/**
* Creates an evaluation overview of the built classifier.
*
* @return the panel to be displayed as result evaluation view for the current decision point
*/
protected JPanel createEvaluationVisualization(Instances data) {
// build text field to display evaluation statistics
JTextPane statistic = new JTextPane();
try {
// build evaluation statistics
Evaluation evaluation = new Evaluation(data);
evaluation.evaluateModel(myClassifier, data);
statistic.setText(
evaluation.toSummaryString()
+ "\n\n"
+ evaluation.toClassDetailsString()
+ "\n\n"
+ evaluation.toMatrixString());
} catch (Exception ex) {
ex.printStackTrace();
return createMessagePanel("Error while creating the decision tree evaluation view");
}
statistic.setFont(new Font("Courier", Font.PLAIN, 14));
statistic.setEditable(false);
statistic.setCaretPosition(0);
JPanel resultViewPanel = new JPanel();
resultViewPanel.setLayout(new BoxLayout(resultViewPanel, BoxLayout.PAGE_AXIS));
resultViewPanel.add(new JScrollPane(statistic));
return resultViewPanel;
}
/**
* 用分类器测试
*
* @param trainFileName
* @param testFileName
*/
public static void classify(String trainFileName, String testFileName) {
try {
File inputFile = new File(fileName + trainFileName); // 训练语料文件
ArffLoader atf = new ArffLoader();
atf.setFile(inputFile);
Instances instancesTrain = atf.getDataSet(); // 读入训练文件
// 设置类标签类
inputFile = new File(fileName + testFileName); // 测试语料文件
atf.setFile(inputFile);
Instances instancesTest = atf.getDataSet(); // 读入测试文件
instancesTest.setClassIndex(instancesTest.numAttributes() - 1);
instancesTrain.setClassIndex(instancesTrain.numAttributes() - 1);
classifier = (Classifier) Class.forName(CLASSIFIERNAME).newInstance();
classifier.buildClassifier(instancesTrain);
Evaluation eval = new Evaluation(instancesTrain);
// 第一个为一个训练过的分类器，第二个参数是在某个数据集上评价的数据集
eval.evaluateModel(classifier, instancesTest);
System.out.println(eval.toClassDetailsString());
System.out.println(eval.toSummaryString());
System.out.println(eval.toMatrixString());
System.out.println("precision is :" + (1 - eval.errorRate()));
} catch (Exception e) {
e.printStackTrace();
}
}
/** evaluates the classifier */
@Override
public void evaluate() throws Exception {
// evaluate classifier and print some statistics
if (_test.classIndex() == -1) _test.setClassIndex(_test.numAttributes() - 1);
Evaluation eval = new Evaluation(_train);
eval.evaluateModel(_cl, _test);
System.out.println(eval.toSummaryString("\nResults\n======\n", false));
System.out.println(eval.toMatrixString());
}
@Override
public void crossValidation(String traindata) throws Exception {
DataSource ds = new DataSource(traindata);
Instances instances = ds.getDataSet();
StringToWordVector stv = new StringToWordVector();
stv.setOptions(
weka.core.Utils.splitOptions(
"-R first-last -W 1000 "
+ "-prune-rate -1.0 -N 0 "
+ "-stemmer weka.core.stemmers.NullStemmer -M 1 "
+ "-tokenizer \"weka.core.tokenizers.WordTokenizer -delimiters \\\" \\r\\n\\t.,;:\\\'\\\"()?!\""));
stv.setInputFormat(instances);
instances = Filter.useFilter(instances, stv);
instances.setClassIndex(0);
Evaluation eval = new Evaluation(instances);
eval.crossValidateModel(this.classifier, instances, 10, new Random(1));
System.out.println(eval.toSummaryString());
System.out.println(eval.toMatrixString());
}
/** outputs some data about the classifier */
public String toString() {
StringBuffer result;
result = new StringBuffer();
result.append("Weka - Demo\n===========\n\n");
result.append(
"Classifier...: "
+ m_Classifier.getClass().getName()
+ " "
+ Utils.joinOptions(m_Classifier.getOptions())
+ "\n");
if (m_Filter instanceof OptionHandler)
result.append(
"Filter.......: "
+ m_Filter.getClass().getName()
+ " "
+ Utils.joinOptions(((OptionHandler) m_Filter).getOptions())
+ "\n");
else result.append("Filter.......: " + m_Filter.getClass().getName() + "\n");
result.append("Training file: " + m_TrainingFile + "\n");
result.append("\n");
result.append(m_Classifier.toString() + "\n");
result.append(m_Evaluation.toSummaryString() + "\n");
try {
result.append(m_Evaluation.toMatrixString() + "\n");
} catch (Exception e) {
e.printStackTrace();
}
try {
result.append(m_Evaluation.toClassDetailsString() + "\n");
} catch (Exception e) {
e.printStackTrace();
}
return result.toString();
}
public static void execSVM(String expName) {
try {
FileWriter outFile = null;
PrintWriter out = null;
outFile = new FileWriter(expName + "-SVM.results");
out = new PrintWriter(outFile);
DateFormat dateFormat = new SimpleDateFormat("yyyy/MM/dd HH:mm:ss");
ProcessTweets tweetsProcessor = null;
System.out.println("***************************************");
System.out.println("***\tEXECUTING TEST\t" + expName + "***");
System.out.println("+++++++++++++++++++++++++++++++++++++++");
out.println("***************************************");
out.println("***\tEXECUTING TEST\t" + expName + "***");
out.println("+++++++++++++++++++++++++++++++++++++++");
out.println("4-Generate classifier " + dateFormat.format(new Date()));
Classifier cls = null;
DataSource sourceTrain = new DataSource(expName + "-train.arff");
Instances dataTrain = sourceTrain.getDataSet();
if (dataTrain.classIndex() == -1) dataTrain.setClassIndex(dataTrain.numAttributes() - 1);
// Entreno el clasificador
// cls = new weka.classifiers.functions.LibSVM();
int clase = dataTrain.numAttributes() - 1;
cls = new weka.classifiers.bayes.ComplementNaiveBayes();
dataTrain.setClassIndex(clase);
cls.buildClassifier(dataTrain);
ObjectOutputStream oos =
new ObjectOutputStream(new FileOutputStream(expName + "-SVM.classifier"));
oos.writeObject(cls);
oos.flush();
oos.close();
DataSource sourceTest = new DataSource(expName + "-test.arff");
Instances dataTest = sourceTest.getDataSet();
dataTest.setClassIndex(clase);
Evaluation eval = new Evaluation(dataTest);
eval.evaluateModel(cls, dataTest);
// Ahora calculo los valores precision, recall y fmeasure. Además saco las matrices de
// confusion
float precision = 0;
float recall = 0;
float fmeasure = 0;
int topeTopics = 8;
for (int ind = 0; ind < topeTopics; ind++) {
precision += eval.precision(ind);
recall += eval.recall(ind);
fmeasure += eval.fMeasure(ind);
}
precision = precision / topeTopics;
recall = recall / topeTopics;
fmeasure = fmeasure / topeTopics;
System.out.println("++++++++++++++ CNB ++++++++++++++++++++");
System.out.println(eval.toMatrixString());
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("++++++++++++++ CNB ++++++++++++++++++++");
out.println(eval.toMatrixString());
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
// OTRO CLASIFICADOR ZeroR
cls = new weka.classifiers.rules.ZeroR();
dataTrain.setClassIndex(clase);
cls.buildClassifier(dataTrain);
eval = new Evaluation(dataTest);
eval.evaluateModel(cls, dataTest);
precision = 0;
recall = 0;
fmeasure = 0;
for (int ind = 0; ind < topeTopics; ind++) {
precision += eval.precision(ind);
recall += eval.recall(ind);
fmeasure += eval.fMeasure(ind);
}
precision = precision / topeTopics;
recall = recall / topeTopics;
fmeasure = fmeasure / topeTopics;
System.out.println("++++++++++++++ ZEROR ++++++++++++++++++++");
System.out.println(eval.toMatrixString());
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("++++++++++++++ ZEROR ++++++++++++++++++++");
out.println(eval.toMatrixString());
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
// OTRO CLASIFICADOR J48
/*
cls = new weka.classifiers.trees.J48();
dataTrain.setClassIndex(clase);
cls.buildClassifier(dataTrain);
eval = new Evaluation(dataTest);
eval.evaluateModel(cls, dataTest);
precision=0;
recall=0;
fmeasure=0;
for(int ind=0; ind<topeTopics; ind++)
{
precision += eval.precision(ind);
recall += eval.recall(ind);
fmeasure += eval.fMeasure(ind);
}
precision = precision / topeTopics;
recall = recall / topeTopics;
fmeasure = fmeasure / topeTopics;
System.out.println("++++++++++++++ J48 ++++++++++++++++++++");
System.out.println(eval.toMatrixString());
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("++++++++++++++ J48 ++++++++++++++++++++");
out.println(eval.toMatrixString());
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
//OTRO SMO
cls = new weka.classifiers.functions.SMO();
dataTrain.setClassIndex(clase);
cls.buildClassifier(dataTrain);
eval = new Evaluation(dataTest);
eval.evaluateModel(cls, dataTest);
precision=0;
recall=0;
fmeasure=0;
for(int ind=0; ind<topeTopics; ind++)
{
precision += eval.precision(ind);
recall += eval.recall(ind);
fmeasure += eval.fMeasure(ind);
}
precision = precision / topeTopics;
recall = recall / topeTopics;
fmeasure = fmeasure / topeTopics;
System.out.println("++++++++++++++ SMO ++++++++++++++++++++");
System.out.println(eval.toMatrixString());
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("++++++++++++++ SMO ++++++++++++++++++++");
out.println(eval.toMatrixString());
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
*/
out.flush();
out.close();
dataTest.delete();
dataTrain.delete();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void exec(PrintWriter printer) {
try {
FileWriter outFile = null;
PrintWriter out = null;
if (printer == null) {
outFile = new FileWriter(id + ".results");
out = new PrintWriter(outFile);
} else out = printer;
DateFormat dateFormat = new SimpleDateFormat("yyyy/MM/dd HH:mm:ss");
ProcessTweets tweetsProcessor = null;
System.out.println("***************************************");
System.out.println("***\tEXECUTING TEST\t" + id + "***");
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.println("Train size:" + traincorpus.size());
System.out.println("Test size:" + testcorpus.size());
out.println("***************************************");
out.println("***\tEXECUTING TEST\t***");
out.println("+++++++++++++++++++++++++++++++++++++++");
out.println("Train size:" + traincorpus.size());
out.println("Test size:" + testcorpus.size());
String cloneID = "";
boolean clonar = false;
if (baseline) {
System.out.println("***************************************");
System.out.println("***\tEXECUTING TEST BASELINE\t***");
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.println("Train size:" + traincorpus.size());
System.out.println("Test size:" + testcorpus.size());
out.println("***************************************");
out.println("***\tEXECUTING TEST\t***");
out.println("+++++++++++++++++++++++++++++++++++++++");
out.println("Train size:" + traincorpus.size());
out.println("Test size:" + testcorpus.size());
BaselineClassifier base = new BaselineClassifier(testcorpus, 8);
precision = base.getPrecision();
recall = base.getRecall();
fmeasure = base.getFmeasure();
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
out.flush();
out.close();
return;
} else {
System.out.println("Stemming: " + stemming);
System.out.println("Lematization:" + lematization);
System.out.println("URLs:" + urls);
System.out.println("Hashtags:" + hashtags);
System.out.println("Mentions:" + mentions);
System.out.println("Unigrams:" + unigrams);
System.out.println("Bigrams:" + bigrams);
System.out.println("TF:" + tf);
System.out.println("TF-IDF:" + tfidf);
out.println("Stemming: " + stemming);
out.println("Lematization:" + lematization);
out.println("URLs:" + urls);
out.println("Hashtags:" + hashtags);
out.println("Mentions:" + mentions);
out.println("Unigrams:" + unigrams);
out.println("Bigrams:" + bigrams);
out.println("TF:" + tf);
out.println("TF-IDF:" + tfidf);
}
// Si tengo los tweets procesados, me evito un nuevo proceso
System.out.println("1-Process tweets " + dateFormat.format(new Date()));
out.println("1-Process tweets " + dateFormat.format(new Date()));
List<ProcessedTweet> train = null;
String[] ids = id.split("-");
cloneID = ids[0] + "-" + (Integer.valueOf(ids[1]) + 6);
if (((Integer.valueOf(ids[1]) / 6) % 2) == 0) clonar = true;
if (new File(id + "-train.ptweets").exists()) {
train = ProcessedTweetSerialization.fromFile(id + "-train.ptweets");
tweetsProcessor =
new ProcessTweets(stemming, lematization, urls, hashtags, mentions, unigrams, bigrams);
if (lematization) {
tweetsProcessor.doLematization(train);
}
if (stemming) {
tweetsProcessor.doStemming(train);
}
} else {
tweetsProcessor =
new ProcessTweets(stemming, lematization, urls, hashtags, mentions, unigrams, bigrams);
// Esto del set training es un añadido para poder diferenciar los idiomas de las url en el
// corpus paralelo
// tweetsProcessor.setTraining(true);
train = tweetsProcessor.processTweets(traincorpus);
// tweetsProcessor.setTraining(false);
ProcessedTweetSerialization.toFile(id + "-train.ptweets", train);
/*
if (clonar)
{
File f = new File (id+"-train.ptweets");
Path p = f.toPath();
CopyOption[] options = new CopyOption[]{
StandardCopyOption.REPLACE_EXISTING,
StandardCopyOption.COPY_ATTRIBUTES
};
Files.copy(p, new File (cloneID+"-train.ptweets").toPath(), options);
Files.copy(p, new File (ids[0]+"-"+(Integer.valueOf(ids[1])+12)+"-train.ptweets").toPath(), options);
Files.copy(p, new File (ids[0]+"-"+(Integer.valueOf(ids[1])+18)+"-train.ptweets").toPath(), options);
Files.copy(p, new File (ids[0]+"-"+(Integer.valueOf(ids[1])+24)+"-train.ptweets").toPath(), options);
Files.copy(p, new File (ids[0]+"-"+(Integer.valueOf(ids[1])+30)+"-train.ptweets").toPath(), options);
}
*/
}
// Generamos las BOW. Igual que antes, si existen no las creo.
System.out.println("2-Fill topics " + dateFormat.format(new Date()));
out.println("2-Fill topics " + dateFormat.format(new Date()));
TopicsList topics = null;
if (new File(id + ".topics").exists()) {
topics = TopicsSerialization.fromFile(id + ".topics");
if (tf) topics.setSelectionFeature(TopicDesc.TERM_TF);
else topics.setSelectionFeature(TopicDesc.TERM_TF_IDF);
topics.prepareTopics();
} else {
topics = new TopicsList();
if (tf) topics.setSelectionFeature(TopicDesc.TERM_TF);
else topics.setSelectionFeature(TopicDesc.TERM_TF_IDF);
System.out.println("Filling topics " + dateFormat.format(new Date()));
topics.fillTopics(train);
System.out.println("Preparing topics topics " + dateFormat.format(new Date()));
// Aquí tengo que serializar antes de preparar, porque si no no puedo calcular los tf y
// tfidf
System.out.println("Serializing topics topics " + dateFormat.format(new Date()));
/*
if (clonar)
{
TopicsSerialization.toFile(cloneID+".topics", topics);
}
*/
topics.prepareTopics();
TopicsSerialization.toFile(id + ".topics", topics);
}
System.out.println("3-Generate arff train file " + dateFormat.format(new Date()));
out.println("3-Generate arff train file " + dateFormat.format(new Date()));
// Si el fichero arff no existe, lo creo. en caso contrario vengo haciendo lo que hasta ahora,
// aprovechar trabajo previo
if (!new File(id + "-train.arff").exists()) {
BufferedWriter bw = topics.generateArffHeader(id + "-train.arff");
int tope = traincorpus.size();
if (tweetsProcessor == null)
tweetsProcessor =
new ProcessTweets(
stemming, lematization, urls, hashtags, mentions, unigrams, bigrams);
for (int indTweet = 0; indTweet < tope; indTweet++) {
topics.generateArffVector(bw, train.get(indTweet));
}
bw.flush();
bw.close();
}
// Ahora proceso los datos de test
System.out.println("5-build test dataset " + dateFormat.format(new Date()));
out.println("5-build test dataset " + dateFormat.format(new Date()));
List<ProcessedTweet> test = null;
if (new File(id + "-test.ptweets").exists())
test = ProcessedTweetSerialization.fromFile(id + "-test.ptweets");
else {
if (tweetsProcessor == null)
tweetsProcessor =
new ProcessTweets(
stemming, lematization, urls, hashtags, mentions, unigrams, bigrams);
test = tweetsProcessor.processTweets(testcorpus);
ProcessedTweetSerialization.toFile(id + "-test.ptweets", test);
/*
if (clonar)
{
File f = new File (id+"-test.ptweets");
Path p = f.toPath();
CopyOption[] options = new CopyOption[]{
StandardCopyOption.REPLACE_EXISTING,
StandardCopyOption.COPY_ATTRIBUTES
};
Files.copy(p, new File (cloneID+"-test.ptweets").toPath(), options);
}
*/
}
// Si el fichero arff no existe, lo creo. en caso contrario vengo haciendo lo que hasta ahora,
// aprovechar trabajo previo
if (!new File(id + "-test.arff").exists()) {
BufferedWriter bw = topics.generateArffHeader(id + "-test.arff");
int tope = testcorpus.size();
if (tweetsProcessor == null)
tweetsProcessor =
new ProcessTweets(
stemming, lematization, urls, hashtags, mentions, unigrams, bigrams);
for (int indTweet = 0; indTweet < tope; indTweet++) {
topics.generateArffVector(bw, test.get(indTweet));
}
bw.flush();
bw.close();
}
int topeTopics = topics.getTopicsList().size();
topics.getTopicsList().clear();
// Genero el clasificador
// FJRM 25-08-2013 Lo cambio de orden para intentar liberar la memoria de los topics y tener
// más libre
System.out.println("4-Generate classifier " + dateFormat.format(new Date()));
out.println("4-Generate classifier " + dateFormat.format(new Date()));
Classifier cls = null;
DataSource sourceTrain = null;
Instances dataTrain = null;
if (new File(id + "-MNB.classifier").exists()) {
ObjectInputStream ois = new ObjectInputStream(new FileInputStream(id + "-MNB.classifier"));
cls = (Classifier) ois.readObject();
ois.close();
} else {
sourceTrain = new DataSource(id + "-train.arff");
dataTrain = sourceTrain.getDataSet();
if (dataTrain.classIndex() == -1) dataTrain.setClassIndex(dataTrain.numAttributes() - 1);
// Entreno el clasificador
cls = new weka.classifiers.bayes.NaiveBayesMultinomial();
int clase = dataTrain.numAttributes() - 1;
dataTrain.setClassIndex(clase);
cls.buildClassifier(dataTrain);
ObjectOutputStream oos =
new ObjectOutputStream(new FileOutputStream(id + "-MNB.classifier"));
oos.writeObject(cls);
oos.flush();
oos.close();
// data.delete();//no borro para el svm
}
// Ahora evaluo el clasificador con los datos de test
System.out.println("6-Evaluate classifier MNB " + dateFormat.format(new Date()));
out.println("6-Evaluate classifier MNB" + dateFormat.format(new Date()));
DataSource sourceTest = new DataSource(id + "-test.arff");
Instances dataTest = sourceTest.getDataSet();
int clase = dataTest.numAttributes() - 1;
dataTest.setClassIndex(clase);
Evaluation eval = new Evaluation(dataTest);
eval.evaluateModel(cls, dataTest);
// Ahora calculo los valores precision, recall y fmeasure. Además saco las matrices de
// confusion
precision = 0;
recall = 0;
fmeasure = 0;
for (int ind = 0; ind < topeTopics; ind++) {
precision += eval.precision(ind);
recall += eval.recall(ind);
fmeasure += eval.fMeasure(ind);
}
precision = precision / topeTopics;
recall = recall / topeTopics;
fmeasure = fmeasure / topeTopics;
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.println(eval.toMatrixString());
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("+++++++++++++++++++++++++++++++++++++++");
out.println(eval.toMatrixString());
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
/* NO BORRAR
System.out.println("7-Evaluate classifier SVM"+dateFormat.format(new Date()));
out.println("7-Evaluate classifier SVM"+dateFormat.format(new Date()));
if (new File(id+"-SVM.classifier").exists())
{
ObjectInputStream ois = new ObjectInputStream(new FileInputStream(id+"-SVM.classifier"));
cls = (Classifier) ois.readObject();
ois.close();
}
else
{
if (dataTrain==null)
{
sourceTrain = new DataSource(id+"-train.arff");
dataTrain = sourceTrain.getDataSet();
if (dataTrain.classIndex() == -1)
dataTrain.setClassIndex(dataTrain.numAttributes() - 1);
}
//Entreno el clasificador
cls = new weka.classifiers.functions.LibSVM();
clase = dataTrain.numAttributes()-1;
dataTrain.setClassIndex(clase);
cls.buildClassifier(dataTrain);
ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream(id+"-SVM.classifier"));
oos.writeObject(cls);
oos.flush();
oos.close();
dataTrain.delete();
}
eval.evaluateModel(cls, dataTest);
precision=0;
recall=0;
fmeasure=0;
for(int ind=0; ind<topeTopics; ind++)
{
precision += eval.precision(ind);
recall += eval.recall(ind);
fmeasure += eval.fMeasure(ind);
}
precision = precision / topeTopics;
recall = recall / topeTopics;
fmeasure = fmeasure / topeTopics;
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.println(eval.toMatrixString());
System.out.println("+++++++++++++++++++++++++++++++++++++++");
System.out.printf("Precision: %.3f\n", precision);
System.out.printf("Recall: %.3f\n", recall);
System.out.printf("F-measure: %.3f\n", fmeasure);
System.out.println("***************************************");
out.println("+++++++++++++++++++++++++++++++++++++++");
out.println(eval.toMatrixString());
out.println("+++++++++++++++++++++++++++++++++++++++");
out.printf("Precision: %.3f\n", precision);
out.printf("Recall: %.3f\n", recall);
out.printf("F-measure: %.3f\n", fmeasure);
out.println("***************************************");
*/
System.out.println("Done " + dateFormat.format(new Date()));
out.println("Done " + dateFormat.format(new Date()));
if (printer == null) {
out.flush();
out.close();
}
// Intento de liberar memoria
if (dataTrain != null) dataTrain.delete();
if (dataTest != null) dataTest.delete();
if (train != null) train.clear();
if (test != null) test.clear();
if (topics != null) {
topics.getTopicsList().clear();
topics = null;
}
if (dataTest != null) dataTest.delete();
if (cls != null) cls = null;
if (tweetsProcessor != null) tweetsProcessor = null;
System.gc();
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
if (args.length < 1) {
System.out.println("usage: C4_5TweetTopicCategorization <root_path>");
System.exit(-1);
}
String rootPath = args[0];
File dataFolder = new File(rootPath + "/data");
String resultFolderPath = rootPath + "/results/C4_5/";
CrisisMailer crisisMailer = CrisisMailer.getCrisisMailer();
Logger logger = Logger.getLogger(C4_5TweetTopicCategorization.class);
PropertyConfigurator.configure(Constants.LOG4J_PROPERTIES_FILE_PATH);
File resultFolder = new File(resultFolderPath);
if (!resultFolder.exists()) resultFolder.mkdir();
CSVLoader csvLoader = new CSVLoader();
try {
for (File dataSetName : dataFolder.listFiles()) {
Instances data = null;
try {
csvLoader.setSource(dataSetName);
csvLoader.setStringAttributes("2");
data = csvLoader.getDataSet();
} catch (IOException ioe) {
logger.error(ioe);
crisisMailer.sendEmailAlert(ioe);
System.exit(-1);
}
data.setClassIndex(data.numAttributes() - 1);
data.deleteWithMissingClass();
Instances vectorizedData = null;
StringToWordVector stringToWordVectorFilter = new StringToWordVector();
try {
stringToWordVectorFilter.setInputFormat(data);
stringToWordVectorFilter.setAttributeIndices("2");
stringToWordVectorFilter.setIDFTransform(true);
stringToWordVectorFilter.setLowerCaseTokens(true);
stringToWordVectorFilter.setOutputWordCounts(false);
stringToWordVectorFilter.setUseStoplist(true);
vectorizedData = Filter.useFilter(data, stringToWordVectorFilter);
vectorizedData.deleteAttributeAt(0);
// System.out.println(vectorizedData);
} catch (Exception exception) {
logger.error(exception);
crisisMailer.sendEmailAlert(exception);
System.exit(-1);
}
J48 j48Classifier = new J48();
/*
FilteredClassifier filteredClassifier = new FilteredClassifier();
filteredClassifier.setFilter(stringToWordVectorFilter);
filteredClassifier.setClassifier(j48Classifier);
*/
try {
Evaluation eval = new Evaluation(vectorizedData);
eval.crossValidateModel(
j48Classifier, vectorizedData, 5, new Random(System.currentTimeMillis()));
FileOutputStream resultOutputStream =
new FileOutputStream(new File(resultFolderPath + dataSetName.getName()));
resultOutputStream.write(eval.toSummaryString("=== Summary ===", false).getBytes());
resultOutputStream.write(eval.toMatrixString().getBytes());
resultOutputStream.write(eval.toClassDetailsString().getBytes());
resultOutputStream.close();
} catch (Exception exception) {
logger.error(exception);
crisisMailer.sendEmailAlert(exception);
System.exit(-1);
}
}
} catch (Exception exception) {
logger.error(exception);
crisisMailer.sendEmailAlert(exception);
System.out.println(-1);
}
}
public double getLiblinear(String path, String train, String test) {
// 本次精确度
double accuracy = 0.0;
try {
LibLINEAR c1 = new LibLINEAR();
// * String[] options=weka.core.Utils.splitOptions(
// * "-S 1 -C 1.0 -E 0.001 -B 0"); c1.setOptions(options);
ArffLoader atf = new ArffLoader();
File TraininputFile = new File(train);
atf.setFile(TraininputFile); // 训练语料文件
Instances instancesTrain = atf.getDataSet(); // 读入训练文件
instancesTrain.setClassIndex(instancesTrain.numAttributes() - 1);
File TestinputFile = new File(test);
atf.setFile(TestinputFile); // 测试语料文件
Instances instancesTest = atf.getDataSet(); // 读入测试文件
// 设置分类属性所在行号（第一行为0号），instancesTest.numAttributes()可以取得属性总数
instancesTest.setClassIndex(instancesTest.numAttributes() - 1);
c1.buildClassifier(instancesTrain); // 训练
Evaluation eval = new Evaluation(instancesTrain);
eval.evaluateModel(c1, instancesTest);
// eval.crossValidateModel(c1, instancesTrain, 10, new
// Random(1));
File newfile = new File(path + "OutLiblinear_temp" + ".txt");
BufferedWriter bufferedWriter =
new BufferedWriter(new OutputStreamWriter(new FileOutputStream(newfile), "utf-8"));
bufferedWriter.write(eval.toSummaryString() + "\r\n");
bufferedWriter.write(eval.toClassDetailsString() + "\r\n");
bufferedWriter.write(eval.toMatrixString() + "\r\n");
bufferedWriter.flush();
bufferedWriter.close();
BufferedReader bufferedReader = new BufferedReader(new FileReader(newfile));
String[] splitLineString = new String[5];
while (bufferedReader.ready()) {
bufferedReader.readLine();
String lineString = bufferedReader.readLine();
splitLineString = lineString.split(" ");
System.out.println(splitLineString[4]);
break;
}
bufferedReader.close();
// 求分类准确度
String tempLine;
BufferedReader tempBF = new BufferedReader(new FileReader(newfile));
while (tempBF.ready()) {
tempLine = tempBF.readLine();
if (tempLine.contains("Correctly Classified Instances")) {
tempLine = tempLine.substring(tempLine.lastIndexOf(".") - 2, tempLine.lastIndexOf(" "));
accuracy = Double.parseDouble(tempLine);
break;
}
}
tempBF.close();
} catch (Exception e) {
System.out.println("Can't run linlinear of weka.");
}
return accuracy;
}
/**
* Accepts and processes a classifier encapsulated in an incremental classifier event
*
* @param ce an <code>IncrementalClassifierEvent</code> value
*/
@Override
public void acceptClassifier(final IncrementalClassifierEvent ce) {
try {
if (ce.getStatus() == IncrementalClassifierEvent.NEW_BATCH) {
m_throughput = new StreamThroughput(statusMessagePrefix());
m_throughput.setSamplePeriod(m_statusFrequency);
// m_eval = new Evaluation(ce.getCurrentInstance().dataset());
m_eval = new Evaluation(ce.getStructure());
m_eval.useNoPriors();
m_dataLegend = new Vector();
m_reset = true;
m_dataPoint = new double[0];
Instances inst = ce.getStructure();
System.err.println("NEW BATCH");
m_instanceCount = 0;
if (m_windowSize > 0) {
m_window = new LinkedList<Instance>();
m_windowEval = new Evaluation(ce.getStructure());
m_windowEval.useNoPriors();
m_windowedPreds = new LinkedList<double[]>();
if (m_logger != null) {
m_logger.logMessage(
statusMessagePrefix()
+ "[IncrementalClassifierEvaluator] Chart output using windowed "
+ "evaluation over "
+ m_windowSize
+ " instances");
}
}
/*
* if (m_logger != null) { m_logger.statusMessage(statusMessagePrefix()
* + "IncrementalClassifierEvaluator: started processing...");
* m_logger.logMessage(statusMessagePrefix() +
* " [IncrementalClassifierEvaluator]" + statusMessagePrefix() +
* " started processing..."); }
*/
} else {
Instance inst = ce.getCurrentInstance();
if (inst != null) {
m_throughput.updateStart();
m_instanceCount++;
// if (inst.attribute(inst.classIndex()).isNominal()) {
double[] dist = ce.getClassifier().distributionForInstance(inst);
double pred = 0;
if (!inst.isMissing(inst.classIndex())) {
if (m_outputInfoRetrievalStats) {
// store predictions so AUC etc can be output.
m_eval.evaluateModelOnceAndRecordPrediction(dist, inst);
} else {
m_eval.evaluateModelOnce(dist, inst);
}
if (m_windowSize > 0) {
m_windowEval.evaluateModelOnce(dist, inst);
m_window.addFirst(inst);
m_windowedPreds.addFirst(dist);
if (m_instanceCount > m_windowSize) {
// "forget" the oldest prediction
Instance oldest = m_window.removeLast();
double[] oldDist = m_windowedPreds.removeLast();
oldest.setWeight(-oldest.weight());
m_windowEval.evaluateModelOnce(oldDist, oldest);
oldest.setWeight(-oldest.weight());
}
}
} else {
pred = ce.getClassifier().classifyInstance(inst);
}
if (inst.classIndex() >= 0) {
// need to check that the class is not missing
if (inst.attribute(inst.classIndex()).isNominal()) {
if (!inst.isMissing(inst.classIndex())) {
if (m_dataPoint.length < 2) {
m_dataPoint = new double[3];
m_dataLegend.addElement("Accuracy");
m_dataLegend.addElement("RMSE (prob)");
m_dataLegend.addElement("Kappa");
}
// int classV = (int) inst.value(inst.classIndex());
if (m_windowSize > 0) {
m_dataPoint[1] = m_windowEval.rootMeanSquaredError();
m_dataPoint[2] = m_windowEval.kappa();
} else {
m_dataPoint[1] = m_eval.rootMeanSquaredError();
m_dataPoint[2] = m_eval.kappa();
}
// int maxO = Utils.maxIndex(dist);
// if (maxO == classV) {
// dist[classV] = -1;
// maxO = Utils.maxIndex(dist);
// }
// m_dataPoint[1] -= dist[maxO];
} else {
if (m_dataPoint.length < 1) {
m_dataPoint = new double[1];
m_dataLegend.addElement("Confidence");
}
}
double primaryMeasure = 0;
if (!inst.isMissing(inst.classIndex())) {
if (m_windowSize > 0) {
primaryMeasure = 1.0 - m_windowEval.errorRate();
} else {
primaryMeasure = 1.0 - m_eval.errorRate();
}
} else {
// record confidence as the primary measure
// (another possibility would be entropy of
// the distribution, or perhaps average
// confidence)
primaryMeasure = dist[Utils.maxIndex(dist)];
}
// double [] dataPoint = new double[1];
m_dataPoint[0] = primaryMeasure;
// double min = 0; double max = 100;
/*
* ChartEvent e = new
* ChartEvent(IncrementalClassifierEvaluator.this, m_dataLegend,
* min, max, dataPoint);
*/
m_ce.setLegendText(m_dataLegend);
m_ce.setMin(0);
m_ce.setMax(1);
m_ce.setDataPoint(m_dataPoint);
m_ce.setReset(m_reset);
m_reset = false;
} else {
// numeric class
if (m_dataPoint.length < 1) {
m_dataPoint = new double[1];
if (inst.isMissing(inst.classIndex())) {
m_dataLegend.addElement("Prediction");
} else {
m_dataLegend.addElement("RMSE");
}
}
if (!inst.isMissing(inst.classIndex())) {
double update;
if (!inst.isMissing(inst.classIndex())) {
if (m_windowSize > 0) {
update = m_windowEval.rootMeanSquaredError();
} else {
update = m_eval.rootMeanSquaredError();
}
} else {
update = pred;
}
m_dataPoint[0] = update;
if (update > m_max) {
m_max = update;
}
if (update < m_min) {
m_min = update;
}
}
m_ce.setLegendText(m_dataLegend);
m_ce.setMin((inst.isMissing(inst.classIndex()) ? m_min : 0));
m_ce.setMax(m_max);
m_ce.setDataPoint(m_dataPoint);
m_ce.setReset(m_reset);
m_reset = false;
}
notifyChartListeners(m_ce);
}
m_throughput.updateEnd(m_logger);
}
if (ce.getStatus() == IncrementalClassifierEvent.BATCH_FINISHED || inst == null) {
if (m_logger != null) {
m_logger.logMessage(
"[IncrementalClassifierEvaluator]"
+ statusMessagePrefix()
+ " Finished processing.");
}
m_throughput.finished(m_logger);
// save memory if using windowed evaluation for charting
m_windowEval = null;
m_window = null;
m_windowedPreds = null;
if (m_textListeners.size() > 0) {
String textTitle = ce.getClassifier().getClass().getName();
textTitle = textTitle.substring(textTitle.lastIndexOf('.') + 1, textTitle.length());
String results =
"=== Performance information ===\n\n"
+ "Scheme: "
+ textTitle
+ "\n"
+ "Relation: "
+ m_eval.getHeader().relationName()
+ "\n\n"
+ m_eval.toSummaryString();
if (m_eval.getHeader().classIndex() >= 0
&& m_eval.getHeader().classAttribute().isNominal()
&& (m_outputInfoRetrievalStats)) {
results += "\n" + m_eval.toClassDetailsString();
}
if (m_eval.getHeader().classIndex() >= 0
&& m_eval.getHeader().classAttribute().isNominal()) {
results += "\n" + m_eval.toMatrixString();
}
textTitle = "Results: " + textTitle;
TextEvent te = new TextEvent(this, results, textTitle);
notifyTextListeners(te);
}
}
}
} catch (Exception ex) {
if (m_logger != null) {
m_logger.logMessage(
"[IncrementalClassifierEvaluator]"
+ statusMessagePrefix()
+ " Error processing prediction "
+ ex.getMessage());
m_logger.statusMessage(
statusMessagePrefix() + "ERROR: problem processing prediction (see log for details)");
}
ex.printStackTrace();
stop();
}
}
