|
a |
|
b/final notebook.ipynb |
|
|
1 |
{ |
|
|
2 |
"cells": [ |
|
|
3 |
{ |
|
|
4 |
"cell_type": "code", |
|
|
5 |
"execution_count": 1, |
|
|
6 |
"id": "52a93d80", |
|
|
7 |
"metadata": {}, |
|
|
8 |
"outputs": [], |
|
|
9 |
"source": [ |
|
|
10 |
"import pandas as pd" |
|
|
11 |
] |
|
|
12 |
}, |
|
|
13 |
{ |
|
|
14 |
"cell_type": "code", |
|
|
15 |
"execution_count": 2, |
|
|
16 |
"id": "5578d52a", |
|
|
17 |
"metadata": { |
|
|
18 |
"scrolled": false |
|
|
19 |
}, |
|
|
20 |
"outputs": [], |
|
|
21 |
"source": [ |
|
|
22 |
"df=pd.read_csv('hemolysis_index_results.csv')\n", |
|
|
23 |
"cost=pd.read_csv(\"redraw_costs.csv\")" |
|
|
24 |
] |
|
|
25 |
}, |
|
|
26 |
{ |
|
|
27 |
"cell_type": "code", |
|
|
28 |
"execution_count": 3, |
|
|
29 |
"id": "cedb75cb", |
|
|
30 |
"metadata": {}, |
|
|
31 |
"outputs": [ |
|
|
32 |
{ |
|
|
33 |
"data": { |
|
|
34 |
"text/html": [ |
|
|
35 |
"<div>\n", |
|
|
36 |
"<style scoped>\n", |
|
|
37 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
38 |
" vertical-align: middle;\n", |
|
|
39 |
" }\n", |
|
|
40 |
"\n", |
|
|
41 |
" .dataframe tbody tr th {\n", |
|
|
42 |
" vertical-align: top;\n", |
|
|
43 |
" }\n", |
|
|
44 |
"\n", |
|
|
45 |
" .dataframe thead th {\n", |
|
|
46 |
" text-align: right;\n", |
|
|
47 |
" }\n", |
|
|
48 |
"</style>\n", |
|
|
49 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
50 |
" <thead>\n", |
|
|
51 |
" <tr style=\"text-align: right;\">\n", |
|
|
52 |
" <th></th>\n", |
|
|
53 |
" <th>COLLECTOR_ID</th>\n", |
|
|
54 |
" <th>REDRAW_COUNT</th>\n", |
|
|
55 |
" </tr>\n", |
|
|
56 |
" </thead>\n", |
|
|
57 |
" <tbody>\n", |
|
|
58 |
" <tr>\n", |
|
|
59 |
" <th>0</th>\n", |
|
|
60 |
" <td>COLLECTOR_101</td>\n", |
|
|
61 |
" <td>1</td>\n", |
|
|
62 |
" </tr>\n", |
|
|
63 |
" <tr>\n", |
|
|
64 |
" <th>1</th>\n", |
|
|
65 |
" <td>COLLECTOR_1013</td>\n", |
|
|
66 |
" <td>2</td>\n", |
|
|
67 |
" </tr>\n", |
|
|
68 |
" <tr>\n", |
|
|
69 |
" <th>2</th>\n", |
|
|
70 |
" <td>COLLECTOR_1028</td>\n", |
|
|
71 |
" <td>3</td>\n", |
|
|
72 |
" </tr>\n", |
|
|
73 |
" <tr>\n", |
|
|
74 |
" <th>3</th>\n", |
|
|
75 |
" <td>COLLECTOR_1029</td>\n", |
|
|
76 |
" <td>1</td>\n", |
|
|
77 |
" </tr>\n", |
|
|
78 |
" <tr>\n", |
|
|
79 |
" <th>4</th>\n", |
|
|
80 |
" <td>COLLECTOR_1031</td>\n", |
|
|
81 |
" <td>1</td>\n", |
|
|
82 |
" </tr>\n", |
|
|
83 |
" <tr>\n", |
|
|
84 |
" <th>...</th>\n", |
|
|
85 |
" <td>...</td>\n", |
|
|
86 |
" <td>...</td>\n", |
|
|
87 |
" </tr>\n", |
|
|
88 |
" <tr>\n", |
|
|
89 |
" <th>1234</th>\n", |
|
|
90 |
" <td>COLLECTOR_981</td>\n", |
|
|
91 |
" <td>1</td>\n", |
|
|
92 |
" </tr>\n", |
|
|
93 |
" <tr>\n", |
|
|
94 |
" <th>1235</th>\n", |
|
|
95 |
" <td>COLLECTOR_984</td>\n", |
|
|
96 |
" <td>3</td>\n", |
|
|
97 |
" </tr>\n", |
|
|
98 |
" <tr>\n", |
|
|
99 |
" <th>1236</th>\n", |
|
|
100 |
" <td>COLLECTOR_989</td>\n", |
|
|
101 |
" <td>2</td>\n", |
|
|
102 |
" </tr>\n", |
|
|
103 |
" <tr>\n", |
|
|
104 |
" <th>1237</th>\n", |
|
|
105 |
" <td>COLLECTOR_991</td>\n", |
|
|
106 |
" <td>1</td>\n", |
|
|
107 |
" </tr>\n", |
|
|
108 |
" <tr>\n", |
|
|
109 |
" <th>1238</th>\n", |
|
|
110 |
" <td>COLLECTOR_992</td>\n", |
|
|
111 |
" <td>2</td>\n", |
|
|
112 |
" </tr>\n", |
|
|
113 |
" </tbody>\n", |
|
|
114 |
"</table>\n", |
|
|
115 |
"<p>1239 rows × 2 columns</p>\n", |
|
|
116 |
"</div>" |
|
|
117 |
], |
|
|
118 |
"text/plain": [ |
|
|
119 |
" COLLECTOR_ID REDRAW_COUNT\n", |
|
|
120 |
"0 COLLECTOR_101 1\n", |
|
|
121 |
"1 COLLECTOR_1013 2\n", |
|
|
122 |
"2 COLLECTOR_1028 3\n", |
|
|
123 |
"3 COLLECTOR_1029 1\n", |
|
|
124 |
"4 COLLECTOR_1031 1\n", |
|
|
125 |
"... ... ...\n", |
|
|
126 |
"1234 COLLECTOR_981 1\n", |
|
|
127 |
"1235 COLLECTOR_984 3\n", |
|
|
128 |
"1236 COLLECTOR_989 2\n", |
|
|
129 |
"1237 COLLECTOR_991 1\n", |
|
|
130 |
"1238 COLLECTOR_992 2\n", |
|
|
131 |
"\n", |
|
|
132 |
"[1239 rows x 2 columns]" |
|
|
133 |
] |
|
|
134 |
}, |
|
|
135 |
"execution_count": 3, |
|
|
136 |
"metadata": {}, |
|
|
137 |
"output_type": "execute_result" |
|
|
138 |
} |
|
|
139 |
], |
|
|
140 |
"source": [ |
|
|
141 |
"redraw = df.query(\"HEMOLYSIS_INDEX > 75\")\n", |
|
|
142 |
"df3 = redraw[['COLLECTOR_ID', 'SPECIMEN_ID', 'HEMOLYSIS_INDEX']].copy()\n", |
|
|
143 |
"df3 = df3.groupby('COLLECTOR_ID')['SPECIMEN_ID'].nunique().reset_index()\n", |
|
|
144 |
"df3 = df3.rename(columns={'SPECIMEN_ID' : 'REDRAW_COUNT'})\n", |
|
|
145 |
"df3" |
|
|
146 |
] |
|
|
147 |
}, |
|
|
148 |
{ |
|
|
149 |
"cell_type": "code", |
|
|
150 |
"execution_count": 4, |
|
|
151 |
"id": "634fe1c8", |
|
|
152 |
"metadata": { |
|
|
153 |
"scrolled": true |
|
|
154 |
}, |
|
|
155 |
"outputs": [ |
|
|
156 |
{ |
|
|
157 |
"data": { |
|
|
158 |
"text/html": [ |
|
|
159 |
"<div>\n", |
|
|
160 |
"<style scoped>\n", |
|
|
161 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
162 |
" vertical-align: middle;\n", |
|
|
163 |
" }\n", |
|
|
164 |
"\n", |
|
|
165 |
" .dataframe tbody tr th {\n", |
|
|
166 |
" vertical-align: top;\n", |
|
|
167 |
" }\n", |
|
|
168 |
"\n", |
|
|
169 |
" .dataframe thead th {\n", |
|
|
170 |
" text-align: right;\n", |
|
|
171 |
" }\n", |
|
|
172 |
"</style>\n", |
|
|
173 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
174 |
" <thead>\n", |
|
|
175 |
" <tr style=\"text-align: right;\">\n", |
|
|
176 |
" <th></th>\n", |
|
|
177 |
" <th>ORDER_ID</th>\n", |
|
|
178 |
" <th>ORDERABLE</th>\n", |
|
|
179 |
" <th>PATIENT_ID</th>\n", |
|
|
180 |
" <th>PATIENT_AGE</th>\n", |
|
|
181 |
" <th>PATIENT_SEX</th>\n", |
|
|
182 |
" <th>PATIENT_RACE</th>\n", |
|
|
183 |
" <th>NURSING_UNIT</th>\n", |
|
|
184 |
" <th>ENCOUNTER_TYPE</th>\n", |
|
|
185 |
" <th>MEDICAL_SERVICE</th>\n", |
|
|
186 |
" <th>SPECIMEN_ID</th>\n", |
|
|
187 |
" <th>SPECIMEN_TYPE</th>\n", |
|
|
188 |
" <th>COLLECTOR_ID</th>\n", |
|
|
189 |
" <th>DRAW_SITE</th>\n", |
|
|
190 |
" <th>COLLECTION_DAY</th>\n", |
|
|
191 |
" <th>COLLECTION_TIME</th>\n", |
|
|
192 |
" <th>HEMOLYSIS_INDEX</th>\n", |
|
|
193 |
" <th>REDRAW_COST</th>\n", |
|
|
194 |
" </tr>\n", |
|
|
195 |
" </thead>\n", |
|
|
196 |
" <tbody>\n", |
|
|
197 |
" <tr>\n", |
|
|
198 |
" <th>0</th>\n", |
|
|
199 |
" <td>ORDER_1179508</td>\n", |
|
|
200 |
" <td>Vancomycin Tr</td>\n", |
|
|
201 |
" <td>PATIENT_131440</td>\n", |
|
|
202 |
" <td>44</td>\n", |
|
|
203 |
" <td>Female</td>\n", |
|
|
204 |
" <td>White</td>\n", |
|
|
205 |
" <td>UNIT_10</td>\n", |
|
|
206 |
" <td>Intensive Care</td>\n", |
|
|
207 |
" <td>Medical</td>\n", |
|
|
208 |
" <td>SPECIMEN_543979</td>\n", |
|
|
209 |
" <td>Blood</td>\n", |
|
|
210 |
" <td>COLLECTOR_2732</td>\n", |
|
|
211 |
" <td>NaN</td>\n", |
|
|
212 |
" <td>6</td>\n", |
|
|
213 |
" <td>23:21:00</td>\n", |
|
|
214 |
" <td>6.0</td>\n", |
|
|
215 |
" <td>162.18</td>\n", |
|
|
216 |
" </tr>\n", |
|
|
217 |
" <tr>\n", |
|
|
218 |
" <th>1</th>\n", |
|
|
219 |
" <td>ORDER_1181190</td>\n", |
|
|
220 |
" <td>Comp Met Plas</td>\n", |
|
|
221 |
" <td>PATIENT_58856</td>\n", |
|
|
222 |
" <td>75</td>\n", |
|
|
223 |
" <td>Male</td>\n", |
|
|
224 |
" <td>White</td>\n", |
|
|
225 |
" <td>UNIT_49</td>\n", |
|
|
226 |
" <td>Inpatient</td>\n", |
|
|
227 |
" <td>Bone Marrow Transplant</td>\n", |
|
|
228 |
" <td>SPECIMEN_544650</td>\n", |
|
|
229 |
" <td>Blood</td>\n", |
|
|
230 |
" <td>COLLECTOR_522</td>\n", |
|
|
231 |
" <td>NaN</td>\n", |
|
|
232 |
" <td>6</td>\n", |
|
|
233 |
" <td>23:16:00</td>\n", |
|
|
234 |
" <td>8.0</td>\n", |
|
|
235 |
" <td>357.15</td>\n", |
|
|
236 |
" </tr>\n", |
|
|
237 |
" <tr>\n", |
|
|
238 |
" <th>2</th>\n", |
|
|
239 |
" <td>ORDER_1181164</td>\n", |
|
|
240 |
" <td>Phos Plas</td>\n", |
|
|
241 |
" <td>PATIENT_58856</td>\n", |
|
|
242 |
" <td>75</td>\n", |
|
|
243 |
" <td>Male</td>\n", |
|
|
244 |
" <td>White</td>\n", |
|
|
245 |
" <td>UNIT_49</td>\n", |
|
|
246 |
" <td>Inpatient</td>\n", |
|
|
247 |
" <td>Bone Marrow Transplant</td>\n", |
|
|
248 |
" <td>SPECIMEN_544650</td>\n", |
|
|
249 |
" <td>Blood</td>\n", |
|
|
250 |
" <td>COLLECTOR_522</td>\n", |
|
|
251 |
" <td>NaN</td>\n", |
|
|
252 |
" <td>6</td>\n", |
|
|
253 |
" <td>23:16:00</td>\n", |
|
|
254 |
" <td>8.0</td>\n", |
|
|
255 |
" <td>357.15</td>\n", |
|
|
256 |
" </tr>\n", |
|
|
257 |
" <tr>\n", |
|
|
258 |
" <th>3</th>\n", |
|
|
259 |
" <td>ORDER_1181191</td>\n", |
|
|
260 |
" <td>Magnesium</td>\n", |
|
|
261 |
" <td>PATIENT_58856</td>\n", |
|
|
262 |
" <td>75</td>\n", |
|
|
263 |
" <td>Male</td>\n", |
|
|
264 |
" <td>White</td>\n", |
|
|
265 |
" <td>UNIT_49</td>\n", |
|
|
266 |
" <td>Inpatient</td>\n", |
|
|
267 |
" <td>Bone Marrow Transplant</td>\n", |
|
|
268 |
" <td>SPECIMEN_544650</td>\n", |
|
|
269 |
" <td>Blood</td>\n", |
|
|
270 |
" <td>COLLECTOR_522</td>\n", |
|
|
271 |
" <td>NaN</td>\n", |
|
|
272 |
" <td>6</td>\n", |
|
|
273 |
" <td>23:16:00</td>\n", |
|
|
274 |
" <td>8.0</td>\n", |
|
|
275 |
" <td>357.15</td>\n", |
|
|
276 |
" </tr>\n", |
|
|
277 |
" <tr>\n", |
|
|
278 |
" <th>4</th>\n", |
|
|
279 |
" <td>ORDER_1180687</td>\n", |
|
|
280 |
" <td>Basic Met Plas</td>\n", |
|
|
281 |
" <td>PATIENT_99436</td>\n", |
|
|
282 |
" <td>40</td>\n", |
|
|
283 |
" <td>Female</td>\n", |
|
|
284 |
" <td>White</td>\n", |
|
|
285 |
" <td>UNIT_161</td>\n", |
|
|
286 |
" <td>Intensive Care</td>\n", |
|
|
287 |
" <td>Cardiology</td>\n", |
|
|
288 |
" <td>SPECIMEN_544632</td>\n", |
|
|
289 |
" <td>Blood</td>\n", |
|
|
290 |
" <td>COLLECTOR_201</td>\n", |
|
|
291 |
" <td>NaN</td>\n", |
|
|
292 |
" <td>6</td>\n", |
|
|
293 |
" <td>23:18:00</td>\n", |
|
|
294 |
" <td>7.0</td>\n", |
|
|
295 |
" <td>162.18</td>\n", |
|
|
296 |
" </tr>\n", |
|
|
297 |
" <tr>\n", |
|
|
298 |
" <th>...</th>\n", |
|
|
299 |
" <td>...</td>\n", |
|
|
300 |
" <td>...</td>\n", |
|
|
301 |
" <td>...</td>\n", |
|
|
302 |
" <td>...</td>\n", |
|
|
303 |
" <td>...</td>\n", |
|
|
304 |
" <td>...</td>\n", |
|
|
305 |
" <td>...</td>\n", |
|
|
306 |
" <td>...</td>\n", |
|
|
307 |
" <td>...</td>\n", |
|
|
308 |
" <td>...</td>\n", |
|
|
309 |
" <td>...</td>\n", |
|
|
310 |
" <td>...</td>\n", |
|
|
311 |
" <td>...</td>\n", |
|
|
312 |
" <td>...</td>\n", |
|
|
313 |
" <td>...</td>\n", |
|
|
314 |
" <td>...</td>\n", |
|
|
315 |
" <td>...</td>\n", |
|
|
316 |
" </tr>\n", |
|
|
317 |
" <tr>\n", |
|
|
318 |
" <th>101169</th>\n", |
|
|
319 |
" <td>ORDER_1253155</td>\n", |
|
|
320 |
" <td>Phos Plas</td>\n", |
|
|
321 |
" <td>PATIENT_74490</td>\n", |
|
|
322 |
" <td>80</td>\n", |
|
|
323 |
" <td>Male</td>\n", |
|
|
324 |
" <td>White</td>\n", |
|
|
325 |
" <td>UNIT_45</td>\n", |
|
|
326 |
" <td>Inpatient</td>\n", |
|
|
327 |
" <td>Bone Marrow Transplant</td>\n", |
|
|
328 |
" <td>SPECIMEN_577685</td>\n", |
|
|
329 |
" <td>Blood</td>\n", |
|
|
330 |
" <td>COLLECTOR_5636</td>\n", |
|
|
331 |
" <td>NaN</td>\n", |
|
|
332 |
" <td>27</td>\n", |
|
|
333 |
" <td>23:10:00</td>\n", |
|
|
334 |
" <td>27.0</td>\n", |
|
|
335 |
" <td>357.15</td>\n", |
|
|
336 |
" </tr>\n", |
|
|
337 |
" <tr>\n", |
|
|
338 |
" <th>101170</th>\n", |
|
|
339 |
" <td>ORDER_1253154</td>\n", |
|
|
340 |
" <td>Magnesium</td>\n", |
|
|
341 |
" <td>PATIENT_74490</td>\n", |
|
|
342 |
" <td>80</td>\n", |
|
|
343 |
" <td>Male</td>\n", |
|
|
344 |
" <td>White</td>\n", |
|
|
345 |
" <td>UNIT_45</td>\n", |
|
|
346 |
" <td>Inpatient</td>\n", |
|
|
347 |
" <td>Bone Marrow Transplant</td>\n", |
|
|
348 |
" <td>SPECIMEN_577685</td>\n", |
|
|
349 |
" <td>Blood</td>\n", |
|
|
350 |
" <td>COLLECTOR_5636</td>\n", |
|
|
351 |
" <td>NaN</td>\n", |
|
|
352 |
" <td>27</td>\n", |
|
|
353 |
" <td>23:10:00</td>\n", |
|
|
354 |
" <td>27.0</td>\n", |
|
|
355 |
" <td>357.15</td>\n", |
|
|
356 |
" </tr>\n", |
|
|
357 |
" <tr>\n", |
|
|
358 |
" <th>101171</th>\n", |
|
|
359 |
" <td>ORDER_1253157</td>\n", |
|
|
360 |
" <td>Uric Acid</td>\n", |
|
|
361 |
" <td>PATIENT_74490</td>\n", |
|
|
362 |
" <td>80</td>\n", |
|
|
363 |
" <td>Male</td>\n", |
|
|
364 |
" <td>White</td>\n", |
|
|
365 |
" <td>UNIT_45</td>\n", |
|
|
366 |
" <td>Inpatient</td>\n", |
|
|
367 |
" <td>Bone Marrow Transplant</td>\n", |
|
|
368 |
" <td>SPECIMEN_577685</td>\n", |
|
|
369 |
" <td>Blood</td>\n", |
|
|
370 |
" <td>COLLECTOR_5636</td>\n", |
|
|
371 |
" <td>NaN</td>\n", |
|
|
372 |
" <td>27</td>\n", |
|
|
373 |
" <td>23:10:00</td>\n", |
|
|
374 |
" <td>27.0</td>\n", |
|
|
375 |
" <td>357.15</td>\n", |
|
|
376 |
" </tr>\n", |
|
|
377 |
" <tr>\n", |
|
|
378 |
" <th>101172</th>\n", |
|
|
379 |
" <td>ORDER_1252360</td>\n", |
|
|
380 |
" <td>Comp Met Plas</td>\n", |
|
|
381 |
" <td>PATIENT_132340</td>\n", |
|
|
382 |
" <td>58</td>\n", |
|
|
383 |
" <td>Male</td>\n", |
|
|
384 |
" <td>White</td>\n", |
|
|
385 |
" <td>UNIT_145</td>\n", |
|
|
386 |
" <td>Emergency</td>\n", |
|
|
387 |
" <td>Neuro Medicine</td>\n", |
|
|
388 |
" <td>SPECIMEN_577345</td>\n", |
|
|
389 |
" <td>Blood</td>\n", |
|
|
390 |
" <td>COLLECTOR_2490</td>\n", |
|
|
391 |
" <td>NaN</td>\n", |
|
|
392 |
" <td>27</td>\n", |
|
|
393 |
" <td>22:55:00</td>\n", |
|
|
394 |
" <td>16.0</td>\n", |
|
|
395 |
" <td>600.00</td>\n", |
|
|
396 |
" </tr>\n", |
|
|
397 |
" <tr>\n", |
|
|
398 |
" <th>101173</th>\n", |
|
|
399 |
" <td>ORDER_1252361</td>\n", |
|
|
400 |
" <td>Thyroid Cascade</td>\n", |
|
|
401 |
" <td>PATIENT_132340</td>\n", |
|
|
402 |
" <td>58</td>\n", |
|
|
403 |
" <td>Male</td>\n", |
|
|
404 |
" <td>White</td>\n", |
|
|
405 |
" <td>UNIT_145</td>\n", |
|
|
406 |
" <td>Emergency</td>\n", |
|
|
407 |
" <td>Neuro Medicine</td>\n", |
|
|
408 |
" <td>SPECIMEN_577345</td>\n", |
|
|
409 |
" <td>Blood</td>\n", |
|
|
410 |
" <td>COLLECTOR_2490</td>\n", |
|
|
411 |
" <td>NaN</td>\n", |
|
|
412 |
" <td>27</td>\n", |
|
|
413 |
" <td>22:55:00</td>\n", |
|
|
414 |
" <td>16.0</td>\n", |
|
|
415 |
" <td>600.00</td>\n", |
|
|
416 |
" </tr>\n", |
|
|
417 |
" </tbody>\n", |
|
|
418 |
"</table>\n", |
|
|
419 |
"<p>101174 rows × 17 columns</p>\n", |
|
|
420 |
"</div>" |
|
|
421 |
], |
|
|
422 |
"text/plain": [ |
|
|
423 |
" ORDER_ID ORDERABLE PATIENT_ID PATIENT_AGE \\\n", |
|
|
424 |
"0 ORDER_1179508 Vancomycin Tr PATIENT_131440 44 \n", |
|
|
425 |
"1 ORDER_1181190 Comp Met Plas PATIENT_58856 75 \n", |
|
|
426 |
"2 ORDER_1181164 Phos Plas PATIENT_58856 75 \n", |
|
|
427 |
"3 ORDER_1181191 Magnesium PATIENT_58856 75 \n", |
|
|
428 |
"4 ORDER_1180687 Basic Met Plas PATIENT_99436 40 \n", |
|
|
429 |
"... ... ... ... ... \n", |
|
|
430 |
"101169 ORDER_1253155 Phos Plas PATIENT_74490 80 \n", |
|
|
431 |
"101170 ORDER_1253154 Magnesium PATIENT_74490 80 \n", |
|
|
432 |
"101171 ORDER_1253157 Uric Acid PATIENT_74490 80 \n", |
|
|
433 |
"101172 ORDER_1252360 Comp Met Plas PATIENT_132340 58 \n", |
|
|
434 |
"101173 ORDER_1252361 Thyroid Cascade PATIENT_132340 58 \n", |
|
|
435 |
"\n", |
|
|
436 |
" PATIENT_SEX PATIENT_RACE NURSING_UNIT ENCOUNTER_TYPE \\\n", |
|
|
437 |
"0 Female White UNIT_10 Intensive Care \n", |
|
|
438 |
"1 Male White UNIT_49 Inpatient \n", |
|
|
439 |
"2 Male White UNIT_49 Inpatient \n", |
|
|
440 |
"3 Male White UNIT_49 Inpatient \n", |
|
|
441 |
"4 Female White UNIT_161 Intensive Care \n", |
|
|
442 |
"... ... ... ... ... \n", |
|
|
443 |
"101169 Male White UNIT_45 Inpatient \n", |
|
|
444 |
"101170 Male White UNIT_45 Inpatient \n", |
|
|
445 |
"101171 Male White UNIT_45 Inpatient \n", |
|
|
446 |
"101172 Male White UNIT_145 Emergency \n", |
|
|
447 |
"101173 Male White UNIT_145 Emergency \n", |
|
|
448 |
"\n", |
|
|
449 |
" MEDICAL_SERVICE SPECIMEN_ID SPECIMEN_TYPE COLLECTOR_ID \\\n", |
|
|
450 |
"0 Medical SPECIMEN_543979 Blood COLLECTOR_2732 \n", |
|
|
451 |
"1 Bone Marrow Transplant SPECIMEN_544650 Blood COLLECTOR_522 \n", |
|
|
452 |
"2 Bone Marrow Transplant SPECIMEN_544650 Blood COLLECTOR_522 \n", |
|
|
453 |
"3 Bone Marrow Transplant SPECIMEN_544650 Blood COLLECTOR_522 \n", |
|
|
454 |
"4 Cardiology SPECIMEN_544632 Blood COLLECTOR_201 \n", |
|
|
455 |
"... ... ... ... ... \n", |
|
|
456 |
"101169 Bone Marrow Transplant SPECIMEN_577685 Blood COLLECTOR_5636 \n", |
|
|
457 |
"101170 Bone Marrow Transplant SPECIMEN_577685 Blood COLLECTOR_5636 \n", |
|
|
458 |
"101171 Bone Marrow Transplant SPECIMEN_577685 Blood COLLECTOR_5636 \n", |
|
|
459 |
"101172 Neuro Medicine SPECIMEN_577345 Blood COLLECTOR_2490 \n", |
|
|
460 |
"101173 Neuro Medicine SPECIMEN_577345 Blood COLLECTOR_2490 \n", |
|
|
461 |
"\n", |
|
|
462 |
" DRAW_SITE COLLECTION_DAY COLLECTION_TIME HEMOLYSIS_INDEX REDRAW_COST \n", |
|
|
463 |
"0 NaN 6 23:21:00 6.0 162.18 \n", |
|
|
464 |
"1 NaN 6 23:16:00 8.0 357.15 \n", |
|
|
465 |
"2 NaN 6 23:16:00 8.0 357.15 \n", |
|
|
466 |
"3 NaN 6 23:16:00 8.0 357.15 \n", |
|
|
467 |
"4 NaN 6 23:18:00 7.0 162.18 \n", |
|
|
468 |
"... ... ... ... ... ... \n", |
|
|
469 |
"101169 NaN 27 23:10:00 27.0 357.15 \n", |
|
|
470 |
"101170 NaN 27 23:10:00 27.0 357.15 \n", |
|
|
471 |
"101171 NaN 27 23:10:00 27.0 357.15 \n", |
|
|
472 |
"101172 NaN 27 22:55:00 16.0 600.00 \n", |
|
|
473 |
"101173 NaN 27 22:55:00 16.0 600.00 \n", |
|
|
474 |
"\n", |
|
|
475 |
"[101174 rows x 17 columns]" |
|
|
476 |
] |
|
|
477 |
}, |
|
|
478 |
"execution_count": 4, |
|
|
479 |
"metadata": {}, |
|
|
480 |
"output_type": "execute_result" |
|
|
481 |
} |
|
|
482 |
], |
|
|
483 |
"source": [ |
|
|
484 |
"df=df.merge(cost,how=\"left\",on=\"ENCOUNTER_TYPE\")\n", |
|
|
485 |
"df" |
|
|
486 |
] |
|
|
487 |
}, |
|
|
488 |
{ |
|
|
489 |
"cell_type": "code", |
|
|
490 |
"execution_count": 5, |
|
|
491 |
"id": "7b1e6c42", |
|
|
492 |
"metadata": { |
|
|
493 |
"scrolled": false |
|
|
494 |
}, |
|
|
495 |
"outputs": [ |
|
|
496 |
{ |
|
|
497 |
"data": { |
|
|
498 |
"text/html": [ |
|
|
499 |
"<div>\n", |
|
|
500 |
"<style scoped>\n", |
|
|
501 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
502 |
" vertical-align: middle;\n", |
|
|
503 |
" }\n", |
|
|
504 |
"\n", |
|
|
505 |
" .dataframe tbody tr th {\n", |
|
|
506 |
" vertical-align: top;\n", |
|
|
507 |
" }\n", |
|
|
508 |
"\n", |
|
|
509 |
" .dataframe thead th {\n", |
|
|
510 |
" text-align: right;\n", |
|
|
511 |
" }\n", |
|
|
512 |
"</style>\n", |
|
|
513 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
514 |
" <thead>\n", |
|
|
515 |
" <tr style=\"text-align: right;\">\n", |
|
|
516 |
" <th></th>\n", |
|
|
517 |
" <th>COLLECTOR_ID</th>\n", |
|
|
518 |
" <th>SPECIMEN_COUNT</th>\n", |
|
|
519 |
" </tr>\n", |
|
|
520 |
" </thead>\n", |
|
|
521 |
" <tbody>\n", |
|
|
522 |
" <tr>\n", |
|
|
523 |
" <th>0</th>\n", |
|
|
524 |
" <td>COLLECTOR_101</td>\n", |
|
|
525 |
" <td>7</td>\n", |
|
|
526 |
" </tr>\n", |
|
|
527 |
" <tr>\n", |
|
|
528 |
" <th>1</th>\n", |
|
|
529 |
" <td>COLLECTOR_1013</td>\n", |
|
|
530 |
" <td>35</td>\n", |
|
|
531 |
" </tr>\n", |
|
|
532 |
" <tr>\n", |
|
|
533 |
" <th>2</th>\n", |
|
|
534 |
" <td>COLLECTOR_1028</td>\n", |
|
|
535 |
" <td>23</td>\n", |
|
|
536 |
" </tr>\n", |
|
|
537 |
" <tr>\n", |
|
|
538 |
" <th>3</th>\n", |
|
|
539 |
" <td>COLLECTOR_1029</td>\n", |
|
|
540 |
" <td>17</td>\n", |
|
|
541 |
" </tr>\n", |
|
|
542 |
" <tr>\n", |
|
|
543 |
" <th>4</th>\n", |
|
|
544 |
" <td>COLLECTOR_1031</td>\n", |
|
|
545 |
" <td>30</td>\n", |
|
|
546 |
" </tr>\n", |
|
|
547 |
" <tr>\n", |
|
|
548 |
" <th>...</th>\n", |
|
|
549 |
" <td>...</td>\n", |
|
|
550 |
" <td>...</td>\n", |
|
|
551 |
" </tr>\n", |
|
|
552 |
" <tr>\n", |
|
|
553 |
" <th>2223</th>\n", |
|
|
554 |
" <td>COLLECTOR_991</td>\n", |
|
|
555 |
" <td>6</td>\n", |
|
|
556 |
" </tr>\n", |
|
|
557 |
" <tr>\n", |
|
|
558 |
" <th>2224</th>\n", |
|
|
559 |
" <td>COLLECTOR_992</td>\n", |
|
|
560 |
" <td>43</td>\n", |
|
|
561 |
" </tr>\n", |
|
|
562 |
" <tr>\n", |
|
|
563 |
" <th>2225</th>\n", |
|
|
564 |
" <td>COLLECTOR_993</td>\n", |
|
|
565 |
" <td>23</td>\n", |
|
|
566 |
" </tr>\n", |
|
|
567 |
" <tr>\n", |
|
|
568 |
" <th>2226</th>\n", |
|
|
569 |
" <td>COLLECTOR_995</td>\n", |
|
|
570 |
" <td>2</td>\n", |
|
|
571 |
" </tr>\n", |
|
|
572 |
" <tr>\n", |
|
|
573 |
" <th>2227</th>\n", |
|
|
574 |
" <td>COLLECTOR_999</td>\n", |
|
|
575 |
" <td>41</td>\n", |
|
|
576 |
" </tr>\n", |
|
|
577 |
" </tbody>\n", |
|
|
578 |
"</table>\n", |
|
|
579 |
"<p>2228 rows × 2 columns</p>\n", |
|
|
580 |
"</div>" |
|
|
581 |
], |
|
|
582 |
"text/plain": [ |
|
|
583 |
" COLLECTOR_ID SPECIMEN_COUNT\n", |
|
|
584 |
"0 COLLECTOR_101 7\n", |
|
|
585 |
"1 COLLECTOR_1013 35\n", |
|
|
586 |
"2 COLLECTOR_1028 23\n", |
|
|
587 |
"3 COLLECTOR_1029 17\n", |
|
|
588 |
"4 COLLECTOR_1031 30\n", |
|
|
589 |
"... ... ...\n", |
|
|
590 |
"2223 COLLECTOR_991 6\n", |
|
|
591 |
"2224 COLLECTOR_992 43\n", |
|
|
592 |
"2225 COLLECTOR_993 23\n", |
|
|
593 |
"2226 COLLECTOR_995 2\n", |
|
|
594 |
"2227 COLLECTOR_999 41\n", |
|
|
595 |
"\n", |
|
|
596 |
"[2228 rows x 2 columns]" |
|
|
597 |
] |
|
|
598 |
}, |
|
|
599 |
"execution_count": 5, |
|
|
600 |
"metadata": {}, |
|
|
601 |
"output_type": "execute_result" |
|
|
602 |
} |
|
|
603 |
], |
|
|
604 |
"source": [ |
|
|
605 |
"#calculate number of specimen per collector\n", |
|
|
606 |
"df2 = df[['COLLECTOR_ID', 'SPECIMEN_ID', 'HEMOLYSIS_INDEX']].copy()\n", |
|
|
607 |
"df2 = df2.groupby('COLLECTOR_ID')['SPECIMEN_ID'].nunique().reset_index()\n", |
|
|
608 |
"df2 = df2.rename(columns={'SPECIMEN_ID' : 'SPECIMEN_COUNT'})\n", |
|
|
609 |
"df2" |
|
|
610 |
] |
|
|
611 |
}, |
|
|
612 |
{ |
|
|
613 |
"cell_type": "code", |
|
|
614 |
"execution_count": 6, |
|
|
615 |
"id": "55aa964e", |
|
|
616 |
"metadata": { |
|
|
617 |
"scrolled": false |
|
|
618 |
}, |
|
|
619 |
"outputs": [ |
|
|
620 |
{ |
|
|
621 |
"data": { |
|
|
622 |
"text/html": [ |
|
|
623 |
"<div>\n", |
|
|
624 |
"<style scoped>\n", |
|
|
625 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
626 |
" vertical-align: middle;\n", |
|
|
627 |
" }\n", |
|
|
628 |
"\n", |
|
|
629 |
" .dataframe tbody tr th {\n", |
|
|
630 |
" vertical-align: top;\n", |
|
|
631 |
" }\n", |
|
|
632 |
"\n", |
|
|
633 |
" .dataframe thead th {\n", |
|
|
634 |
" text-align: right;\n", |
|
|
635 |
" }\n", |
|
|
636 |
"</style>\n", |
|
|
637 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
638 |
" <thead>\n", |
|
|
639 |
" <tr style=\"text-align: right;\">\n", |
|
|
640 |
" <th></th>\n", |
|
|
641 |
" <th>COLLECTOR_ID</th>\n", |
|
|
642 |
" <th>median_hi</th>\n", |
|
|
643 |
" </tr>\n", |
|
|
644 |
" </thead>\n", |
|
|
645 |
" <tbody>\n", |
|
|
646 |
" <tr>\n", |
|
|
647 |
" <th>0</th>\n", |
|
|
648 |
" <td>COLLECTOR_101</td>\n", |
|
|
649 |
" <td>9.0</td>\n", |
|
|
650 |
" </tr>\n", |
|
|
651 |
" <tr>\n", |
|
|
652 |
" <th>1</th>\n", |
|
|
653 |
" <td>COLLECTOR_1013</td>\n", |
|
|
654 |
" <td>12.0</td>\n", |
|
|
655 |
" </tr>\n", |
|
|
656 |
" <tr>\n", |
|
|
657 |
" <th>2</th>\n", |
|
|
658 |
" <td>COLLECTOR_1028</td>\n", |
|
|
659 |
" <td>8.0</td>\n", |
|
|
660 |
" </tr>\n", |
|
|
661 |
" <tr>\n", |
|
|
662 |
" <th>3</th>\n", |
|
|
663 |
" <td>COLLECTOR_1029</td>\n", |
|
|
664 |
" <td>5.0</td>\n", |
|
|
665 |
" </tr>\n", |
|
|
666 |
" <tr>\n", |
|
|
667 |
" <th>4</th>\n", |
|
|
668 |
" <td>COLLECTOR_1031</td>\n", |
|
|
669 |
" <td>15.5</td>\n", |
|
|
670 |
" </tr>\n", |
|
|
671 |
" <tr>\n", |
|
|
672 |
" <th>...</th>\n", |
|
|
673 |
" <td>...</td>\n", |
|
|
674 |
" <td>...</td>\n", |
|
|
675 |
" </tr>\n", |
|
|
676 |
" <tr>\n", |
|
|
677 |
" <th>2223</th>\n", |
|
|
678 |
" <td>COLLECTOR_991</td>\n", |
|
|
679 |
" <td>16.5</td>\n", |
|
|
680 |
" </tr>\n", |
|
|
681 |
" <tr>\n", |
|
|
682 |
" <th>2224</th>\n", |
|
|
683 |
" <td>COLLECTOR_992</td>\n", |
|
|
684 |
" <td>16.0</td>\n", |
|
|
685 |
" </tr>\n", |
|
|
686 |
" <tr>\n", |
|
|
687 |
" <th>2225</th>\n", |
|
|
688 |
" <td>COLLECTOR_993</td>\n", |
|
|
689 |
" <td>11.0</td>\n", |
|
|
690 |
" </tr>\n", |
|
|
691 |
" <tr>\n", |
|
|
692 |
" <th>2226</th>\n", |
|
|
693 |
" <td>COLLECTOR_995</td>\n", |
|
|
694 |
" <td>7.5</td>\n", |
|
|
695 |
" </tr>\n", |
|
|
696 |
" <tr>\n", |
|
|
697 |
" <th>2227</th>\n", |
|
|
698 |
" <td>COLLECTOR_999</td>\n", |
|
|
699 |
" <td>12.0</td>\n", |
|
|
700 |
" </tr>\n", |
|
|
701 |
" </tbody>\n", |
|
|
702 |
"</table>\n", |
|
|
703 |
"<p>2228 rows × 2 columns</p>\n", |
|
|
704 |
"</div>" |
|
|
705 |
], |
|
|
706 |
"text/plain": [ |
|
|
707 |
" COLLECTOR_ID median_hi\n", |
|
|
708 |
"0 COLLECTOR_101 9.0\n", |
|
|
709 |
"1 COLLECTOR_1013 12.0\n", |
|
|
710 |
"2 COLLECTOR_1028 8.0\n", |
|
|
711 |
"3 COLLECTOR_1029 5.0\n", |
|
|
712 |
"4 COLLECTOR_1031 15.5\n", |
|
|
713 |
"... ... ...\n", |
|
|
714 |
"2223 COLLECTOR_991 16.5\n", |
|
|
715 |
"2224 COLLECTOR_992 16.0\n", |
|
|
716 |
"2225 COLLECTOR_993 11.0\n", |
|
|
717 |
"2226 COLLECTOR_995 7.5\n", |
|
|
718 |
"2227 COLLECTOR_999 12.0\n", |
|
|
719 |
"\n", |
|
|
720 |
"[2228 rows x 2 columns]" |
|
|
721 |
] |
|
|
722 |
}, |
|
|
723 |
"execution_count": 6, |
|
|
724 |
"metadata": {}, |
|
|
725 |
"output_type": "execute_result" |
|
|
726 |
} |
|
|
727 |
], |
|
|
728 |
"source": [ |
|
|
729 |
"#%% compute median hemolysis index per collector\n", |
|
|
730 |
"def compute_median(X:pd.DataFrame)->float:\n", |
|
|
731 |
" '''Return median hemolsysis index across a collectors samples'''\n", |
|
|
732 |
" median=X.drop_duplicates(subset='SPECIMEN_ID')['HEMOLYSIS_INDEX'].median()\n", |
|
|
733 |
" return(median)\n", |
|
|
734 |
"\n", |
|
|
735 |
"median_hi=df.groupby('COLLECTOR_ID').apply(lambda X: compute_median(X))\n", |
|
|
736 |
"median_hi=median_hi.reset_index().rename(columns={0:'median_hi'})\n", |
|
|
737 |
"median_hi" |
|
|
738 |
] |
|
|
739 |
}, |
|
|
740 |
{ |
|
|
741 |
"cell_type": "code", |
|
|
742 |
"execution_count": 7, |
|
|
743 |
"id": "adb51e58", |
|
|
744 |
"metadata": {}, |
|
|
745 |
"outputs": [ |
|
|
746 |
{ |
|
|
747 |
"data": { |
|
|
748 |
"text/html": [ |
|
|
749 |
"<div>\n", |
|
|
750 |
"<style scoped>\n", |
|
|
751 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
752 |
" vertical-align: middle;\n", |
|
|
753 |
" }\n", |
|
|
754 |
"\n", |
|
|
755 |
" .dataframe tbody tr th {\n", |
|
|
756 |
" vertical-align: top;\n", |
|
|
757 |
" }\n", |
|
|
758 |
"\n", |
|
|
759 |
" .dataframe thead th {\n", |
|
|
760 |
" text-align: right;\n", |
|
|
761 |
" }\n", |
|
|
762 |
"</style>\n", |
|
|
763 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
764 |
" <thead>\n", |
|
|
765 |
" <tr style=\"text-align: right;\">\n", |
|
|
766 |
" <th></th>\n", |
|
|
767 |
" <th>COLLECTOR_ID</th>\n", |
|
|
768 |
" <th>ENCOUNTER_TYPE</th>\n", |
|
|
769 |
" </tr>\n", |
|
|
770 |
" </thead>\n", |
|
|
771 |
" <tbody>\n", |
|
|
772 |
" <tr>\n", |
|
|
773 |
" <th>0</th>\n", |
|
|
774 |
" <td>COLLECTOR_2732</td>\n", |
|
|
775 |
" <td>Intensive Care</td>\n", |
|
|
776 |
" </tr>\n", |
|
|
777 |
" <tr>\n", |
|
|
778 |
" <th>1</th>\n", |
|
|
779 |
" <td>COLLECTOR_522</td>\n", |
|
|
780 |
" <td>Inpatient</td>\n", |
|
|
781 |
" </tr>\n", |
|
|
782 |
" <tr>\n", |
|
|
783 |
" <th>2</th>\n", |
|
|
784 |
" <td>COLLECTOR_201</td>\n", |
|
|
785 |
" <td>Intensive Care</td>\n", |
|
|
786 |
" </tr>\n", |
|
|
787 |
" <tr>\n", |
|
|
788 |
" <th>3</th>\n", |
|
|
789 |
" <td>COLLECTOR_3469</td>\n", |
|
|
790 |
" <td>Emergency</td>\n", |
|
|
791 |
" </tr>\n", |
|
|
792 |
" <tr>\n", |
|
|
793 |
" <th>4</th>\n", |
|
|
794 |
" <td>COLLECTOR_2720</td>\n", |
|
|
795 |
" <td>Intensive Care</td>\n", |
|
|
796 |
" </tr>\n", |
|
|
797 |
" <tr>\n", |
|
|
798 |
" <th>...</th>\n", |
|
|
799 |
" <td>...</td>\n", |
|
|
800 |
" <td>...</td>\n", |
|
|
801 |
" </tr>\n", |
|
|
802 |
" <tr>\n", |
|
|
803 |
" <th>2224</th>\n", |
|
|
804 |
" <td>COLLECTOR_4046</td>\n", |
|
|
805 |
" <td>Inpatient</td>\n", |
|
|
806 |
" </tr>\n", |
|
|
807 |
" <tr>\n", |
|
|
808 |
" <th>2225</th>\n", |
|
|
809 |
" <td>COLLECTOR_3746</td>\n", |
|
|
810 |
" <td>Outpatient</td>\n", |
|
|
811 |
" </tr>\n", |
|
|
812 |
" <tr>\n", |
|
|
813 |
" <th>2226</th>\n", |
|
|
814 |
" <td>COLLECTOR_1858</td>\n", |
|
|
815 |
" <td>Emergency</td>\n", |
|
|
816 |
" </tr>\n", |
|
|
817 |
" <tr>\n", |
|
|
818 |
" <th>2227</th>\n", |
|
|
819 |
" <td>COLLECTOR_4625</td>\n", |
|
|
820 |
" <td>Inpatient</td>\n", |
|
|
821 |
" </tr>\n", |
|
|
822 |
" <tr>\n", |
|
|
823 |
" <th>2228</th>\n", |
|
|
824 |
" <td>COLLECTOR_693</td>\n", |
|
|
825 |
" <td>Inpatient</td>\n", |
|
|
826 |
" </tr>\n", |
|
|
827 |
" </tbody>\n", |
|
|
828 |
"</table>\n", |
|
|
829 |
"<p>2229 rows × 2 columns</p>\n", |
|
|
830 |
"</div>" |
|
|
831 |
], |
|
|
832 |
"text/plain": [ |
|
|
833 |
" COLLECTOR_ID ENCOUNTER_TYPE\n", |
|
|
834 |
"0 COLLECTOR_2732 Intensive Care\n", |
|
|
835 |
"1 COLLECTOR_522 Inpatient\n", |
|
|
836 |
"2 COLLECTOR_201 Intensive Care\n", |
|
|
837 |
"3 COLLECTOR_3469 Emergency\n", |
|
|
838 |
"4 COLLECTOR_2720 Intensive Care\n", |
|
|
839 |
"... ... ...\n", |
|
|
840 |
"2224 COLLECTOR_4046 Inpatient\n", |
|
|
841 |
"2225 COLLECTOR_3746 Outpatient\n", |
|
|
842 |
"2226 COLLECTOR_1858 Emergency\n", |
|
|
843 |
"2227 COLLECTOR_4625 Inpatient\n", |
|
|
844 |
"2228 COLLECTOR_693 Inpatient\n", |
|
|
845 |
"\n", |
|
|
846 |
"[2229 rows x 2 columns]" |
|
|
847 |
] |
|
|
848 |
}, |
|
|
849 |
"execution_count": 7, |
|
|
850 |
"metadata": {}, |
|
|
851 |
"output_type": "execute_result" |
|
|
852 |
} |
|
|
853 |
], |
|
|
854 |
"source": [ |
|
|
855 |
"#determine specialized encoutner type for each collector\n", |
|
|
856 |
"df4 = df[['COLLECTOR_ID', 'ENCOUNTER_TYPE']].drop_duplicates(subset='COLLECTOR_ID').reset_index(drop=True).copy()\n", |
|
|
857 |
"df4" |
|
|
858 |
] |
|
|
859 |
}, |
|
|
860 |
{ |
|
|
861 |
"cell_type": "code", |
|
|
862 |
"execution_count": 8, |
|
|
863 |
"id": "16712b4e", |
|
|
864 |
"metadata": { |
|
|
865 |
"scrolled": false |
|
|
866 |
}, |
|
|
867 |
"outputs": [ |
|
|
868 |
{ |
|
|
869 |
"data": { |
|
|
870 |
"text/html": [ |
|
|
871 |
"<div>\n", |
|
|
872 |
"<style scoped>\n", |
|
|
873 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
874 |
" vertical-align: middle;\n", |
|
|
875 |
" }\n", |
|
|
876 |
"\n", |
|
|
877 |
" .dataframe tbody tr th {\n", |
|
|
878 |
" vertical-align: top;\n", |
|
|
879 |
" }\n", |
|
|
880 |
"\n", |
|
|
881 |
" .dataframe thead th {\n", |
|
|
882 |
" text-align: right;\n", |
|
|
883 |
" }\n", |
|
|
884 |
"</style>\n", |
|
|
885 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
886 |
" <thead>\n", |
|
|
887 |
" <tr style=\"text-align: right;\">\n", |
|
|
888 |
" <th></th>\n", |
|
|
889 |
" <th>SPLIT</th>\n", |
|
|
890 |
" <th>COLLECTOR_ID</th>\n", |
|
|
891 |
" <th>RELEVANCE</th>\n", |
|
|
892 |
" <th>median_hi</th>\n", |
|
|
893 |
" <th>SPECIMEN_COUNT</th>\n", |
|
|
894 |
" <th>REDRAW_COUNT</th>\n", |
|
|
895 |
" <th>ENCOUNTER_TYPE</th>\n", |
|
|
896 |
" <th>REDRAW_COST</th>\n", |
|
|
897 |
" <th>REDRAW_PERCENT</th>\n", |
|
|
898 |
" </tr>\n", |
|
|
899 |
" </thead>\n", |
|
|
900 |
" <tbody>\n", |
|
|
901 |
" <tr>\n", |
|
|
902 |
" <th>0</th>\n", |
|
|
903 |
" <td>TRAIN</td>\n", |
|
|
904 |
" <td>COLLECTOR_13</td>\n", |
|
|
905 |
" <td>0.00000</td>\n", |
|
|
906 |
" <td>29.0</td>\n", |
|
|
907 |
" <td>2.0</td>\n", |
|
|
908 |
" <td>0.0</td>\n", |
|
|
909 |
" <td>Inpatient</td>\n", |
|
|
910 |
" <td>357.15</td>\n", |
|
|
911 |
" <td>0.000000</td>\n", |
|
|
912 |
" </tr>\n", |
|
|
913 |
" <tr>\n", |
|
|
914 |
" <th>1</th>\n", |
|
|
915 |
" <td>TRAIN</td>\n", |
|
|
916 |
" <td>COLLECTOR_2184</td>\n", |
|
|
917 |
" <td>0.00000</td>\n", |
|
|
918 |
" <td>18.0</td>\n", |
|
|
919 |
" <td>13.0</td>\n", |
|
|
920 |
" <td>2.0</td>\n", |
|
|
921 |
" <td>Inpatient</td>\n", |
|
|
922 |
" <td>357.15</td>\n", |
|
|
923 |
" <td>0.153846</td>\n", |
|
|
924 |
" </tr>\n", |
|
|
925 |
" <tr>\n", |
|
|
926 |
" <th>2</th>\n", |
|
|
927 |
" <td>TRAIN</td>\n", |
|
|
928 |
" <td>COLLECTOR_798</td>\n", |
|
|
929 |
" <td>0.00000</td>\n", |
|
|
930 |
" <td>13.0</td>\n", |
|
|
931 |
" <td>39.0</td>\n", |
|
|
932 |
" <td>2.0</td>\n", |
|
|
933 |
" <td>Intensive Care</td>\n", |
|
|
934 |
" <td>162.18</td>\n", |
|
|
935 |
" <td>0.051282</td>\n", |
|
|
936 |
" </tr>\n", |
|
|
937 |
" <tr>\n", |
|
|
938 |
" <th>3</th>\n", |
|
|
939 |
" <td>TRAIN</td>\n", |
|
|
940 |
" <td>COLLECTOR_492</td>\n", |
|
|
941 |
" <td>0.32436</td>\n", |
|
|
942 |
" <td>21.0</td>\n", |
|
|
943 |
" <td>20.0</td>\n", |
|
|
944 |
" <td>2.0</td>\n", |
|
|
945 |
" <td>Intensive Care</td>\n", |
|
|
946 |
" <td>162.18</td>\n", |
|
|
947 |
" <td>0.100000</td>\n", |
|
|
948 |
" </tr>\n", |
|
|
949 |
" <tr>\n", |
|
|
950 |
" <th>4</th>\n", |
|
|
951 |
" <td>TRAIN</td>\n", |
|
|
952 |
" <td>COLLECTOR_2658</td>\n", |
|
|
953 |
" <td>0.00000</td>\n", |
|
|
954 |
" <td>10.5</td>\n", |
|
|
955 |
" <td>26.0</td>\n", |
|
|
956 |
" <td>0.0</td>\n", |
|
|
957 |
" <td>Inpatient</td>\n", |
|
|
958 |
" <td>357.15</td>\n", |
|
|
959 |
" <td>0.000000</td>\n", |
|
|
960 |
" </tr>\n", |
|
|
961 |
" <tr>\n", |
|
|
962 |
" <th>...</th>\n", |
|
|
963 |
" <td>...</td>\n", |
|
|
964 |
" <td>...</td>\n", |
|
|
965 |
" <td>...</td>\n", |
|
|
966 |
" <td>...</td>\n", |
|
|
967 |
" <td>...</td>\n", |
|
|
968 |
" <td>...</td>\n", |
|
|
969 |
" <td>...</td>\n", |
|
|
970 |
" <td>...</td>\n", |
|
|
971 |
" <td>...</td>\n", |
|
|
972 |
" </tr>\n", |
|
|
973 |
" <tr>\n", |
|
|
974 |
" <th>1338</th>\n", |
|
|
975 |
" <td>TRAIN</td>\n", |
|
|
976 |
" <td>COLLECTOR_3798</td>\n", |
|
|
977 |
" <td>0.00000</td>\n", |
|
|
978 |
" <td>33.0</td>\n", |
|
|
979 |
" <td>9.0</td>\n", |
|
|
980 |
" <td>1.0</td>\n", |
|
|
981 |
" <td>Inpatient</td>\n", |
|
|
982 |
" <td>357.15</td>\n", |
|
|
983 |
" <td>0.111111</td>\n", |
|
|
984 |
" </tr>\n", |
|
|
985 |
" <tr>\n", |
|
|
986 |
" <th>1339</th>\n", |
|
|
987 |
" <td>TRAIN</td>\n", |
|
|
988 |
" <td>COLLECTOR_3397</td>\n", |
|
|
989 |
" <td>0.00000</td>\n", |
|
|
990 |
" <td>12.5</td>\n", |
|
|
991 |
" <td>46.0</td>\n", |
|
|
992 |
" <td>3.0</td>\n", |
|
|
993 |
" <td>Inpatient</td>\n", |
|
|
994 |
" <td>357.15</td>\n", |
|
|
995 |
" <td>0.065217</td>\n", |
|
|
996 |
" </tr>\n", |
|
|
997 |
" <tr>\n", |
|
|
998 |
" <th>1340</th>\n", |
|
|
999 |
" <td>TRAIN</td>\n", |
|
|
1000 |
" <td>COLLECTOR_33</td>\n", |
|
|
1001 |
" <td>0.00000</td>\n", |
|
|
1002 |
" <td>13.0</td>\n", |
|
|
1003 |
" <td>43.0</td>\n", |
|
|
1004 |
" <td>2.0</td>\n", |
|
|
1005 |
" <td>Inpatient</td>\n", |
|
|
1006 |
" <td>357.15</td>\n", |
|
|
1007 |
" <td>0.046512</td>\n", |
|
|
1008 |
" </tr>\n", |
|
|
1009 |
" <tr>\n", |
|
|
1010 |
" <th>1341</th>\n", |
|
|
1011 |
" <td>TRAIN</td>\n", |
|
|
1012 |
" <td>COLLECTOR_3001</td>\n", |
|
|
1013 |
" <td>0.00000</td>\n", |
|
|
1014 |
" <td>13.0</td>\n", |
|
|
1015 |
" <td>3.0</td>\n", |
|
|
1016 |
" <td>0.0</td>\n", |
|
|
1017 |
" <td>Inpatient</td>\n", |
|
|
1018 |
" <td>357.15</td>\n", |
|
|
1019 |
" <td>0.000000</td>\n", |
|
|
1020 |
" </tr>\n", |
|
|
1021 |
" <tr>\n", |
|
|
1022 |
" <th>1342</th>\n", |
|
|
1023 |
" <td>TRAIN</td>\n", |
|
|
1024 |
" <td>COLLECTOR_4667</td>\n", |
|
|
1025 |
" <td>0.00000</td>\n", |
|
|
1026 |
" <td>13.0</td>\n", |
|
|
1027 |
" <td>6.0</td>\n", |
|
|
1028 |
" <td>0.0</td>\n", |
|
|
1029 |
" <td>Inpatient</td>\n", |
|
|
1030 |
" <td>357.15</td>\n", |
|
|
1031 |
" <td>0.000000</td>\n", |
|
|
1032 |
" </tr>\n", |
|
|
1033 |
" </tbody>\n", |
|
|
1034 |
"</table>\n", |
|
|
1035 |
"<p>1343 rows × 9 columns</p>\n", |
|
|
1036 |
"</div>" |
|
|
1037 |
], |
|
|
1038 |
"text/plain": [ |
|
|
1039 |
" SPLIT COLLECTOR_ID RELEVANCE median_hi SPECIMEN_COUNT \\\n", |
|
|
1040 |
"0 TRAIN COLLECTOR_13 0.00000 29.0 2.0 \n", |
|
|
1041 |
"1 TRAIN COLLECTOR_2184 0.00000 18.0 13.0 \n", |
|
|
1042 |
"2 TRAIN COLLECTOR_798 0.00000 13.0 39.0 \n", |
|
|
1043 |
"3 TRAIN COLLECTOR_492 0.32436 21.0 20.0 \n", |
|
|
1044 |
"4 TRAIN COLLECTOR_2658 0.00000 10.5 26.0 \n", |
|
|
1045 |
"... ... ... ... ... ... \n", |
|
|
1046 |
"1338 TRAIN COLLECTOR_3798 0.00000 33.0 9.0 \n", |
|
|
1047 |
"1339 TRAIN COLLECTOR_3397 0.00000 12.5 46.0 \n", |
|
|
1048 |
"1340 TRAIN COLLECTOR_33 0.00000 13.0 43.0 \n", |
|
|
1049 |
"1341 TRAIN COLLECTOR_3001 0.00000 13.0 3.0 \n", |
|
|
1050 |
"1342 TRAIN COLLECTOR_4667 0.00000 13.0 6.0 \n", |
|
|
1051 |
"\n", |
|
|
1052 |
" REDRAW_COUNT ENCOUNTER_TYPE REDRAW_COST REDRAW_PERCENT \n", |
|
|
1053 |
"0 0.0 Inpatient 357.15 0.000000 \n", |
|
|
1054 |
"1 2.0 Inpatient 357.15 0.153846 \n", |
|
|
1055 |
"2 2.0 Intensive Care 162.18 0.051282 \n", |
|
|
1056 |
"3 2.0 Intensive Care 162.18 0.100000 \n", |
|
|
1057 |
"4 0.0 Inpatient 357.15 0.000000 \n", |
|
|
1058 |
"... ... ... ... ... \n", |
|
|
1059 |
"1338 1.0 Inpatient 357.15 0.111111 \n", |
|
|
1060 |
"1339 3.0 Inpatient 357.15 0.065217 \n", |
|
|
1061 |
"1340 2.0 Inpatient 357.15 0.046512 \n", |
|
|
1062 |
"1341 0.0 Inpatient 357.15 0.000000 \n", |
|
|
1063 |
"1342 0.0 Inpatient 357.15 0.000000 \n", |
|
|
1064 |
"\n", |
|
|
1065 |
"[1343 rows x 9 columns]" |
|
|
1066 |
] |
|
|
1067 |
}, |
|
|
1068 |
"execution_count": 8, |
|
|
1069 |
"metadata": {}, |
|
|
1070 |
"output_type": "execute_result" |
|
|
1071 |
} |
|
|
1072 |
], |
|
|
1073 |
"source": [ |
|
|
1074 |
"#join features with train collector ids in sample solution \n", |
|
|
1075 |
"train=pd.read_csv('train.csv')\n", |
|
|
1076 |
"train=train.merge(median_hi,how='left',on='COLLECTOR_ID')\n", |
|
|
1077 |
"train=train.merge(df2,how='left',on='COLLECTOR_ID')\n", |
|
|
1078 |
"train=train.merge(df3,how='left',on='COLLECTOR_ID')\n", |
|
|
1079 |
"train=train.merge(df4,how='left',on='COLLECTOR_ID')\n", |
|
|
1080 |
"train=train.merge(cost,how='left',on='ENCOUNTER_TYPE')\n", |
|
|
1081 |
"train['REDRAW_COUNT'] = train['REDRAW_COUNT'].fillna(0)\n", |
|
|
1082 |
"train['REDRAW_PERCENT'] = train['REDRAW_COUNT'] / train['SPECIMEN_COUNT']\n", |
|
|
1083 |
"train" |
|
|
1084 |
] |
|
|
1085 |
}, |
|
|
1086 |
{ |
|
|
1087 |
"cell_type": "code", |
|
|
1088 |
"execution_count": 9, |
|
|
1089 |
"id": "775a5158", |
|
|
1090 |
"metadata": {}, |
|
|
1091 |
"outputs": [ |
|
|
1092 |
{ |
|
|
1093 |
"data": { |
|
|
1094 |
"text/html": [ |
|
|
1095 |
"<div>\n", |
|
|
1096 |
"<style scoped>\n", |
|
|
1097 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1098 |
" vertical-align: middle;\n", |
|
|
1099 |
" }\n", |
|
|
1100 |
"\n", |
|
|
1101 |
" .dataframe tbody tr th {\n", |
|
|
1102 |
" vertical-align: top;\n", |
|
|
1103 |
" }\n", |
|
|
1104 |
"\n", |
|
|
1105 |
" .dataframe thead th {\n", |
|
|
1106 |
" text-align: right;\n", |
|
|
1107 |
" }\n", |
|
|
1108 |
"</style>\n", |
|
|
1109 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1110 |
" <thead>\n", |
|
|
1111 |
" <tr style=\"text-align: right;\">\n", |
|
|
1112 |
" <th></th>\n", |
|
|
1113 |
" <th>RELEVANCE</th>\n", |
|
|
1114 |
" <th>median_hi</th>\n", |
|
|
1115 |
" <th>REDRAW_COUNT</th>\n", |
|
|
1116 |
" <th>ENCOUNTER_TYPE</th>\n", |
|
|
1117 |
" <th>REDRAW_COST</th>\n", |
|
|
1118 |
" <th>REDRAW_PERCENT</th>\n", |
|
|
1119 |
" </tr>\n", |
|
|
1120 |
" </thead>\n", |
|
|
1121 |
" <tbody>\n", |
|
|
1122 |
" <tr>\n", |
|
|
1123 |
" <th>0</th>\n", |
|
|
1124 |
" <td>0.00000</td>\n", |
|
|
1125 |
" <td>29.0</td>\n", |
|
|
1126 |
" <td>0.0</td>\n", |
|
|
1127 |
" <td>Inpatient</td>\n", |
|
|
1128 |
" <td>357.15</td>\n", |
|
|
1129 |
" <td>0.000000</td>\n", |
|
|
1130 |
" </tr>\n", |
|
|
1131 |
" <tr>\n", |
|
|
1132 |
" <th>1</th>\n", |
|
|
1133 |
" <td>0.00000</td>\n", |
|
|
1134 |
" <td>18.0</td>\n", |
|
|
1135 |
" <td>2.0</td>\n", |
|
|
1136 |
" <td>Inpatient</td>\n", |
|
|
1137 |
" <td>357.15</td>\n", |
|
|
1138 |
" <td>0.153846</td>\n", |
|
|
1139 |
" </tr>\n", |
|
|
1140 |
" <tr>\n", |
|
|
1141 |
" <th>2</th>\n", |
|
|
1142 |
" <td>0.00000</td>\n", |
|
|
1143 |
" <td>13.0</td>\n", |
|
|
1144 |
" <td>2.0</td>\n", |
|
|
1145 |
" <td>Intensive Care</td>\n", |
|
|
1146 |
" <td>162.18</td>\n", |
|
|
1147 |
" <td>0.051282</td>\n", |
|
|
1148 |
" </tr>\n", |
|
|
1149 |
" <tr>\n", |
|
|
1150 |
" <th>3</th>\n", |
|
|
1151 |
" <td>0.32436</td>\n", |
|
|
1152 |
" <td>21.0</td>\n", |
|
|
1153 |
" <td>2.0</td>\n", |
|
|
1154 |
" <td>Intensive Care</td>\n", |
|
|
1155 |
" <td>162.18</td>\n", |
|
|
1156 |
" <td>0.100000</td>\n", |
|
|
1157 |
" </tr>\n", |
|
|
1158 |
" <tr>\n", |
|
|
1159 |
" <th>4</th>\n", |
|
|
1160 |
" <td>0.00000</td>\n", |
|
|
1161 |
" <td>10.5</td>\n", |
|
|
1162 |
" <td>0.0</td>\n", |
|
|
1163 |
" <td>Inpatient</td>\n", |
|
|
1164 |
" <td>357.15</td>\n", |
|
|
1165 |
" <td>0.000000</td>\n", |
|
|
1166 |
" </tr>\n", |
|
|
1167 |
" <tr>\n", |
|
|
1168 |
" <th>...</th>\n", |
|
|
1169 |
" <td>...</td>\n", |
|
|
1170 |
" <td>...</td>\n", |
|
|
1171 |
" <td>...</td>\n", |
|
|
1172 |
" <td>...</td>\n", |
|
|
1173 |
" <td>...</td>\n", |
|
|
1174 |
" <td>...</td>\n", |
|
|
1175 |
" </tr>\n", |
|
|
1176 |
" <tr>\n", |
|
|
1177 |
" <th>1338</th>\n", |
|
|
1178 |
" <td>0.00000</td>\n", |
|
|
1179 |
" <td>33.0</td>\n", |
|
|
1180 |
" <td>1.0</td>\n", |
|
|
1181 |
" <td>Inpatient</td>\n", |
|
|
1182 |
" <td>357.15</td>\n", |
|
|
1183 |
" <td>0.111111</td>\n", |
|
|
1184 |
" </tr>\n", |
|
|
1185 |
" <tr>\n", |
|
|
1186 |
" <th>1339</th>\n", |
|
|
1187 |
" <td>0.00000</td>\n", |
|
|
1188 |
" <td>12.5</td>\n", |
|
|
1189 |
" <td>3.0</td>\n", |
|
|
1190 |
" <td>Inpatient</td>\n", |
|
|
1191 |
" <td>357.15</td>\n", |
|
|
1192 |
" <td>0.065217</td>\n", |
|
|
1193 |
" </tr>\n", |
|
|
1194 |
" <tr>\n", |
|
|
1195 |
" <th>1340</th>\n", |
|
|
1196 |
" <td>0.00000</td>\n", |
|
|
1197 |
" <td>13.0</td>\n", |
|
|
1198 |
" <td>2.0</td>\n", |
|
|
1199 |
" <td>Inpatient</td>\n", |
|
|
1200 |
" <td>357.15</td>\n", |
|
|
1201 |
" <td>0.046512</td>\n", |
|
|
1202 |
" </tr>\n", |
|
|
1203 |
" <tr>\n", |
|
|
1204 |
" <th>1341</th>\n", |
|
|
1205 |
" <td>0.00000</td>\n", |
|
|
1206 |
" <td>13.0</td>\n", |
|
|
1207 |
" <td>0.0</td>\n", |
|
|
1208 |
" <td>Inpatient</td>\n", |
|
|
1209 |
" <td>357.15</td>\n", |
|
|
1210 |
" <td>0.000000</td>\n", |
|
|
1211 |
" </tr>\n", |
|
|
1212 |
" <tr>\n", |
|
|
1213 |
" <th>1342</th>\n", |
|
|
1214 |
" <td>0.00000</td>\n", |
|
|
1215 |
" <td>13.0</td>\n", |
|
|
1216 |
" <td>0.0</td>\n", |
|
|
1217 |
" <td>Inpatient</td>\n", |
|
|
1218 |
" <td>357.15</td>\n", |
|
|
1219 |
" <td>0.000000</td>\n", |
|
|
1220 |
" </tr>\n", |
|
|
1221 |
" </tbody>\n", |
|
|
1222 |
"</table>\n", |
|
|
1223 |
"<p>1343 rows × 6 columns</p>\n", |
|
|
1224 |
"</div>" |
|
|
1225 |
], |
|
|
1226 |
"text/plain": [ |
|
|
1227 |
" RELEVANCE median_hi REDRAW_COUNT ENCOUNTER_TYPE REDRAW_COST \\\n", |
|
|
1228 |
"0 0.00000 29.0 0.0 Inpatient 357.15 \n", |
|
|
1229 |
"1 0.00000 18.0 2.0 Inpatient 357.15 \n", |
|
|
1230 |
"2 0.00000 13.0 2.0 Intensive Care 162.18 \n", |
|
|
1231 |
"3 0.32436 21.0 2.0 Intensive Care 162.18 \n", |
|
|
1232 |
"4 0.00000 10.5 0.0 Inpatient 357.15 \n", |
|
|
1233 |
"... ... ... ... ... ... \n", |
|
|
1234 |
"1338 0.00000 33.0 1.0 Inpatient 357.15 \n", |
|
|
1235 |
"1339 0.00000 12.5 3.0 Inpatient 357.15 \n", |
|
|
1236 |
"1340 0.00000 13.0 2.0 Inpatient 357.15 \n", |
|
|
1237 |
"1341 0.00000 13.0 0.0 Inpatient 357.15 \n", |
|
|
1238 |
"1342 0.00000 13.0 0.0 Inpatient 357.15 \n", |
|
|
1239 |
"\n", |
|
|
1240 |
" REDRAW_PERCENT \n", |
|
|
1241 |
"0 0.000000 \n", |
|
|
1242 |
"1 0.153846 \n", |
|
|
1243 |
"2 0.051282 \n", |
|
|
1244 |
"3 0.100000 \n", |
|
|
1245 |
"4 0.000000 \n", |
|
|
1246 |
"... ... \n", |
|
|
1247 |
"1338 0.111111 \n", |
|
|
1248 |
"1339 0.065217 \n", |
|
|
1249 |
"1340 0.046512 \n", |
|
|
1250 |
"1341 0.000000 \n", |
|
|
1251 |
"1342 0.000000 \n", |
|
|
1252 |
"\n", |
|
|
1253 |
"[1343 rows x 6 columns]" |
|
|
1254 |
] |
|
|
1255 |
}, |
|
|
1256 |
"execution_count": 9, |
|
|
1257 |
"metadata": {}, |
|
|
1258 |
"output_type": "execute_result" |
|
|
1259 |
} |
|
|
1260 |
], |
|
|
1261 |
"source": [ |
|
|
1262 |
"#remove redundant columns\n", |
|
|
1263 |
"train = train.drop(['SPLIT', 'SPECIMEN_COUNT', 'COLLECTOR_ID'], axis = 1)\n", |
|
|
1264 |
"train" |
|
|
1265 |
] |
|
|
1266 |
}, |
|
|
1267 |
{ |
|
|
1268 |
"cell_type": "code", |
|
|
1269 |
"execution_count": 10, |
|
|
1270 |
"id": "90827e7b", |
|
|
1271 |
"metadata": {}, |
|
|
1272 |
"outputs": [ |
|
|
1273 |
{ |
|
|
1274 |
"data": { |
|
|
1275 |
"text/html": [ |
|
|
1276 |
"<div>\n", |
|
|
1277 |
"<style scoped>\n", |
|
|
1278 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1279 |
" vertical-align: middle;\n", |
|
|
1280 |
" }\n", |
|
|
1281 |
"\n", |
|
|
1282 |
" .dataframe tbody tr th {\n", |
|
|
1283 |
" vertical-align: top;\n", |
|
|
1284 |
" }\n", |
|
|
1285 |
"\n", |
|
|
1286 |
" .dataframe thead th {\n", |
|
|
1287 |
" text-align: right;\n", |
|
|
1288 |
" }\n", |
|
|
1289 |
"</style>\n", |
|
|
1290 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1291 |
" <thead>\n", |
|
|
1292 |
" <tr style=\"text-align: right;\">\n", |
|
|
1293 |
" <th></th>\n", |
|
|
1294 |
" <th>RELEVANCE</th>\n", |
|
|
1295 |
" <th>median_hi</th>\n", |
|
|
1296 |
" <th>REDRAW_COUNT</th>\n", |
|
|
1297 |
" <th>REDRAW_COST</th>\n", |
|
|
1298 |
" <th>REDRAW_PERCENT</th>\n", |
|
|
1299 |
" </tr>\n", |
|
|
1300 |
" </thead>\n", |
|
|
1301 |
" <tbody>\n", |
|
|
1302 |
" <tr>\n", |
|
|
1303 |
" <th>0</th>\n", |
|
|
1304 |
" <td>0.000000</td>\n", |
|
|
1305 |
" <td>29.0</td>\n", |
|
|
1306 |
" <td>0.0</td>\n", |
|
|
1307 |
" <td>357.15</td>\n", |
|
|
1308 |
" <td>0.000000</td>\n", |
|
|
1309 |
" </tr>\n", |
|
|
1310 |
" <tr>\n", |
|
|
1311 |
" <th>1</th>\n", |
|
|
1312 |
" <td>0.000000</td>\n", |
|
|
1313 |
" <td>18.0</td>\n", |
|
|
1314 |
" <td>2.0</td>\n", |
|
|
1315 |
" <td>357.15</td>\n", |
|
|
1316 |
" <td>0.153846</td>\n", |
|
|
1317 |
" </tr>\n", |
|
|
1318 |
" <tr>\n", |
|
|
1319 |
" <th>4</th>\n", |
|
|
1320 |
" <td>0.000000</td>\n", |
|
|
1321 |
" <td>10.5</td>\n", |
|
|
1322 |
" <td>0.0</td>\n", |
|
|
1323 |
" <td>357.15</td>\n", |
|
|
1324 |
" <td>0.000000</td>\n", |
|
|
1325 |
" </tr>\n", |
|
|
1326 |
" <tr>\n", |
|
|
1327 |
" <th>7</th>\n", |
|
|
1328 |
" <td>0.912717</td>\n", |
|
|
1329 |
" <td>10.0</td>\n", |
|
|
1330 |
" <td>1.0</td>\n", |
|
|
1331 |
" <td>357.15</td>\n", |
|
|
1332 |
" <td>0.045455</td>\n", |
|
|
1333 |
" </tr>\n", |
|
|
1334 |
" <tr>\n", |
|
|
1335 |
" <th>8</th>\n", |
|
|
1336 |
" <td>0.000000</td>\n", |
|
|
1337 |
" <td>10.0</td>\n", |
|
|
1338 |
" <td>0.0</td>\n", |
|
|
1339 |
" <td>357.15</td>\n", |
|
|
1340 |
" <td>0.000000</td>\n", |
|
|
1341 |
" </tr>\n", |
|
|
1342 |
" <tr>\n", |
|
|
1343 |
" <th>...</th>\n", |
|
|
1344 |
" <td>...</td>\n", |
|
|
1345 |
" <td>...</td>\n", |
|
|
1346 |
" <td>...</td>\n", |
|
|
1347 |
" <td>...</td>\n", |
|
|
1348 |
" <td>...</td>\n", |
|
|
1349 |
" </tr>\n", |
|
|
1350 |
" <tr>\n", |
|
|
1351 |
" <th>1338</th>\n", |
|
|
1352 |
" <td>0.000000</td>\n", |
|
|
1353 |
" <td>33.0</td>\n", |
|
|
1354 |
" <td>1.0</td>\n", |
|
|
1355 |
" <td>357.15</td>\n", |
|
|
1356 |
" <td>0.111111</td>\n", |
|
|
1357 |
" </tr>\n", |
|
|
1358 |
" <tr>\n", |
|
|
1359 |
" <th>1339</th>\n", |
|
|
1360 |
" <td>0.000000</td>\n", |
|
|
1361 |
" <td>12.5</td>\n", |
|
|
1362 |
" <td>3.0</td>\n", |
|
|
1363 |
" <td>357.15</td>\n", |
|
|
1364 |
" <td>0.065217</td>\n", |
|
|
1365 |
" </tr>\n", |
|
|
1366 |
" <tr>\n", |
|
|
1367 |
" <th>1340</th>\n", |
|
|
1368 |
" <td>0.000000</td>\n", |
|
|
1369 |
" <td>13.0</td>\n", |
|
|
1370 |
" <td>2.0</td>\n", |
|
|
1371 |
" <td>357.15</td>\n", |
|
|
1372 |
" <td>0.046512</td>\n", |
|
|
1373 |
" </tr>\n", |
|
|
1374 |
" <tr>\n", |
|
|
1375 |
" <th>1341</th>\n", |
|
|
1376 |
" <td>0.000000</td>\n", |
|
|
1377 |
" <td>13.0</td>\n", |
|
|
1378 |
" <td>0.0</td>\n", |
|
|
1379 |
" <td>357.15</td>\n", |
|
|
1380 |
" <td>0.000000</td>\n", |
|
|
1381 |
" </tr>\n", |
|
|
1382 |
" <tr>\n", |
|
|
1383 |
" <th>1342</th>\n", |
|
|
1384 |
" <td>0.000000</td>\n", |
|
|
1385 |
" <td>13.0</td>\n", |
|
|
1386 |
" <td>0.0</td>\n", |
|
|
1387 |
" <td>357.15</td>\n", |
|
|
1388 |
" <td>0.000000</td>\n", |
|
|
1389 |
" </tr>\n", |
|
|
1390 |
" </tbody>\n", |
|
|
1391 |
"</table>\n", |
|
|
1392 |
"<p>937 rows × 5 columns</p>\n", |
|
|
1393 |
"</div>" |
|
|
1394 |
], |
|
|
1395 |
"text/plain": [ |
|
|
1396 |
" RELEVANCE median_hi REDRAW_COUNT REDRAW_COST REDRAW_PERCENT\n", |
|
|
1397 |
"0 0.000000 29.0 0.0 357.15 0.000000\n", |
|
|
1398 |
"1 0.000000 18.0 2.0 357.15 0.153846\n", |
|
|
1399 |
"4 0.000000 10.5 0.0 357.15 0.000000\n", |
|
|
1400 |
"7 0.912717 10.0 1.0 357.15 0.045455\n", |
|
|
1401 |
"8 0.000000 10.0 0.0 357.15 0.000000\n", |
|
|
1402 |
"... ... ... ... ... ...\n", |
|
|
1403 |
"1338 0.000000 33.0 1.0 357.15 0.111111\n", |
|
|
1404 |
"1339 0.000000 12.5 3.0 357.15 0.065217\n", |
|
|
1405 |
"1340 0.000000 13.0 2.0 357.15 0.046512\n", |
|
|
1406 |
"1341 0.000000 13.0 0.0 357.15 0.000000\n", |
|
|
1407 |
"1342 0.000000 13.0 0.0 357.15 0.000000\n", |
|
|
1408 |
"\n", |
|
|
1409 |
"[937 rows x 5 columns]" |
|
|
1410 |
] |
|
|
1411 |
}, |
|
|
1412 |
"execution_count": 10, |
|
|
1413 |
"metadata": {}, |
|
|
1414 |
"output_type": "execute_result" |
|
|
1415 |
} |
|
|
1416 |
], |
|
|
1417 |
"source": [ |
|
|
1418 |
"#filter for only Emergency and Inpatient collectors\n", |
|
|
1419 |
"emergency = train.loc[(train['ENCOUNTER_TYPE'] == \"Emergency\") | (train['ENCOUNTER_TYPE'] == \"Inpatient\")]\n", |
|
|
1420 |
"emergency = emergency.drop('ENCOUNTER_TYPE', axis=1)\n", |
|
|
1421 |
"emergency" |
|
|
1422 |
] |
|
|
1423 |
}, |
|
|
1424 |
{ |
|
|
1425 |
"cell_type": "code", |
|
|
1426 |
"execution_count": 11, |
|
|
1427 |
"id": "613d0944", |
|
|
1428 |
"metadata": {}, |
|
|
1429 |
"outputs": [], |
|
|
1430 |
"source": [ |
|
|
1431 |
"import pandas as pd\n", |
|
|
1432 |
"import numpy as np\n", |
|
|
1433 |
"import xgboost as xgb\n", |
|
|
1434 |
"from sklearn.model_selection import train_test_split\n", |
|
|
1435 |
"from sklearn.metrics import mean_squared_error" |
|
|
1436 |
] |
|
|
1437 |
}, |
|
|
1438 |
{ |
|
|
1439 |
"cell_type": "code", |
|
|
1440 |
"execution_count": 12, |
|
|
1441 |
"id": "9e8eb69c", |
|
|
1442 |
"metadata": {}, |
|
|
1443 |
"outputs": [], |
|
|
1444 |
"source": [ |
|
|
1445 |
"X = emergency.drop('RELEVANCE', axis=1)\n", |
|
|
1446 |
"y = emergency['RELEVANCE']\n", |
|
|
1447 |
"\n", |
|
|
1448 |
"#Select only nonzero relevance scores to train on\n", |
|
|
1449 |
"X=X[y>0]\n", |
|
|
1450 |
"y=y[y>0]\n", |
|
|
1451 |
"\n", |
|
|
1452 |
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" |
|
|
1453 |
] |
|
|
1454 |
}, |
|
|
1455 |
{ |
|
|
1456 |
"cell_type": "code", |
|
|
1457 |
"execution_count": 13, |
|
|
1458 |
"id": "e3153ef9", |
|
|
1459 |
"metadata": {}, |
|
|
1460 |
"outputs": [], |
|
|
1461 |
"source": [ |
|
|
1462 |
"dtrain = xgb.DMatrix(X_train, label=y_train)\n", |
|
|
1463 |
"dtest = xgb.DMatrix(X_test, label=y_test)\n", |
|
|
1464 |
"params = {\n", |
|
|
1465 |
" \"max_depth\": 15,\n", |
|
|
1466 |
" \"eta\": 0.3,\n", |
|
|
1467 |
" \"subsample\": 1.0,\n", |
|
|
1468 |
" \"colsample_bytree\": 1.0,\n", |
|
|
1469 |
" \"learning_rate\": 0.35,\n", |
|
|
1470 |
" \"objective\": \"reg:squarederror\",\n", |
|
|
1471 |
" \"eval_metric\": \"rmse\"\n", |
|
|
1472 |
"}" |
|
|
1473 |
] |
|
|
1474 |
}, |
|
|
1475 |
{ |
|
|
1476 |
"cell_type": "code", |
|
|
1477 |
"execution_count": 14, |
|
|
1478 |
"id": "d951fb6b", |
|
|
1479 |
"metadata": {}, |
|
|
1480 |
"outputs": [], |
|
|
1481 |
"source": [ |
|
|
1482 |
"num_round = 100\n", |
|
|
1483 |
"bst = xgb.train(params, dtrain, num_round)" |
|
|
1484 |
] |
|
|
1485 |
}, |
|
|
1486 |
{ |
|
|
1487 |
"cell_type": "code", |
|
|
1488 |
"execution_count": 15, |
|
|
1489 |
"id": "9a096d9f", |
|
|
1490 |
"metadata": {}, |
|
|
1491 |
"outputs": [ |
|
|
1492 |
{ |
|
|
1493 |
"name": "stdout", |
|
|
1494 |
"output_type": "stream", |
|
|
1495 |
"text": [ |
|
|
1496 |
"RMSE: 3.329161021152597\n" |
|
|
1497 |
] |
|
|
1498 |
} |
|
|
1499 |
], |
|
|
1500 |
"source": [ |
|
|
1501 |
"preds = bst.predict(dtest)\n", |
|
|
1502 |
"rmse = mean_squared_error(y_test, preds, squared=False)\n", |
|
|
1503 |
"print(\"RMSE:\", rmse)" |
|
|
1504 |
] |
|
|
1505 |
}, |
|
|
1506 |
{ |
|
|
1507 |
"cell_type": "code", |
|
|
1508 |
"execution_count": 16, |
|
|
1509 |
"id": "d0f696f3", |
|
|
1510 |
"metadata": {}, |
|
|
1511 |
"outputs": [ |
|
|
1512 |
{ |
|
|
1513 |
"data": { |
|
|
1514 |
"text/html": [ |
|
|
1515 |
"<div>\n", |
|
|
1516 |
"<style scoped>\n", |
|
|
1517 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1518 |
" vertical-align: middle;\n", |
|
|
1519 |
" }\n", |
|
|
1520 |
"\n", |
|
|
1521 |
" .dataframe tbody tr th {\n", |
|
|
1522 |
" vertical-align: top;\n", |
|
|
1523 |
" }\n", |
|
|
1524 |
"\n", |
|
|
1525 |
" .dataframe thead th {\n", |
|
|
1526 |
" text-align: right;\n", |
|
|
1527 |
" }\n", |
|
|
1528 |
"</style>\n", |
|
|
1529 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1530 |
" <thead>\n", |
|
|
1531 |
" <tr style=\"text-align: right;\">\n", |
|
|
1532 |
" <th></th>\n", |
|
|
1533 |
" <th>SPLIT</th>\n", |
|
|
1534 |
" <th>COLLECTOR_ID</th>\n", |
|
|
1535 |
" <th>median_hi</th>\n", |
|
|
1536 |
" <th>SPECIMEN_COUNT</th>\n", |
|
|
1537 |
" <th>REDRAW_COUNT</th>\n", |
|
|
1538 |
" <th>ENCOUNTER_TYPE</th>\n", |
|
|
1539 |
" <th>REDRAW_COST</th>\n", |
|
|
1540 |
" <th>REDRAW_PERCENT</th>\n", |
|
|
1541 |
" </tr>\n", |
|
|
1542 |
" </thead>\n", |
|
|
1543 |
" <tbody>\n", |
|
|
1544 |
" <tr>\n", |
|
|
1545 |
" <th>0</th>\n", |
|
|
1546 |
" <td>TEST</td>\n", |
|
|
1547 |
" <td>COLLECTOR_2011</td>\n", |
|
|
1548 |
" <td>32.0</td>\n", |
|
|
1549 |
" <td>17.0</td>\n", |
|
|
1550 |
" <td>4.0</td>\n", |
|
|
1551 |
" <td>Emergency</td>\n", |
|
|
1552 |
" <td>600.00</td>\n", |
|
|
1553 |
" <td>0.235294</td>\n", |
|
|
1554 |
" </tr>\n", |
|
|
1555 |
" <tr>\n", |
|
|
1556 |
" <th>1</th>\n", |
|
|
1557 |
" <td>TEST</td>\n", |
|
|
1558 |
" <td>COLLECTOR_1550</td>\n", |
|
|
1559 |
" <td>50.0</td>\n", |
|
|
1560 |
" <td>9.0</td>\n", |
|
|
1561 |
" <td>3.0</td>\n", |
|
|
1562 |
" <td>Inpatient</td>\n", |
|
|
1563 |
" <td>357.15</td>\n", |
|
|
1564 |
" <td>0.333333</td>\n", |
|
|
1565 |
" </tr>\n", |
|
|
1566 |
" <tr>\n", |
|
|
1567 |
" <th>2</th>\n", |
|
|
1568 |
" <td>TEST</td>\n", |
|
|
1569 |
" <td>COLLECTOR_4570</td>\n", |
|
|
1570 |
" <td>8.0</td>\n", |
|
|
1571 |
" <td>32.0</td>\n", |
|
|
1572 |
" <td>2.0</td>\n", |
|
|
1573 |
" <td>Intensive Care</td>\n", |
|
|
1574 |
" <td>162.18</td>\n", |
|
|
1575 |
" <td>0.062500</td>\n", |
|
|
1576 |
" </tr>\n", |
|
|
1577 |
" <tr>\n", |
|
|
1578 |
" <th>3</th>\n", |
|
|
1579 |
" <td>TEST</td>\n", |
|
|
1580 |
" <td>COLLECTOR_3531</td>\n", |
|
|
1581 |
" <td>9.0</td>\n", |
|
|
1582 |
" <td>7.0</td>\n", |
|
|
1583 |
" <td>0.0</td>\n", |
|
|
1584 |
" <td>Inpatient</td>\n", |
|
|
1585 |
" <td>357.15</td>\n", |
|
|
1586 |
" <td>0.000000</td>\n", |
|
|
1587 |
" </tr>\n", |
|
|
1588 |
" <tr>\n", |
|
|
1589 |
" <th>4</th>\n", |
|
|
1590 |
" <td>TEST</td>\n", |
|
|
1591 |
" <td>COLLECTOR_5020</td>\n", |
|
|
1592 |
" <td>31.0</td>\n", |
|
|
1593 |
" <td>18.0</td>\n", |
|
|
1594 |
" <td>2.0</td>\n", |
|
|
1595 |
" <td>Emergency</td>\n", |
|
|
1596 |
" <td>600.00</td>\n", |
|
|
1597 |
" <td>0.111111</td>\n", |
|
|
1598 |
" </tr>\n", |
|
|
1599 |
" <tr>\n", |
|
|
1600 |
" <th>...</th>\n", |
|
|
1601 |
" <td>...</td>\n", |
|
|
1602 |
" <td>...</td>\n", |
|
|
1603 |
" <td>...</td>\n", |
|
|
1604 |
" <td>...</td>\n", |
|
|
1605 |
" <td>...</td>\n", |
|
|
1606 |
" <td>...</td>\n", |
|
|
1607 |
" <td>...</td>\n", |
|
|
1608 |
" <td>...</td>\n", |
|
|
1609 |
" </tr>\n", |
|
|
1610 |
" <tr>\n", |
|
|
1611 |
" <th>890</th>\n", |
|
|
1612 |
" <td>TEST</td>\n", |
|
|
1613 |
" <td>COLLECTOR_2848</td>\n", |
|
|
1614 |
" <td>14.0</td>\n", |
|
|
1615 |
" <td>31.0</td>\n", |
|
|
1616 |
" <td>1.0</td>\n", |
|
|
1617 |
" <td>Inpatient</td>\n", |
|
|
1618 |
" <td>357.15</td>\n", |
|
|
1619 |
" <td>0.032258</td>\n", |
|
|
1620 |
" </tr>\n", |
|
|
1621 |
" <tr>\n", |
|
|
1622 |
" <th>891</th>\n", |
|
|
1623 |
" <td>TEST</td>\n", |
|
|
1624 |
" <td>COLLECTOR_1501</td>\n", |
|
|
1625 |
" <td>1.0</td>\n", |
|
|
1626 |
" <td>1.0</td>\n", |
|
|
1627 |
" <td>0.0</td>\n", |
|
|
1628 |
" <td>Inpatient</td>\n", |
|
|
1629 |
" <td>357.15</td>\n", |
|
|
1630 |
" <td>0.000000</td>\n", |
|
|
1631 |
" </tr>\n", |
|
|
1632 |
" <tr>\n", |
|
|
1633 |
" <th>892</th>\n", |
|
|
1634 |
" <td>TEST</td>\n", |
|
|
1635 |
" <td>COLLECTOR_860</td>\n", |
|
|
1636 |
" <td>72.0</td>\n", |
|
|
1637 |
" <td>48.0</td>\n", |
|
|
1638 |
" <td>23.0</td>\n", |
|
|
1639 |
" <td>Inpatient</td>\n", |
|
|
1640 |
" <td>357.15</td>\n", |
|
|
1641 |
" <td>0.479167</td>\n", |
|
|
1642 |
" </tr>\n", |
|
|
1643 |
" <tr>\n", |
|
|
1644 |
" <th>893</th>\n", |
|
|
1645 |
" <td>TEST</td>\n", |
|
|
1646 |
" <td>COLLECTOR_3200</td>\n", |
|
|
1647 |
" <td>30.0</td>\n", |
|
|
1648 |
" <td>3.0</td>\n", |
|
|
1649 |
" <td>1.0</td>\n", |
|
|
1650 |
" <td>Inpatient</td>\n", |
|
|
1651 |
" <td>357.15</td>\n", |
|
|
1652 |
" <td>0.333333</td>\n", |
|
|
1653 |
" </tr>\n", |
|
|
1654 |
" <tr>\n", |
|
|
1655 |
" <th>894</th>\n", |
|
|
1656 |
" <td>TEST</td>\n", |
|
|
1657 |
" <td>COLLECTOR_4788</td>\n", |
|
|
1658 |
" <td>12.0</td>\n", |
|
|
1659 |
" <td>4.0</td>\n", |
|
|
1660 |
" <td>1.0</td>\n", |
|
|
1661 |
" <td>Intensive Care</td>\n", |
|
|
1662 |
" <td>162.18</td>\n", |
|
|
1663 |
" <td>0.250000</td>\n", |
|
|
1664 |
" </tr>\n", |
|
|
1665 |
" </tbody>\n", |
|
|
1666 |
"</table>\n", |
|
|
1667 |
"<p>895 rows × 8 columns</p>\n", |
|
|
1668 |
"</div>" |
|
|
1669 |
], |
|
|
1670 |
"text/plain": [ |
|
|
1671 |
" SPLIT COLLECTOR_ID median_hi SPECIMEN_COUNT REDRAW_COUNT \\\n", |
|
|
1672 |
"0 TEST COLLECTOR_2011 32.0 17.0 4.0 \n", |
|
|
1673 |
"1 TEST COLLECTOR_1550 50.0 9.0 3.0 \n", |
|
|
1674 |
"2 TEST COLLECTOR_4570 8.0 32.0 2.0 \n", |
|
|
1675 |
"3 TEST COLLECTOR_3531 9.0 7.0 0.0 \n", |
|
|
1676 |
"4 TEST COLLECTOR_5020 31.0 18.0 2.0 \n", |
|
|
1677 |
".. ... ... ... ... ... \n", |
|
|
1678 |
"890 TEST COLLECTOR_2848 14.0 31.0 1.0 \n", |
|
|
1679 |
"891 TEST COLLECTOR_1501 1.0 1.0 0.0 \n", |
|
|
1680 |
"892 TEST COLLECTOR_860 72.0 48.0 23.0 \n", |
|
|
1681 |
"893 TEST COLLECTOR_3200 30.0 3.0 1.0 \n", |
|
|
1682 |
"894 TEST COLLECTOR_4788 12.0 4.0 1.0 \n", |
|
|
1683 |
"\n", |
|
|
1684 |
" ENCOUNTER_TYPE REDRAW_COST REDRAW_PERCENT \n", |
|
|
1685 |
"0 Emergency 600.00 0.235294 \n", |
|
|
1686 |
"1 Inpatient 357.15 0.333333 \n", |
|
|
1687 |
"2 Intensive Care 162.18 0.062500 \n", |
|
|
1688 |
"3 Inpatient 357.15 0.000000 \n", |
|
|
1689 |
"4 Emergency 600.00 0.111111 \n", |
|
|
1690 |
".. ... ... ... \n", |
|
|
1691 |
"890 Inpatient 357.15 0.032258 \n", |
|
|
1692 |
"891 Inpatient 357.15 0.000000 \n", |
|
|
1693 |
"892 Inpatient 357.15 0.479167 \n", |
|
|
1694 |
"893 Inpatient 357.15 0.333333 \n", |
|
|
1695 |
"894 Intensive Care 162.18 0.250000 \n", |
|
|
1696 |
"\n", |
|
|
1697 |
"[895 rows x 8 columns]" |
|
|
1698 |
] |
|
|
1699 |
}, |
|
|
1700 |
"execution_count": 16, |
|
|
1701 |
"metadata": {}, |
|
|
1702 |
"output_type": "execute_result" |
|
|
1703 |
} |
|
|
1704 |
], |
|
|
1705 |
"source": [ |
|
|
1706 |
"#calculate features for test set\n", |
|
|
1707 |
"test=pd.read_csv('test.csv')\n", |
|
|
1708 |
"test=test.merge(median_hi,how='left',on='COLLECTOR_ID')\n", |
|
|
1709 |
"test=test.merge(df2,how='left',on='COLLECTOR_ID')\n", |
|
|
1710 |
"test=test.merge(df3,how='left',on='COLLECTOR_ID')\n", |
|
|
1711 |
"test=test.merge(df4,how='left',on='COLLECTOR_ID')\n", |
|
|
1712 |
"test=test.merge(cost,how='left',on='ENCOUNTER_TYPE')\n", |
|
|
1713 |
"test['REDRAW_COUNT'] = test['REDRAW_COUNT'].fillna(0)\n", |
|
|
1714 |
"test['REDRAW_PERCENT'] = test['REDRAW_COUNT'] / test['SPECIMEN_COUNT']\n", |
|
|
1715 |
"test" |
|
|
1716 |
] |
|
|
1717 |
}, |
|
|
1718 |
{ |
|
|
1719 |
"cell_type": "code", |
|
|
1720 |
"execution_count": 17, |
|
|
1721 |
"id": "61f0a30f", |
|
|
1722 |
"metadata": {}, |
|
|
1723 |
"outputs": [ |
|
|
1724 |
{ |
|
|
1725 |
"data": { |
|
|
1726 |
"text/html": [ |
|
|
1727 |
"<div>\n", |
|
|
1728 |
"<style scoped>\n", |
|
|
1729 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1730 |
" vertical-align: middle;\n", |
|
|
1731 |
" }\n", |
|
|
1732 |
"\n", |
|
|
1733 |
" .dataframe tbody tr th {\n", |
|
|
1734 |
" vertical-align: top;\n", |
|
|
1735 |
" }\n", |
|
|
1736 |
"\n", |
|
|
1737 |
" .dataframe thead th {\n", |
|
|
1738 |
" text-align: right;\n", |
|
|
1739 |
" }\n", |
|
|
1740 |
"</style>\n", |
|
|
1741 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1742 |
" <thead>\n", |
|
|
1743 |
" <tr style=\"text-align: right;\">\n", |
|
|
1744 |
" <th></th>\n", |
|
|
1745 |
" <th>median_hi</th>\n", |
|
|
1746 |
" <th>REDRAW_COUNT</th>\n", |
|
|
1747 |
" <th>REDRAW_COST</th>\n", |
|
|
1748 |
" <th>REDRAW_PERCENT</th>\n", |
|
|
1749 |
" </tr>\n", |
|
|
1750 |
" </thead>\n", |
|
|
1751 |
" <tbody>\n", |
|
|
1752 |
" <tr>\n", |
|
|
1753 |
" <th>0</th>\n", |
|
|
1754 |
" <td>32.0</td>\n", |
|
|
1755 |
" <td>4.0</td>\n", |
|
|
1756 |
" <td>600.00</td>\n", |
|
|
1757 |
" <td>0.235294</td>\n", |
|
|
1758 |
" </tr>\n", |
|
|
1759 |
" <tr>\n", |
|
|
1760 |
" <th>1</th>\n", |
|
|
1761 |
" <td>50.0</td>\n", |
|
|
1762 |
" <td>3.0</td>\n", |
|
|
1763 |
" <td>357.15</td>\n", |
|
|
1764 |
" <td>0.333333</td>\n", |
|
|
1765 |
" </tr>\n", |
|
|
1766 |
" <tr>\n", |
|
|
1767 |
" <th>3</th>\n", |
|
|
1768 |
" <td>9.0</td>\n", |
|
|
1769 |
" <td>0.0</td>\n", |
|
|
1770 |
" <td>357.15</td>\n", |
|
|
1771 |
" <td>0.000000</td>\n", |
|
|
1772 |
" </tr>\n", |
|
|
1773 |
" <tr>\n", |
|
|
1774 |
" <th>4</th>\n", |
|
|
1775 |
" <td>31.0</td>\n", |
|
|
1776 |
" <td>2.0</td>\n", |
|
|
1777 |
" <td>600.00</td>\n", |
|
|
1778 |
" <td>0.111111</td>\n", |
|
|
1779 |
" </tr>\n", |
|
|
1780 |
" <tr>\n", |
|
|
1781 |
" <th>6</th>\n", |
|
|
1782 |
" <td>16.0</td>\n", |
|
|
1783 |
" <td>0.0</td>\n", |
|
|
1784 |
" <td>357.15</td>\n", |
|
|
1785 |
" <td>0.000000</td>\n", |
|
|
1786 |
" </tr>\n", |
|
|
1787 |
" <tr>\n", |
|
|
1788 |
" <th>...</th>\n", |
|
|
1789 |
" <td>...</td>\n", |
|
|
1790 |
" <td>...</td>\n", |
|
|
1791 |
" <td>...</td>\n", |
|
|
1792 |
" <td>...</td>\n", |
|
|
1793 |
" </tr>\n", |
|
|
1794 |
" <tr>\n", |
|
|
1795 |
" <th>888</th>\n", |
|
|
1796 |
" <td>12.5</td>\n", |
|
|
1797 |
" <td>1.0</td>\n", |
|
|
1798 |
" <td>357.15</td>\n", |
|
|
1799 |
" <td>0.019231</td>\n", |
|
|
1800 |
" </tr>\n", |
|
|
1801 |
" <tr>\n", |
|
|
1802 |
" <th>890</th>\n", |
|
|
1803 |
" <td>14.0</td>\n", |
|
|
1804 |
" <td>1.0</td>\n", |
|
|
1805 |
" <td>357.15</td>\n", |
|
|
1806 |
" <td>0.032258</td>\n", |
|
|
1807 |
" </tr>\n", |
|
|
1808 |
" <tr>\n", |
|
|
1809 |
" <th>891</th>\n", |
|
|
1810 |
" <td>1.0</td>\n", |
|
|
1811 |
" <td>0.0</td>\n", |
|
|
1812 |
" <td>357.15</td>\n", |
|
|
1813 |
" <td>0.000000</td>\n", |
|
|
1814 |
" </tr>\n", |
|
|
1815 |
" <tr>\n", |
|
|
1816 |
" <th>892</th>\n", |
|
|
1817 |
" <td>72.0</td>\n", |
|
|
1818 |
" <td>23.0</td>\n", |
|
|
1819 |
" <td>357.15</td>\n", |
|
|
1820 |
" <td>0.479167</td>\n", |
|
|
1821 |
" </tr>\n", |
|
|
1822 |
" <tr>\n", |
|
|
1823 |
" <th>893</th>\n", |
|
|
1824 |
" <td>30.0</td>\n", |
|
|
1825 |
" <td>1.0</td>\n", |
|
|
1826 |
" <td>357.15</td>\n", |
|
|
1827 |
" <td>0.333333</td>\n", |
|
|
1828 |
" </tr>\n", |
|
|
1829 |
" </tbody>\n", |
|
|
1830 |
"</table>\n", |
|
|
1831 |
"<p>635 rows × 4 columns</p>\n", |
|
|
1832 |
"</div>" |
|
|
1833 |
], |
|
|
1834 |
"text/plain": [ |
|
|
1835 |
" median_hi REDRAW_COUNT REDRAW_COST REDRAW_PERCENT\n", |
|
|
1836 |
"0 32.0 4.0 600.00 0.235294\n", |
|
|
1837 |
"1 50.0 3.0 357.15 0.333333\n", |
|
|
1838 |
"3 9.0 0.0 357.15 0.000000\n", |
|
|
1839 |
"4 31.0 2.0 600.00 0.111111\n", |
|
|
1840 |
"6 16.0 0.0 357.15 0.000000\n", |
|
|
1841 |
".. ... ... ... ...\n", |
|
|
1842 |
"888 12.5 1.0 357.15 0.019231\n", |
|
|
1843 |
"890 14.0 1.0 357.15 0.032258\n", |
|
|
1844 |
"891 1.0 0.0 357.15 0.000000\n", |
|
|
1845 |
"892 72.0 23.0 357.15 0.479167\n", |
|
|
1846 |
"893 30.0 1.0 357.15 0.333333\n", |
|
|
1847 |
"\n", |
|
|
1848 |
"[635 rows x 4 columns]" |
|
|
1849 |
] |
|
|
1850 |
}, |
|
|
1851 |
"execution_count": 17, |
|
|
1852 |
"metadata": {}, |
|
|
1853 |
"output_type": "execute_result" |
|
|
1854 |
} |
|
|
1855 |
], |
|
|
1856 |
"source": [ |
|
|
1857 |
"test = test.drop(['SPLIT', 'SPECIMEN_COUNT', 'COLLECTOR_ID'], axis = 1)\n", |
|
|
1858 |
"test = test.loc[(test['ENCOUNTER_TYPE'] == \"Emergency\") | (test['ENCOUNTER_TYPE'] == \"Inpatient\")]\n", |
|
|
1859 |
"test = test.drop('ENCOUNTER_TYPE', axis=1)\n", |
|
|
1860 |
"test" |
|
|
1861 |
] |
|
|
1862 |
}, |
|
|
1863 |
{ |
|
|
1864 |
"cell_type": "code", |
|
|
1865 |
"execution_count": 18, |
|
|
1866 |
"id": "572def32", |
|
|
1867 |
"metadata": {}, |
|
|
1868 |
"outputs": [ |
|
|
1869 |
{ |
|
|
1870 |
"data": { |
|
|
1871 |
"text/html": [ |
|
|
1872 |
"<div>\n", |
|
|
1873 |
"<style scoped>\n", |
|
|
1874 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1875 |
" vertical-align: middle;\n", |
|
|
1876 |
" }\n", |
|
|
1877 |
"\n", |
|
|
1878 |
" .dataframe tbody tr th {\n", |
|
|
1879 |
" vertical-align: top;\n", |
|
|
1880 |
" }\n", |
|
|
1881 |
"\n", |
|
|
1882 |
" .dataframe thead th {\n", |
|
|
1883 |
" text-align: right;\n", |
|
|
1884 |
" }\n", |
|
|
1885 |
"</style>\n", |
|
|
1886 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1887 |
" <thead>\n", |
|
|
1888 |
" <tr style=\"text-align: right;\">\n", |
|
|
1889 |
" <th></th>\n", |
|
|
1890 |
" <th>median_hi</th>\n", |
|
|
1891 |
" <th>REDRAW_COUNT</th>\n", |
|
|
1892 |
" <th>REDRAW_COST</th>\n", |
|
|
1893 |
" <th>REDRAW_PERCENT</th>\n", |
|
|
1894 |
" <th>pred</th>\n", |
|
|
1895 |
" </tr>\n", |
|
|
1896 |
" </thead>\n", |
|
|
1897 |
" <tbody>\n", |
|
|
1898 |
" <tr>\n", |
|
|
1899 |
" <th>0</th>\n", |
|
|
1900 |
" <td>32.0</td>\n", |
|
|
1901 |
" <td>4.0</td>\n", |
|
|
1902 |
" <td>600.00</td>\n", |
|
|
1903 |
" <td>0.235294</td>\n", |
|
|
1904 |
" <td>1.953370</td>\n", |
|
|
1905 |
" </tr>\n", |
|
|
1906 |
" <tr>\n", |
|
|
1907 |
" <th>1</th>\n", |
|
|
1908 |
" <td>50.0</td>\n", |
|
|
1909 |
" <td>3.0</td>\n", |
|
|
1910 |
" <td>357.15</td>\n", |
|
|
1911 |
" <td>0.333333</td>\n", |
|
|
1912 |
" <td>2.510889</td>\n", |
|
|
1913 |
" </tr>\n", |
|
|
1914 |
" <tr>\n", |
|
|
1915 |
" <th>3</th>\n", |
|
|
1916 |
" <td>9.0</td>\n", |
|
|
1917 |
" <td>0.0</td>\n", |
|
|
1918 |
" <td>357.15</td>\n", |
|
|
1919 |
" <td>0.000000</td>\n", |
|
|
1920 |
" <td>0.304316</td>\n", |
|
|
1921 |
" </tr>\n", |
|
|
1922 |
" <tr>\n", |
|
|
1923 |
" <th>4</th>\n", |
|
|
1924 |
" <td>31.0</td>\n", |
|
|
1925 |
" <td>2.0</td>\n", |
|
|
1926 |
" <td>600.00</td>\n", |
|
|
1927 |
" <td>0.111111</td>\n", |
|
|
1928 |
" <td>1.311873</td>\n", |
|
|
1929 |
" </tr>\n", |
|
|
1930 |
" <tr>\n", |
|
|
1931 |
" <th>6</th>\n", |
|
|
1932 |
" <td>16.0</td>\n", |
|
|
1933 |
" <td>0.0</td>\n", |
|
|
1934 |
" <td>357.15</td>\n", |
|
|
1935 |
" <td>0.000000</td>\n", |
|
|
1936 |
" <td>0.332751</td>\n", |
|
|
1937 |
" </tr>\n", |
|
|
1938 |
" <tr>\n", |
|
|
1939 |
" <th>...</th>\n", |
|
|
1940 |
" <td>...</td>\n", |
|
|
1941 |
" <td>...</td>\n", |
|
|
1942 |
" <td>...</td>\n", |
|
|
1943 |
" <td>...</td>\n", |
|
|
1944 |
" <td>...</td>\n", |
|
|
1945 |
" </tr>\n", |
|
|
1946 |
" <tr>\n", |
|
|
1947 |
" <th>888</th>\n", |
|
|
1948 |
" <td>12.5</td>\n", |
|
|
1949 |
" <td>1.0</td>\n", |
|
|
1950 |
" <td>357.15</td>\n", |
|
|
1951 |
" <td>0.019231</td>\n", |
|
|
1952 |
" <td>1.501695</td>\n", |
|
|
1953 |
" </tr>\n", |
|
|
1954 |
" <tr>\n", |
|
|
1955 |
" <th>890</th>\n", |
|
|
1956 |
" <td>14.0</td>\n", |
|
|
1957 |
" <td>1.0</td>\n", |
|
|
1958 |
" <td>357.15</td>\n", |
|
|
1959 |
" <td>0.032258</td>\n", |
|
|
1960 |
" <td>1.442110</td>\n", |
|
|
1961 |
" </tr>\n", |
|
|
1962 |
" <tr>\n", |
|
|
1963 |
" <th>891</th>\n", |
|
|
1964 |
" <td>1.0</td>\n", |
|
|
1965 |
" <td>0.0</td>\n", |
|
|
1966 |
" <td>357.15</td>\n", |
|
|
1967 |
" <td>0.000000</td>\n", |
|
|
1968 |
" <td>0.356631</td>\n", |
|
|
1969 |
" </tr>\n", |
|
|
1970 |
" <tr>\n", |
|
|
1971 |
" <th>892</th>\n", |
|
|
1972 |
" <td>72.0</td>\n", |
|
|
1973 |
" <td>23.0</td>\n", |
|
|
1974 |
" <td>357.15</td>\n", |
|
|
1975 |
" <td>0.479167</td>\n", |
|
|
1976 |
" <td>0.846387</td>\n", |
|
|
1977 |
" </tr>\n", |
|
|
1978 |
" <tr>\n", |
|
|
1979 |
" <th>893</th>\n", |
|
|
1980 |
" <td>30.0</td>\n", |
|
|
1981 |
" <td>1.0</td>\n", |
|
|
1982 |
" <td>357.15</td>\n", |
|
|
1983 |
" <td>0.333333</td>\n", |
|
|
1984 |
" <td>1.144415</td>\n", |
|
|
1985 |
" </tr>\n", |
|
|
1986 |
" </tbody>\n", |
|
|
1987 |
"</table>\n", |
|
|
1988 |
"<p>635 rows × 5 columns</p>\n", |
|
|
1989 |
"</div>" |
|
|
1990 |
], |
|
|
1991 |
"text/plain": [ |
|
|
1992 |
" median_hi REDRAW_COUNT REDRAW_COST REDRAW_PERCENT pred\n", |
|
|
1993 |
"0 32.0 4.0 600.00 0.235294 1.953370\n", |
|
|
1994 |
"1 50.0 3.0 357.15 0.333333 2.510889\n", |
|
|
1995 |
"3 9.0 0.0 357.15 0.000000 0.304316\n", |
|
|
1996 |
"4 31.0 2.0 600.00 0.111111 1.311873\n", |
|
|
1997 |
"6 16.0 0.0 357.15 0.000000 0.332751\n", |
|
|
1998 |
".. ... ... ... ... ...\n", |
|
|
1999 |
"888 12.5 1.0 357.15 0.019231 1.501695\n", |
|
|
2000 |
"890 14.0 1.0 357.15 0.032258 1.442110\n", |
|
|
2001 |
"891 1.0 0.0 357.15 0.000000 0.356631\n", |
|
|
2002 |
"892 72.0 23.0 357.15 0.479167 0.846387\n", |
|
|
2003 |
"893 30.0 1.0 357.15 0.333333 1.144415\n", |
|
|
2004 |
"\n", |
|
|
2005 |
"[635 rows x 5 columns]" |
|
|
2006 |
] |
|
|
2007 |
}, |
|
|
2008 |
"execution_count": 18, |
|
|
2009 |
"metadata": {}, |
|
|
2010 |
"output_type": "execute_result" |
|
|
2011 |
} |
|
|
2012 |
], |
|
|
2013 |
"source": [ |
|
|
2014 |
"dtestset = xgb.DMatrix(test)\n", |
|
|
2015 |
"predictions = bst.predict(dtestset)\n", |
|
|
2016 |
"test[\"pred\"]=predictions\n", |
|
|
2017 |
"test" |
|
|
2018 |
] |
|
|
2019 |
}, |
|
|
2020 |
{ |
|
|
2021 |
"cell_type": "code", |
|
|
2022 |
"execution_count": 19, |
|
|
2023 |
"id": "fe3e4e03", |
|
|
2024 |
"metadata": {}, |
|
|
2025 |
"outputs": [ |
|
|
2026 |
{ |
|
|
2027 |
"data": { |
|
|
2028 |
"text/html": [ |
|
|
2029 |
"<div>\n", |
|
|
2030 |
"<style scoped>\n", |
|
|
2031 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
2032 |
" vertical-align: middle;\n", |
|
|
2033 |
" }\n", |
|
|
2034 |
"\n", |
|
|
2035 |
" .dataframe tbody tr th {\n", |
|
|
2036 |
" vertical-align: top;\n", |
|
|
2037 |
" }\n", |
|
|
2038 |
"\n", |
|
|
2039 |
" .dataframe thead th {\n", |
|
|
2040 |
" text-align: right;\n", |
|
|
2041 |
" }\n", |
|
|
2042 |
"</style>\n", |
|
|
2043 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
2044 |
" <thead>\n", |
|
|
2045 |
" <tr style=\"text-align: right;\">\n", |
|
|
2046 |
" <th></th>\n", |
|
|
2047 |
" <th>SPLIT</th>\n", |
|
|
2048 |
" <th>COLLECTOR_ID</th>\n", |
|
|
2049 |
" <th>pred</th>\n", |
|
|
2050 |
" </tr>\n", |
|
|
2051 |
" </thead>\n", |
|
|
2052 |
" <tbody>\n", |
|
|
2053 |
" <tr>\n", |
|
|
2054 |
" <th>0</th>\n", |
|
|
2055 |
" <td>TEST</td>\n", |
|
|
2056 |
" <td>COLLECTOR_2011</td>\n", |
|
|
2057 |
" <td>1.953370</td>\n", |
|
|
2058 |
" </tr>\n", |
|
|
2059 |
" <tr>\n", |
|
|
2060 |
" <th>1</th>\n", |
|
|
2061 |
" <td>TEST</td>\n", |
|
|
2062 |
" <td>COLLECTOR_1550</td>\n", |
|
|
2063 |
" <td>2.510889</td>\n", |
|
|
2064 |
" </tr>\n", |
|
|
2065 |
" <tr>\n", |
|
|
2066 |
" <th>2</th>\n", |
|
|
2067 |
" <td>TEST</td>\n", |
|
|
2068 |
" <td>COLLECTOR_4570</td>\n", |
|
|
2069 |
" <td>NaN</td>\n", |
|
|
2070 |
" </tr>\n", |
|
|
2071 |
" <tr>\n", |
|
|
2072 |
" <th>3</th>\n", |
|
|
2073 |
" <td>TEST</td>\n", |
|
|
2074 |
" <td>COLLECTOR_3531</td>\n", |
|
|
2075 |
" <td>0.304316</td>\n", |
|
|
2076 |
" </tr>\n", |
|
|
2077 |
" <tr>\n", |
|
|
2078 |
" <th>4</th>\n", |
|
|
2079 |
" <td>TEST</td>\n", |
|
|
2080 |
" <td>COLLECTOR_5020</td>\n", |
|
|
2081 |
" <td>1.311873</td>\n", |
|
|
2082 |
" </tr>\n", |
|
|
2083 |
" <tr>\n", |
|
|
2084 |
" <th>...</th>\n", |
|
|
2085 |
" <td>...</td>\n", |
|
|
2086 |
" <td>...</td>\n", |
|
|
2087 |
" <td>...</td>\n", |
|
|
2088 |
" </tr>\n", |
|
|
2089 |
" <tr>\n", |
|
|
2090 |
" <th>890</th>\n", |
|
|
2091 |
" <td>TEST</td>\n", |
|
|
2092 |
" <td>COLLECTOR_2848</td>\n", |
|
|
2093 |
" <td>1.442110</td>\n", |
|
|
2094 |
" </tr>\n", |
|
|
2095 |
" <tr>\n", |
|
|
2096 |
" <th>891</th>\n", |
|
|
2097 |
" <td>TEST</td>\n", |
|
|
2098 |
" <td>COLLECTOR_1501</td>\n", |
|
|
2099 |
" <td>0.356631</td>\n", |
|
|
2100 |
" </tr>\n", |
|
|
2101 |
" <tr>\n", |
|
|
2102 |
" <th>892</th>\n", |
|
|
2103 |
" <td>TEST</td>\n", |
|
|
2104 |
" <td>COLLECTOR_860</td>\n", |
|
|
2105 |
" <td>0.846387</td>\n", |
|
|
2106 |
" </tr>\n", |
|
|
2107 |
" <tr>\n", |
|
|
2108 |
" <th>893</th>\n", |
|
|
2109 |
" <td>TEST</td>\n", |
|
|
2110 |
" <td>COLLECTOR_3200</td>\n", |
|
|
2111 |
" <td>1.144415</td>\n", |
|
|
2112 |
" </tr>\n", |
|
|
2113 |
" <tr>\n", |
|
|
2114 |
" <th>894</th>\n", |
|
|
2115 |
" <td>TEST</td>\n", |
|
|
2116 |
" <td>COLLECTOR_4788</td>\n", |
|
|
2117 |
" <td>NaN</td>\n", |
|
|
2118 |
" </tr>\n", |
|
|
2119 |
" </tbody>\n", |
|
|
2120 |
"</table>\n", |
|
|
2121 |
"<p>895 rows × 3 columns</p>\n", |
|
|
2122 |
"</div>" |
|
|
2123 |
], |
|
|
2124 |
"text/plain": [ |
|
|
2125 |
" SPLIT COLLECTOR_ID pred\n", |
|
|
2126 |
"0 TEST COLLECTOR_2011 1.953370\n", |
|
|
2127 |
"1 TEST COLLECTOR_1550 2.510889\n", |
|
|
2128 |
"2 TEST COLLECTOR_4570 NaN\n", |
|
|
2129 |
"3 TEST COLLECTOR_3531 0.304316\n", |
|
|
2130 |
"4 TEST COLLECTOR_5020 1.311873\n", |
|
|
2131 |
".. ... ... ...\n", |
|
|
2132 |
"890 TEST COLLECTOR_2848 1.442110\n", |
|
|
2133 |
"891 TEST COLLECTOR_1501 0.356631\n", |
|
|
2134 |
"892 TEST COLLECTOR_860 0.846387\n", |
|
|
2135 |
"893 TEST COLLECTOR_3200 1.144415\n", |
|
|
2136 |
"894 TEST COLLECTOR_4788 NaN\n", |
|
|
2137 |
"\n", |
|
|
2138 |
"[895 rows x 3 columns]" |
|
|
2139 |
] |
|
|
2140 |
}, |
|
|
2141 |
"execution_count": 19, |
|
|
2142 |
"metadata": {}, |
|
|
2143 |
"output_type": "execute_result" |
|
|
2144 |
} |
|
|
2145 |
], |
|
|
2146 |
"source": [ |
|
|
2147 |
"sub=pd.read_csv('sample_solution.csv')\n", |
|
|
2148 |
"sub = sub.merge(test['pred'], how='left', left_index=True, right_index=True)\n", |
|
|
2149 |
"sub" |
|
|
2150 |
] |
|
|
2151 |
}, |
|
|
2152 |
{ |
|
|
2153 |
"cell_type": "code", |
|
|
2154 |
"execution_count": 20, |
|
|
2155 |
"id": "bed71081", |
|
|
2156 |
"metadata": { |
|
|
2157 |
"scrolled": true |
|
|
2158 |
}, |
|
|
2159 |
"outputs": [ |
|
|
2160 |
{ |
|
|
2161 |
"data": { |
|
|
2162 |
"text/html": [ |
|
|
2163 |
"<div>\n", |
|
|
2164 |
"<style scoped>\n", |
|
|
2165 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
2166 |
" vertical-align: middle;\n", |
|
|
2167 |
" }\n", |
|
|
2168 |
"\n", |
|
|
2169 |
" .dataframe tbody tr th {\n", |
|
|
2170 |
" vertical-align: top;\n", |
|
|
2171 |
" }\n", |
|
|
2172 |
"\n", |
|
|
2173 |
" .dataframe thead th {\n", |
|
|
2174 |
" text-align: right;\n", |
|
|
2175 |
" }\n", |
|
|
2176 |
"</style>\n", |
|
|
2177 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
2178 |
" <thead>\n", |
|
|
2179 |
" <tr style=\"text-align: right;\">\n", |
|
|
2180 |
" <th></th>\n", |
|
|
2181 |
" <th>SPLIT</th>\n", |
|
|
2182 |
" <th>COLLECTOR_ID</th>\n", |
|
|
2183 |
" <th>pred</th>\n", |
|
|
2184 |
" </tr>\n", |
|
|
2185 |
" </thead>\n", |
|
|
2186 |
" <tbody>\n", |
|
|
2187 |
" <tr>\n", |
|
|
2188 |
" <th>183</th>\n", |
|
|
2189 |
" <td>TEST</td>\n", |
|
|
2190 |
" <td>COLLECTOR_5162</td>\n", |
|
|
2191 |
" <td>36.953739</td>\n", |
|
|
2192 |
" </tr>\n", |
|
|
2193 |
" <tr>\n", |
|
|
2194 |
" <th>163</th>\n", |
|
|
2195 |
" <td>TEST</td>\n", |
|
|
2196 |
" <td>COLLECTOR_2973</td>\n", |
|
|
2197 |
" <td>36.892879</td>\n", |
|
|
2198 |
" </tr>\n", |
|
|
2199 |
" <tr>\n", |
|
|
2200 |
" <th>850</th>\n", |
|
|
2201 |
" <td>TEST</td>\n", |
|
|
2202 |
" <td>COLLECTOR_2028</td>\n", |
|
|
2203 |
" <td>13.891359</td>\n", |
|
|
2204 |
" </tr>\n", |
|
|
2205 |
" <tr>\n", |
|
|
2206 |
" <th>76</th>\n", |
|
|
2207 |
" <td>TEST</td>\n", |
|
|
2208 |
" <td>COLLECTOR_1491</td>\n", |
|
|
2209 |
" <td>11.083419</td>\n", |
|
|
2210 |
" </tr>\n", |
|
|
2211 |
" <tr>\n", |
|
|
2212 |
" <th>786</th>\n", |
|
|
2213 |
" <td>TEST</td>\n", |
|
|
2214 |
" <td>COLLECTOR_1460</td>\n", |
|
|
2215 |
" <td>6.416948</td>\n", |
|
|
2216 |
" </tr>\n", |
|
|
2217 |
" <tr>\n", |
|
|
2218 |
" <th>...</th>\n", |
|
|
2219 |
" <td>...</td>\n", |
|
|
2220 |
" <td>...</td>\n", |
|
|
2221 |
" <td>...</td>\n", |
|
|
2222 |
" </tr>\n", |
|
|
2223 |
" <tr>\n", |
|
|
2224 |
" <th>882</th>\n", |
|
|
2225 |
" <td>TEST</td>\n", |
|
|
2226 |
" <td>COLLECTOR_3097</td>\n", |
|
|
2227 |
" <td>NaN</td>\n", |
|
|
2228 |
" </tr>\n", |
|
|
2229 |
" <tr>\n", |
|
|
2230 |
" <th>883</th>\n", |
|
|
2231 |
" <td>TEST</td>\n", |
|
|
2232 |
" <td>COLLECTOR_310</td>\n", |
|
|
2233 |
" <td>NaN</td>\n", |
|
|
2234 |
" </tr>\n", |
|
|
2235 |
" <tr>\n", |
|
|
2236 |
" <th>884</th>\n", |
|
|
2237 |
" <td>TEST</td>\n", |
|
|
2238 |
" <td>COLLECTOR_5283</td>\n", |
|
|
2239 |
" <td>NaN</td>\n", |
|
|
2240 |
" </tr>\n", |
|
|
2241 |
" <tr>\n", |
|
|
2242 |
" <th>889</th>\n", |
|
|
2243 |
" <td>TEST</td>\n", |
|
|
2244 |
" <td>COLLECTOR_418</td>\n", |
|
|
2245 |
" <td>NaN</td>\n", |
|
|
2246 |
" </tr>\n", |
|
|
2247 |
" <tr>\n", |
|
|
2248 |
" <th>894</th>\n", |
|
|
2249 |
" <td>TEST</td>\n", |
|
|
2250 |
" <td>COLLECTOR_4788</td>\n", |
|
|
2251 |
" <td>NaN</td>\n", |
|
|
2252 |
" </tr>\n", |
|
|
2253 |
" </tbody>\n", |
|
|
2254 |
"</table>\n", |
|
|
2255 |
"<p>895 rows × 3 columns</p>\n", |
|
|
2256 |
"</div>" |
|
|
2257 |
], |
|
|
2258 |
"text/plain": [ |
|
|
2259 |
" SPLIT COLLECTOR_ID pred\n", |
|
|
2260 |
"183 TEST COLLECTOR_5162 36.953739\n", |
|
|
2261 |
"163 TEST COLLECTOR_2973 36.892879\n", |
|
|
2262 |
"850 TEST COLLECTOR_2028 13.891359\n", |
|
|
2263 |
"76 TEST COLLECTOR_1491 11.083419\n", |
|
|
2264 |
"786 TEST COLLECTOR_1460 6.416948\n", |
|
|
2265 |
".. ... ... ...\n", |
|
|
2266 |
"882 TEST COLLECTOR_3097 NaN\n", |
|
|
2267 |
"883 TEST COLLECTOR_310 NaN\n", |
|
|
2268 |
"884 TEST COLLECTOR_5283 NaN\n", |
|
|
2269 |
"889 TEST COLLECTOR_418 NaN\n", |
|
|
2270 |
"894 TEST COLLECTOR_4788 NaN\n", |
|
|
2271 |
"\n", |
|
|
2272 |
"[895 rows x 3 columns]" |
|
|
2273 |
] |
|
|
2274 |
}, |
|
|
2275 |
"execution_count": 20, |
|
|
2276 |
"metadata": {}, |
|
|
2277 |
"output_type": "execute_result" |
|
|
2278 |
} |
|
|
2279 |
], |
|
|
2280 |
"source": [ |
|
|
2281 |
"sub=sub.sort_values(by=\"pred\",ascending=False)\n", |
|
|
2282 |
"sub" |
|
|
2283 |
] |
|
|
2284 |
}, |
|
|
2285 |
{ |
|
|
2286 |
"cell_type": "code", |
|
|
2287 |
"execution_count": 21, |
|
|
2288 |
"id": "05ea00b3", |
|
|
2289 |
"metadata": {}, |
|
|
2290 |
"outputs": [], |
|
|
2291 |
"source": [ |
|
|
2292 |
"sub[['SPLIT','COLLECTOR_ID']].to_csv('mlsub5.csv',index=False)" |
|
|
2293 |
] |
|
|
2294 |
}, |
|
|
2295 |
{ |
|
|
2296 |
"cell_type": "code", |
|
|
2297 |
"execution_count": null, |
|
|
2298 |
"id": "34c106ff", |
|
|
2299 |
"metadata": {}, |
|
|
2300 |
"outputs": [], |
|
|
2301 |
"source": [] |
|
|
2302 |
} |
|
|
2303 |
], |
|
|
2304 |
"metadata": { |
|
|
2305 |
"kernelspec": { |
|
|
2306 |
"display_name": "Python 3", |
|
|
2307 |
"language": "python", |
|
|
2308 |
"name": "python3" |
|
|
2309 |
}, |
|
|
2310 |
"language_info": { |
|
|
2311 |
"codemirror_mode": { |
|
|
2312 |
"name": "ipython", |
|
|
2313 |
"version": 3 |
|
|
2314 |
}, |
|
|
2315 |
"file_extension": ".py", |
|
|
2316 |
"mimetype": "text/x-python", |
|
|
2317 |
"name": "python", |
|
|
2318 |
"nbconvert_exporter": "python", |
|
|
2319 |
"pygments_lexer": "ipython3", |
|
|
2320 |
"version": "3.8.8" |
|
|
2321 |
} |
|
|
2322 |
}, |
|
|
2323 |
"nbformat": 4, |
|
|
2324 |
"nbformat_minor": 5 |
|
|
2325 |
} |