鎴戠殑weka github鍦板潃錛?a >https://github.com/changedi/weka錛屽彧璇籫it璺緞錛歡it://github.com/changedi/weka.git錛屾榪巉ork
]]>
http://weka.wikispaces.com/ARFF+files+from+Text+Collections
weka鍙互浠ョ洰褰曞艦寮忚鍏ユ暟鎹?/strong>銆?br />鐒跺悗鍐嶇畝鍗曡涓涓媤eka鍦ㄥ仛鏂囨湰鐗瑰緛鍐呭澶勭悊鏃跺欓渶瑕佹敞鎰忕殑涓滆タ錛?br />澹版槑涓鐐癸紝鍦╳eka鐨刧ui涓嬫槸娌℃硶浣跨敤榪欎釜鍔熻兘鐨勶細浠ョ洰褰曞艦寮忚鍏ユ暟鎹?br />棣栧厛錛屾妸瑕佸鐞嗙殑鏁版嵁鍐欏叆鍒拌繖鏍風殑鐩綍緇撴瀯涓嬶細
... | +- text_example | +- class1 | | | + file1.txt | | | + file2.txt | | | ... | +- class2 | | | + another_file1.txt | | | + another_file2.txt | | | ...
鐒跺悗鍦ㄦ簮鐮佸寘涓嬶紝鍛戒護琛屾墽琛?java weka.core.converters.TextDirectoryLoader -dir text_example > text_example.arff
鍏朵腑text_example灝辨槸鏁版嵁鎵鍦ㄧ殑鐩綍錛岃屽悗闈㈢殑arff鏂囦歡灝辨槸鐢熸垚鐨刟rff鏂囦歡銆傚彟澶栧煎緱琛ュ厖鐨勪竴鐐規槸鍦ㄨ幏寰楄繖鏍風殑arff鍚庡摝錛屾枃鏈唴瀹規槸浣滀負涓涓瓧絎︿覆鐗瑰緛瀛樺湪鐨勶紝涔熷氨鏄鐢熸垚鐨刟rff灝辨槸涓涓壒寰侀」鍔犱竴涓被鏍囩錛屽叾涓殑綾繪爣灝辨槸text_example鐩綍涓嬬駭classX瀛愮洰褰曠殑鍚嶅瓧銆備負浜嗘洿鏂逛究浣跨敤錛寃eka鎻愪緵浜嗕竴涓湁鐩戠潱鐨勫睘鎬ц繃婊ゅ櫒錛屽府鍔╁垎璇嶏紙榪欓噷鎸囪嫳鏂囩殑split錛?——StringToWordVector錛岃繖涓槸鍙互鍋歍F/IDF鐨剘~~
涓嬮潰鐨勭畝鍗曚唬鐮佸彲浠ュ畬鎴愪竴涓垎綾伙細
1
import weka.core.*;
2import weka.core.converters.*;
3import weka.classifiers.trees.*;
4import weka.filters.*;
5import weka.filters.unsupervised.attribute.*;
6
7import java.io.*;
8
9
/**
10
* Example class that converts HTML files stored in a directory structure into
11 * and ARFF file using the TextDirectoryLoader converter. It then applies the
12 * StringToWordVector to the data and feeds a J48 classifier with it.
13 *
14 * @author FracPete (fracpete at waikato dot ac dot nz)
15
*/
16public class TextCategorizationTest {
17
18
/**
19 * Expects the first parameter to point to the directory with the text files.
20 * In that directory, each sub-directory represents a class and the text
21 * files in these sub-directories will be labeled as such.
22 *
23 * @param args the commandline arguments
24 * @throws Exception if something goes wrong
25
*/
26 public static void main(String[] args) throws Exception {
27 // convert the directory into a dataset
28 TextDirectoryLoader loader = new TextDirectoryLoader();
29 loader.setDirectory(new File("./text_example"));
30 Instances dataRaw = loader.getDataSet();
31 System.out.println("\n\nImported data:\n\n" + dataRaw.numClasses());
32
33 // apply the StringToWordVector
34 // (see the source code of setOptions(String[]) method of the filter
35 // if you want to know which command-line option corresponds to which
36 // bean property)
37 StringToWordVector filter = new StringToWordVector();
38 filter.setInputFormat(dataRaw);
39 Instances dataFiltered = Filter.useFilter(dataRaw, filter);
40 System.out.println("\n\nFiltered data:\n\n" + dataFiltered);
41
42 // train J48 and output model
43 J48 classifier = new J48();
44 classifier.buildClassifier(dataFiltered);
45 System.out.println("\n\nClassifier model:\n\n" + classifier);
46 }
47}
48
import weka.core.*;2
import weka.core.converters.*;3
import weka.classifiers.trees.*;4
import weka.filters.*;5
import weka.filters.unsupervised.attribute.*;6
7
import java.io.*;8
9
/**
10
* Example class that converts HTML files stored in a directory structure into 11
* and ARFF file using the TextDirectoryLoader converter. It then applies the12
* StringToWordVector to the data and feeds a J48 classifier with it.13
*14
* @author FracPete (fracpete at waikato dot ac dot nz)15
*/16
public class TextCategorizationTest {
17
18
/**
19
* Expects the first parameter to point to the directory with the text files.20
* In that directory, each sub-directory represents a class and the text21
* files in these sub-directories will be labeled as such.22
*23
* @param args the commandline arguments24
* @throws Exception if something goes wrong25
*/26
public static void main(String[] args) throws Exception {27
// convert the directory into a dataset28
TextDirectoryLoader loader = new TextDirectoryLoader();29
loader.setDirectory(new File("./text_example"));30
Instances dataRaw = loader.getDataSet();31
System.out.println("\n\nImported data:\n\n" + dataRaw.numClasses());32
33
// apply the StringToWordVector34
// (see the source code of setOptions(String[]) method of the filter35
// if you want to know which command-line option corresponds to which36
// bean property)37
StringToWordVector filter = new StringToWordVector();38
filter.setInputFormat(dataRaw);39
Instances dataFiltered = Filter.useFilter(dataRaw, filter);40
System.out.println("\n\nFiltered data:\n\n" + dataFiltered);41
42
// train J48 and output model43
J48 classifier = new J48();44
classifier.buildClassifier(dataFiltered);45
System.out.println("\n\nClassifier model:\n\n" + classifier);46
}47
}48
鏈鍚庯紝鎴戣繕鏄緩璁暟鎹緩妯″拰鐢熸垚閮借嚜宸卞啓紼嬪簭錛屾暟鎹噯澶囧線寰鑷繁鐨勭▼搴忔墠鑳藉噯紜殑鎺у埗錛寃eka鏈澶氭槸甯垜浠仛涓涓媠election鍜宑lassification銆?br />鍙﹀琛ュ厖涓鐐癸紝寰堝鏈嬪弸闂埌浜嗗浣曞仛鏂囨湰鍒嗙被錛屽ソ鍚э紝濡傛灉澶у鎳掑緱鍘昏paper鐨勮瘽錛岄鍏堟垜鏅強涓鐐癸紝涓嶇浠涔堝垎綾伙紝鍒嗙被鍣ㄥ熀鏈槸鍙互閫氱敤鐨勶紝娉ㄦ剰鏄熀鏈傚叧閿槸妯″瀷鐨勬瀯寤哄拰鐗瑰緛鐨勭敓鎴愩傝嚦浜庢枃鏈垎綾諱腑鐢ㄥ埌鐨勭壒寰侊紝TF*IDF榪樻湁鍏朵粬濡備簰淇℃伅錛屽崱鏂圭粺璁★紝鏈熸湜浜ゅ弶鐔電瓑絳夛紝鍏紡鎽嗗湪閭ｉ噷錛岃綆楃湡鐨勪笉闅俱傚洜涓哄氨鎴戞帴瑙﹁繃鐨勫垎綾婚棶棰橈紝鏂囨湰鍒嗙被鐨勭壒寰佽綆楀簲璇ユ槸寰堝鏄撶殑浜嗐?br />
]]>
1/**
2 *
3 */
4package edu.tju.ikse.mi.util;
5
6import java.io.File;
7import java.io.IOException;
8import java.util.Random;
9
10import weka.attributeSelection.ASEvaluation;
11import weka.attributeSelection.ASSearch;
12import weka.attributeSelection.AttributeSelection;
13import weka.attributeSelection.BestFirst;
14import weka.attributeSelection.CfsSubsetEval;
15import weka.core.Instances;
16import weka.core.converters.ArffLoader;
17
18/**
19 * @author Jia Yu
20 * @date 2010-11-23
21 */
22public class WekaSelector {
23
24 private ArffLoader loader;
25 private Instances dataSet;
26 private File arffFile;
27 private int sizeOfDataset;
28 private int numOfOldAttributes;
29 private int numOfNewAttributes;
30 private int classIndex;
31 private int[] selectedAttributes;
32
33 public WekaSelector(File file) throws IOException {
34 loader = new ArffLoader();
35 arffFile = file;
36 loader.setFile(arffFile);
37 dataSet = loader.getDataSet();
38 sizeOfDataset = dataSet.numInstances();
39 numOfOldAttributes = dataSet.numAttributes();
40 classIndex = numOfOldAttributes - 1;
41 dataSet.setClassIndex(classIndex);
42 }
43
44 public void select() throws Exception {
45 ASEvaluation evaluator = new CfsSubsetEval();
46 ASSearch search = new BestFirst();
47 AttributeSelection eval = null;
48
49 eval = new AttributeSelection();
50 eval.setEvaluator(evaluator);
51 eval.setSearch(search);
52
53 eval.SelectAttributes(dataSet);
54 numOfNewAttributes = eval.numberAttributesSelected();
55 selectedAttributes = eval.selectedAttributes();
56 System.out.println("result is "+eval.toResultsString());
57 /*
58 Random random = new Random(seed);
59 dataSet.randomize(random);
60 if (dataSet.attribute(classIndex).isNominal()) {
61 dataSet.stratify(numFolds);
62 }
63 for (int fold = 0; fold < numFolds; fold++) {
64 Instances train = dataSet.trainCV(numFolds, fold, random);
65 eval.selectAttributesCVSplit(train);
66 }
67 System.out.println("result is "+eval.CVResultsString());
68 */
69 System.out.println("old number of Attributes is "+numOfOldAttributes);
70 System.out.println("new number of Attributes is "+numOfNewAttributes);
71 for(int i=0;i<selectedAttributes.length;i++){
72 System.out.println(selectedAttributes[i]);
73 }
74 }
75
76 /**
77 * @param args
78 */
79 public static void main(String[] args) {
80 // TODO Auto-generated method stub
81 File file = new File("iris.arff");
82 try {
83 WekaSelector ws = new WekaSelector(file);
84 ws.select();
85
86 } catch (IOException e) {
87 // TODO Auto-generated catch block
88 e.printStackTrace();
89 } catch (Exception e) {
90 // TODO Auto-generated catch block
91 e.printStackTrace();
92 }
93
94 }
95
96}
97
/**2
* 3
*/4
package edu.tju.ikse.mi.util;5
6
import java.io.File;7
import java.io.IOException;8
import java.util.Random;9
10
import weka.attributeSelection.ASEvaluation;11
import weka.attributeSelection.ASSearch;12
import weka.attributeSelection.AttributeSelection;13
import weka.attributeSelection.BestFirst;14
import weka.attributeSelection.CfsSubsetEval;15
import weka.core.Instances;16
import weka.core.converters.ArffLoader;17
18
/**19
* @author Jia Yu20
* @date 2010-11-2321
*/22
public class WekaSelector {23
24
private ArffLoader loader;25
private Instances dataSet;26
private File arffFile;27
private int sizeOfDataset;28
private int numOfOldAttributes;29
private int numOfNewAttributes;30
private int classIndex;31
private int[] selectedAttributes;32
33
public WekaSelector(File file) throws IOException {34
loader = new ArffLoader();35
arffFile = file;36
loader.setFile(arffFile);37
dataSet = loader.getDataSet();38
sizeOfDataset = dataSet.numInstances();39
numOfOldAttributes = dataSet.numAttributes();40
classIndex = numOfOldAttributes - 1;41
dataSet.setClassIndex(classIndex);42
}43
44
public void select() throws Exception {45
ASEvaluation evaluator = new CfsSubsetEval();46
ASSearch search = new BestFirst();47
AttributeSelection eval = null;48
49
eval = new AttributeSelection();50
eval.setEvaluator(evaluator);51
eval.setSearch(search);52
53
eval.SelectAttributes(dataSet);54
numOfNewAttributes = eval.numberAttributesSelected();55
selectedAttributes = eval.selectedAttributes();56
System.out.println("result is "+eval.toResultsString());57
/*58
Random random = new Random(seed);59
dataSet.randomize(random);60
if (dataSet.attribute(classIndex).isNominal()) {61
dataSet.stratify(numFolds);62
}63
for (int fold = 0; fold < numFolds; fold++) {64
Instances train = dataSet.trainCV(numFolds, fold, random);65
eval.selectAttributesCVSplit(train);66
}67
System.out.println("result is "+eval.CVResultsString());68
*/69
System.out.println("old number of Attributes is "+numOfOldAttributes);70
System.out.println("new number of Attributes is "+numOfNewAttributes);71
for(int i=0;i<selectedAttributes.length;i++){72
System.out.println(selectedAttributes[i]);73
}74
}75
76
/**77
* @param args78
*/79
public static void main(String[] args) {80
// TODO Auto-generated method stub81
File file = new File("iris.arff");82
try {83
WekaSelector ws = new WekaSelector(file);84
ws.select();85
86
} catch (IOException e) {87
// TODO Auto-generated catch block88
e.printStackTrace();89
} catch (Exception e) {90
// TODO Auto-generated catch block91
e.printStackTrace();92
}93
94
}95
96
}97
鍏朵腑鐨勬敞閲婇儴鍒嗘槸浣跨敤浜ゅ弶楠岃瘉鐨勯儴鍒嗐傞粯璁ゆ槸鍗佹姌浜ゅ弶楠岃瘉錛屽綋鐒惰繖涓彲浠ラ氳繃set鏂規硶璁劇疆銆傚叿浣撶殑浣跨敤鎴栬呯敤鍒皉educe dimensionality鐨勬柟娉曞ぇ瀹跺彲浠ュ弬鐪嬫簮浠ｇ爜銆傛瘯绔焪eka寮婧愬緢鏄柟渚褲傛簮浠ｇ爜娑夊強鍒扮殑綾諱富瑕佹槸鏌ョ湅weka.attributeSelection.AttributeSelection綾誨氨鍙互浜嗐傚綋鐒跺浣曡皟鐢ㄥ拰閫夋嫨鍙互鐪嬬湅weka.gui.explorer.AttributeSelectionPanel綾匯?br />
涓婇潰浠ｇ爜鐨勫疄楠岀粨鏋滃涓嬶細
result is
=== Attribute Selection on all input data ===
Search Method:
Best first.
Start set: no attributes
Search direction: forward
Stale search after 5 node expansions
Total number of subsets evaluated: 12
Merit of best subset found: 0.887
Attribute Subset Evaluator (supervised, Class (nominal): 5 class):
CFS Subset Evaluator
Including locally predictive attributes
Selected attributes: 3,4 : 2
petallength
petalwidth
old number of Attributes is 5
new number of Attributes is 2
2
3
4
鍘熸潵鐨刬ris鏁版嵁闆嗕腑鍏辨湁4涓睘鎬э紙鍖呭惈涓涓垎綾葷被鏍囨墍浠ヤ竴鍏?緇達級錛岀粡榪囩壒寰侀夋嫨鍚庯紝鍙湁絎?鍜岀4涓や釜緇村害鐨勭壒寰佷繚鐣欙紝鎵浠ユ柊鐗瑰緛瀛愰泦鏈変袱涓淮搴︼紙涓嶅寘鍚被鏍囷紝鏈夌偣緇曪紝涓嶅ソ鎰忔濓紝鎴戞繪槸榪欐牱錛夈?br />
鏈鍚庣殑2錛?錛?鏄睘鎬ф暟緇勭殑涓嬫爣錛岃〃紺虹粡榪囩壒寰侀夋嫨淇濈暀鐨勫睘鎬у瓙闆嗘槸絎?錛?錛?涓睘鎬с?br />
]]>
]]>