com.datastax.data.prepare.spark.dataset.HierarchicalCluster Maven / Gradle / Ivy
package com.datastax.data.prepare.spark.dataset;
import com.datastax.insight.spec.Operator;
import com.datastax.insight.annonation.InsightComponent;
import com.datastax.insight.annonation.InsightComponentArg;
import com.datastax.data.prepare.spark.dataset.hierarchicalCluster.Pink;
import org.apache.spark.sql.Dataset;
/**
* @author yusf
*/
public class HierarchicalCluster implements Operator {
@InsightComponent(name = "cluster", description = "cluster")
public static Dataset cluster(
@InsightComponentArg(externalInput = true, name = "数据集", description = "数据集") Dataset data,
@InsightComponentArg(externalInput = true, name = "numSplits", description = "numSplits") int numSplits,
@InsightComponentArg(name = "K", description = "k") int K,
@InsightComponentArg(name = "threshold", description = "threshold") double threshold,
@InsightComponentArg(name = "tmpFileDir", description = "tmpFileDir") String tmpFileDir){
return Pink.runCLuster(data,numSplits,K,threshold,tmpFileDir);
}
}