Stanford CoreNLP API
edu.stanford.nlp.ie.crf

## Class CRFNonLinearLogConditionalObjectiveFunction

• ### Field Summary

Fields
Modifier and Type Field and Description
`static boolean` `DEBUG`
`protected double` `epsilon`
`boolean` `gradientsOnly`
`static int` `HUBER_PRIOR`
`static int` `L1_PRIOR`
`static int` `NO_PRIOR`
`protected int` `prior`
`static int` `QUADRATIC_PRIOR`
`static int` `QUARTIC_PRIOR`
`protected double` `sigma`
`static boolean` `VERBOSE`
• ### Fields inherited from class edu.stanford.nlp.optimization.AbstractCachingDiffFunction

`derivative, generator, value`
• ### Method Summary

All Methods
Modifier and Type Method and Description
`void` `calculate(double[] x)`
Calculates both value and partial derivatives at the point x, and save them internally.
`int` `domainDimension()`
Returns the number of dimensions in the function's domain
`double[][]` `empty2D()`
`double[][]` `emptyFull2D()`
`CliquePotentialFunction` `getCliquePotentialFunction(double[] x)`
`int[][]` `getFeatureGrouping()`
`static int` `getPriorType(String priorTypeStr)`
`Set<Integer>` `getRegularizerParamRange(double[] x)`
`double[]` `initial()`
Returns the intitial point in the domain (but not necessarily a feasible one).
`Triple<double[][],double[][],double[][]>` `separateWeights(double[] x)`
`double[][]` `to2D(double[] linearWeights)`
• ### Methods inherited from class edu.stanford.nlp.optimization.AbstractCachingDiffFunction

`clearCache, copy, derivativeAt, ensure, getDerivative, gradientCheck, gradientCheck, lastValue, randomInitial, valueAt`
• ### Methods inherited from class java.lang.Object

`clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait`
• ### Field Detail

• #### NO_PRIOR

`public static final int NO_PRIOR`
Constant Field Values

`public static final int QUADRATIC_PRIOR`
Constant Field Values
• #### HUBER_PRIOR

`public static final int HUBER_PRIOR`
Constant Field Values
• #### QUARTIC_PRIOR

`public static final int QUARTIC_PRIOR`
Constant Field Values
• #### L1_PRIOR

`public static final int L1_PRIOR`
Constant Field Values
• #### prior

`protected int prior`
• #### sigma

`protected double sigma`
• #### epsilon

`protected double epsilon`
• #### VERBOSE

`public static boolean VERBOSE`
• #### DEBUG

`public static boolean DEBUG`

`public boolean gradientsOnly`
• ### Method Detail

• #### getPriorType

`public static int getPriorType(String priorTypeStr)`
• #### domainDimension

`public int domainDimension()`
Description copied from interface: `Function`
Returns the number of dimensions in the function's domain
Specified by:
`domainDimension` in interface `Function`
Returns:
the number of domain dimensions
• #### initial

`public double[] initial()`
Description copied from interface: `HasInitial`
Returns the intitial point in the domain (but not necessarily a feasible one).
Specified by:
`initial` in interface `HasInitial`
Overrides:
`initial` in class `AbstractCachingDiffFunction`
Returns:
a domain point
• #### separateWeights

`public Triple<double[][],double[][],double[][]> separateWeights(double[] x)`
• #### getCliquePotentialFunction

`public CliquePotentialFunction getCliquePotentialFunction(double[] x)`
Specified by:
`getCliquePotentialFunction` in interface `HasCliquePotentialFunction`
• #### calculate

`public void calculate(double[] x)`
Calculates both value and partial derivatives at the point x, and save them internally.
Specified by:
`calculate` in class `AbstractCachingDiffFunction`
Parameters:
`x` - The point at which to calculate the function
• #### getRegularizerParamRange

`public Set<Integer> getRegularizerParamRange(double[] x)`
Specified by:
`getRegularizerParamRange` in interface `HasRegularizerParamRange`
• #### to2D

`public double[][] to2D(double[] linearWeights)`
• #### empty2D

`public double[][] empty2D()`
• #### emptyFull2D

`public double[][] emptyFull2D()`
• #### getFeatureGrouping

`public int[][] getFeatureGrouping()`
Specified by:
`getFeatureGrouping` in interface `HasFeatureGrouping`