回答編集履歴
3
訂正
answer
CHANGED
|
@@ -150,4 +150,70 @@
|
|
|
150
150
|
}
|
|
151
151
|
}
|
|
152
152
|
}
|
|
153
|
+
```
|
|
154
|
+
|
|
155
|
+
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
|
|
156
|
+
```java
|
|
157
|
+
import java.util.*;
|
|
158
|
+
import java.lang.String;
|
|
159
|
+
|
|
160
|
+
/**
|
|
161
|
+
* doc 文書 term 用語
|
|
162
|
+
*/
|
|
163
|
+
public class TF1 {
|
|
164
|
+
public static double tf(String term, String[] doc) {
|
|
165
|
+
double result = 0;
|
|
166
|
+
for (String word : doc) {
|
|
167
|
+
if (term.equalsIgnoreCase(word))
|
|
168
|
+
result++;
|
|
169
|
+
}
|
|
170
|
+
return (double) result / doc.length;
|
|
171
|
+
}
|
|
172
|
+
|
|
173
|
+
public static void main(String[] args) {
|
|
174
|
+
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";
|
|
175
|
+
|
|
176
|
+
String[] doc2 = str.split(" ");
|
|
177
|
+
TreeMap<String,Double> c=new TreeMap<>();
|
|
178
|
+
|
|
179
|
+
for (String words : doc2) {
|
|
180
|
+
double tf1 = tf(words, doc2);
|
|
181
|
+
if (!str.equalsIgnoreCase(words)) {
|
|
182
|
+
c.put(words,tf1);
|
|
183
|
+
}
|
|
184
|
+
|
|
185
|
+
}
|
|
186
|
+
System.out.println("重複した単語を表示させない");
|
|
187
|
+
for(String er:c.keySet()){
|
|
188
|
+
System.out.println(er+":"+c.get(er));
|
|
189
|
+
}
|
|
190
|
+
TreeMap<String,Double> c2=new TreeMap<>(new CX(c));
|
|
191
|
+
c2.putAll(c);
|
|
192
|
+
System.out.println("\n\n降順にソート");
|
|
193
|
+
|
|
194
|
+
for(String er:c2.keySet()){
|
|
195
|
+
System.out.println(er+":"+c.get(er));
|
|
196
|
+
}
|
|
197
|
+
}
|
|
198
|
+
|
|
199
|
+
|
|
200
|
+
}
|
|
201
|
+
|
|
202
|
+
class CX implements Comparator<String> {
|
|
203
|
+
private Map<String, Double> map;
|
|
204
|
+
public CX(Map<String, Double> map) {
|
|
205
|
+
this.map = map;
|
|
206
|
+
}
|
|
207
|
+
public int compare(String key1, String key2) {
|
|
208
|
+
double value1 = map.get(key1);
|
|
209
|
+
double value2 = map.get(key2);
|
|
210
|
+
if(value1 == value2)
|
|
211
|
+
return key1.toLowerCase().compareTo(key2.toLowerCase());
|
|
212
|
+
else if(value1 < value2)
|
|
213
|
+
return 1;
|
|
214
|
+
else
|
|
215
|
+
return -1;
|
|
216
|
+
}
|
|
217
|
+
}
|
|
218
|
+
|
|
153
219
|
```
|
2
訂正
answer
CHANGED
|
@@ -137,7 +137,7 @@
|
|
|
137
137
|
}
|
|
138
138
|
|
|
139
139
|
public static void main(String[] args) {
|
|
140
|
-
String str = "
|
|
140
|
+
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";
|
|
141
141
|
|
|
142
142
|
String[] doc2 = str.split(" ");
|
|
143
143
|
|
1
訂正
answer
CHANGED
|
@@ -116,4 +116,38 @@
|
|
|
116
116
|
}
|
|
117
117
|
|
|
118
118
|
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
質問文のエラーを訂正したものが以下です
|
|
122
|
+
```java
|
|
123
|
+
import java.util.List;
|
|
124
|
+
import java.lang.String;
|
|
125
|
+
|
|
126
|
+
/**
|
|
127
|
+
* doc 文書 term 用語
|
|
128
|
+
*/
|
|
129
|
+
public class TF1 {
|
|
130
|
+
public static double tf(String term, String[] doc) {
|
|
131
|
+
double result = 0;
|
|
132
|
+
for (String word : doc) {
|
|
133
|
+
if (term.equalsIgnoreCase(word))
|
|
134
|
+
result++;
|
|
135
|
+
}
|
|
136
|
+
return (double) result / doc.length;
|
|
137
|
+
}
|
|
138
|
+
|
|
139
|
+
public static void main(String[] args) {
|
|
140
|
+
String str = "An ant goes to a place which is a kind of a hole.";
|
|
141
|
+
|
|
142
|
+
String[] doc2 = str.split(" ");
|
|
143
|
+
|
|
144
|
+
for (String words : doc2) {
|
|
145
|
+
double tf1 = tf(words, doc2);
|
|
146
|
+
if (!str.equalsIgnoreCase(words)) {
|
|
147
|
+
System.out.print(words + ":");
|
|
148
|
+
System.out.println(tf1);
|
|
149
|
+
}
|
|
150
|
+
}
|
|
151
|
+
}
|
|
152
|
+
}
|
|
119
153
|
```
|