public class GenerateTrainingData
extends java.lang.Object
Modifier and Type | Field and Description |
---|---|
(package private) java.util.List<java.util.List<java.lang.Comparable>> |
features |
(package private) java.util.Set<java.lang.String> |
keywords |
(package private) java.util.Set<java.lang.String> |
stopwords |
Constructor and Description |
---|
GenerateTrainingData(java.lang.String keywordsFileName,
java.lang.String stopwordsFileName) |
Modifier and Type | Method and Description |
---|---|
static void |
main(java.lang.String[] args)
keywordsFile and stopwordsFile must point to the files in the resources
dataFile is your own sentence-level data in the format (class_label: C,
P, S): sentence|class_label sentence|class_label ...
|
void |
makeFeatures(java.lang.String fname)
set "features" - list of features.
|
private void |
printLibsvmDataToFile(java.lang.String fname) |
private static java.util.Set<java.lang.String> |
readLinesFromFile(java.lang.String fileName) |
java.util.Set<java.lang.String> keywords
java.util.Set<java.lang.String> stopwords
java.util.List<java.util.List<java.lang.Comparable>> features
GenerateTrainingData(java.lang.String keywordsFileName, java.lang.String stopwordsFileName)
private static java.util.Set<java.lang.String> readLinesFromFile(java.lang.String fileName) throws java.io.IOException
java.io.IOException
public void makeFeatures(java.lang.String fname)
private void printLibsvmDataToFile(java.lang.String fname)
public static void main(java.lang.String[] args)