Question

我正在使用Spark版本2.2.0和Scala版本2.11.8。我使用以下代码创建并保存了决策树二进制分类模型：

package...
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.tree.DecisionTree
import org.apache.spark.mllib.tree.model.DecisionTreeModel
import org.apache.spark.mllib.util.MLUtils
import org.apache.spark.sql.SparkSession


object DecisionTreeClassification {

def main(args: Array[String]): Unit = {

val sparkSession = SparkSession.builder
  .master("local[*]")
  .appName("Decision Tree")
  .getOrCreate()
// Load and parse the data file.
val data = MLUtils.loadLibSVMFile(sparkSession.sparkContext, "path/to/file/xyz.txt")
// Split the data into training and test sets (20% held out for testing)
val splits = data.randomSplit(Array(0.8, 0.2))
val (trainingData, testData) = (splits(0), splits(1))

// Train a DecisionTree model.
//  Empty categoricalFeaturesInfo indicates all features are continuous.
val numClasses = 2
val categoricalFeaturesInfo = Map[Int, Int]()
val impurity = "gini"
val maxDepth = 5
val maxBins = 32

val model = DecisionTree.trainClassifier(trainingData, numClasses, categoricalFeaturesInfo,
  impurity, maxDepth, maxBins)

// Evaluate model on test instances and compute test error
val labelAndPreds = testData.map { point =>
  val prediction = model.predict(point.features)
  (point.label, prediction) 
}
val testErr = labelAndPreds.filter(r => r._1 != r._2).count().toDouble / testData.count()
println(s"Test Error = $testErr")
println(s"Learned classification tree model:\n ${model.toDebugString}")

// Save and load model
model.save(sparkSession.sparkContext, "target/tmp/myDecisionTreeClassificationModel")
val sameModel = DecisionTreeModel.load(sparkSession.sparkContext, "target/tmp/myDecisionTreeClassificationModel")
// $example off$

sparkSession.sparkContext.stop()
}  
}

现在，我想使用此保存的模型预测新数据的标签（0或1）。我是Spark的新手，有人可以让我知道该怎么做吗？

Answer 1

我找到了这个问题的答案，所以我认为如果有人正在寻找类似问题的答案，我应该分享它

要对新数据进行预测，只需在停止spark会话之前添加几行：

 val newData = MLUtils.loadLibSVMFile(sparkSession.sparkContext, "path/to/file/abc.txt")

 val newDataPredictions = newData.map 
    { point =>
      val newPrediction = model.predict(point.features)
      (point.label, newPrediction)
    }
    newDataPredictions.foreach(f => println("Predicted label", f._2))

使用保存的Spark mllib决策树二进制分类模型预测新数据

1 个答案: