이 시나리오 사용할 수있는 VectorAssemBler
여기 는 https://spark.apache.org/docs/2.0.2/ml-features.html#vectorassembler
희망 아래 링크는이
작동 학습과 사용 검사에 대한 샘플 코드
import java.util.Arrays;
import org.apache.spark.ml.feature.VectorAssembler;
import org.apache.spark.ml.linalg.VectorUDT;
import org.apache.spark.ml.linalg.Vectors;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.types.*;
import static org.apache.spark.sql.types.DataTypes.*;
StructType schema = createStructType(new StructField[]{
createStructField("id", IntegerType, false),
createStructField("hour", IntegerType, false),
createStructField("mobile", DoubleType, false),
createStructField("userFeatures", new VectorUDT(), false),
createStructField("clicked", DoubleType, false)
});
Row row = RowFactory.create(0, 18, 1.0, Vectors.dense(0.0, 10.0, 0.5), 1.0);
Dataset<Row> dataset = spark.createDataFrame(Arrays.asList(row), schema);
VectorAssembler assembler = new VectorAssembler()
.setInputCols(new String[]{"hour", "mobile", "userFeatures"})
.setOutputCol("features");
Dataset<Row> output = assembler.transform(dataset);
System.out.println(output.select("features", "clicked").first());
입니다