接口 UnivariateFeatureSelectorParams<T>
-
- 类型参数:
T- The class type of this instance.
- 所有超级接口:
org.apache.flink.ml.common.param.HasFeaturesCol<T>,org.apache.flink.ml.common.param.HasLabelCol<T>,org.apache.flink.ml.common.param.HasOutputCol<T>,UnivariateFeatureSelectorModelParams<T>,org.apache.flink.ml.param.WithParams<T>
- 所有已知实现类:
UnivariateFeatureSelector
public interface UnivariateFeatureSelectorParams<T> extends org.apache.flink.ml.common.param.HasLabelCol<T>, UnivariateFeatureSelectorModelParams<T>
Params forUnivariateFeatureSelector.
-
-
字段概要
字段 修饰符和类型 字段 说明 static StringCATEGORICALstatic StringCONTINUOUSstatic StringFDRstatic org.apache.flink.ml.param.Param<String>FEATURE_TYPESupported options of the feature type.static StringFPRstatic StringFWEstatic org.apache.flink.ml.param.Param<String>LABEL_TYPESupported options of the label type.static StringNUM_TOP_FEATURESstatic StringPERCENTILEstatic org.apache.flink.ml.param.Param<String>SELECTION_MODESupported options of the feature selection mode.static org.apache.flink.ml.param.Param<Double>SELECTION_THRESHOLD
-
方法概要
所有方法 实例方法 默认方法 修饰符和类型 方法 说明 default StringgetFeatureType()default StringgetLabelType()default StringgetSelectionMode()default DoublegetSelectionThreshold()default TsetFeatureType(String value)default TsetLabelType(String value)default TsetSelectionMode(String value)default TsetSelectionThreshold(double value)
-
-
-
字段详细资料
-
FEATURE_TYPE
static final org.apache.flink.ml.param.Param<String> FEATURE_TYPE
Supported options of the feature type.- categorical: the features are categorical data.
- continuous: the features are continuous data.
-
LABEL_TYPE
static final org.apache.flink.ml.param.Param<String> LABEL_TYPE
Supported options of the label type.- categorical: the label is categorical data.
- continuous: the label is continuous data.
-
SELECTION_MODE
static final org.apache.flink.ml.param.Param<String> SELECTION_MODE
Supported options of the feature selection mode.- numTopFeatures: chooses a fixed number of top features according to a hypothesis.
- percentile: similar to numTopFeatures but chooses a fraction of all features instead of a fixed number.
- fpr: chooses all features whose p-value are below a threshold, thus controlling the false positive rate of selection.
- fdr: uses the Benjamini-Hochberg procedure to choose all features whose false discovery rate is below a threshold.
- fwe: chooses all features whose p-values are below a threshold. The threshold is scaled by 1/numFeatures, thus controlling the family-wise error rate of selection.
-
SELECTION_THRESHOLD
static final org.apache.flink.ml.param.Param<Double> SELECTION_THRESHOLD
-
-