public class LinearSVC extends Classifier<Vector,LinearSVC,LinearSVCModel> implements LinearSVCParams, DefaultParamsWritable
This binary classifier optimizes the Hinge Loss using the OWLQN optimizer. Only supports L2 regularization currently.
| Modifier and Type | Method and Description |
|---|---|
LinearSVC |
copy(ParamMap extra)
Creates a copy of this instance with the same UID and some extra params.
|
static LinearSVC |
load(String path) |
static MLReader<T> |
read() |
LinearSVC |
setAggregationDepth(int value)
Suggested depth for treeAggregate (greater than or equal to 2).
|
LinearSVC |
setFitIntercept(boolean value)
Whether to fit an intercept term.
|
LinearSVC |
setMaxIter(int value)
Set the maximum number of iterations.
|
LinearSVC |
setRegParam(double value)
Set the regularization parameter.
|
LinearSVC |
setStandardization(boolean value)
Whether to standardize the training features before fitting the model.
|
LinearSVC |
setThreshold(double value)
Set threshold in binary classification.
|
LinearSVC |
setTol(double value)
Set the convergence tolerance of iterations.
|
LinearSVC |
setWeightCol(String value)
Set the value of param
weightCol. |
String |
uid()
An immutable unique ID for the object and its derivatives.
|
setRawPredictionColfit, setFeaturesCol, setLabelCol, setPredictionCol, transformSchemaequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitthresholdvalidateAndTransformSchemagetLabelCol, labelColfeaturesCol, getFeaturesColgetPredictionCol, predictionColclear, copyValues, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, paramMap, params, set, set, set, setDefault, setDefault, shouldOwntoStringgetRawPredictionCol, rawPredictionColgetRegParam, regParamgetMaxIter, maxIterfitIntercept, getFitInterceptgetStandardization, standardizationgetWeightCol, weightColaggregationDepth, getAggregationDepthgetThresholdwritesaveinitializeLogging, initializeLogIfNecessary, initializeLogIfNecessary, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarningpublic static LinearSVC load(String path)
public static MLReader<T> read()
public String uid()
Identifiableuid in interface Identifiablepublic LinearSVC setRegParam(double value)
value - (undocumented)public LinearSVC setMaxIter(int value)
value - (undocumented)public LinearSVC setFitIntercept(boolean value)
value - (undocumented)public LinearSVC setTol(double value)
value - (undocumented)public LinearSVC setStandardization(boolean value)
value - (undocumented)public LinearSVC setWeightCol(String value)
weightCol.
If this is not set or empty, we treat all instance weights as 1.0.
Default is not set, so all instances have weight one.
value - (undocumented)public LinearSVC setThreshold(double value)
value - (undocumented)public LinearSVC setAggregationDepth(int value)
value - (undocumented)