T
- public class S3VMLight<T> extends java.lang.Object implements TransductiveClassifier<T>
Transductive SVM using S3VMLight
Making large-Scale SVM Learning Practical
T. Joachims
Advances in Kernel Methods - Support Vector Learning, B. Schölkopf and C. Burges and A. Smola (ed.), MIT-Press, 1999
Constructor and Description |
---|
S3VMLight(Kernel<T> kernel)
Constructor using specific kernel as input space similarity function
|
Modifier and Type | Method and Description |
---|---|
double |
getC()
Tells the hyperparameter C
|
int |
getNumplus()
Tells the number of positive samples (used for transductive label estimation)
|
void |
setC(double c)
Sets the hyperparameter C
|
void |
setNumplus(int numplus)
Sets the number of positive samples (used for transductive label estimation)
|
void |
train(java.util.List<TrainingSample<T>> trainList,
java.util.List<TrainingSample<T>> testList)
Train the classifier on trainList, with the help of testList in a transductive way.
|
double |
valueOf(T t)
prediction output for t.
|
public void train(java.util.List<TrainingSample<T>> trainList, java.util.List<TrainingSample<T>> testList)
TransductiveClassifier
train
in interface TransductiveClassifier<T>
public double valueOf(T t)
TransductiveClassifier
valueOf
in interface TransductiveClassifier<T>
t
- sample to evaluatepublic double getC()
public void setC(double c)
c
- the hyperparameter Cpublic int getNumplus()
public void setNumplus(int numplus)
numplus
-