Spark随机森林算法交叉验证、管道模型（pipeline）、模型评估代码实例

package cn.itcast.tags.ml.classification

import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.RandomForestClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, StringIndexerModel, VectorIndexer, VectorIndexerModel}
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.tuning.{CrossValidator, CrossValidatorModel, ParamGridBuilder}
import org.apache.spark.sql.{DataFrame, SparkSession}

object RfModel {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder()
      .appName(this.getClass.getSimpleName.stripSuffix("$"))
      .master("local[4]")
      .getOrCreate()
    import org.apache.spark.sql.functions._
    import spark.implicits._

    // 1. 加载数据
    val dataframe: DataFrame = spark.read
      .format("libsvm")
      .load("datas/ship/total001.txt")

    // 划分数据集：训练数据和测试数据
    va