程序包 org.apache.flink.ml.feature.univariatefeatureselector

类 UnivariateFeatureSelector

java.lang.Object

org.apache.flink.ml.feature.univariatefeatureselector.UnivariateFeatureSelector

所有已实现的接口:

Serializable, org.apache.flink.ml.api.Estimator<UnivariateFeatureSelector,UnivariateFeatureSelectorModel>, org.apache.flink.ml.api.Stage<UnivariateFeatureSelector>, org.apache.flink.ml.common.param.HasFeaturesCol<UnivariateFeatureSelector>, org.apache.flink.ml.common.param.HasLabelCol<UnivariateFeatureSelector>, org.apache.flink.ml.common.param.HasOutputCol<UnivariateFeatureSelector>, UnivariateFeatureSelectorModelParams<UnivariateFeatureSelector>, UnivariateFeatureSelectorParams<UnivariateFeatureSelector>, org.apache.flink.ml.param.WithParams<UnivariateFeatureSelector>

public class UnivariateFeatureSelector
extends Object
implements org.apache.flink.ml.api.Estimator<UnivariateFeatureSelector,UnivariateFeatureSelectorModel>, UnivariateFeatureSelectorParams<UnivariateFeatureSelector>

An Estimator which selects features based on univariate statistical tests against labels.

Currently, Flink supports three Univariate Feature Selectors: chi-squared, ANOVA F-test and F-value. User can choose Univariate Feature Selector by setting `featureType` and `labelType`, and Flink will pick the score function based on the specified `featureType` and `labelType`.

The following combination of `featureType` and `labelType` are supported:

• `featureType` `categorical` and `labelType` `categorical`: Flink uses chi-squared, i.e. chi2 in sklearn.
• `featureType` `continuous` and `labelType` `categorical`: Flink uses ANOVA F-test, i.e. f_classif in sklearn.
• `featureType` `continuous` and `labelType` `continuous`: Flink uses F-value, i.e. f_regression in sklearn.

The `UnivariateFeatureSelector` supports different selection modes:

• 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.

By default, the selection mode is `numTopFeatures`.

另请参阅:

序列化表格

字段概要

从接口继承的字段 org.apache.flink.ml.common.param.HasFeaturesCol

FEATURES_COL

从接口继承的字段 org.apache.flink.ml.common.param.HasLabelCol

LABEL_COL

从接口继承的字段 org.apache.flink.ml.common.param.HasOutputCol

OUTPUT_COL

从接口继承的字段 org.apache.flink.ml.feature.univariatefeatureselector.UnivariateFeatureSelectorParams

CATEGORICAL, CONTINUOUS, FDR, FEATURE_TYPE, FPR, FWE, LABEL_TYPE, NUM_TOP_FEATURES, PERCENTILE, SELECTION_MODE, SELECTION_THRESHOLD

构造器概要

构造器

构造器	说明
UnivariateFeatureSelector()

方法概要

修饰符和类型	方法	说明
UnivariateFeatureSelectorModel	fit(org.apache.flink.table.api.Table... inputs)
Map<org.apache.flink.ml.param.Param<?>,Object>	getParamMap()
static UnivariateFeatureSelector	load(org.apache.flink.table.api.bridge.java.StreamTableEnvironment tEnv, String path)
void	save(String path)

从类继承的方法 java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

从接口继承的方法 org.apache.flink.ml.common.param.HasFeaturesCol

getFeaturesCol, setFeaturesCol

从接口继承的方法 org.apache.flink.ml.common.param.HasLabelCol

getLabelCol, setLabelCol

从接口继承的方法 org.apache.flink.ml.common.param.HasOutputCol

getOutputCol, setOutputCol

从接口继承的方法 org.apache.flink.ml.feature.univariatefeatureselector.UnivariateFeatureSelectorParams

getFeatureType, getLabelType, getSelectionMode, getSelectionThreshold, setFeatureType, setLabelType, setSelectionMode, setSelectionThreshold

从接口继承的方法 org.apache.flink.ml.param.WithParams

get, getParam, set

构造器详细资料

UnivariateFeatureSelector

public UnivariateFeatureSelector()

方法详细资料

fit

public UnivariateFeatureSelectorModel fit(org.apache.flink.table.api.Table... inputs)

指定者:

fit 在接口中 org.apache.flink.ml.api.Estimator<UnivariateFeatureSelector,UnivariateFeatureSelectorModel>

getParamMap

public Map<org.apache.flink.ml.param.Param<?>,Object> getParamMap()

指定者:

getParamMap 在接口中 org.apache.flink.ml.param.WithParams<UnivariateFeatureSelector>

save

public void save(String path)
          throws IOException

指定者:

save 在接口中 org.apache.flink.ml.api.Stage<UnivariateFeatureSelector>

抛出:

IOException

load

public static UnivariateFeatureSelector load(org.apache.flink.table.api.bridge.java.StreamTableEnvironment tEnv,
                                             String path)
                                      throws IOException

抛出:

IOException