org.maltparser.ml.lib
Class MaltLiblinearModel
java.lang.Object
org.maltparser.ml.lib.MaltLiblinearModel
- All Implemented Interfaces:
- Serializable, MaltLibModel
public class MaltLiblinearModel
- extends Object
- implements Serializable, MaltLibModel
This class borrows code from liblinear.Model.java of the Java implementation of the liblinear package.
MaltLiblinearModel stores the model obtained from the training procedure. In addition to the original code the model is more integrated to
MaltParser. Instead of moving features from MaltParser's internal data structures to liblinear's data structure it uses MaltParser's data
structure directly on the model.
- Author:
- Johan Hall
- See Also:
- Serialized Form
MaltLiblinearModel
public MaltLiblinearModel(liblinear.Model model,
liblinear.SolverType solverType)
MaltLiblinearModel
public MaltLiblinearModel(Reader inputReader)
throws IOException
- Throws:
IOException
MaltLiblinearModel
public MaltLiblinearModel(File modelFile)
throws IOException
- Throws:
IOException
getNrClass
public int getNrClass()
- Returns:
- number of classes
getNrFeature
public int getNrFeature()
- Returns:
- number of features
getLabels
public int[] getLabels()
getFeatureWeights
public double[] getFeatureWeights()
- The nr_feature*nr_class array w gives feature weights. We use one
against the rest for multi-class classification, so each feature
index corresponds to nr_class weight values. Weights are
organized in the following way
+------------------+------------------+------------+
| nr_class weights | nr_class weights | ...
| for 1st feature | for 2nd feature |
+------------------+------------------+------------+
If bias >= 0, x becomes [x; bias]. The number of features is
increased by one, so w is a (nr_feature+1)*nr_class array. The
value of bias is stored in the variable bias.
- Returns:
- a copy of the feature weight array as described
- See Also:
getBias()
isProbabilityModel
public boolean isProbabilityModel()
- Returns:
- true for logistic regression solvers
getBias
public double getBias()
predict
public int[] predict(MaltFeatureNode[] x)
- Specified by:
predict
in interface MaltLibModel
hashCode
public int hashCode()
- Overrides:
hashCode
in class Object
equals
public boolean equals(Object obj)
- Overrides:
equals
in class Object
toString
public String toString()
- Overrides:
toString
in class Object
Copyright 2007-2011 Johan Hall, Jens Nilsson and Joakim Nivre.