Spark-MLlib 学习入门到掌握-FeatureHasher特征向量[9]

FeatureHasher:将不同数据类型通过hash算法转换成特征向量。如String、bool、int等等。

  def FeatureHasher(): Unit ={
    import org.apache.spark.ml.feature.FeatureHasher
    val spark: SparkSession = SparkSession.builder().appName("implicits").master("local[2]").getOrCreate()

    val dataset = spark.createDataFrame(Seq(
      (2.2, true, "1", "foo"),
      (3.3, false, "2", "bar"),
      (4.4, false, "3", "baz"),
      (5.5, false, "4", "foo")
    )).toDF("real", "bool", "stringNum", "string")

    val hasher = new FeatureHasher()
      //输入映射列
      .setInputCols("real", "bool", "stringNum", "string")
      //输出映射列
      .setOutputCol("features")

    val featurized = hasher.transform(dataset)
    //输出特征向量
    featurized.show(false)
    [0,WrappedArray(a, b, c),(3,[0,1,2],[1.0,1.0,1.0])]
    [1,WrappedArray(a, b, b, c, a),(3,[0,1,2],[2.0,2.0,1.0])]
  }

运行结果：