回答編集履歴
3
訂正
test
CHANGED
|
@@ -303,3 +303,135 @@
|
|
|
303
303
|
}
|
|
304
304
|
|
|
305
305
|
```
|
|
306
|
+
|
|
307
|
+
|
|
308
|
+
|
|
309
|
+
重複したものを表示させない・降順ソートした表示は以下です
|
|
310
|
+
|
|
311
|
+
```java
|
|
312
|
+
|
|
313
|
+
import java.util.*;
|
|
314
|
+
|
|
315
|
+
import java.lang.String;
|
|
316
|
+
|
|
317
|
+
|
|
318
|
+
|
|
319
|
+
/**
|
|
320
|
+
|
|
321
|
+
* doc 文書 term 用語
|
|
322
|
+
|
|
323
|
+
*/
|
|
324
|
+
|
|
325
|
+
public class TF1 {
|
|
326
|
+
|
|
327
|
+
public static double tf(String term, String[] doc) {
|
|
328
|
+
|
|
329
|
+
double result = 0;
|
|
330
|
+
|
|
331
|
+
for (String word : doc) {
|
|
332
|
+
|
|
333
|
+
if (term.equalsIgnoreCase(word))
|
|
334
|
+
|
|
335
|
+
result++;
|
|
336
|
+
|
|
337
|
+
}
|
|
338
|
+
|
|
339
|
+
return (double) result / doc.length;
|
|
340
|
+
|
|
341
|
+
}
|
|
342
|
+
|
|
343
|
+
|
|
344
|
+
|
|
345
|
+
public static void main(String[] args) {
|
|
346
|
+
|
|
347
|
+
String str = "It is a Java beginner who is studying Java by self taught. I'd like to create a program that reads English text files in Java and displays TFIDF of each English word, but I can not do it well by all means. I tried to make only TF. I do not know the meaning of the error. Since I do not know how to read the file, I typed in English directly. I omitted it here because it is long. I also want to display descending order";
|
|
348
|
+
|
|
349
|
+
|
|
350
|
+
|
|
351
|
+
String[] doc2 = str.split(" ");
|
|
352
|
+
|
|
353
|
+
TreeMap<String,Double> c=new TreeMap<>();
|
|
354
|
+
|
|
355
|
+
|
|
356
|
+
|
|
357
|
+
for (String words : doc2) {
|
|
358
|
+
|
|
359
|
+
double tf1 = tf(words, doc2);
|
|
360
|
+
|
|
361
|
+
if (!str.equalsIgnoreCase(words)) {
|
|
362
|
+
|
|
363
|
+
c.put(words,tf1);
|
|
364
|
+
|
|
365
|
+
}
|
|
366
|
+
|
|
367
|
+
|
|
368
|
+
|
|
369
|
+
}
|
|
370
|
+
|
|
371
|
+
System.out.println("重複した単語を表示させない");
|
|
372
|
+
|
|
373
|
+
for(String er:c.keySet()){
|
|
374
|
+
|
|
375
|
+
System.out.println(er+":"+c.get(er));
|
|
376
|
+
|
|
377
|
+
}
|
|
378
|
+
|
|
379
|
+
TreeMap<String,Double> c2=new TreeMap<>(new CX(c));
|
|
380
|
+
|
|
381
|
+
c2.putAll(c);
|
|
382
|
+
|
|
383
|
+
System.out.println("\n\n降順にソート");
|
|
384
|
+
|
|
385
|
+
|
|
386
|
+
|
|
387
|
+
for(String er:c2.keySet()){
|
|
388
|
+
|
|
389
|
+
System.out.println(er+":"+c.get(er));
|
|
390
|
+
|
|
391
|
+
}
|
|
392
|
+
|
|
393
|
+
}
|
|
394
|
+
|
|
395
|
+
|
|
396
|
+
|
|
397
|
+
|
|
398
|
+
|
|
399
|
+
}
|
|
400
|
+
|
|
401
|
+
|
|
402
|
+
|
|
403
|
+
class CX implements Comparator<String> {
|
|
404
|
+
|
|
405
|
+
private Map<String, Double> map;
|
|
406
|
+
|
|
407
|
+
public CX(Map<String, Double> map) {
|
|
408
|
+
|
|
409
|
+
this.map = map;
|
|
410
|
+
|
|
411
|
+
}
|
|
412
|
+
|
|
413
|
+
public int compare(String key1, String key2) {
|
|
414
|
+
|
|
415
|
+
double value1 = map.get(key1);
|
|
416
|
+
|
|
417
|
+
double value2 = map.get(key2);
|
|
418
|
+
|
|
419
|
+
if(value1 == value2)
|
|
420
|
+
|
|
421
|
+
return key1.toLowerCase().compareTo(key2.toLowerCase());
|
|
422
|
+
|
|
423
|
+
else if(value1 < value2)
|
|
424
|
+
|
|
425
|
+
return 1;
|
|
426
|
+
|
|
427
|
+
else
|
|
428
|
+
|
|
429
|
+
return -1;
|
|
430
|
+
|
|
431
|
+
}
|
|
432
|
+
|
|
433
|
+
}
|
|
434
|
+
|
|
435
|
+
|
|
436
|
+
|
|
437
|
+
```
|
2
訂正
test
CHANGED
|
@@ -276,7 +276,7 @@
|
|
|
276
276
|
|
|
277
277
|
public static void main(String[] args) {
|
|
278
278
|
|
|
279
|
-
String str = "
|
|
279
|
+
String str = "It is a Java beginner who is studying Java by self taught. I'd like to create a program that reads English text files in Java and displays TFIDF of each English word, but I can not do it well by all means. I tried to make only TF. I do not know the meaning of the error. Since I do not know how to read the file, I typed in English directly. I omitted it here because it is long. I also want to display descending order";
|
|
280
280
|
|
|
281
281
|
|
|
282
282
|
|
1
訂正
test
CHANGED
|
@@ -235,3 +235,71 @@
|
|
|
235
235
|
|
|
236
236
|
|
|
237
237
|
```
|
|
238
|
+
|
|
239
|
+
|
|
240
|
+
|
|
241
|
+
質問文のエラーを訂正したものが以下です
|
|
242
|
+
|
|
243
|
+
```java
|
|
244
|
+
|
|
245
|
+
import java.util.List;
|
|
246
|
+
|
|
247
|
+
import java.lang.String;
|
|
248
|
+
|
|
249
|
+
|
|
250
|
+
|
|
251
|
+
/**
|
|
252
|
+
|
|
253
|
+
* doc 文書 term 用語
|
|
254
|
+
|
|
255
|
+
*/
|
|
256
|
+
|
|
257
|
+
public class TF1 {
|
|
258
|
+
|
|
259
|
+
public static double tf(String term, String[] doc) {
|
|
260
|
+
|
|
261
|
+
double result = 0;
|
|
262
|
+
|
|
263
|
+
for (String word : doc) {
|
|
264
|
+
|
|
265
|
+
if (term.equalsIgnoreCase(word))
|
|
266
|
+
|
|
267
|
+
result++;
|
|
268
|
+
|
|
269
|
+
}
|
|
270
|
+
|
|
271
|
+
return (double) result / doc.length;
|
|
272
|
+
|
|
273
|
+
}
|
|
274
|
+
|
|
275
|
+
|
|
276
|
+
|
|
277
|
+
public static void main(String[] args) {
|
|
278
|
+
|
|
279
|
+
String str = "An ant goes to a place which is a kind of a hole.";
|
|
280
|
+
|
|
281
|
+
|
|
282
|
+
|
|
283
|
+
String[] doc2 = str.split(" ");
|
|
284
|
+
|
|
285
|
+
|
|
286
|
+
|
|
287
|
+
for (String words : doc2) {
|
|
288
|
+
|
|
289
|
+
double tf1 = tf(words, doc2);
|
|
290
|
+
|
|
291
|
+
if (!str.equalsIgnoreCase(words)) {
|
|
292
|
+
|
|
293
|
+
System.out.print(words + ":");
|
|
294
|
+
|
|
295
|
+
System.out.println(tf1);
|
|
296
|
+
|
|
297
|
+
}
|
|
298
|
+
|
|
299
|
+
}
|
|
300
|
+
|
|
301
|
+
}
|
|
302
|
+
|
|
303
|
+
}
|
|
304
|
+
|
|
305
|
+
```
|