|
91 |
" <th>air_pollution</th>\n", |
|
|
92 |
" <th>alcohol_use</th>\n", |
|
|
93 |
" <th>dust_allergy</th>\n", |
|
|
94 |
" <th>occupational_hazards</th>\n", |
|
|
95 |
" <th>genetic_risk</th>\n", |
|
|
96 |
" <th>chronic_lung_disease</th>\n", |
|
|
97 |
" <th>balanced_diet</th>\n", |
|
|
98 |
" <th>...</th>\n", |
|
|
99 |
" <th>fatigue</th>\n", |
|
|
100 |
" <th>weight_loss</th>\n", |
|
|
101 |
" <th>shortness_of_breath</th>\n", |
|
|
102 |
" <th>wheezing</th>\n", |
|
|
103 |
" <th>swallowing_difficulty</th>\n", |
|
|
104 |
" <th>clubbing_of_finger_nails</th>\n", |
|
|
105 |
" <th>frequent_cold</th>\n", |
|
|
106 |
" <th>dry_cough</th>\n", |
|
|
107 |
" <th>snoring</th>\n", |
|
|
108 |
" <th>level</th>\n", |
|
|
109 |
" </tr>\n", |
|
|
110 |
" </thead>\n", |
|
|
111 |
" <tbody>\n", |
|
|
112 |
" <tr>\n", |
|
|
113 |
" <th>0</th>\n", |
|
|
114 |
" <td>P1</td>\n", |
|
|
115 |
" <td>33</td>\n", |
|
|
116 |
" <td>1</td>\n", |
|
|
117 |
" <td>2</td>\n", |
|
|
118 |
" <td>4</td>\n", |
|
|
119 |
" <td>5</td>\n", |
|
|
120 |
" <td>4</td>\n", |
|
|
121 |
" <td>3</td>\n", |
|
|
122 |
" <td>2</td>\n", |
|
|
123 |
" <td>2</td>\n", |
|
|
124 |
" <td>...</td>\n", |
|
|
125 |
" <td>3</td>\n", |
|
|
126 |
" <td>4</td>\n", |
|
|
127 |
" <td>2</td>\n", |
|
|
128 |
" <td>2</td>\n", |
|
|
129 |
" <td>3</td>\n", |
|
|
130 |
" <td>1</td>\n", |
|
|
131 |
" <td>2</td>\n", |
|
|
132 |
" <td>3</td>\n", |
|
|
133 |
" <td>4</td>\n", |
|
|
134 |
" <td>Low</td>\n", |
|
|
135 |
" </tr>\n", |
|
|
136 |
" <tr>\n", |
|
|
137 |
" <th>1</th>\n", |
|
|
138 |
" <td>P10</td>\n", |
|
|
139 |
" <td>17</td>\n", |
|
|
140 |
" <td>1</td>\n", |
|
|
141 |
" <td>3</td>\n", |
|
|
142 |
" <td>1</td>\n", |
|
|
143 |
" <td>5</td>\n", |
|
|
144 |
" <td>3</td>\n", |
|
|
145 |
" <td>4</td>\n", |
|
|
146 |
" <td>2</td>\n", |
|
|
147 |
" <td>2</td>\n", |
|
|
148 |
" <td>...</td>\n", |
|
|
149 |
" <td>1</td>\n", |
|
|
150 |
" <td>3</td>\n", |
|
|
151 |
" <td>7</td>\n", |
|
|
152 |
" <td>8</td>\n", |
|
|
153 |
" <td>6</td>\n", |
|
|
154 |
" <td>2</td>\n", |
|
|
155 |
" <td>1</td>\n", |
|
|
156 |
" <td>7</td>\n", |
|
|
157 |
" <td>2</td>\n", |
|
|
158 |
" <td>Medium</td>\n", |
|
|
159 |
" </tr>\n", |
|
|
160 |
" <tr>\n", |
|
|
161 |
" <th>2</th>\n", |
|
|
162 |
" <td>P107</td>\n", |
|
|
163 |
" <td>44</td>\n", |
|
|
164 |
" <td>1</td>\n", |
|
|
165 |
" <td>6</td>\n", |
|
|
166 |
" <td>7</td>\n", |
|
|
167 |
" <td>7</td>\n", |
|
|
168 |
" <td>7</td>\n", |
|
|
169 |
" <td>7</td>\n", |
|
|
170 |
" <td>6</td>\n", |
|
|
171 |
" <td>7</td>\n", |
|
|
172 |
" <td>...</td>\n", |
|
|
173 |
" <td>5</td>\n", |
|
|
174 |
" <td>3</td>\n", |
|
|
175 |
" <td>2</td>\n", |
|
|
176 |
" <td>7</td>\n", |
|
|
177 |
" <td>8</td>\n", |
|
|
178 |
" <td>2</td>\n", |
|
|
179 |
" <td>4</td>\n", |
|
|
180 |
" <td>5</td>\n", |
|
|
181 |
" <td>3</td>\n", |
|
|
182 |
" <td>High</td>\n", |
|
|
183 |
" </tr>\n", |
|
|
184 |
" </tbody>\n", |
|
|
185 |
"</table>\n", |
|
|
186 |
"<p>3 rows × 25 columns</p>\n", |
|
|
187 |
"</div>" |
|
|
188 |
], |
|
|
189 |
"text/plain": [ |
|
|
190 |
" patient_id age gender air_pollution alcohol_use dust_allergy \\\n", |
|
|
191 |
"0 P1 33 1 2 4 5 \n", |
|
|
192 |
"1 P10 17 1 3 1 5 \n", |
|
|
193 |
"2 P107 44 1 6 7 7 \n", |
|
|
194 |
"\n", |
|
|
195 |
" occupational_hazards genetic_risk chronic_lung_disease balanced_diet \\\n", |
|
|
196 |
"0 4 3 2 2 \n", |
|
|
197 |
"1 3 4 2 2 \n", |
|
|
198 |
"2 7 7 6 7 \n", |
|
|
199 |
"\n", |
|
|
200 |
" ... fatigue weight_loss shortness_of_breath wheezing \\\n", |
|
|
201 |
"0 ... 3 4 2 2 \n", |
|
|
202 |
"1 ... 1 3 7 8 \n", |
|
|
203 |
"2 ... 5 3 2 7 \n", |
|
|
204 |
"\n", |
|
|
205 |
" swallowing_difficulty clubbing_of_finger_nails frequent_cold dry_cough \\\n", |
|
|
206 |
"0 3 1 2 3 \n", |
|
|
207 |
"1 6 2 1 7 \n", |
|
|
208 |
"2 8 2 4 5 \n", |
|
|
209 |
"\n", |
|
|
210 |
" snoring level \n", |
|
|
211 |
"0 4 Low \n", |
|
|
212 |
"1 2 Medium \n", |
|
|
213 |
"2 3 High \n", |
|
|
214 |
"\n", |
|
|
215 |
"[3 rows x 25 columns]" |
|
|
216 |
] |
|
|
217 |
}, |
|
|
218 |
"execution_count": 3, |
|
|
219 |
"metadata": {}, |
|
|
220 |
"output_type": "execute_result" |
|
|
221 |
} |
|
|
222 |
], |
|
|
223 |
"source": [ |
|
|
224 |
"LUNG_CANCER_filepath = os.path.join('cancer_patient.csv')\n", |
|
|
225 |
"LUNG_CANCER = pd.read_csv(LUNG_CANCER_filepath)\n", |
|
|
226 |
"LUNG_CANCER.head(3)" |
|
|
227 |
] |
|
|
228 |
}, |
|
|
229 |
{ |
|
|
230 |
"cell_type": "code", |
|
|
231 |
"execution_count": 44, |
|
|
232 |
"metadata": {}, |
|
|
233 |
"outputs": [ |
|
|
234 |
{ |
|
|
235 |
"data": { |
|
|
236 |
"text/html": [ |
|
|
237 |
"<div>\n", |
|
|
238 |
"<style scoped>\n", |
|
|
239 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
240 |
" vertical-align: middle;\n", |
|
|
241 |
" }\n", |
|
|
242 |
"\n", |
|
|
243 |
" .dataframe tbody tr th {\n", |
|
|
244 |
" vertical-align: top;\n", |
|
|
245 |
" }\n", |
|
|
246 |
"\n", |
|
|
247 |
" .dataframe thead th {\n", |
|
|
248 |
" text-align: right;\n", |
|
|
249 |
" }\n", |
|
|
250 |
"</style>\n", |
|
|
251 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
252 |
" <thead>\n", |
|
|
253 |
" <tr style=\"text-align: right;\">\n", |
|
|
254 |
" <th></th>\n", |
|
|
255 |
" <th>patient_id</th>\n", |
|
|
256 |
" <th>age</th>\n", |
|
|
257 |
" <th>gender</th>\n", |
|
|
258 |
" <th>air_pollution</th>\n", |
|
|
259 |
" <th>alcohol_use</th>\n", |
|
|
260 |
" <th>dust_allergy</th>\n", |
|
|
261 |
" <th>occupational_hazards</th>\n", |
|
|
262 |
" <th>genetic_risk</th>\n", |
|
|
263 |
" <th>chronic_lung_disease</th>\n", |
|
|
264 |
" <th>balanced_diet</th>\n", |
|
|
265 |
" <th>...</th>\n", |
|
|
266 |
" <th>fatigue</th>\n", |
|
|
267 |
" <th>weight_loss</th>\n", |
|
|
268 |
" <th>shortness_of_breath</th>\n", |
|
|
269 |
" <th>wheezing</th>\n", |
|
|
270 |
" <th>swallowing_difficulty</th>\n", |
|
|
271 |
" <th>clubbing_of_finger_nails</th>\n", |
|
|
272 |
" <th>frequent_cold</th>\n", |
|
|
273 |
" <th>dry_cough</th>\n", |
|
|
274 |
" <th>snoring</th>\n", |
|
|
275 |
" <th>level</th>\n", |
|
|
276 |
" </tr>\n", |
|
|
277 |
" </thead>\n", |
|
|
278 |
" <tbody>\n", |
|
|
279 |
" <tr>\n", |
|
|
280 |
" <th>997</th>\n", |
|
|
281 |
" <td>P997</td>\n", |
|
|
282 |
" <td>25</td>\n", |
|
|
283 |
" <td>2</td>\n", |
|
|
284 |
" <td>4</td>\n", |
|
|
285 |
" <td>5</td>\n", |
|
|
286 |
" <td>6</td>\n", |
|
|
287 |
" <td>5</td>\n", |
|
|
288 |
" <td>5</td>\n", |
|
|
289 |
" <td>4</td>\n", |
|
|
290 |
" <td>6</td>\n", |
|
|
291 |
" <td>...</td>\n", |
|
|
292 |
" <td>8</td>\n", |
|
|
293 |
" <td>7</td>\n", |
|
|
294 |
" <td>9</td>\n", |
|
|
295 |
" <td>2</td>\n", |
|
|
296 |
" <td>1</td>\n", |
|
|
297 |
" <td>4</td>\n", |
|
|
298 |
" <td>6</td>\n", |
|
|
299 |
" <td>7</td>\n", |
|
|
300 |
" <td>2</td>\n", |
|
|
301 |
" <td>High</td>\n", |
|
|
302 |
" </tr>\n", |
|
|
303 |
" <tr>\n", |
|
|
304 |
" <th>998</th>\n", |
|
|
305 |
" <td>P998</td>\n", |
|
|
306 |
" <td>18</td>\n", |
|
|
307 |
" <td>2</td>\n", |
|
|
308 |
" <td>6</td>\n", |
|
|
309 |
" <td>8</td>\n", |
|
|
310 |
" <td>7</td>\n", |
|
|
311 |
" <td>7</td>\n", |
|
|
312 |
" <td>7</td>\n", |
|
|
313 |
" <td>6</td>\n", |
|
|
314 |
" <td>7</td>\n", |
|
|
315 |
" <td>...</td>\n", |
|
|
316 |
" <td>3</td>\n", |
|
|
317 |
" <td>2</td>\n", |
|
|
318 |
" <td>4</td>\n", |
|
|
319 |
" <td>1</td>\n", |
|
|
320 |
" <td>4</td>\n", |
|
|
321 |
" <td>2</td>\n", |
|
|
322 |
" <td>4</td>\n", |
|
|
323 |
" <td>2</td>\n", |
|
|
324 |
" <td>3</td>\n", |
|
|
325 |
" <td>High</td>\n", |
|
|
326 |
" </tr>\n", |
|
|
327 |
" <tr>\n", |
|
|
328 |
" <th>999</th>\n", |
|
|
329 |
" <td>P999</td>\n", |
|
|
330 |
" <td>47</td>\n", |
|
|
331 |
" <td>1</td>\n", |
|
|
332 |
" <td>6</td>\n", |
|
|
333 |
" <td>5</td>\n", |
|
|
334 |
" <td>6</td>\n", |
|
|
335 |
" <td>5</td>\n", |
|
|
336 |
" <td>5</td>\n", |
|
|
337 |
" <td>4</td>\n", |
|
|
338 |
" <td>6</td>\n", |
|
|
339 |
" <td>...</td>\n", |
|
|
340 |
" <td>8</td>\n", |
|
|
341 |
" <td>7</td>\n", |
|
|
342 |
" <td>9</td>\n", |
|
|
343 |
" <td>2</td>\n", |
|
|
344 |
" <td>1</td>\n", |
|
|
345 |
" <td>4</td>\n", |
|
|
346 |
" <td>6</td>\n", |
|
|
347 |
" <td>7</td>\n", |
|
|
348 |
" <td>2</td>\n", |
|
|
349 |
" <td>High</td>\n", |
|
|
350 |
" </tr>\n", |
|
|
351 |
" </tbody>\n", |
|
|
352 |
"</table>\n", |
|
|
353 |
"<p>3 rows × 25 columns</p>\n", |
|
|
354 |
"</div>" |
|
|
355 |
], |
|
|
356 |
"text/plain": [ |
|
|
357 |
" patient_id age gender air_pollution alcohol_use dust_allergy \\\n", |
|
|
358 |
"997 P997 25 2 4 5 6 \n", |
|
|
359 |
"998 P998 18 2 6 8 7 \n", |
|
|
360 |
"999 P999 47 1 6 5 6 \n", |
|
|
361 |
"\n", |
|
|
362 |
" occupational_hazards genetic_risk chronic_lung_disease balanced_diet \\\n", |
|
|
363 |
"997 5 5 4 6 \n", |
|
|
364 |
"998 7 7 6 7 \n", |
|
|
365 |
"999 5 5 4 6 \n", |
|
|
366 |
"\n", |
|
|
367 |
" ... fatigue weight_loss shortness_of_breath wheezing \\\n", |
|
|
368 |
"997 ... 8 7 9 2 \n", |
|
|
369 |
"998 ... 3 2 4 1 \n", |
|
|
370 |
"999 ... 8 7 9 2 \n", |
|
|
371 |
"\n", |
|
|
372 |
" swallowing_difficulty clubbing_of_finger_nails frequent_cold \\\n", |
|
|
373 |
"997 1 4 6 \n", |
|
|
374 |
"998 4 2 4 \n", |
|
|
375 |
"999 1 4 6 \n", |
|
|
376 |
"\n", |
|
|
377 |
" dry_cough snoring level \n", |
|
|
378 |
"997 7 2 High \n", |
|
|
379 |
"998 2 3 High \n", |
|
|
380 |
"999 7 2 High \n", |
|
|
381 |
"\n", |
|
|
382 |
"[3 rows x 25 columns]" |
|
|
383 |
] |
|
|
384 |
}, |
|
|
385 |
"execution_count": 44, |
|
|
386 |
"metadata": {}, |
|
|
387 |
"output_type": "execute_result" |
|
|
388 |
} |
|
|
389 |
], |
|
|
390 |
"source": [ |
|
|
391 |
"LUNG_CANCER.tail(3)" |
|
|
392 |
] |
|
|
393 |
}, |
|
|
394 |
{ |
|
|
395 |
"cell_type": "markdown", |
|
|
396 |
"metadata": {}, |
|
|
397 |
"source": [ |
|
|
398 |
"<a id='msvl'></a>\n", |
|
|
399 |
"### Missing Values\n", |
|
|
400 |
"---\n", |
|
|
401 |
"1. we will drop the missing values if there is one" |
|
|
402 |
] |
|
|
403 |
}, |
|
|
404 |
{ |
|
|
405 |
"cell_type": "code", |
|
|
406 |
"execution_count": 45, |
|
|
407 |
"metadata": {}, |
|
|
408 |
"outputs": [ |
|
|
409 |
{ |
|
|
410 |
"data": { |
|
|
411 |
"text/plain": [ |
|
|
412 |
"patient_id 0\n", |
|
|
413 |
"age 0\n", |
|
|
414 |
"gender 0\n", |
|
|
415 |
"air_pollution 0\n", |
|
|
416 |
"alcohol_use 0\n", |
|
|
417 |
"dust_allergy 0\n", |
|
|
418 |
"occupational_hazards 0\n", |
|
|
419 |
"genetic_risk 0\n", |
|
|
420 |
"chronic_lung_disease 0\n", |
|
|
421 |
"balanced_diet 0\n", |
|
|
422 |
"obesity 0\n", |
|
|
423 |
"smoking 0\n", |
|
|
424 |
"passive_smoker 0\n", |
|
|
425 |
"chest_pain 0\n", |
|
|
426 |
"coughing_of_blood 0\n", |
|
|
427 |
"fatigue 0\n", |
|
|
428 |
"weight_loss 0\n", |
|
|
429 |
"shortness_of_breath 0\n", |
|
|
430 |
"wheezing 0\n", |
|
|
431 |
"swallowing_difficulty 0\n", |
|
|
432 |
"clubbing_of_finger_nails 0\n", |
|
|
433 |
"frequent_cold 0\n", |
|
|
434 |
"dry_cough 0\n", |
|
|
435 |
"snoring 0\n", |
|
|
436 |
"level 0\n", |
|
|
437 |
"dtype: int64" |
|
|
438 |
] |
|
|
439 |
}, |
|
|
440 |
"execution_count": 45, |
|
|
441 |
"metadata": {}, |
|
|
442 |
"output_type": "execute_result" |
|
|
443 |
} |
|
|
444 |
], |
|
|
445 |
"source": [ |
|
|
446 |
"LUNG_CANCER.isnull().sum()" |
|
|
447 |
] |
|
|
448 |
}, |
|
|
449 |
{ |
|
|
450 |
"cell_type": "code", |
|
|
451 |
"execution_count": 5, |
|
|
452 |
"metadata": {}, |
|
|
453 |
"outputs": [], |
|
|
454 |
"source": [ |
|
|
455 |
"LUNG_CANCER.dropna(inplace=True)" |
|
|
456 |
] |
|
|
457 |
}, |
|
|
458 |
{ |
|
|
459 |
"cell_type": "code", |
|
|
460 |
"execution_count": 6, |
|
|
461 |
"metadata": {}, |
|
|
462 |
"outputs": [ |
|
|
463 |
{ |
|
|
464 |
"data": { |
|
|
465 |
"text/plain": [ |
|
|
466 |
"patient_id 0\n", |
|
|
467 |
"age 0\n", |
|
|
468 |
"gender 0\n", |
|
|
469 |
"air_pollution 0\n", |
|
|
470 |
"alcohol_use 0\n", |
|
|
471 |
"dust_allergy 0\n", |
|
|
472 |
"occupational_hazards 0\n", |
|
|
473 |
"genetic_risk 0\n", |
|
|
474 |
"chronic_lung_disease 0\n", |
|
|
475 |
"balanced_diet 0\n", |
|
|
476 |
"obesity 0\n", |
|
|
477 |
"smoking 0\n", |
|
|
478 |
"passive_smoker 0\n", |
|
|
479 |
"chest_pain 0\n", |
|
|
480 |
"coughing_of_blood 0\n", |
|
|
481 |
"fatigue 0\n", |
|
|
482 |
"weight_loss 0\n", |
|
|
483 |
"shortness_of_breath 0\n", |
|
|
484 |
"wheezing 0\n", |
|
|
485 |
"swallowing_difficulty 0\n", |
|
|
486 |
"clubbing_of_finger_nails 0\n", |
|
|
487 |
"frequent_cold 0\n", |
|
|
488 |
"dry_cough 0\n", |
|
|
489 |
"snoring 0\n", |
|
|
490 |
"level 0\n", |
|
|
491 |
"dtype: int64" |
|
|
492 |
] |
|
|
493 |
}, |
|
|
494 |
"execution_count": 6, |
|
|
495 |
"metadata": {}, |
|
|
496 |
"output_type": "execute_result" |
|
|
497 |
} |
|
|
498 |
], |
|
|
499 |
"source": [ |
|
|
500 |
"LUNG_CANCER.isnull().sum()" |
|
|
501 |
] |
|
|
502 |
}, |
|
|
503 |
{ |
|
|
504 |
"cell_type": "markdown", |
|
|
505 |
"metadata": {}, |
|
|
506 |
"source": [ |
|
|
507 |
"<a id='implementation'></a>\n", |
|
|
508 |
"## Implementation of Logistic Regression\n", |
|
|
509 |
"---\n" |
|
|
510 |
] |
|
|
511 |
}, |
|
|
512 |
{ |
|
|
513 |
"cell_type": "markdown", |
|
|
514 |
"metadata": {}, |
|
|
515 |
"source": [ |
|
|
516 |
"<a id='LEVEL'></a>\n", |
|
|
517 |
"### Level: Low, Medium, High\n", |
|
|
518 |
"---" |
|
|
519 |
] |
|
|
520 |
}, |
|
|
521 |
{ |
|
|
522 |
"cell_type": "code", |
|
|
523 |
"execution_count": 7, |
|
|
524 |
"metadata": {}, |
|
|
525 |
"outputs": [ |
|
|
526 |
{ |
|
|
527 |
"data": { |
|
|
528 |
"text/html": [ |
|
|
529 |
"<div>\n", |
|
|
530 |
"<style scoped>\n", |
|
|
531 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
532 |
" vertical-align: middle;\n", |
|
|
533 |
" }\n", |
|
|
534 |
"\n", |
|
|
535 |
" .dataframe tbody tr th {\n", |
|
|
536 |
" vertical-align: top;\n", |
|
|
537 |
" }\n", |
|
|
538 |
"\n", |
|
|
539 |
" .dataframe thead th {\n", |
|
|
540 |
" text-align: right;\n", |
|
|
541 |
" }\n", |
|
|
542 |
"</style>\n", |
|
|
543 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
544 |
" <thead>\n", |
|
|
545 |
" <tr style=\"text-align: right;\">\n", |
|
|
546 |
" <th></th>\n", |
|
|
547 |
" <th>age</th>\n", |
|
|
548 |
" <th>gender</th>\n", |
|
|
549 |
" <th>air_pollution</th>\n", |
|
|
550 |
" <th>alcohol_use</th>\n", |
|
|
551 |
" <th>dust_allergy</th>\n", |
|
|
552 |
" <th>occupational_hazards</th>\n", |
|
|
553 |
" <th>genetic_risk</th>\n", |
|
|
554 |
" <th>chronic_lung_disease</th>\n", |
|
|
555 |
" <th>balanced_diet</th>\n", |
|
|
556 |
" <th>obesity</th>\n", |
|
|
557 |
" <th>...</th>\n", |
|
|
558 |
" <th>coughing_of_blood</th>\n", |
|
|
559 |
" <th>fatigue</th>\n", |
|
|
560 |
" <th>weight_loss</th>\n", |
|
|
561 |
" <th>shortness_of_breath</th>\n", |
|
|
562 |
" <th>wheezing</th>\n", |
|
|
563 |
" <th>swallowing_difficulty</th>\n", |
|
|
564 |
" <th>clubbing_of_finger_nails</th>\n", |
|
|
565 |
" <th>frequent_cold</th>\n", |
|
|
566 |
" <th>dry_cough</th>\n", |
|
|
567 |
" <th>snoring</th>\n", |
|
|
568 |
" </tr>\n", |
|
|
569 |
" </thead>\n", |
|
|
570 |
" <tbody>\n", |
|
|
571 |
" <tr>\n", |
|
|
572 |
" <th>count</th>\n", |
|
|
573 |
" <td>1000.000000</td>\n", |
|
|
574 |
" <td>1000.000000</td>\n", |
|
|
575 |
" <td>1000.0000</td>\n", |
|
|
576 |
" <td>1000.000000</td>\n", |
|
|
577 |
" <td>1000.000000</td>\n", |
|
|
578 |
" <td>1000.000000</td>\n", |
|
|
579 |
" <td>1000.000000</td>\n", |
|
|
580 |
" <td>1000.000000</td>\n", |
|
|
581 |
" <td>1000.000000</td>\n", |
|
|
582 |
" <td>1000.000000</td>\n", |
|
|
583 |
" <td>...</td>\n", |
|
|
584 |
" <td>1000.000000</td>\n", |
|
|
585 |
" <td>1000.000000</td>\n", |
|
|
586 |
" <td>1000.000000</td>\n", |
|
|
587 |
" <td>1000.000000</td>\n", |
|
|
588 |
" <td>1000.000000</td>\n", |
|
|
589 |
" <td>1000.000000</td>\n", |
|
|
590 |
" <td>1000.000000</td>\n", |
|
|
591 |
" <td>1000.000000</td>\n", |
|
|
592 |
" <td>1000.000000</td>\n", |
|
|
593 |
" <td>1000.000000</td>\n", |
|
|
594 |
" </tr>\n", |
|
|
595 |
" <tr>\n", |
|
|
596 |
" <th>mean</th>\n", |
|
|
597 |
" <td>37.174000</td>\n", |
|
|
598 |
" <td>1.402000</td>\n", |
|
|
599 |
" <td>3.8400</td>\n", |
|
|
600 |
" <td>4.563000</td>\n", |
|
|
601 |
" <td>5.165000</td>\n", |
|
|
602 |
" <td>4.840000</td>\n", |
|
|
603 |
" <td>4.580000</td>\n", |
|
|
604 |
" <td>4.380000</td>\n", |
|
|
605 |
" <td>4.491000</td>\n", |
|
|
606 |
" <td>4.465000</td>\n", |
|
|
607 |
" <td>...</td>\n", |
|
|
608 |
" <td>4.859000</td>\n", |
|
|
609 |
" <td>3.856000</td>\n", |
|
|
610 |
" <td>3.855000</td>\n", |
|
|
611 |
" <td>4.240000</td>\n", |
|
|
612 |
" <td>3.777000</td>\n", |
|
|
613 |
" <td>3.746000</td>\n", |
|
|
614 |
" <td>3.923000</td>\n", |
|
|
615 |
" <td>3.536000</td>\n", |
|
|
616 |
" <td>3.853000</td>\n", |
|
|
617 |
" <td>2.926000</td>\n", |
|
|
618 |
" </tr>\n", |
|
|
619 |
" <tr>\n", |
|
|
620 |
" <th>std</th>\n", |
|
|
621 |
" <td>12.005493</td>\n", |
|
|
622 |
" <td>0.490547</td>\n", |
|
|
623 |
" <td>2.0304</td>\n", |
|
|
624 |
" <td>2.620477</td>\n", |
|
|
625 |
" <td>1.980833</td>\n", |
|
|
626 |
" <td>2.107805</td>\n", |
|
|
627 |
" <td>2.126999</td>\n", |
|
|
628 |
" <td>1.848518</td>\n", |
|
|
629 |
" <td>2.135528</td>\n", |
|
|
630 |
" <td>2.124921</td>\n", |
|
|
631 |
" <td>...</td>\n", |
|
|
632 |
" <td>2.427965</td>\n", |
|
|
633 |
" <td>2.244616</td>\n", |
|
|
634 |
" <td>2.206546</td>\n", |
|
|
635 |
" <td>2.285087</td>\n", |
|
|
636 |
" <td>2.041921</td>\n", |
|
|
637 |
" <td>2.270383</td>\n", |
|
|
638 |
" <td>2.388048</td>\n", |
|
|
639 |
" <td>1.832502</td>\n", |
|
|
640 |
" <td>2.039007</td>\n", |
|
|
641 |
" <td>1.474686</td>\n", |
|
|
642 |
" </tr>\n", |
|
|
643 |
" <tr>\n", |
|
|
644 |
" <th>min</th>\n", |
|
|
645 |
" <td>14.000000</td>\n", |
|
|
646 |
" <td>1.000000</td>\n", |
|
|
647 |
" <td>1.0000</td>\n", |
|
|
648 |
" <td>1.000000</td>\n", |
|
|
649 |
" <td>1.000000</td>\n", |
|
|
650 |
" <td>1.000000</td>\n", |
|
|
651 |
" <td>1.000000</td>\n", |
|
|
652 |
" <td>1.000000</td>\n", |
|
|
653 |
" <td>1.000000</td>\n", |
|
|
654 |
" <td>1.000000</td>\n", |
|
|
655 |
" <td>...</td>\n", |
|
|
656 |
" <td>1.000000</td>\n", |
|
|
657 |
" <td>1.000000</td>\n", |
|
|
658 |
" <td>1.000000</td>\n", |
|
|
659 |
" <td>1.000000</td>\n", |
|
|
660 |
" <td>1.000000</td>\n", |
|
|
661 |
" <td>1.000000</td>\n", |
|
|
662 |
" <td>1.000000</td>\n", |
|
|
663 |
" <td>1.000000</td>\n", |
|
|
664 |
" <td>1.000000</td>\n", |
|
|
665 |
" <td>1.000000</td>\n", |
|
|
666 |
" </tr>\n", |
|
|
667 |
" <tr>\n", |
|
|
668 |
" <th>25%</th>\n", |
|
|
669 |
" <td>27.750000</td>\n", |
|
|
670 |
" <td>1.000000</td>\n", |
|
|
671 |
" <td>2.0000</td>\n", |
|
|
672 |
" <td>2.000000</td>\n", |
|
|
673 |
" <td>4.000000</td>\n", |
|
|
674 |
" <td>3.000000</td>\n", |
|
|
675 |
" <td>2.000000</td>\n", |
|
|
676 |
" <td>3.000000</td>\n", |
|
|
677 |
" <td>2.000000</td>\n", |
|
|
678 |
" <td>3.000000</td>\n", |
|
|
679 |
" <td>...</td>\n", |
|
|
680 |
" <td>3.000000</td>\n", |
|
|
681 |
" <td>2.000000</td>\n", |
|
|
682 |
" <td>2.000000</td>\n", |
|
|
683 |
" <td>2.000000</td>\n", |
|
|
684 |
" <td>2.000000</td>\n", |
|
|
685 |
" <td>2.000000</td>\n", |
|
|
686 |
" <td>2.000000</td>\n", |
|
|
687 |
" <td>2.000000</td>\n", |
|
|
688 |
" <td>2.000000</td>\n", |
|
|
689 |
" <td>2.000000</td>\n", |
|
|
690 |
" </tr>\n", |
|
|
691 |
" <tr>\n", |
|
|
692 |
" <th>50%</th>\n", |
|
|
693 |
" <td>36.000000</td>\n", |
|
|
694 |
" <td>1.000000</td>\n", |
|
|
695 |
" <td>3.0000</td>\n", |
|
|
696 |
" <td>5.000000</td>\n", |
|
|
697 |
" <td>6.000000</td>\n", |
|
|
698 |
" <td>5.000000</td>\n", |
|
|
699 |
" <td>5.000000</td>\n", |
|
|
700 |
" <td>4.000000</td>\n", |
|
|
701 |
" <td>4.000000</td>\n", |
|
|
702 |
" <td>4.000000</td>\n", |
|
|
703 |
" <td>...</td>\n", |
|
|
704 |
" <td>4.000000</td>\n", |
|
|
705 |
" <td>3.000000</td>\n", |
|
|
706 |
" <td>3.000000</td>\n", |
|
|
707 |
" <td>4.000000</td>\n", |
|
|
708 |
" <td>4.000000</td>\n", |
|
|
709 |
" <td>4.000000</td>\n", |
|
|
710 |
" <td>4.000000</td>\n", |
|
|
711 |
" <td>3.000000</td>\n", |
|
|
712 |
" <td>4.000000</td>\n", |
|
|
713 |
" <td>3.000000</td>\n", |
|
|
714 |
" </tr>\n", |
|
|
715 |
" <tr>\n", |
|
|
716 |
" <th>75%</th>\n", |
|
|
717 |
" <td>45.000000</td>\n", |
|
|
718 |
" <td>2.000000</td>\n", |
|
|
719 |
" <td>6.0000</td>\n", |
|
|
720 |
" <td>7.000000</td>\n", |
|
|
721 |
" <td>7.000000</td>\n", |
|
|
722 |
" <td>7.000000</td>\n", |
|
|
723 |
" <td>7.000000</td>\n", |
|
|
724 |
" <td>6.000000</td>\n", |
|
|
725 |
" <td>7.000000</td>\n", |
|
|
726 |
" <td>7.000000</td>\n", |
|
|
727 |
" <td>...</td>\n", |
|
|
728 |
" <td>7.000000</td>\n", |
|
|
729 |
" <td>5.000000</td>\n", |
|
|
730 |
" <td>6.000000</td>\n", |
|
|
731 |
" <td>6.000000</td>\n", |
|
|
732 |
" <td>5.000000</td>\n", |
|
|
733 |
" <td>5.000000</td>\n", |
|
|
734 |
" <td>5.000000</td>\n", |
|
|
735 |
" <td>5.000000</td>\n", |
|
|
736 |
" <td>6.000000</td>\n", |
|
|
737 |
" <td>4.000000</td>\n", |
|
|
738 |
" </tr>\n", |
|
|
739 |
" <tr>\n", |
|
|
740 |
" <th>max</th>\n", |
|
|
741 |
" <td>73.000000</td>\n", |
|
|
742 |
" <td>2.000000</td>\n", |
|
|
743 |
" <td>8.0000</td>\n", |
|
|
744 |
" <td>8.000000</td>\n", |
|
|
745 |
" <td>8.000000</td>\n", |
|
|
746 |
" <td>8.000000</td>\n", |
|
|
747 |
" <td>7.000000</td>\n", |
|
|
748 |
" <td>7.000000</td>\n", |
|
|
749 |
" <td>7.000000</td>\n", |
|
|
750 |
" <td>7.000000</td>\n", |
|
|
751 |
" <td>...</td>\n", |
|
|
752 |
" <td>9.000000</td>\n", |
|
|
753 |
" <td>9.000000</td>\n", |
|
|
754 |
" <td>8.000000</td>\n", |
|
|
755 |
" <td>9.000000</td>\n", |
|
|
756 |
" <td>8.000000</td>\n", |
|
|
757 |
" <td>8.000000</td>\n", |
|
|
758 |
" <td>9.000000</td>\n", |
|
|
759 |
" <td>7.000000</td>\n", |
|
|
760 |
" <td>7.000000</td>\n", |
|
|
761 |
" <td>7.000000</td>\n", |
|
|
762 |
" </tr>\n", |
|
|
763 |
" </tbody>\n", |
|
|
764 |
"</table>\n", |
|
|
765 |
"<p>8 rows × 23 columns</p>\n", |
|
|
766 |
"</div>" |
|
|
767 |
], |
|
|
768 |
"text/plain": [ |
|
|
769 |
" age gender air_pollution alcohol_use dust_allergy \\\n", |
|
|
770 |
"count 1000.000000 1000.000000 1000.0000 1000.000000 1000.000000 \n", |
|
|
771 |
"mean 37.174000 1.402000 3.8400 4.563000 5.165000 \n", |
|
|
772 |
"std 12.005493 0.490547 2.0304 2.620477 1.980833 \n", |
|
|
773 |
"min 14.000000 1.000000 1.0000 1.000000 1.000000 \n", |
|
|
774 |
"25% 27.750000 1.000000 2.0000 2.000000 4.000000 \n", |
|
|
775 |
"50% 36.000000 1.000000 3.0000 5.000000 6.000000 \n", |
|
|
776 |
"75% 45.000000 2.000000 6.0000 7.000000 7.000000 \n", |
|
|
777 |
"max 73.000000 2.000000 8.0000 8.000000 8.000000 \n", |
|
|
778 |
"\n", |
|
|
779 |
" occupational_hazards genetic_risk chronic_lung_disease \\\n", |
|
|
780 |
"count 1000.000000 1000.000000 1000.000000 \n", |
|
|
781 |
"mean 4.840000 4.580000 4.380000 \n", |
|
|
782 |
"std 2.107805 2.126999 1.848518 \n", |
|
|
783 |
"min 1.000000 1.000000 1.000000 \n", |
|
|
784 |
"25% 3.000000 2.000000 3.000000 \n", |
|
|
785 |
"50% 5.000000 5.000000 4.000000 \n", |
|
|
786 |
"75% 7.000000 7.000000 6.000000 \n", |
|
|
787 |
"max 8.000000 7.000000 7.000000 \n", |
|
|
788 |
"\n", |
|
|
789 |
" balanced_diet obesity ... coughing_of_blood \\\n", |
|
|
790 |
"count 1000.000000 1000.000000 ... 1000.000000 \n", |
|
|
791 |
"mean 4.491000 4.465000 ... 4.859000 \n", |
|
|
792 |
"std 2.135528 2.124921 ... 2.427965 \n", |
|
|
793 |
"min 1.000000 1.000000 ... 1.000000 \n", |
|
|
794 |
"25% 2.000000 3.000000 ... 3.000000 \n", |
|
|
795 |
"50% 4.000000 4.000000 ... 4.000000 \n", |
|
|
796 |
"75% 7.000000 7.000000 ... 7.000000 \n", |
|
|
797 |
"max 7.000000 7.000000 ... 9.000000 \n", |
|
|
798 |
"\n", |
|
|
799 |
" fatigue weight_loss shortness_of_breath wheezing \\\n", |
|
|
800 |
"count 1000.000000 1000.000000 1000.000000 1000.000000 \n", |
|
|
801 |
"mean 3.856000 3.855000 4.240000 3.777000 \n", |
|
|
802 |
"std 2.244616 2.206546 2.285087 2.041921 \n", |
|
|
803 |
"min 1.000000 1.000000 1.000000 1.000000 \n", |
|
|
804 |
"25% 2.000000 2.000000 2.000000 2.000000 \n", |
|
|
805 |
"50% 3.000000 3.000000 4.000000 4.000000 \n", |
|
|
806 |
"75% 5.000000 6.000000 6.000000 5.000000 \n", |
|
|
807 |
"max 9.000000 8.000000 9.000000 8.000000 \n", |
|
|
808 |
"\n", |
|
|
809 |
" swallowing_difficulty clubbing_of_finger_nails frequent_cold \\\n", |
|
|
810 |
"count 1000.000000 1000.000000 1000.000000 \n", |
|
|
811 |
"mean 3.746000 3.923000 3.536000 \n", |
|
|
812 |
"std 2.270383 2.388048 1.832502 \n", |
|
|
813 |
"min 1.000000 1.000000 1.000000 \n", |
|
|
814 |
"25% 2.000000 2.000000 2.000000 \n", |
|
|
815 |
"50% 4.000000 4.000000 3.000000 \n", |
|
|
816 |
"75% 5.000000 5.000000 5.000000 \n", |
|
|
817 |
"max 8.000000 9.000000 7.000000 \n", |
|
|
818 |
"\n", |
|
|
819 |
" dry_cough snoring \n", |
|
|
820 |
"count 1000.000000 1000.000000 \n", |
|
|
821 |
"mean 3.853000 2.926000 \n", |
|
|
822 |
"std 2.039007 1.474686 \n", |
|
|
823 |
"min 1.000000 1.000000 \n", |
|
|
824 |
"25% 2.000000 2.000000 \n", |
|
|
825 |
"50% 4.000000 3.000000 \n", |
|
|
826 |
"75% 6.000000 4.000000 \n", |
|
|
827 |
"max 7.000000 7.000000 \n", |
|
|
828 |
"\n", |
|
|
829 |
"[8 rows x 23 columns]" |
|
|
830 |
] |
|
|
831 |
}, |
|
|
832 |
"execution_count": 7, |
|
|
833 |
"metadata": {}, |
|
|
834 |
"output_type": "execute_result" |
|
|
835 |
} |
|
|
836 |
], |
|
|
837 |
"source": [ |
|
|
838 |
"## Describe our dataset\n", |
|
|
839 |
"LUNG_CANCER.describe()" |
|
|
840 |
] |
|
|
841 |
}, |
|
|
842 |
{ |
|
|
843 |
"cell_type": "code", |
|
|
844 |
"execution_count": 8, |
|
|
845 |
"metadata": {}, |
|
|
846 |
"outputs": [ |
|
|
847 |
{ |
|
|
848 |
"name": "stdout", |
|
|
849 |
"output_type": "stream", |
|
|
850 |
"text": [ |
|
|
851 |
"<class 'pandas.core.frame.DataFrame'>\n", |
|
|
852 |
"Int64Index: 1000 entries, 0 to 999\n", |
|
|
853 |
"Data columns (total 25 columns):\n", |
|
|
854 |
"patient_id 1000 non-null object\n", |
|
|
855 |
"age 1000 non-null int64\n", |
|
|
856 |
"gender 1000 non-null int64\n", |
|
|
857 |
"air_pollution 1000 non-null int64\n", |
|
|
858 |
"alcohol_use 1000 non-null int64\n", |
|
|
859 |
"dust_allergy 1000 non-null int64\n", |
|
|
860 |
"occupational_hazards 1000 non-null int64\n", |
|
|
861 |
"genetic_risk 1000 non-null int64\n", |
|
|
862 |
"chronic_lung_disease 1000 non-null int64\n", |
|
|
863 |
"balanced_diet 1000 non-null int64\n", |
|
|
864 |
"obesity 1000 non-null int64\n", |
|
|
865 |
"smoking 1000 non-null int64\n", |
|
|
866 |
"passive_smoker 1000 non-null int64\n", |
|
|
867 |
"chest_pain 1000 non-null int64\n", |
|
|
868 |
"coughing_of_blood 1000 non-null int64\n", |
|
|
869 |
"fatigue 1000 non-null int64\n", |
|
|
870 |
"weight_loss 1000 non-null int64\n", |
|
|
871 |
"shortness_of_breath 1000 non-null int64\n", |
|
|
872 |
"wheezing 1000 non-null int64\n", |
|
|
873 |
"swallowing_difficulty 1000 non-null int64\n", |
|
|
874 |
"clubbing_of_finger_nails 1000 non-null int64\n", |
|
|
875 |
"frequent_cold 1000 non-null int64\n", |
|
|
876 |
"dry_cough 1000 non-null int64\n", |
|
|
877 |
"snoring 1000 non-null int64\n", |
|
|
878 |
"level 1000 non-null object\n", |
|
|
879 |
"dtypes: int64(23), object(2)\n", |
|
|
880 |
"memory usage: 203.1+ KB\n" |
|
|
881 |
] |
|
|
882 |
} |
|
|
883 |
], |
|
|
884 |
"source": [ |
|
|
885 |
"LUNG_CANCER.info()" |
|
|
886 |
] |
|
|
887 |
}, |
|
|
888 |
{ |
|
|
889 |
"cell_type": "markdown", |
|
|
890 |
"metadata": {}, |
|
|
891 |
"source": [ |
|
|
892 |
"### here we have a categorical Column in our dataset which is Level" |
|
|
893 |
] |
|
|
894 |
}, |
|
|
895 |
{ |
|
|
896 |
"cell_type": "code", |
|
|
897 |
"execution_count": 9, |
|
|
898 |
"metadata": {}, |
|
|
899 |
"outputs": [ |
|
|
900 |
{ |
|
|
901 |
"data": { |
|
|
902 |
"text/html": [ |
|
|
903 |
"<div>\n", |
|
|
904 |
"<style scoped>\n", |
|
|
905 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
906 |
" vertical-align: middle;\n", |
|
|
907 |
" }\n", |
|
|
908 |
"\n", |
|
|
909 |
" .dataframe tbody tr th {\n", |
|
|
910 |
" vertical-align: top;\n", |
|
|
911 |
" }\n", |
|
|
912 |
"\n", |
|
|
913 |
" .dataframe thead th {\n", |
|
|
914 |
" text-align: right;\n", |
|
|
915 |
" }\n", |
|
|
916 |
"</style>\n", |
|
|
917 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
918 |
" <thead>\n", |
|
|
919 |
" <tr style=\"text-align: right;\">\n", |
|
|
920 |
" <th></th>\n", |
|
|
921 |
" <th>patient_id</th>\n", |
|
|
922 |
" <th>age</th>\n", |
|
|
923 |
" <th>gender</th>\n", |
|
|
924 |
" <th>air_pollution</th>\n", |
|
|
925 |
" <th>alcohol_use</th>\n", |
|
|
926 |
" <th>dust_allergy</th>\n", |
|
|
927 |
" <th>occupational_hazards</th>\n", |
|
|
928 |
" <th>genetic_risk</th>\n", |
|
|
929 |
" <th>chronic_lung_disease</th>\n", |
|
|
930 |
" <th>balanced_diet</th>\n", |
|
|
931 |
" <th>...</th>\n", |
|
|
932 |
" <th>fatigue</th>\n", |
|
|
933 |
" <th>weight_loss</th>\n", |
|
|
934 |
" <th>shortness_of_breath</th>\n", |
|
|
935 |
" <th>wheezing</th>\n", |
|
|
936 |
" <th>swallowing_difficulty</th>\n", |
|
|
937 |
" <th>clubbing_of_finger_nails</th>\n", |
|
|
938 |
" <th>frequent_cold</th>\n", |
|
|
939 |
" <th>dry_cough</th>\n", |
|
|
940 |
" <th>snoring</th>\n", |
|
|
941 |
" <th>level</th>\n", |
|
|
942 |
" </tr>\n", |
|
|
943 |
" </thead>\n", |
|
|
944 |
" <tbody>\n", |
|
|
945 |
" <tr>\n", |
|
|
946 |
" <th>0</th>\n", |
|
|
947 |
" <td>P1</td>\n", |
|
|
948 |
" <td>33</td>\n", |
|
|
949 |
" <td>1</td>\n", |
|
|
950 |
" <td>2</td>\n", |
|
|
951 |
" <td>4</td>\n", |
|
|
952 |
" <td>5</td>\n", |
|
|
953 |
" <td>4</td>\n", |
|
|
954 |
" <td>3</td>\n", |
|
|
955 |
" <td>2</td>\n", |
|
|
956 |
" <td>2</td>\n", |
|
|
957 |
" <td>...</td>\n", |
|
|
958 |
" <td>3</td>\n", |
|
|
959 |
" <td>4</td>\n", |
|
|
960 |
" <td>2</td>\n", |
|
|
961 |
" <td>2</td>\n", |
|
|
962 |
" <td>3</td>\n", |
|
|
963 |
" <td>1</td>\n", |
|
|
964 |
" <td>2</td>\n", |
|
|
965 |
" <td>3</td>\n", |
|
|
966 |
" <td>4</td>\n", |
|
|
967 |
" <td>1</td>\n", |
|
|
968 |
" </tr>\n", |
|
|
969 |
" <tr>\n", |
|
|
970 |
" <th>1</th>\n", |
|
|
971 |
" <td>P10</td>\n", |
|
|
972 |
" <td>17</td>\n", |
|
|
973 |
" <td>1</td>\n", |
|
|
974 |
" <td>3</td>\n", |
|
|
975 |
" <td>1</td>\n", |
|
|
976 |
" <td>5</td>\n", |
|
|
977 |
" <td>3</td>\n", |
|
|
978 |
" <td>4</td>\n", |
|
|
979 |
" <td>2</td>\n", |
|
|
980 |
" <td>2</td>\n", |
|
|
981 |
" <td>...</td>\n", |
|
|
982 |
" <td>1</td>\n", |
|
|
983 |
" <td>3</td>\n", |
|
|
984 |
" <td>7</td>\n", |
|
|
985 |
" <td>8</td>\n", |
|
|
986 |
" <td>6</td>\n", |
|
|
987 |
" <td>2</td>\n", |
|
|
988 |
" <td>1</td>\n", |
|
|
989 |
" <td>7</td>\n", |
|
|
990 |
" <td>2</td>\n", |
|
|
991 |
" <td>2</td>\n", |
|
|
992 |
" </tr>\n", |
|
|
993 |
" <tr>\n", |
|
|
994 |
" <th>2</th>\n", |
|
|
995 |
" <td>P107</td>\n", |
|
|
996 |
" <td>44</td>\n", |
|
|
997 |
" <td>1</td>\n", |
|
|
998 |
" <td>6</td>\n", |
|
|
999 |
" <td>7</td>\n", |
|
|
1000 |
" <td>7</td>\n", |
|
|
1001 |
" <td>7</td>\n", |
|
|
1002 |
" <td>7</td>\n", |
|
|
1003 |
" <td>6</td>\n", |
|
|
1004 |
" <td>7</td>\n", |
|
|
1005 |
" <td>...</td>\n", |
|
|
1006 |
" <td>5</td>\n", |
|
|
1007 |
" <td>3</td>\n", |
|
|
1008 |
" <td>2</td>\n", |
|
|
1009 |
" <td>7</td>\n", |
|
|
1010 |
" <td>8</td>\n", |
|
|
1011 |
" <td>2</td>\n", |
|
|
1012 |
" <td>4</td>\n", |
|
|
1013 |
" <td>5</td>\n", |
|
|
1014 |
" <td>3</td>\n", |
|
|
1015 |
" <td>3</td>\n", |
|
|
1016 |
" </tr>\n", |
|
|
1017 |
" <tr>\n", |
|
|
1018 |
" <th>3</th>\n", |
|
|
1019 |
" <td>P189</td>\n", |
|
|
1020 |
" <td>39</td>\n", |
|
|
1021 |
" <td>2</td>\n", |
|
|
1022 |
" <td>6</td>\n", |
|
|
1023 |
" <td>8</td>\n", |
|
|
1024 |
" <td>7</td>\n", |
|
|
1025 |
" <td>7</td>\n", |
|
|
1026 |
" <td>7</td>\n", |
|
|
1027 |
" <td>6</td>\n", |
|
|
1028 |
" <td>7</td>\n", |
|
|
1029 |
" <td>...</td>\n", |
|
|
1030 |
" <td>3</td>\n", |
|
|
1031 |
" <td>2</td>\n", |
|
|
1032 |
" <td>4</td>\n", |
|
|
1033 |
" <td>1</td>\n", |
|
|
1034 |
" <td>4</td>\n", |
|
|
1035 |
" <td>2</td>\n", |
|
|
1036 |
" <td>4</td>\n", |
|
|
1037 |
" <td>2</td>\n", |
|
|
1038 |
" <td>3</td>\n", |
|
|
1039 |
" <td>3</td>\n", |
|
|
1040 |
" </tr>\n", |
|
|
1041 |
" </tbody>\n", |
|
|
1042 |
"</table>\n", |
|
|
1043 |
"<p>4 rows × 25 columns</p>\n", |
|
|
1044 |
"</div>" |
|
|
1045 |
], |
|
|
1046 |
"text/plain": [ |
|
|
1047 |
" patient_id age gender air_pollution alcohol_use dust_allergy \\\n", |
|
|
1048 |
"0 P1 33 1 2 4 5 \n", |
|
|
1049 |
"1 P10 17 1 3 1 5 \n", |
|
|
1050 |
"2 P107 44 1 6 7 7 \n", |
|
|
1051 |
"3 P189 39 2 6 8 7 \n", |
|
|
1052 |
"\n", |
|
|
1053 |
" occupational_hazards genetic_risk chronic_lung_disease balanced_diet \\\n", |
|
|
1054 |
"0 4 3 2 2 \n", |
|
|
1055 |
"1 3 4 2 2 \n", |
|
|
1056 |
"2 7 7 6 7 \n", |
|
|
1057 |
"3 7 7 6 7 \n", |
|
|
1058 |
"\n", |
|
|
1059 |
" ... fatigue weight_loss shortness_of_breath wheezing \\\n", |
|
|
1060 |
"0 ... 3 4 2 2 \n", |
|
|
1061 |
"1 ... 1 3 7 8 \n", |
|
|
1062 |
"2 ... 5 3 2 7 \n", |
|
|
1063 |
"3 ... 3 2 4 1 \n", |
|
|
1064 |
"\n", |
|
|
1065 |
" swallowing_difficulty clubbing_of_finger_nails frequent_cold dry_cough \\\n", |
|
|
1066 |
"0 3 1 2 3 \n", |
|
|
1067 |
"1 6 2 1 7 \n", |
|
|
1068 |
"2 8 2 4 5 \n", |
|
|
1069 |
"3 4 2 4 2 \n", |
|
|
1070 |
"\n", |
|
|
1071 |
" snoring level \n", |
|
|
1072 |
"0 4 1 \n", |
|
|
1073 |
"1 2 2 \n", |
|
|
1074 |
"2 3 3 \n", |
|
|
1075 |
"3 3 3 \n", |
|
|
1076 |
"\n", |
|
|
1077 |
"[4 rows x 25 columns]" |
|
|
1078 |
] |
|
|
1079 |
}, |
|
|
1080 |
"execution_count": 9, |
|
|
1081 |
"metadata": {}, |
|
|
1082 |
"output_type": "execute_result" |
|
|
1083 |
} |
|
|
1084 |
], |
|
|
1085 |
"source": [ |
|
|
1086 |
"def data_cleaning(data):\n", |
|
|
1087 |
" LUNG_CANCER[\"age\"]=data[\"age\"].fillna(LUNG_CANCER[\"age\"].median())\n", |
|
|
1088 |
" \n", |
|
|
1089 |
" \n", |
|
|
1090 |
" LUNG_CANCER.loc[data[\"level\"]==\"Low\",\"level\"]=1\n", |
|
|
1091 |
" LUNG_CANCER.loc[data[\"level\"]==\"Medium\",\"level\"]=2\n", |
|
|
1092 |
" LUNG_CANCER.loc[data[\"level\"]==\"High\",\"level\"]=3\n", |
|
|
1093 |
" \n", |
|
|
1094 |
" return data\n", |
|
|
1095 |
"\n", |
|
|
1096 |
"LUNG_CANCER=data_cleaning(LUNG_CANCER)\n", |
|
|
1097 |
"LUNG_CANCER.head(4)" |
|
|
1098 |
] |
|
|
1099 |
}, |
|
|
1100 |
{ |
|
|
1101 |
"cell_type": "code", |
|
|
1102 |
"execution_count": 10, |
|
|
1103 |
"metadata": {}, |
|
|
1104 |
"outputs": [ |
|
|
1105 |
{ |
|
|
1106 |
"data": { |
|
|
1107 |
"text/html": [ |
|
|
1108 |
"<div>\n", |
|
|
1109 |
"<style scoped>\n", |
|
|
1110 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1111 |
" vertical-align: middle;\n", |
|
|
1112 |
" }\n", |
|
|
1113 |
"\n", |
|
|
1114 |
" .dataframe tbody tr th {\n", |
|
|
1115 |
" vertical-align: top;\n", |
|
|
1116 |
" }\n", |
|
|
1117 |
"\n", |
|
|
1118 |
" .dataframe thead th {\n", |
|
|
1119 |
" text-align: right;\n", |
|
|
1120 |
" }\n", |
|
|
1121 |
"</style>\n", |
|
|
1122 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1123 |
" <thead>\n", |
|
|
1124 |
" <tr style=\"text-align: right;\">\n", |
|
|
1125 |
" <th></th>\n", |
|
|
1126 |
" <th>patient_id</th>\n", |
|
|
1127 |
" <th>age</th>\n", |
|
|
1128 |
" <th>gender</th>\n", |
|
|
1129 |
" <th>air_pollution</th>\n", |
|
|
1130 |
" <th>alcohol_use</th>\n", |
|
|
1131 |
" <th>dust_allergy</th>\n", |
|
|
1132 |
" <th>occupational_hazards</th>\n", |
|
|
1133 |
" <th>genetic_risk</th>\n", |
|
|
1134 |
" <th>chronic_lung_disease</th>\n", |
|
|
1135 |
" <th>balanced_diet</th>\n", |
|
|
1136 |
" <th>...</th>\n", |
|
|
1137 |
" <th>weight_loss</th>\n", |
|
|
1138 |
" <th>shortness_of_breath</th>\n", |
|
|
1139 |
" <th>wheezing</th>\n", |
|
|
1140 |
" <th>swallowing_difficulty</th>\n", |
|
|
1141 |
" <th>clubbing_of_finger_nails</th>\n", |
|
|
1142 |
" <th>frequent_cold</th>\n", |
|
|
1143 |
" <th>dry_cough</th>\n", |
|
|
1144 |
" <th>snoring</th>\n", |
|
|
1145 |
" <th>level</th>\n", |
|
|
1146 |
" <th>intercept</th>\n", |
|
|
1147 |
" </tr>\n", |
|
|
1148 |
" </thead>\n", |
|
|
1149 |
" <tbody>\n", |
|
|
1150 |
" <tr>\n", |
|
|
1151 |
" <th>0</th>\n", |
|
|
1152 |
" <td>P1</td>\n", |
|
|
1153 |
" <td>33</td>\n", |
|
|
1154 |
" <td>1</td>\n", |
|
|
1155 |
" <td>2</td>\n", |
|
|
1156 |
" <td>4</td>\n", |
|
|
1157 |
" <td>5</td>\n", |
|
|
1158 |
" <td>4</td>\n", |
|
|
1159 |
" <td>3</td>\n", |
|
|
1160 |
" <td>2</td>\n", |
|
|
1161 |
" <td>2</td>\n", |
|
|
1162 |
" <td>...</td>\n", |
|
|
1163 |
" <td>4</td>\n", |
|
|
1164 |
" <td>2</td>\n", |
|
|
1165 |
" <td>2</td>\n", |
|
|
1166 |
" <td>3</td>\n", |
|
|
1167 |
" <td>1</td>\n", |
|
|
1168 |
" <td>2</td>\n", |
|
|
1169 |
" <td>3</td>\n", |
|
|
1170 |
" <td>4</td>\n", |
|
|
1171 |
" <td>1</td>\n", |
|
|
1172 |
" <td>1.0</td>\n", |
|
|
1173 |
" </tr>\n", |
|
|
1174 |
" <tr>\n", |
|
|
1175 |
" <th>1</th>\n", |
|
|
1176 |
" <td>P10</td>\n", |
|
|
1177 |
" <td>17</td>\n", |
|
|
1178 |
" <td>1</td>\n", |
|
|
1179 |
" <td>3</td>\n", |
|
|
1180 |
" <td>1</td>\n", |
|
|
1181 |
" <td>5</td>\n", |
|
|
1182 |
" <td>3</td>\n", |
|
|
1183 |
" <td>4</td>\n", |
|
|
1184 |
" <td>2</td>\n", |
|
|
1185 |
" <td>2</td>\n", |
|
|
1186 |
" <td>...</td>\n", |
|
|
1187 |
" <td>3</td>\n", |
|
|
1188 |
" <td>7</td>\n", |
|
|
1189 |
" <td>8</td>\n", |
|
|
1190 |
" <td>6</td>\n", |
|
|
1191 |
" <td>2</td>\n", |
|
|
1192 |
" <td>1</td>\n", |
|
|
1193 |
" <td>7</td>\n", |
|
|
1194 |
" <td>2</td>\n", |
|
|
1195 |
" <td>2</td>\n", |
|
|
1196 |
" <td>1.0</td>\n", |
|
|
1197 |
" </tr>\n", |
|
|
1198 |
" <tr>\n", |
|
|
1199 |
" <th>2</th>\n", |
|
|
1200 |
" <td>P107</td>\n", |
|
|
1201 |
" <td>44</td>\n", |
|
|
1202 |
" <td>1</td>\n", |
|
|
1203 |
" <td>6</td>\n", |
|
|
1204 |
" <td>7</td>\n", |
|
|
1205 |
" <td>7</td>\n", |
|
|
1206 |
" <td>7</td>\n", |
|
|
1207 |
" <td>7</td>\n", |
|
|
1208 |
" <td>6</td>\n", |
|
|
1209 |
" <td>7</td>\n", |
|
|
1210 |
" <td>...</td>\n", |
|
|
1211 |
" <td>3</td>\n", |
|
|
1212 |
" <td>2</td>\n", |
|
|
1213 |
" <td>7</td>\n", |
|
|
1214 |
" <td>8</td>\n", |
|
|
1215 |
" <td>2</td>\n", |
|
|
1216 |
" <td>4</td>\n", |
|
|
1217 |
" <td>5</td>\n", |
|
|
1218 |
" <td>3</td>\n", |
|
|
1219 |
" <td>3</td>\n", |
|
|
1220 |
" <td>1.0</td>\n", |
|
|
1221 |
" </tr>\n", |
|
|
1222 |
" <tr>\n", |
|
|
1223 |
" <th>3</th>\n", |
|
|
1224 |
" <td>P189</td>\n", |
|
|
1225 |
" <td>39</td>\n", |
|
|
1226 |
" <td>2</td>\n", |
|
|
1227 |
" <td>6</td>\n", |
|
|
1228 |
" <td>8</td>\n", |
|
|
1229 |
" <td>7</td>\n", |
|
|
1230 |
" <td>7</td>\n", |
|
|
1231 |
" <td>7</td>\n", |
|
|
1232 |
" <td>6</td>\n", |
|
|
1233 |
" <td>7</td>\n", |
|
|
1234 |
" <td>...</td>\n", |
|
|
1235 |
" <td>2</td>\n", |
|
|
1236 |
" <td>4</td>\n", |
|
|
1237 |
" <td>1</td>\n", |
|
|
1238 |
" <td>4</td>\n", |
|
|
1239 |
" <td>2</td>\n", |
|
|
1240 |
" <td>4</td>\n", |
|
|
1241 |
" <td>2</td>\n", |
|
|
1242 |
" <td>3</td>\n", |
|
|
1243 |
" <td>3</td>\n", |
|
|
1244 |
" <td>1.0</td>\n", |
|
|
1245 |
" </tr>\n", |
|
|
1246 |
" </tbody>\n", |
|
|
1247 |
"</table>\n", |
|
|
1248 |
"<p>4 rows × 26 columns</p>\n", |
|
|
1249 |
"</div>" |
|
|
1250 |
], |
|
|
1251 |
"text/plain": [ |
|
|
1252 |
" patient_id age gender air_pollution alcohol_use dust_allergy \\\n", |
|
|
1253 |
"0 P1 33 1 2 4 5 \n", |
|
|
1254 |
"1 P10 17 1 3 1 5 \n", |
|
|
1255 |
"2 P107 44 1 6 7 7 \n", |
|
|
1256 |
"3 P189 39 2 6 8 7 \n", |
|
|
1257 |
"\n", |
|
|
1258 |
" occupational_hazards genetic_risk chronic_lung_disease balanced_diet \\\n", |
|
|
1259 |
"0 4 3 2 2 \n", |
|
|
1260 |
"1 3 4 2 2 \n", |
|
|
1261 |
"2 7 7 6 7 \n", |
|
|
1262 |
"3 7 7 6 7 \n", |
|
|
1263 |
"\n", |
|
|
1264 |
" ... weight_loss shortness_of_breath wheezing \\\n", |
|
|
1265 |
"0 ... 4 2 2 \n", |
|
|
1266 |
"1 ... 3 7 8 \n", |
|
|
1267 |
"2 ... 3 2 7 \n", |
|
|
1268 |
"3 ... 2 4 1 \n", |
|
|
1269 |
"\n", |
|
|
1270 |
" swallowing_difficulty clubbing_of_finger_nails frequent_cold dry_cough \\\n", |
|
|
1271 |
"0 3 1 2 3 \n", |
|
|
1272 |
"1 6 2 1 7 \n", |
|
|
1273 |
"2 8 2 4 5 \n", |
|
|
1274 |
"3 4 2 4 2 \n", |
|
|
1275 |
"\n", |
|
|
1276 |
" snoring level intercept \n", |
|
|
1277 |
"0 4 1 1.0 \n", |
|
|
1278 |
"1 2 2 1.0 \n", |
|
|
1279 |
"2 3 3 1.0 \n", |
|
|
1280 |
"3 3 3 1.0 \n", |
|
|
1281 |
"\n", |
|
|
1282 |
"[4 rows x 26 columns]" |
|
|
1283 |
] |
|
|
1284 |
}, |
|
|
1285 |
"execution_count": 10, |
|
|
1286 |
"metadata": {}, |
|
|
1287 |
"output_type": "execute_result" |
|
|
1288 |
} |
|
|
1289 |
], |
|
|
1290 |
"source": [ |
|
|
1291 |
"## now lets add the intercept\n", |
|
|
1292 |
"\n", |
|
|
1293 |
"LUNG_CANCER['intercept'] = 1.0\n", |
|
|
1294 |
"\n", |
|
|
1295 |
"## we have a dataset that is ready for analysis\n", |
|
|
1296 |
"LUNG_CANCER.head(4)" |
|
|
1297 |
] |
|
|
1298 |
}, |
|
|
1299 |
{ |
|
|
1300 |
"cell_type": "code", |
|
|
1301 |
"execution_count": 11, |
|
|
1302 |
"metadata": {}, |
|
|
1303 |
"outputs": [ |
|
|
1304 |
{ |
|
|
1305 |
"name": "stdout", |
|
|
1306 |
"output_type": "stream", |
|
|
1307 |
"text": [ |
|
|
1308 |
"(1000, 17) (1000,)\n", |
|
|
1309 |
"(700, 17) (700,)\n", |
|
|
1310 |
"(300, 17) (300,)\n" |
|
|
1311 |
] |
|
|
1312 |
}, |
|
|
1313 |
{ |
|
|
1314 |
"name": "stderr", |
|
|
1315 |
"output_type": "stream", |
|
|
1316 |
"text": [ |
|
|
1317 |
"C:\\Users\\Lina\\Anaconda3\\lib\\site-packages\\sklearn\\cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n", |
|
|
1318 |
" \"This module will be removed in 0.20.\", DeprecationWarning)\n" |
|
|
1319 |
] |
|
|
1320 |
} |
|
|
1321 |
], |
|
|
1322 |
"source": [ |
|
|
1323 |
"'''Define y and X'''\n", |
|
|
1324 |
"y = LUNG_CANCER['level'] \n", |
|
|
1325 |
"columns_ = LUNG_CANCER.columns.tolist()\n", |
|
|
1326 |
"exclude_col = ['level','patient_id','alcohol_use','dust_allergy','occupational_hazards','balanced_diet','obesity','snoring','frequent_cold']\n", |
|
|
1327 |
"X = LUNG_CANCER[[i for i in columns_ if i not in exclude_col]]\n", |
|
|
1328 |
"X = st.add_constant(X, prepend = False) \n", |
|
|
1329 |
"print (X.shape, y.shape)\n", |
|
|
1330 |
"\n", |
|
|
1331 |
"'''Split the data'''\n", |
|
|
1332 |
"from sklearn.cross_validation import train_test_split\n", |
|
|
1333 |
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=40)\n", |
|
|
1334 |
"\n", |
|
|
1335 |
"print (X_train.shape, y_train.shape)\n", |
|
|
1336 |
"print (X_test.shape, y_test.shape)" |
|
|
1337 |
] |
|
|
1338 |
}, |
|
|
1339 |
{ |
|
|
1340 |
"cell_type": "code", |
|
|
1341 |
"execution_count": 12, |
|
|
1342 |
"metadata": {}, |
|
|
1343 |
"outputs": [ |
|
|
1344 |
{ |
|
|
1345 |
"data": { |
|
|
1346 |
"text/plain": [ |
|
|
1347 |
"Index(['patient_id', 'age', 'gender', 'air_pollution', 'alcohol_use',\n", |
|
|
1348 |
" 'dust_allergy', 'occupational_hazards', 'genetic_risk',\n", |
|
|
1349 |
" 'chronic_lung_disease', 'balanced_diet', 'obesity', 'smoking',\n", |
|
|
1350 |
" 'passive_smoker', 'chest_pain', 'coughing_of_blood', 'fatigue',\n", |
|
|
1351 |
" 'weight_loss', 'shortness_of_breath', 'wheezing',\n", |
|
|
1352 |
" 'swallowing_difficulty', 'clubbing_of_finger_nails', 'frequent_cold',\n", |
|
|
1353 |
" 'dry_cough', 'snoring', 'level', 'intercept'],\n", |
|
|
1354 |
" dtype='object')" |
|
|
1355 |
] |
|
|
1356 |
}, |
|
|
1357 |
"execution_count": 12, |
|
|
1358 |
"metadata": {}, |
|
|
1359 |
"output_type": "execute_result" |
|
|
1360 |
} |
|
|
1361 |
], |
|
|
1362 |
"source": [ |
|
|
1363 |
"LUNG_CANCER.columns" |
|
|
1364 |
] |
|
|
1365 |
}, |
|
|
1366 |
{ |
|
|
1367 |
"cell_type": "code", |
|
|
1368 |
"execution_count": 13, |
|
|
1369 |
"metadata": {}, |
|
|
1370 |
"outputs": [ |
|
|
1371 |
{ |
|
|
1372 |
"data": { |
|
|
1373 |
"text/plain": [ |
|
|
1374 |
"array([[-3.17685199e-02, 1.47464418e-01, 1.91315555e-01,\n", |
|
|
1375 |
" -1.07116609e+00, 3.29164839e-02, 6.86628736e-02,\n", |
|
|
1376 |
" -1.37516216e+00, 7.06189546e-01, -1.28525724e+00,\n", |
|
|
1377 |
" -1.53738658e+00, 1.03157677e-01, -3.54326295e-01,\n", |
|
|
1378 |
" -9.39638735e-01, -7.18157437e-01, -1.24079736e+00,\n", |
|
|
1379 |
" -4.89756753e-01, 2.93152389e-06],\n", |
|
|
1380 |
" [ 3.66812895e-02, -2.78637530e-01, -5.08674811e-01,\n", |
|
|
1381 |
" 6.64688514e-01, -4.37367788e-01, -2.12402217e-01,\n", |
|
|
1382 |
" 1.47896467e-01, -7.19789255e-01, 2.09123966e-02,\n", |
|
|
1383 |
" 3.45001892e-01, -5.25706903e-01, -2.19421558e-01,\n", |
|
|
1384 |
" 7.03518991e-01, 1.15699818e-02, 6.00934480e-01,\n", |
|
|
1385 |
" 2.57988306e-02, 1.51172633e-08],\n", |
|
|
1386 |
" [-4.91276964e-03, 1.31173112e-01, 3.17359256e-01,\n", |
|
|
1387 |
" 4.06477580e-01, 4.04451304e-01, 1.43739344e-01,\n", |
|
|
1388 |
" 1.22726570e+00, 1.35997095e-02, 1.26434485e+00,\n", |
|
|
1389 |
" 1.19238469e+00, 4.22549226e-01, 5.73747853e-01,\n", |
|
|
1390 |
" 2.36119744e-01, 7.06587455e-01, 6.39862879e-01,\n", |
|
|
1391 |
" 4.63957923e-01, -2.94664117e-06]])" |
|
|
1392 |
] |
|
|
1393 |
}, |
|
|
1394 |
"execution_count": 13, |
|
|
1395 |
"metadata": {}, |
|
|
1396 |
"output_type": "execute_result" |
|
|
1397 |
} |
|
|
1398 |
], |
|
|
1399 |
"source": [ |
|
|
1400 |
"## Set up the regression\n", |
|
|
1401 |
"\n", |
|
|
1402 |
"mul_lr = LogisticRegression(multi_class='multinomial',solver ='newton-cg').fit(X_train,y_train)\n", |
|
|
1403 |
"\n", |
|
|
1404 |
"## lets get the results\n", |
|
|
1405 |
"mul_lr.intercept_\n", |
|
|
1406 |
"mul_lr.coef_" |
|
|
1407 |
] |
|
|
1408 |
}, |
|
|
1409 |
{ |
|
|
1410 |
"cell_type": "code", |
|
|
1411 |
"execution_count": 14, |
|
|
1412 |
"metadata": {}, |
|
|
1413 |
"outputs": [ |
|
|
1414 |
{ |
|
|
1415 |
"name": "stdout", |
|
|
1416 |
"output_type": "stream", |
|
|
1417 |
"text": [ |
|
|
1418 |
"Warning: Maximum number of iterations has been exceeded.\n", |
|
|
1419 |
" Current function value: 0.097334\n", |
|
|
1420 |
" Iterations: 35\n", |
|
|
1421 |
" Function evaluations: 38\n", |
|
|
1422 |
" Gradient evaluations: 38\n", |
|
|
1423 |
" MNLogit Regression Results \n", |
|
|
1424 |
"==============================================================================\n", |
|
|
1425 |
"Dep. Variable: level No. Observations: 700\n", |
|
|
1426 |
"Model: MNLogit Df Residuals: 666\n", |
|
|
1427 |
"Method: MLE Df Model: 32\n", |
|
|
1428 |
"Date: Tue, 04 Dec 2018 Pseudo R-squ.: 0.9112\n", |
|
|
1429 |
"Time: 20:33:12 Log-Likelihood: -68.134\n", |
|
|
1430 |
"converged: False LL-Null: -767.63\n", |
|
|
1431 |
" LLR p-value: 5.963e-274\n", |
|
|
1432 |
"============================================================================================\n", |
|
|
1433 |
" level=2 coef std err z P>|z| [0.025 0.975]\n", |
|
|
1434 |
"--------------------------------------------------------------------------------------------\n", |
|
|
1435 |
"age -0.1031 0.060 -1.728 0.084 -0.220 0.014\n", |
|
|
1436 |
"gender -10.9784 3.356 -3.271 0.001 -17.556 -4.400\n", |
|
|
1437 |
"air_pollution -2.6913 1.131 -2.379 0.017 -4.908 -0.474\n", |
|
|
1438 |
"genetic_risk 5.0468 1.404 3.594 0.000 2.295 7.799\n", |
|
|
1439 |
"chronic_lung_disease -2.7845 0.910 -3.059 0.002 -4.569 -1.000\n", |
|
|
1440 |
"smoking -0.9366 0.569 -1.647 0.099 -2.051 0.178\n", |
|
|
1441 |
"passive_smoker 1.4782 0.672 2.200 0.028 0.162 2.795\n", |
|
|
1442 |
"chest_pain -0.8705 0.682 -1.276 0.202 -2.208 0.467\n", |
|
|
1443 |
"coughing_of_blood 0.0447 0.545 0.082 0.935 -1.024 1.113\n", |
|
|
1444 |
"fatigue 5.8949 1.561 3.775 0.000 2.835 8.955\n", |
|
|
1445 |
"weight_loss -1.6336 0.832 -1.964 0.050 -3.264 -0.003\n", |
|
|
1446 |
"shortness_of_breath -0.0884 0.551 -0.160 0.873 -1.169 0.992\n", |
|
|
1447 |
"wheezing 0.6777 0.877 0.773 0.440 -1.041 2.397\n", |
|
|
1448 |
"swallowing_difficulty 0.5567 0.668 0.834 0.405 -0.752 1.866\n", |
|
|
1449 |
"clubbing_of_finger_nails 3.7198 1.152 3.229 0.001 1.462 5.978\n", |
|
|
1450 |
"dry_cough -0.6692 0.579 -1.156 0.248 -1.804 0.465\n", |
|
|
1451 |
"intercept -5.1110 2.439 -2.096 0.036 -9.891 -0.331\n", |
|
|
1452 |
"--------------------------------------------------------------------------------------------\n", |
|
|
1453 |
" level=3 coef std err z P>|z| [0.025 0.975]\n", |
|
|
1454 |
"--------------------------------------------------------------------------------------------\n", |
|
|
1455 |
"age -1.0151 0.427 -2.379 0.017 -1.851 -0.179\n", |
|
|
1456 |
"gender -12.5765 3.659 -3.437 0.001 -19.749 -5.404\n", |
|
|
1457 |
"air_pollution 1.4011 1.765 0.794 0.427 -2.059 4.861\n", |
|
|
1458 |
"genetic_risk 4.5602 4.878 0.935 0.350 -5.000 14.121\n", |
|
|
1459 |
"chronic_lung_disease 0.0066 3.619 0.002 0.999 -7.087 7.100\n", |
|
|
1460 |
"smoking -3.5495 1.631 -2.177 0.030 -6.746 -0.353\n", |
|
|
1461 |
"passive_smoker 11.2581 3.068 3.669 0.000 5.245 17.271\n", |
|
|
1462 |
"chest_pain -4.3841 3.281 -1.336 0.182 -10.815 2.047\n", |
|
|
1463 |
"coughing_of_blood 1.3247 3.298 0.402 0.688 -5.140 7.789\n", |
|
|
1464 |
"fatigue 7.5920 1.937 3.919 0.000 3.795 11.389\n", |
|
|
1465 |
"weight_loss -1.4729 2.535 -0.581 0.561 -6.441 3.495\n", |
|
|
1466 |
"shortness_of_breath 3.0151 1.000 3.016 0.003 1.056 4.975\n", |
|
|
1467 |
"wheezing -3.7620 1.886 -1.994 0.046 -7.459 -0.065\n", |
|
|
1468 |
"swallowing_difficulty 0.1687 0.817 0.206 0.836 -1.433 1.771\n", |
|
|
1469 |
"clubbing_of_finger_nails 0.6814 2.566 0.266 0.791 -4.348 5.710\n", |
|
|
1470 |
"dry_cough -1.6649 1.083 -1.537 0.124 -3.788 0.458\n", |
|
|
1471 |
"intercept -10.5903 3.496 -3.029 0.002 -17.442 -3.738\n", |
|
|
1472 |
"============================================================================================\n" |
|
|
1473 |
] |
|
|
1474 |
}, |
|
|
1475 |
{ |
|
|
1476 |
"name": "stderr", |
|
|
1477 |
"output_type": "stream", |
|
|
1478 |
"text": [ |
|
|
1479 |
"C:\\Users\\Lina\\Anaconda3\\lib\\site-packages\\statsmodels\\base\\model.py:508: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n", |
|
|
1480 |
" \"Check mle_retvals\", ConvergenceWarning)\n" |
|
|
1481 |
] |
|
|
1482 |
} |
|
|
1483 |
], |
|
|
1484 |
"source": [ |
|
|
1485 |
"## Set up the regression\n", |
|
|
1486 |
"\n", |
|
|
1487 |
"logit = sm.MNLogit(y_train, X_train)\n", |
|
|
1488 |
"logit_result = logit.fit(method='bfgs')\n", |
|
|
1489 |
"\n", |
|
|
1490 |
"## lets get the results\n", |
|
|
1491 |
"print(logit_result.summary())" |
|
|
1492 |
] |
|
|
1493 |
}, |
|
|
1494 |
{ |
|
|
1495 |
"cell_type": "code", |
|
|
1496 |
"execution_count": 15, |
|
|
1497 |
"metadata": {}, |
|
|
1498 |
"outputs": [ |
|
|
1499 |
{ |
|
|
1500 |
"name": "stdout", |
|
|
1501 |
"output_type": "stream", |
|
|
1502 |
"text": [ |
|
|
1503 |
"Coeffieients\n", |
|
|
1504 |
" 0 1\n", |
|
|
1505 |
"age -0.103143 -1.015068\n", |
|
|
1506 |
"gender -10.978373 -12.576457\n", |
|
|
1507 |
"air_pollution -2.691276 1.401134\n", |
|
|
1508 |
"genetic_risk 5.046776 4.560153\n", |
|
|
1509 |
"chronic_lung_disease -2.784542 0.006603\n", |
|
|
1510 |
"smoking -0.936573 -3.549460\n", |
|
|
1511 |
"passive_smoker 1.478245 11.258127\n", |
|
|
1512 |
"chest_pain -0.870475 -4.384082\n", |
|
|
1513 |
"coughing_of_blood 0.044676 1.324661\n", |
|
|
1514 |
"fatigue 5.894866 7.592025\n", |
|
|
1515 |
"weight_loss -1.633568 -1.472910\n", |
|
|
1516 |
"shortness_of_breath -0.088386 3.015135\n", |
|
|
1517 |
"wheezing 0.677735 -3.762030\n", |
|
|
1518 |
"swallowing_difficulty 0.556677 0.168725\n", |
|
|
1519 |
"clubbing_of_finger_nails 3.719845 0.681413\n", |
|
|
1520 |
"dry_cough -0.669196 -1.664935\n", |
|
|
1521 |
"intercept -5.111022 -10.590282\n", |
|
|
1522 |
"\n", |
|
|
1523 |
"\n", |
|
|
1524 |
"p-Values\n", |
|
|
1525 |
" 0 1\n", |
|
|
1526 |
"age 0.083975 0.017339\n", |
|
|
1527 |
"gender 0.001071 0.000589\n", |
|
|
1528 |
"air_pollution 0.017339 0.427364\n", |
|
|
1529 |
"genetic_risk 0.000325 0.349867\n", |
|
|
1530 |
"chronic_lung_disease 0.002224 0.998544\n", |
|
|
1531 |
"smoking 0.099470 0.029504\n", |
|
|
1532 |
"passive_smoker 0.027775 0.000243\n", |
|
|
1533 |
"chest_pain 0.201996 0.181521\n", |
|
|
1534 |
"coughing_of_blood 0.934670 0.687977\n", |
|
|
1535 |
"fatigue 0.000160 0.000089\n", |
|
|
1536 |
"weight_loss 0.049567 0.561152\n", |
|
|
1537 |
"shortness_of_breath 0.872586 0.002563\n", |
|
|
1538 |
"wheezing 0.439681 0.046131\n", |
|
|
1539 |
"swallowing_difficulty 0.404531 0.836471\n", |
|
|
1540 |
"clubbing_of_finger_nails 0.001242 0.790572\n", |
|
|
1541 |
"dry_cough 0.247558 0.124328\n", |
|
|
1542 |
"intercept 0.036120 0.002451\n", |
|
|
1543 |
"\n", |
|
|
1544 |
"\n", |
|
|
1545 |
"Dependent variables\n", |
|
|
1546 |
"level\n" |
|
|
1547 |
] |
|
|
1548 |
} |
|
|
1549 |
], |
|
|
1550 |
"source": [ |
|
|
1551 |
"print(\"Coeffieients\")\n", |
|
|
1552 |
"print(logit_result.params)\n", |
|
|
1553 |
"print (\"\\n\")\n", |
|
|
1554 |
"print(\"p-Values\")\n", |
|
|
1555 |
"print(logit_result.pvalues)\n", |
|
|
1556 |
"print (\"\\n\")\n", |
|
|
1557 |
"print(\"Dependent variables\")\n", |
|
|
1558 |
"print(logit.endog_names)" |
|
|
1559 |
] |
|
|
1560 |
}, |
|
|
1561 |
{ |
|
|
1562 |
"cell_type": "markdown", |
|
|
1563 |
"metadata": {}, |
|
|
1564 |
"source": [ |
|
|
1565 |
"## Interpreting logistic regression coefficients.\n", |
|
|
1566 |
"In this case, using the odds ratio will help us understand how 1 unit of increase or decrease in any of the variables affects the odds of being admitted." |
|
|
1567 |
] |
|
|
1568 |
}, |
|
|
1569 |
{ |
|
|
1570 |
"cell_type": "code", |
|
|
1571 |
"execution_count": 57, |
|
|
1572 |
"metadata": {}, |
|
|
1573 |
"outputs": [ |
|
|
1574 |
{ |
|
|
1575 |
"name": "stdout", |
|
|
1576 |
"output_type": "stream", |
|
|
1577 |
"text": [ |
|
|
1578 |
" 0 1\n", |
|
|
1579 |
"age 0.901998 0.362378\n", |
|
|
1580 |
"gender 0.000017 0.000003\n", |
|
|
1581 |
"air_pollution 0.067794 4.059801\n", |
|
|
1582 |
"genetic_risk 155.520200 95.598101\n", |
|
|
1583 |
"chronic_lung_disease 0.061757 1.006625\n", |
|
|
1584 |
"smoking 0.391969 0.028740\n", |
|
|
1585 |
"passive_smoker 4.385243 77507.296804\n", |
|
|
1586 |
"chest_pain 0.418752 0.012474\n", |
|
|
1587 |
"coughing_of_blood 1.045689 3.760909\n", |
|
|
1588 |
"fatigue 363.168194 1982.323098\n", |
|
|
1589 |
"weight_loss 0.195232 0.229257\n", |
|
|
1590 |
"shortness_of_breath 0.915408 20.391840\n", |
|
|
1591 |
"wheezing 1.969412 0.023237\n", |
|
|
1592 |
"swallowing_difficulty 1.744865 1.183795\n", |
|
|
1593 |
"clubbing_of_finger_nails 41.257983 1.976668\n", |
|
|
1594 |
"dry_cough 0.512120 0.189203\n", |
|
|
1595 |
"intercept 0.006030 0.000025\n" |
|
|
1596 |
] |
|
|
1597 |
} |
|
|
1598 |
], |
|
|
1599 |
"source": [ |
|
|
1600 |
"print (np.exp(logit_result.params))" |
|
|
1601 |
] |
|
|
1602 |
}, |
|
|
1603 |
{ |
|
|
1604 |
"cell_type": "markdown", |
|
|
1605 |
"metadata": {}, |
|
|
1606 |
"source": [ |
|
|
1607 |
"These values are from our train set, now lets predict on our test set" |
|
|
1608 |
] |
|
|
1609 |
}, |
|
|
1610 |
{ |
|
|
1611 |
"cell_type": "markdown", |
|
|
1612 |
"metadata": {}, |
|
|
1613 |
"source": [ |
|
|
1614 |
"<span style=\"color:red\">Please explain more about the coefficients and p-values and what they mean, e.g. which features are most important? which has a higher influence on each level based on coefficients?</span>" |
|
|
1615 |
] |
|
|
1616 |
}, |
|
|
1617 |
{ |
|
|
1618 |
"cell_type": "markdown", |
|
|
1619 |
"metadata": {}, |
|
|
1620 |
"source": [ |
|
|
1621 |
"## Predicting and Evaluating\n", |
|
|
1622 |
"If we call the predict method, we will get the predictive probabilities. But to make a prediction if a patient has a Low, Medium, High Lung cancer we must convert these predicted probabilities into class labels 0=Low or 1 = Medium or 2=High. " |
|
|
1623 |
] |
|
|
1624 |
}, |
|
|
1625 |
{ |
|
|
1626 |
"cell_type": "code", |
|
|
1627 |
"execution_count": 58, |
|
|
1628 |
"metadata": {}, |
|
|
1629 |
"outputs": [ |
|
|
1630 |
{ |
|
|
1631 |
"name": "stdout", |
|
|
1632 |
"output_type": "stream", |
|
|
1633 |
"text": [ |
|
|
1634 |
" 0 1 2\n", |
|
|
1635 |
"204 9.739892e-01 2.601079e-02 5.988912e-25\n", |
|
|
1636 |
"71 9.941086e-01 3.641338e-12 5.891434e-03\n", |
|
|
1637 |
"594 4.357147e-09 1.000000e+00 1.202880e-27\n", |
|
|
1638 |
"672 9.685383e-01 8.177787e-05 3.137988e-02\n", |
|
|
1639 |
"14 3.378482e-20 6.732186e-23 1.000000e+00\n", |
|
|
1640 |
"64 9.966876e-01 3.312377e-03 1.929552e-26\n", |
|
|
1641 |
"340 1.792525e-06 9.999982e-01 2.440023e-22\n", |
|
|
1642 |
"135 2.908870e-06 3.631127e-06 9.999935e-01\n", |
|
|
1643 |
"350 1.321207e-03 9.986788e-01 1.271600e-26\n", |
|
|
1644 |
"976 6.893179e-18 2.766205e-23 1.000000e+00\n" |
|
|
1645 |
] |
|
|
1646 |
} |
|
|
1647 |
], |
|
|
1648 |
"source": [ |
|
|
1649 |
"## Here we have the predictive probabilities\n", |
|
|
1650 |
"predictions = logit_result.predict(X_test)\n", |
|
|
1651 |
"print(predictions[:10])" |
|
|
1652 |
] |
|
|
1653 |
}, |
|
|
1654 |
{ |
|
|
1655 |
"cell_type": "code", |
|
|
1656 |
"execution_count": 60, |
|
|
1657 |
"metadata": {}, |
|
|
1658 |
"outputs": [ |
|
|
1659 |
{ |
|
|
1660 |
"data": { |
|
|
1661 |
"image/png": "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\n", |
|
|
1662 |
"text/plain": [ |
|
|
1663 |
"<Figure size 432x288 with 1 Axes>" |
|
|
1664 |
] |
|
|
1665 |
}, |
|
|
1666 |
"metadata": {}, |
|
|
1667 |
"output_type": "display_data" |
|
|
1668 |
} |
|
|
1669 |
], |
|
|
1670 |
"source": [ |
|
|
1671 |
"plt.hist(predictions);" |
|
|
1672 |
] |
|
|
1673 |
}, |
|
|
1674 |
{ |
|
|
1675 |
"cell_type": "markdown", |
|
|
1676 |
"metadata": {}, |
|
|
1677 |
"source": [ |
|
|
1678 |
"### Confusion matrix and Classification report\n", |
|
|
1679 |
"---" |
|
|
1680 |
] |
|
|
1681 |
}, |
|
|
1682 |
{ |
|
|
1683 |
"cell_type": "code", |
|
|
1684 |
"execution_count": 61, |
|
|
1685 |
"metadata": {}, |
|
|
1686 |
"outputs": [ |
|
|
1687 |
{ |
|
|
1688 |
"data": { |
|
|
1689 |
"text/plain": [ |
|
|
1690 |
"LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n", |
|
|
1691 |
" intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n", |
|
|
1692 |
" penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n", |
|
|
1693 |
" verbose=0, warm_start=False)" |
|
|
1694 |
] |
|
|
1695 |
}, |
|
|
1696 |
"execution_count": 61, |
|
|
1697 |
"metadata": {}, |
|
|
1698 |
"output_type": "execute_result" |
|
|
1699 |
} |
|
|
1700 |
], |
|
|
1701 |
"source": [ |
|
|
1702 |
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)\n", |
|
|
1703 |
"logreg = LogisticRegression()\n", |
|
|
1704 |
"logreg.fit(X_train, y_train)" |
|
|
1705 |
] |
|
|
1706 |
}, |
|
|
1707 |
{ |
|
|
1708 |
"cell_type": "code", |
|
|
1709 |
"execution_count": 62, |
|
|
1710 |
"metadata": {}, |
|
|
1711 |
"outputs": [ |
|
|
1712 |
{ |
|
|
1713 |
"name": "stdout", |
|
|
1714 |
"output_type": "stream", |
|
|
1715 |
"text": [ |
|
|
1716 |
"Accuracy of logistic regression classifier on test set: 0.97\n" |
|
|
1717 |
] |
|
|
1718 |
} |
|
|
1719 |
], |
|
|
1720 |
"source": [ |
|
|
1721 |
"y_pred = logreg.predict(X_test)\n", |
|
|
1722 |
"print('Accuracy of logistic regression classifier on test set: {:.2f}'.format(logreg.score(X_test, y_test)))" |
|
|
1723 |
] |
|
|
1724 |
}, |
|
|
1725 |
{ |
|
|
1726 |
"cell_type": "code", |
|
|
1727 |
"execution_count": 63, |
|
|
1728 |
"metadata": {}, |
|
|
1729 |
"outputs": [ |
|
|
1730 |
{ |
|
|
1731 |
"name": "stdout", |
|
|
1732 |
"output_type": "stream", |
|
|
1733 |
"text": [ |
|
|
1734 |
"length of oversampled data is 720\n", |
|
|
1735 |
"Number of no subscription in oversampled data 0\n", |
|
|
1736 |
"Number of subscription 240\n", |
|
|
1737 |
"Proportion of no subscription data in oversampled data is 0.0\n", |
|
|
1738 |
"Proportion of subscription data in oversampled data is 0.3333333333333333\n" |
|
|
1739 |
] |
|
|
1740 |
} |
|
|
1741 |
], |
|
|
1742 |
"source": [ |
|
|
1743 |
"from imblearn.over_sampling import SMOTE\n", |
|
|
1744 |
"columns = X_train.columns\n", |
|
|
1745 |
"os = SMOTE(random_state=0)\n", |
|
|
1746 |
"os_data_X,os_data_y=os.fit_sample(X_train, y_train)\n", |
|
|
1747 |
"os_data_X = pd.DataFrame(data=os_data_X,columns=columns )\n", |
|
|
1748 |
"os_data_y= pd.DataFrame(data=os_data_y,columns=['y'])\n", |
|
|
1749 |
"# we can Check the numbers of our data\n", |
|
|
1750 |
"print(\"length of oversampled data is \",len(os_data_X))\n", |
|
|
1751 |
"print(\"Number of no subscription in oversampled data\",len(os_data_y[os_data_y['y']==0]))\n", |
|
|
1752 |
"print(\"Number of subscription\",len(os_data_y[os_data_y['y']==1]))\n", |
|
|
1753 |
"print(\"Proportion of no subscription data in oversampled data is \",len(os_data_y[os_data_y['y']==0])/len(os_data_X))\n", |
|
|
1754 |
"print(\"Proportion of subscription data in oversampled data is \",len(os_data_y[os_data_y['y']==1])/len(os_data_X))" |
|
|
1755 |
] |
|
|
1756 |
}, |
|
|
1757 |
{ |
|
|
1758 |
"cell_type": "code", |
|
|
1759 |
"execution_count": 64, |
|
|
1760 |
"metadata": {}, |
|
|
1761 |
"outputs": [ |
|
|
1762 |
{ |
|
|
1763 |
"name": "stdout", |
|
|
1764 |
"output_type": "stream", |
|
|
1765 |
"text": [ |
|
|
1766 |
"[ True True True True True True True True True True True True\n", |
|
|
1767 |
" True True True True True]\n", |
|
|
1768 |
"[1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1]\n" |
|
|
1769 |
] |
|
|
1770 |
} |
|
|
1771 |
], |
|
|
1772 |
"source": [ |
|
|
1773 |
"from sklearn.feature_selection import RFE\n", |
|
|
1774 |
"logreg = LogisticRegression()\n", |
|
|
1775 |
"rfe = RFE(logreg, 20)\n", |
|
|
1776 |
"rfe = rfe.fit(os_data_X, os_data_y.values.ravel())\n", |
|
|
1777 |
"print(rfe.support_)\n", |
|
|
1778 |
"print(rfe.ranking_)" |
|
|
1779 |
] |
|
|
1780 |
}, |
|
|
1781 |
{ |
|
|
1782 |
"cell_type": "code", |
|
|
1783 |
"execution_count": 65, |
|
|
1784 |
"metadata": {}, |
|
|
1785 |
"outputs": [ |
|
|
1786 |
{ |
|
|
1787 |
"name": "stdout", |
|
|
1788 |
"output_type": "stream", |
|
|
1789 |
"text": [ |
|
|
1790 |
"[[ 76 0 0]\n", |
|
|
1791 |
" [ 4 83 5]\n", |
|
|
1792 |
" [ 0 0 132]]\n" |
|
|
1793 |
] |
|
|
1794 |
}, |
|
|
1795 |
{ |
|
|
1796 |
"data": { |
|
|
1797 |
"text/html": [ |
|
|
1798 |
"<div>\n", |
|
|
1799 |
"<style scoped>\n", |
|
|
1800 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1801 |
" vertical-align: middle;\n", |
|
|
1802 |
" }\n", |
|
|
1803 |
"\n", |
|
|
1804 |
" .dataframe tbody tr th {\n", |
|
|
1805 |
" vertical-align: top;\n", |
|
|
1806 |
" }\n", |
|
|
1807 |
"\n", |
|
|
1808 |
" .dataframe thead th {\n", |
|
|
1809 |
" text-align: right;\n", |
|
|
1810 |
" }\n", |
|
|
1811 |
"</style>\n", |
|
|
1812 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1813 |
" <thead>\n", |
|
|
1814 |
" <tr style=\"text-align: right;\">\n", |
|
|
1815 |
" <th></th>\n", |
|
|
1816 |
" <th>Predict_Label_0 Low</th>\n", |
|
|
1817 |
" <th>Predict_Label_1 Medium</th>\n", |
|
|
1818 |
" <th>Predict_Label_2 High</th>\n", |
|
|
1819 |
" </tr>\n", |
|
|
1820 |
" </thead>\n", |
|
|
1821 |
" <tbody>\n", |
|
|
1822 |
" <tr>\n", |
|
|
1823 |
" <th>True_Label_0 Low</th>\n", |
|
|
1824 |
" <td>76</td>\n", |
|
|
1825 |
" <td>0</td>\n", |
|
|
1826 |
" <td>0</td>\n", |
|
|
1827 |
" </tr>\n", |
|
|
1828 |
" <tr>\n", |
|
|
1829 |
" <th>True_Label_1 Medium</th>\n", |
|
|
1830 |
" <td>4</td>\n", |
|
|
1831 |
" <td>83</td>\n", |
|
|
1832 |
" <td>5</td>\n", |
|
|
1833 |
" </tr>\n", |
|
|
1834 |
" <tr>\n", |
|
|
1835 |
" <th>True_Label_2 High</th>\n", |
|
|
1836 |
" <td>0</td>\n", |
|
|
1837 |
" <td>0</td>\n", |
|
|
1838 |
" <td>132</td>\n", |
|
|
1839 |
" </tr>\n", |
|
|
1840 |
" </tbody>\n", |
|
|
1841 |
"</table>\n", |
|
|
1842 |
"</div>" |
|
|
1843 |
], |
|
|
1844 |
"text/plain": [ |
|
|
1845 |
" Predict_Label_0 Low Predict_Label_1 Medium \\\n", |
|
|
1846 |
"True_Label_0 Low 76 0 \n", |
|
|
1847 |
"True_Label_1 Medium 4 83 \n", |
|
|
1848 |
"True_Label_2 High 0 0 \n", |
|
|
1849 |
"\n", |
|
|
1850 |
" Predict_Label_2 High \n", |
|
|
1851 |
"True_Label_0 Low 0 \n", |
|
|
1852 |
"True_Label_1 Medium 5 \n", |
|
|
1853 |
"True_Label_2 High 132 " |
|
|
1854 |
] |
|
|
1855 |
}, |
|
|
1856 |
"execution_count": 65, |
|
|
1857 |
"metadata": {}, |
|
|
1858 |
"output_type": "execute_result" |
|
|
1859 |
} |
|
|
1860 |
], |
|
|
1861 |
"source": [ |
|
|
1862 |
"from sklearn.metrics import confusion_matrix\n", |
|
|
1863 |
"confusion_matrix = confusion_matrix(y_test, y_pred)\n", |
|
|
1864 |
"print(confusion_matrix)\n", |
|
|
1865 |
"confusion = pd.DataFrame(confusion_matrix,index=['True_Label_0 Low', 'True_Label_1 Medium','True_Label_2 High'],\n", |
|
|
1866 |
" columns=['Predict_Label_0 Low', 'Predict_Label_1 Medium','Predict_Label_2 High'])\n", |
|
|
1867 |
"\n", |
|
|
1868 |
"confusion" |
|
|
1869 |
] |
|
|
1870 |
}, |
|
|
1871 |
{ |
|
|
1872 |
"cell_type": "code", |
|
|
1873 |
"execution_count": 66, |
|
|
1874 |
"metadata": {}, |
|
|
1875 |
"outputs": [ |
|
|
1876 |
{ |
|
|
1877 |
"name": "stdout", |
|
|
1878 |
"output_type": "stream", |
|
|
1879 |
"text": [ |
|
|
1880 |
"[[ 40 0 0 0 0 0 0]\n", |
|
|
1881 |
" [121 91 0 0 0 0 0]\n", |
|
|
1882 |
" [ 92 81 0 0 0 0 0]\n", |
|
|
1883 |
" [ 20 20 0 0 0 0 0]\n", |
|
|
1884 |
" [ 0 20 80 0 0 0 0]\n", |
|
|
1885 |
" [ 20 20 68 0 0 0 0]\n", |
|
|
1886 |
" [ 10 100 217 0 0 0 0]]\n" |
|
|
1887 |
] |
|
|
1888 |
}, |
|
|
1889 |
{ |
|
|
1890 |
"data": { |
|
|
1891 |
"text/html": [ |
|
|
1892 |
"<div>\n", |
|
|
1893 |
"<style scoped>\n", |
|
|
1894 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1895 |
" vertical-align: middle;\n", |
|
|
1896 |
" }\n", |
|
|
1897 |
"\n", |
|
|
1898 |
" .dataframe tbody tr th {\n", |
|
|
1899 |
" vertical-align: top;\n", |
|
|
1900 |
" }\n", |
|
|
1901 |
"\n", |
|
|
1902 |
" .dataframe thead th {\n", |
|
|
1903 |
" text-align: right;\n", |
|
|
1904 |
" }\n", |
|
|
1905 |
"</style>\n", |
|
|
1906 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1907 |
" <thead>\n", |
|
|
1908 |
" <tr style=\"text-align: right;\">\n", |
|
|
1909 |
" <th></th>\n", |
|
|
1910 |
" <th>level Low</th>\n", |
|
|
1911 |
" <th>level Medium</th>\n", |
|
|
1912 |
" <th>level High</th>\n", |
|
|
1913 |
" <th>Predected_Label_4</th>\n", |
|
|
1914 |
" <th>Predected_Label_5</th>\n", |
|
|
1915 |
" <th>Predected_Label_6</th>\n", |
|
|
1916 |
" <th>Predected_Label_7</th>\n", |
|
|
1917 |
" </tr>\n", |
|
|
1918 |
" </thead>\n", |
|
|
1919 |
" <tbody>\n", |
|
|
1920 |
" <tr>\n", |
|
|
1921 |
" <th>genetic_risk_level_1</th>\n", |
|
|
1922 |
" <td>40</td>\n", |
|
|
1923 |
" <td>0</td>\n", |
|
|
1924 |
" <td>0</td>\n", |
|
|
1925 |
" <td>0</td>\n", |
|
|
1926 |
" <td>0</td>\n", |
|
|
1927 |
" <td>0</td>\n", |
|
|
1928 |
" <td>0</td>\n", |
|
|
1929 |
" </tr>\n", |
|
|
1930 |
" <tr>\n", |
|
|
1931 |
" <th>genetic_risk_level_2</th>\n", |
|
|
1932 |
" <td>121</td>\n", |
|
|
1933 |
" <td>91</td>\n", |
|
|
1934 |
" <td>0</td>\n", |
|
|
1935 |
" <td>0</td>\n", |
|
|
1936 |
" <td>0</td>\n", |
|
|
1937 |
" <td>0</td>\n", |
|
|
1938 |
" <td>0</td>\n", |
|
|
1939 |
" </tr>\n", |
|
|
1940 |
" <tr>\n", |
|
|
1941 |
" <th>genetic_risk_level_3</th>\n", |
|
|
1942 |
" <td>92</td>\n", |
|
|
1943 |
" <td>81</td>\n", |
|
|
1944 |
" <td>0</td>\n", |
|
|
1945 |
" <td>0</td>\n", |
|
|
1946 |
" <td>0</td>\n", |
|
|
1947 |
" <td>0</td>\n", |
|
|
1948 |
" <td>0</td>\n", |
|
|
1949 |
" </tr>\n", |
|
|
1950 |
" <tr>\n", |
|
|
1951 |
" <th>genetic_risk_level_4</th>\n", |
|
|
1952 |
" <td>20</td>\n", |
|
|
1953 |
" <td>20</td>\n", |
|
|
1954 |
" <td>0</td>\n", |
|
|
1955 |
" <td>0</td>\n", |
|
|
1956 |
" <td>0</td>\n", |
|
|
1957 |
" <td>0</td>\n", |
|
|
1958 |
" <td>0</td>\n", |
|
|
1959 |
" </tr>\n", |
|
|
1960 |
" <tr>\n", |
|
|
1961 |
" <th>genetic_risk_level_5</th>\n", |
|
|
1962 |
" <td>0</td>\n", |
|
|
1963 |
" <td>20</td>\n", |
|
|
1964 |
" <td>80</td>\n", |
|
|
1965 |
" <td>0</td>\n", |
|
|
1966 |
" <td>0</td>\n", |
|
|
1967 |
" <td>0</td>\n", |
|
|
1968 |
" <td>0</td>\n", |
|
|
1969 |
" </tr>\n", |
|
|
1970 |
" <tr>\n", |
|
|
1971 |
" <th>genetic_risk_level_6</th>\n", |
|
|
1972 |
" <td>20</td>\n", |
|
|
1973 |
" <td>20</td>\n", |
|
|
1974 |
" <td>68</td>\n", |
|
|
1975 |
" <td>0</td>\n", |
|
|
1976 |
" <td>0</td>\n", |
|
|
1977 |
" <td>0</td>\n", |
|
|
1978 |
" <td>0</td>\n", |
|
|
1979 |
" </tr>\n", |
|
|
1980 |
" <tr>\n", |
|
|
1981 |
" <th>genetic_risk_level_7</th>\n", |
|
|
1982 |
" <td>10</td>\n", |
|
|
1983 |
" <td>100</td>\n", |
|
|
1984 |
" <td>217</td>\n", |
|
|
1985 |
" <td>0</td>\n", |
|
|
1986 |
" <td>0</td>\n", |
|
|
1987 |
" <td>0</td>\n", |
|
|
1988 |
" <td>0</td>\n", |
|
|
1989 |
" </tr>\n", |
|
|
1990 |
" </tbody>\n", |
|
|
1991 |
"</table>\n", |
|
|
1992 |
"</div>" |
|
|
1993 |
], |
|
|
1994 |
"text/plain": [ |
|
|
1995 |
" level Low level Medium level High Predected_Label_4 \\\n", |
|
|
1996 |
"genetic_risk_level_1 40 0 0 0 \n", |
|
|
1997 |
"genetic_risk_level_2 121 91 0 0 \n", |
|
|
1998 |
"genetic_risk_level_3 92 81 0 0 \n", |
|
|
1999 |
"genetic_risk_level_4 20 20 0 0 \n", |
|
|
2000 |
"genetic_risk_level_5 0 20 80 0 \n", |
|
|
2001 |
"genetic_risk_level_6 20 20 68 0 \n", |
|
|
2002 |
"genetic_risk_level_7 10 100 217 0 \n", |
|
|
2003 |
"\n", |
|
|
2004 |
" Predected_Label_5 Predected_Label_6 Predected_Label_7 \n", |
|
|
2005 |
"genetic_risk_level_1 0 0 0 \n", |
|
|
2006 |
"genetic_risk_level_2 0 0 0 \n", |
|
|
2007 |
"genetic_risk_level_3 0 0 0 \n", |
|
|
2008 |
"genetic_risk_level_4 0 0 0 \n", |
|
|
2009 |
"genetic_risk_level_5 0 0 0 \n", |
|
|
2010 |
"genetic_risk_level_6 0 0 0 \n", |
|
|
2011 |
"genetic_risk_level_7 0 0 0 " |
|
|
2012 |
] |
|
|
2013 |
}, |
|
|
2014 |
"execution_count": 66, |
|
|
2015 |
"metadata": {}, |
|
|
2016 |
"output_type": "execute_result" |
|
|
2017 |
} |
|
|
2018 |
], |
|
|
2019 |
"source": [ |
|
|
2020 |
"from sklearn.metrics import confusion_matrix\n", |
|
|
2021 |
"confusion_matrix = confusion_matrix(LUNG_CANCER.genetic_risk, LUNG_CANCER.level)\n", |
|
|
2022 |
"print(confusion_matrix)\n", |
|
|
2023 |
"confusion = pd.DataFrame(confusion_matrix,index=['genetic_risk_level_1', 'genetic_risk_level_2','genetic_risk_level_3','genetic_risk_level_4', 'genetic_risk_level_5','genetic_risk_level_6','genetic_risk_level_7'],\n", |
|
|
2024 |
" columns=['level Low', 'level Medium','level High','Predected_Label_4', 'Predected_Label_5','Predected_Label_6','Predected_Label_7'])\n", |
|
|
2025 |
"\n", |
|
|
2026 |
"confusion" |
|
|
2027 |
] |
|
|
2028 |
}, |
|
|
2029 |
{ |
|
|
2030 |
"cell_type": "code", |
|
|
2031 |
"execution_count": 32, |
|
|
2032 |
"metadata": {}, |
|
|
2033 |
"outputs": [ |
|
|
2034 |
{ |
|
|
2035 |
"data": { |
|
|
2036 |
"text/plain": [ |
|
|
2037 |
"LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n", |
|
|
2038 |
" intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n", |
|
|
2039 |
" penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n", |
|
|
2040 |
" verbose=0, warm_start=False)" |
|
|
2041 |
] |
|
|
2042 |
}, |
|
|
2043 |
"execution_count": 32, |
|
|
2044 |
"metadata": {}, |
|
|
2045 |
"output_type": "execute_result" |
|
|
2046 |
} |
|
|
2047 |
], |
|
|
2048 |
"source": [ |
|
|
2049 |
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)\n", |
|
|
2050 |
"logreg = LogisticRegression()\n", |
|
|
2051 |
"logreg.fit(X_train, y_train)" |
|
|
2052 |
] |
|
|
2053 |
}, |
|
|
2054 |
{ |
|
|
2055 |
"cell_type": "code", |
|
|
2056 |
"execution_count": 33, |
|
|
2057 |
"metadata": {}, |
|
|
2058 |
"outputs": [ |
|
|
2059 |
{ |
|
|
2060 |
"name": "stdout", |
|
|
2061 |
"output_type": "stream", |
|
|
2062 |
"text": [ |
|
|
2063 |
"Accuracy of logistic regression classifier on test set: 0.97\n" |
|
|
2064 |
] |
|
|
2065 |
} |
|
|
2066 |
], |
|
|
2067 |
"source": [ |
|
|
2068 |
"y_pred = logreg.predict(X_test)\n", |
|
|
2069 |
"print('Accuracy of logistic regression classifier on test set: {:.2f}'.format(logreg.score(X_test, y_test)))" |
|
|
2070 |
] |
|
|
2071 |
}, |
|
|
2072 |
{ |
|
|
2073 |
"cell_type": "markdown", |
|
|
2074 |
"metadata": {}, |
|
|
2075 |
"source": [ |
|
|
2076 |
"## Compute precision, recall, F-measure and support" |
|
|
2077 |
] |
|
|
2078 |
}, |
|
|
2079 |
{ |
|
|
2080 |
"cell_type": "code", |
|
|
2081 |
"execution_count": 79, |
|
|
2082 |
"metadata": {}, |
|
|
2083 |
"outputs": [ |
|
|
2084 |
{ |
|
|
2085 |
"name": "stdout", |
|
|
2086 |
"output_type": "stream", |
|
|
2087 |
"text": [ |
|
|
2088 |
" precision recall f1-score support\n", |
|
|
2089 |
"\n", |
|
|
2090 |
" 1 0.950 1.000 0.974 76\n", |
|
|
2091 |
" 2 1.000 0.902 0.949 92\n", |
|
|
2092 |
" 3 0.964 1.000 0.981 132\n", |
|
|
2093 |
"\n", |
|
|
2094 |
"avg / total 0.971 0.970 0.970 300\n", |
|
|
2095 |
"\n" |
|
|
2096 |
] |
|
|
2097 |
} |
|
|
2098 |
], |
|
|
2099 |
"source": [ |
|
|
2100 |
"from sklearn.metrics import classification_report\n", |
|
|
2101 |
"print (classification_report(y_test, y_pred, digits=3))" |
|
|
2102 |
] |
|
|
2103 |
}, |
|
|
2104 |
{ |
|
|
2105 |
"cell_type": "markdown", |
|
|
2106 |
"metadata": {}, |
|
|
2107 |
"source": [ |
|
|
2108 |
"Interpretation: Of the entire test set, 97% of patients have level cancer High." |
|
|
2109 |
] |
|
|
2110 |
}, |
|
|
2111 |
{ |
|
|
2112 |
"cell_type": "markdown", |
|
|
2113 |
"metadata": {}, |
|
|
2114 |
"source": [ |
|
|
2115 |
"## Lets implement the same logistic regression using scikit learn\n", |
|
|
2116 |
"\n", |
|
|
2117 |
"---" |
|
|
2118 |
] |
|
|
2119 |
}, |
|
|
2120 |
{ |
|
|
2121 |
"cell_type": "code", |
|
|
2122 |
"execution_count": 81, |
|
|
2123 |
"metadata": {}, |
|
|
2124 |
"outputs": [ |
|
|
2125 |
{ |
|
|
2126 |
"name": "stdout", |
|
|
2127 |
"output_type": "stream", |
|
|
2128 |
"text": [ |
|
|
2129 |
"3 365\n", |
|
|
2130 |
"2 332\n", |
|
|
2131 |
"1 303\n", |
|
|
2132 |
"Name: level, dtype: int64 \n", |
|
|
2133 |
"\n" |
|
|
2134 |
] |
|
|
2135 |
} |
|
|
2136 |
], |
|
|
2137 |
"source": [ |
|
|
2138 |
"'''Remeber that 1 is Low, 2 is Medium, 3 is High'''\n", |
|
|
2139 |
"print (LUNG_CANCER['level'].value_counts(), \"\\n\" )" |
|
|
2140 |
] |
|
|
2141 |
}, |
|
|
2142 |
{ |
|
|
2143 |
"cell_type": "code", |
|
|
2144 |
"execution_count": 82, |
|
|
2145 |
"metadata": {}, |
|
|
2146 |
"outputs": [ |
|
|
2147 |
{ |
|
|
2148 |
"data": { |
|
|
2149 |
"text/plain": [ |
|
|
2150 |
"LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n", |
|
|
2151 |
" intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n", |
|
|
2152 |
" penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n", |
|
|
2153 |
" verbose=0, warm_start=False)" |
|
|
2154 |
] |
|
|
2155 |
}, |
|
|
2156 |
"execution_count": 82, |
|
|
2157 |
"metadata": {}, |
|
|
2158 |
"output_type": "execute_result" |
|
|
2159 |
} |
|
|
2160 |
], |
|
|
2161 |
"source": [ |
|
|
2162 |
"logistic = LogisticRegression()\n", |
|
|
2163 |
"logistic.fit(X_train, y_train)" |
|
|
2164 |
] |
|
|
2165 |
}, |
|
|
2166 |
{ |
|
|
2167 |
"cell_type": "code", |
|
|
2168 |
"execution_count": 83, |
|
|
2169 |
"metadata": {}, |
|
|
2170 |
"outputs": [ |
|
|
2171 |
{ |
|
|
2172 |
"name": "stdout", |
|
|
2173 |
"output_type": "stream", |
|
|
2174 |
"text": [ |
|
|
2175 |
"[[ 76 0 0]\n", |
|
|
2176 |
" [ 4 83 5]\n", |
|
|
2177 |
" [ 0 0 132]]\n" |
|
|
2178 |
] |
|
|
2179 |
}, |
|
|
2180 |
{ |
|
|
2181 |
"data": { |
|
|
2182 |
"text/html": [ |
|
|
2183 |
"<div>\n", |
|
|
2184 |
"<style scoped>\n", |
|
|
2185 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
2186 |
" vertical-align: middle;\n", |
|
|
2187 |
" }\n", |
|
|
2188 |
"\n", |
|
|
2189 |
" .dataframe tbody tr th {\n", |
|
|
2190 |
" vertical-align: top;\n", |
|
|
2191 |
" }\n", |
|
|
2192 |
"\n", |
|
|
2193 |
" .dataframe thead th {\n", |
|
|
2194 |
" text-align: right;\n", |
|
|
2195 |
" }\n", |
|
|
2196 |
"</style>\n", |
|
|
2197 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
2198 |
" <thead>\n", |
|
|
2199 |
" <tr style=\"text-align: right;\">\n", |
|
|
2200 |
" <th></th>\n", |
|
|
2201 |
" <th>Predict_Label_0 Low</th>\n", |
|
|
2202 |
" <th>Predict_Label_1 Medium</th>\n", |
|
|
2203 |
" <th>Predict_Label_2 High</th>\n", |
|
|
2204 |
" </tr>\n", |
|
|
2205 |
" </thead>\n", |
|
|
2206 |
" <tbody>\n", |
|
|
2207 |
" <tr>\n", |
|
|
2208 |
" <th>True_Label_0 Low</th>\n", |
|
|
2209 |
" <td>76</td>\n", |
|
|
2210 |
" <td>0</td>\n", |
|
|
2211 |
" <td>0</td>\n", |
|
|
2212 |
" </tr>\n", |
|
|
2213 |
" <tr>\n", |
|
|
2214 |
" <th>True_Label_1 Medium</th>\n", |
|
|
2215 |
" <td>4</td>\n", |
|
|
2216 |
" <td>83</td>\n", |
|
|
2217 |
" <td>5</td>\n", |
|
|
2218 |
" </tr>\n", |
|
|
2219 |
" <tr>\n", |
|
|
2220 |
" <th>True_Label_2 High</th>\n", |
|
|
2221 |
" <td>0</td>\n", |
|
|
2222 |
" <td>0</td>\n", |
|
|
2223 |
" <td>132</td>\n", |
|
|
2224 |
" </tr>\n", |
|
|
2225 |
" </tbody>\n", |
|
|
2226 |
"</table>\n", |
|
|
2227 |
"</div>" |
|
|
2228 |
], |
|
|
2229 |
"text/plain": [ |
|
|
2230 |
" Predict_Label_0 Low Predict_Label_1 Medium \\\n", |
|
|
2231 |
"True_Label_0 Low 76 0 \n", |
|
|
2232 |
"True_Label_1 Medium 4 83 \n", |
|
|
2233 |
"True_Label_2 High 0 0 \n", |
|
|
2234 |
"\n", |
|
|
2235 |
" Predict_Label_2 High \n", |
|
|
2236 |
"True_Label_0 Low 0 \n", |
|
|
2237 |
"True_Label_1 Medium 5 \n", |
|
|
2238 |
"True_Label_2 High 132 " |
|
|
2239 |
] |
|
|
2240 |
}, |
|
|
2241 |
"execution_count": 83, |
|
|
2242 |
"metadata": {}, |
|
|
2243 |
"output_type": "execute_result" |
|
|
2244 |
} |
|
|
2245 |
], |
|
|
2246 |
"source": [ |
|
|
2247 |
"from sklearn.metrics import confusion_matrix\n", |
|
|
2248 |
"y_pred=logistic.predict(X_test)\n", |
|
|
2249 |
"confusion_matrix = confusion_matrix(y_test, y_pred)\n", |
|
|
2250 |
"print(confusion_matrix)\n", |
|
|
2251 |
"confusion = pd.DataFrame(confusion_matrix,index=['True_Label_0 Low', 'True_Label_1 Medium','True_Label_2 High'],\n", |
|
|
2252 |
" columns=['Predict_Label_0 Low', 'Predict_Label_1 Medium','Predict_Label_2 High'])\n", |
|
|
2253 |
"\n", |
|
|
2254 |
"confusion" |
|
|
2255 |
] |
|
|
2256 |
}, |
|
|
2257 |
{ |
|
|
2258 |
"cell_type": "code", |
|
|
2259 |
"execution_count": 84, |
|
|
2260 |
"metadata": {}, |
|
|
2261 |
"outputs": [ |
|
|
2262 |
{ |
|
|
2263 |
"name": "stdout", |
|
|
2264 |
"output_type": "stream", |
|
|
2265 |
"text": [ |
|
|
2266 |
" precision recall f1-score support\n", |
|
|
2267 |
"\n", |
|
|
2268 |
" 1 0.950 1.000 0.974 76\n", |
|
|
2269 |
" 2 1.000 0.902 0.949 92\n", |
|
|
2270 |
" 3 0.964 1.000 0.981 132\n", |
|
|
2271 |
"\n", |
|
|
2272 |
"avg / total 0.971 0.970 0.970 300\n", |
|
|
2273 |
"\n" |
|
|
2274 |
] |
|
|
2275 |
} |
|
|
2276 |
], |
|
|
2277 |
"source": [ |
|
|
2278 |
"print (classification_report(y_test, y_pred, digits=3))" |
|
|
2279 |
] |
|
|
2280 |
}, |
|
|
2281 |
{ |
|
|
2282 |
"cell_type": "markdown", |
|
|
2283 |
"metadata": {}, |
|
|
2284 |
"source": [ |
|
|
2285 |
"Interpretation: Of the entire test set, 97% of patients have level cancer High." |
|
|
2286 |
] |
|
|
2287 |
}, |
|
|
2288 |
{ |
|
|
2289 |
"cell_type": "code", |
|
|
2290 |
"execution_count": 86, |
|
|
2291 |
"metadata": {}, |
|
|
2292 |
"outputs": [ |
|
|
2293 |
{ |
|
|
2294 |
"data": { |
|
|
2295 |
"text/plain": [ |
|
|
2296 |
"LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n", |
|
|
2297 |
" intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n", |
|
|
2298 |
" penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n", |
|
|
2299 |
" verbose=0, warm_start=False)" |
|
|
2300 |
] |
|
|
2301 |
}, |
|
|
2302 |
"execution_count": 86, |
|
|
2303 |
"metadata": {}, |
|
|
2304 |
"output_type": "execute_result" |
|
|
2305 |
} |
|
|
2306 |
], |
|
|
2307 |
"source": [ |
|
|
2308 |
"'''Use scikit learn'''\n", |
|
|
2309 |
"r_d_logistic = LogisticRegression()\n", |
|
|
2310 |
"r_d_logistic.fit(X_train, y_train)" |
|
|
2311 |
] |
|
|
2312 |
}, |
|
|
2313 |
{ |
|
|
2314 |
"cell_type": "markdown", |
|
|
2315 |
"metadata": {}, |
|
|
2316 |
"source": [ |
|
|
2317 |
"### Calculate accuracy, Misclassification Rate (Error Rate), Precision, Recall\n", |
|
|
2318 |
"---" |
|
|
2319 |
] |
|
|
2320 |
}, |
|
|
2321 |
{ |
|
|
2322 |
"cell_type": "code", |
|
|
2323 |
"execution_count": 87, |
|
|
2324 |
"metadata": {}, |
|
|
2325 |
"outputs": [ |
|
|
2326 |
{ |
|
|
2327 |
"name": "stdout", |
|
|
2328 |
"output_type": "stream", |
|
|
2329 |
"text": [ |
|
|
2330 |
"Accuracy score: 97.000\n" |
|
|
2331 |
] |
|
|
2332 |
} |
|
|
2333 |
], |
|
|
2334 |
"source": [ |
|
|
2335 |
"## Accuracy\n", |
|
|
2336 |
"## How often is the classifier correct?\n", |
|
|
2337 |
"from sklearn.metrics import accuracy_score\n", |
|
|
2338 |
"\n", |
|
|
2339 |
"acc = accuracy_score(y_test, y_pred)\n", |
|
|
2340 |
"print (\"Accuracy score: %.3f\" %(acc*100))" |
|
|
2341 |
] |
|
|
2342 |
}, |
|
|
2343 |
{ |
|
|
2344 |
"cell_type": "code", |
|
|
2345 |
"execution_count": null, |
|
|
2346 |
"metadata": {}, |
|
|
2347 |
"outputs": [], |
|
|
2348 |
"source": [] |
|
|
2349 |
} |
|
|
2350 |
], |
|
|
2351 |
"metadata": { |
|
|
2352 |
"kernelspec": { |
|
|
2353 |
"display_name": "Python 3", |
|
|
2354 |
"language": "python", |
|
|
2355 |
"name": "python3" |
|
|
2356 |
}, |
|
|
2357 |
"language_info": { |
|
|
2358 |
"codemirror_mode": { |
|
|
2359 |
"name": "ipython", |
|
|
2360 |
"version": 3 |
|
|
2361 |
}, |
|
|
2362 |
"file_extension": ".py", |
|
|
2363 |
"mimetype": "text/x-python", |
|
|
2364 |
"name": "python", |
|
|
2365 |
"nbconvert_exporter": "python", |
|
|
2366 |
"pygments_lexer": "ipython3", |
|
|
2367 |
"version": "3.6.5" |
|
|
2368 |
} |
|
|
2369 |
}, |
|
|
2370 |
"nbformat": 4, |
|
|
2371 |
"nbformat_minor": 1 |
|
|
2372 |
} |