Notes

/*
* Düzeltilecek kısımlar var. Dosyaları çağırırken hızlı olsun diye direk yazdım. Onlar gui'ye uyarlanacak.
*/
public boolean createClassifierProp(String corpusTSV, String classifierName) throws FileNotFoundException, UnsupportedEncodingException {
String builder = "#location of the training filen"
+ "trainFile = data/NER/" + corpusTSV + "n"
+ "#location where you would like to save (serialize to) yourn"
+ "#classifier; adding .gz at the end automatically gzips the file,n"
+ "#making it faster and smallern"
+ "serializeTo = data/NER/" + classifierName + ".ser.gzn"
+ "n"
+ "#structure of your training file; this tells the classifiern"
+ "#that the word is in column 0 and the correct answer is inn"
+ "#column 1n"
+ "map = word=0,answer=1n"
+ "n"
+ "#these are the features we'd like to train withn"
+ "#some are discussed below, the rest can ben"
+ "#understood by looking at NERFeatureFactoryn"
+ "useClassFeature=truen"
+ "useWord=truen"
+ "useNGrams=truen"
+ "#no ngrams will be included that do not contain either then"
+ "#beginning or end of the wordn"
+ "noMidNGrams=truen"
+ "useDisjunctive=truen"
+ "maxNGramLeng=6n"
+ "usePrev=truen"
+ "useNext=truen"
+ "useSequences=truen"
+ "usePrevSequences=truen"
+ "maxLeft=1n"
+ "#the next 4 deal with word shape featuresn"
+ "useTypeSeqs=truen"
+ "useTypeSeqs2=truen"
+ "useTypeySequences=truen"
+ "wordShape=chris2useLC";

try (PrintWriter writer = new PrintWriter(new File("data/NER/classifier.prop"), "UTF-8")) {
writer.println(builder);
}
return false;

}

public boolean createClassifier(String classifierProp) throws IOException, InterruptedException {
String[] cmd = {
"/bin/bash",
"-c",
"java -Xmx16G -cp data/NER/stanford-ner/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier -prop data/NER/" + classifierProp};
Process p = Runtime.getRuntime().exec(cmd);
p.waitFor();
BufferedReader stdInput = new BufferedReader(new InputStreamReader(p.getInputStream()));

BufferedReader stdError = new BufferedReader(new InputStreamReader(p.getErrorStream()));

System.out.println("Here is the standard output of the command:n");
String s = null;
while ((s = stdInput.readLine()) != null) {
System.out.println(s);
}

System.out.println("Here is the standard error of the command (if any):n");
while ((s = stdError.readLine()) != null) {
System.out.println(s);
}

return true;
}

public void testClassifier(String serGZ,String textName) throws IOException, InterruptedException {

String[] cmd = {
"/bin/bash",
"-c",
"java -Xmx16G -cp data/NER/stanford-ner/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier data/NER/"+serGZ+".ser.gz -textFile data/NER/"+textName+" -outputFormat tabbedEntities"
+ ""};
Process p = Runtime.getRuntime().exec(cmd);
p.waitFor();
BufferedReader stdInput = new BufferedReader(new InputStreamReader(p.getInputStream()));

BufferedReader stdError = new BufferedReader(new InputStreamReader(p.getErrorStream()));

System.out.println("Here is the standard output of the command:n");
String s = null;
while ((s = stdInput.readLine()) != null) {
if (s.length() > 0) {
char a = s.charAt(s.length() - 1);
int b = a;
if (b != 48) {
System.out.println(s);
}
}
}

System.out.println("Here is the standard error of the command (if any):n");
while ((s = stdError.readLine()) != null) {
System.out.println(s);
}

}

public void testClassifier2(String serGZ,String textName) throws IOException, InterruptedException {

String[] cmd = {
"/bin/bash",
"-c",
" java -Xmx16G -cp data/NER/stanford-ner/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier data/NER/"+serGZ+".ser.gz -textFile data/NER/"+textName+" -outputFormat tabbedEntities >data/NER/output.txt"
+ ""};
Process p = Runtime.getRuntime().exec(cmd);
p.waitFor();
BufferedReader stdInput = new BufferedReader(new InputStreamReader(p.getInputStream()));

BufferedReader stdError = new BufferedReader(new InputStreamReader(p.getErrorStream()));

System.out.println("Here is the standard output of the command:n");
String s = null;
while ((s = stdInput.readLine()) != null) {
if (s.length() > 0) {
char a = s.charAt(s.length() - 1);
int b = a;
if (b != 48) {
System.out.println(s);
}
}
}

System.out.println("Here is the standard error of the command (if any):n");
while ((s = stdError.readLine()) != null) {
System.out.println(s);
}

}