kubapok
/
polish-urban-legends-public
1
0
Fork 16
Code Issues Pull Requests Releases Wiki Activity

Compare commits

merge into: kubapok:master
Branches Tags
kubapok:master
s426225:master
...
pull from: s426225:master
Branches Tags
s426225:master
kubapok:master

1 Commits
master ... master

Author SHA1 Message Date
szypol 148368be03 finally... after platform change solution works 2021-07-09 00:35:30 +02:00
5 changed files with 883 additions and 0 deletions
Show Stats Expand all files Collapse all files

87
dev-0/out.tsv Normal file
View File

@ -0,0 +1,87 @@
39
32
0
20
2
22
41
11
4
5
46
22
30
14
6
25
34
40
18
13
12
23
17
9
11
35
3
17
13
30
24
36
29
47
25
8
44
49
3
20
4
26
41
10
43
15
8
30
11
42
37
0
24
35
7
9
30
30
24
27
8
33
11
31
22
28
1
45
21
8
2
18
16
1
30
11
11
7
10
38
5
48
5
13
1
19
13
1 39
2 32
3 0
4 20
5 2
6 22
7 41
8 11
9 4
10 5
11 46
12 22
13 30
14 14
15 6
16 25
17 34
18 40
19 18
20 13
21 12
22 23
23 17
24 9
25 11
26 35
27 3
28 17
29 13
30 30
31 24
32 36
33 29
34 47
35 25
36 8
37 44
38 49
39 3
40 20
41 4
42 26
43 41
44 10
45 43
46 15
47 8
48 30
49 11
50 42
51 37
52 0
53 24
54 35
55 7
56 9
57 30
58 30
59 24
60 27
61 8
62 33
63 11
64 31
65 22
66 28
67 1
68 45
69 21
70 8
71 2
72 18
73 16
74 1
75 30
76 11
77 11
78 7
79 10
80 38
81 5
82 48
83 5
84 13
85 1
86 19
87 13

BIN
geval Executable file
View File

Binary file not shown.

70
kMeans.ipynb Normal file
View File

@ -0,0 +1,70 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f7e1ae0d",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import csv\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"from sklearn.cluster import KMeans"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7582a8dd",
"metadata": {},
"outputs": [],
"source": [
"#dev0\n",
"dev0_data = pd.read_csv('dev-0/in.tsv', header=None, quoting=csv.QUOTE_NONE, sep='\\t')\n",
"\n",
"dev0_y = KMeans(n_clusters=50).fit_predict(TfidfVectorizer().fit_transform(dev0_data[0].values))\n",
"\n",
"#zapis wyników\n",
"dev0_y.tofile('dev-0/out.tsv', sep='\\n')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d3c75abc",
"metadata": {},
"outputs": [],
"source": [
"#TestA\n",
"testA_data = pd.read_csv('test-A/in.tsv', header=None, quoting=csv.QUOTE_NONE, sep='\\t')\n",
"\n",
"testA_y = KMeans(n_clusters=50).fit_predict(TfidfVectorizer().fit_transform(testA_data[0].values))\n",
"\n",
"#zapis wyników\n",
"testA_y.tofile('test-A/out.tsv', sep='\\n')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

35
kMeans.py Normal file
View File

@ -0,0 +1,35 @@
#!/usr/bin/env python
# coding: utf-8
# In[1]:
import pandas as pd
import csv
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
# In[2]:
#dev0
dev0_data = pd.read_csv('dev-0/in.tsv', header=None, quoting=csv.QUOTE_NONE, sep='\t')
dev0_y = KMeans(n_clusters=50).fit_predict(TfidfVectorizer().fit_transform(dev0_data[0].values))
#zapis wyników
dev0_y.tofile('dev-0/out.tsv', sep='\n')
# In[3]:
#TestA
testA_data = pd.read_csv('test-A/in.tsv', header=None, quoting=csv.QUOTE_NONE, sep='\t')
testA_y = KMeans(n_clusters=50).fit_predict(TfidfVectorizer().fit_transform(testA_data[0].values))
#zapis wyników
testA_y.tofile('test-A/out.tsv', sep='\n')

691
test-A/out.tsv Normal file
View File

@ -0,0 +1,691 @@
22
48
25
10
33
8
13
39
24
47
26
4
15
24
3
18
33
12
33
3
12
34
8
9
0
23
0
28
39
0
21
39
8
2
38
48
4
19
2
21
43
33
17
21
26
26
26
11
25
3
25
19
10
9
28
7
19
25
17
45
19
17
0
47
24
46
9
8
17
24
28
38
33
18
19
33
1
45
43
23
23
6
5
48
33
16
33
41
24
43
24
28
38
33
33
17
22
0
19
19
14
34
33
41
4
42
14
23
12
16
15
2
24
25
12
18
17
16
14
10
45
39
20
17
19
2
33
7
15
19
28
38
12
7
26
38
36
23
5
10
20
26
45
36
14
10
17
36
29
7
33
17
17
3
9
4
33
45
18
34
37
12
42
11
28
17
5
37
38
38
48
28
21
19
33
5
9
26
7
30
6
11
45
16
14
0
39
5
39
28
22
14
4
42
39
45
10
25
10
22
23
31
22
26
33
17
25
11
16
22
24
43
19
33
11
4
39
8
44
24
3
7
23
30
5
38
37
12
40
19
17
41
7
11
8
24
38
9
19
10
22
24
46
26
23
44
28
28
26
11
24
16
6
21
31
5
12
3
19
45
7
39
13
23
36
12
10
16
31
39
26
12
28
45
8
13
26
15
45
18
12
28
13
24
15
27
49
25
17
8
19
24
14
23
48
28
17
27
17
26
26
12
16
28
28
26
33
13
16
19
17
1
18
21
40
16
28
45
11
47
43
5
34
1
19
43
16
33
14
26
33
19
13
7
19
25
23
18
28
10
19
29
39
3
9
45
41
4
42
43
14
32
28
39
33
19
28
23
41
47
37
26
14
24
28
23
2
21
32
37
17
19
4
20
39
28
7
17
7
12
38
23
26
13
22
15
47
4
41
8
12
46
0
25
33
48
22
12
33
26
26
10
7
39
7
3
19
39
29
39
43
27
39
23
7
28
32
28
23
14
23
49
20
8
37
31
25
33
28
3
17
9
11
19
6
29
33
39
9
8
44
25
43
19
33
30
18
6
39
26
23
48
11
39
35
19
24
11
9
28
14
42
3
16
21
47
25
23
20
43
43
16
43
19
16
26
31
19
17
44
37
5
24
23
24
35
17
1
31
16
20
25
11
24
15
19
39
36
13
32
39
25
16
19
19
18
34
18
15
26
8
37
24
16
19
4
30
33
48
11
21
23
37
12
23
33
16
40
39
21
6
12
33
2
14
34
23
3
28
42
25
27
33
35
39
8
44
21
23
15
18
43
31
33
38
6
22
22
38
46
8
25
45
39
23
23
7
28
39
38
25
25
24
16
43
4
15
41
4
19
7
45
12
8
12
19
6
7
45
28
30
24
23
8
24
48
22
29
29
20
25
3
28
24
7
35
28
15
35
26
4
15
22
41
4
12
45
32
16
16
45
34
28
25
16
5
26
23
17
26
4
11
19
33
39
23
5
9
44
23
3
22
28
7
39
37
12
10
12
48
28
26
6
4
24
7
17
31
4
24
4
8
12
16
17
21
44
12
32
14
15
33
43
37
16
40
19
28
14
12
44
38
23
37
15
2
3
41
22
47
37
1 22
2 48
3 25
4 10
5 33
6 8
7 13
8 39
9 24
10 47
11 26
12 4
13 15
14 24
15 3
16 18
17 33
18 12
19 33
20 3
21 12
22 34
23 8
24 9
25 0
26 23
27 0
28 28
29 39
30 0
31 21
32 39
33 8
34 2
35 38
36 48
37 4
38 19
39 2
40 21
41 43
42 33
43 17
44 21
45 26
46 26
47 26
48 11
49 25
50 3
51 25
52 19
53 10
54 9
55 28
56 7
57 19
58 25
59 17
60 45
61 19
62 17
63 0
64 47
65 24
66 46
67 9
68 8
69 17
70 24
71 28
72 38
73 33
74 18
75 19
76 33
77 1
78 45
79 43
80 23
81 23
82 6
83 5
84 48
85 33
86 16
87 33
88 41
89 24
90 43
91 24
92 28
93 38
94 33
95 33
96 17
97 22
98 0
99 19
100 19
101 14
102 34
103 33
104 41
105 4
106 42
107 14
108 23
109 12
110 16
111 15
112 2
113 24
114 25
115 12
116 18
117 17
118 16
119 14
120 10
121 45
122 39
123 20
124 17
125 19
126 2
127 33
128 7
129 15
130 19
131 28
132 38
133 12
134 7
135 26
136 38
137 36
138 23
139 5
140 10
141 20
142 26
143 45
144 36
145 14
146 10
147 17
148 36
149 29
150 7
151 33
152 17
153 17
154 3
155 9
156 4
157 33
158 45
159 18
160 34
161 37
162 12
163 42
164 11
165 28
166 17
167 5
168 37
169 38
170 38
171 48
172 28
173 21
174 19
175 33
176 5
177 9
178 26
179 7
180 30
181 6
182 11
183 45
184 16
185 14
186 0
187 39
188 5
189 39
190 28
191 22
192 14
193 4
194 42
195 39
196 45
197 10
198 25
199 10
200 22
201 23
202 31
203 22
204 26
205 33
206 17
207 25
208 11
209 16
210 22
211 24
212 43
213 19
214 33
215 11
216 4
217 39
218 8
219 44
220 24
221 3
222 7
223 23
224 30
225 5
226 38
227 37
228 12
229 40
230 19
231 17
232 41
233 7
234 11
235 8
236 24
237 38
238 9
239 19
240 10
241 22
242 24
243 46
244 26
245 23
246 44
247 28
248 28
249 26
250 11
251 24
252 16
253 6
254 21
255 31
256 5
257 12
258 3
259 19
260 45
261 7
262 39
263 13
264 23
265 36
266 12
267 10
268 16
269 31
270 39
271 26
272 12
273 28
274 45
275 8
276 13
277 26
278 15
279 45
280 18
281 12
282 28
283 13
284 24
285 15
286 27
287 49
288 25
289 17
290 8
291 19
292 24
293 14
294 23
295 48
296 28
297 17
298 27
299 17
300 26
301 26
302 12
303 16
304 28
305 28
306 26
307 33
308 13
309 16
310 19
311 17
312 1
313 18
314 21
315 40
316 16
317 28
318 45
319 11
320 47
321 43
322 5
323 34
324 1
325 19
326 43
327 16
328 33
329 14
330 26
331 33
332 19
333 13
334 7
335 19
336 25
337 23
338 18
339 28
340 10
341 19
342 29
343 39
344 3
345 9
346 45
347 41
348 4
349 42
350 43
351 14
352 32
353 28
354 39
355 33
356 19
357 28
358 23
359 41
360 47
361 37
362 26
363 14
364 24
365 28
366 23
367 2
368 21
369 32
370 37
371 17
372 19
373 4
374 20
375 39
376 28
377 7
378 17
379 7
380 12
381 38
382 23
383 26
384 13
385 22
386 15
387 47
388 4
389 41
390 8
391 12
392 46
393 0
394 25
395 33
396 48
397 22
398 12
399 33
400 26
401 26
402 10
403 7
404 39
405 7
406 3
407 19
408 39
409 29
410 39
411 43
412 27
413 39
414 23
415 7
416 28
417 32
418 28
419 23
420 14
421 23
422 49
423 20
424 8
425 37
426 31
427 25
428 33
429 28
430 3
431 17
432 9
433 11
434 19
435 6
436 29
437 33
438 39
439 9
440 8
441 44
442 25
443 43
444 19
445 33
446 30
447 18
448 6
449 39
450 26
451 23
452 48
453 11
454 39
455 35
456 19
457 24
458 11
459 9
460 28
461 14
462 42
463 3
464 16
465 21
466 47
467 25
468 23
469 20
470 43
471 43
472 16
473 43
474 19
475 16
476 26
477 31
478 19
479 17
480 44
481 37
482 5
483 24
484 23
485 24
486 35
487 17
488 1
489 31
490 16
491 20
492 25
493 11
494 24
495 15
496 19
497 39
498 36
499 13
500 32
501 39
502 25
503 16
504 19
505 19
506 18
507 34
508 18
509 15
510 26
511 8
512 37
513 24
514 16
515 19
516 4
517 30
518 33
519 48
520 11
521 21
522 23
523 37
524 12
525 23
526 33
527 16
528 40
529 39
530 21
531 6
532 12
533 33
534 2
535 14
536 34
537 23
538 3
539 28
540 42
541 25
542 27
543 33
544 35
545 39
546 8
547 44
548 21
549 23
550 15
551 18
552 43
553 31
554 33
555 38
556 6
557 22
558 22
559 38
560 46
561 8
562 25
563 45
564 39
565 23
566 23
567 7
568 28
569 39
570 38
571 25
572 25
573 24
574 16
575 43
576 4
577 15
578 41
579 4
580 19
581 7
582 45
583 12
584 8
585 12
586 19
587 6
588 7
589 45
590 28
591 30
592 24
593 23
594 8
595 24
596 48
597 22
598 29
599 29
600 20
601 25
602 3
603 28
604 24
605 7
606 35
607 28
608 15
609 35
610 26
611 4
612 15
613 22
614 41
615 4
616 12
617 45
618 32
619 16
620 16
621 45
622 34
623 28
624 25
625 16
626 5
627 26
628 23
629 17
630 26
631 4
632 11
633 19
634 33
635 39
636 23
637 5
638 9
639 44
640 23
641 3
642 22
643 28
644 7
645 39
646 37
647 12
648 10
649 12
650 48
651 28
652 26
653 6
654 4
655 24
656 7
657 17
658 31
659 4
660 24
661 4
662 8
663 12
664 16
665 17
666 21
667 44
668 12
669 32
670 14
671 15
672 33
673 43
674 37
675 16
676 40
677 19
678 28
679 14
680 12
681 44
682 38
683 23
684 37
685 15
686 2
687 3
688 41
689 22
690 47
691 37