scala-sparkML学习笔记：模型评估

                 本文链接：[https://blog.csdn.net/u014365862/article/details/100147276](https://blog.csdn.net/u014365862/article/details/100147276) 

// 二分类下的模型评估。
// Precision by threshold
val precision = metrics.precisionByThreshold
precision.foreach { case (t, p) =>
  println(s"Threshold: $t, Precision: $p")
}

// Recall by threshold
val recall = metrics.recallByThreshold
recall.foreach { case (t, r) =>
  println(s"Threshold: $t, Recall: $r")
}

// Precision-Recall Curve
val PRC = metrics.pr

// F-measure
val f1Score = metrics.fMeasureByThreshold
f1Score.foreach { case (t, f) =>
  println(s"Threshold: $t, F-score: $f, Beta = 1")
}

val beta = 0.5
val fScore = metrics.fMeasureByThreshold(beta)
f1Score.foreach { case (t, f) =>
  println(s"Threshold: $t, F-score: $f, Beta = 0.5")
}

// AUPRC
val auPRC = metrics.areaUnderPR
println(s"Area under precision-recall curve = $auPRC")

// Compute thresholds used in ROC and PR curves
val thresholds = precision.map(_._1)

// ROC Curve
val roc = metrics.roc

// AUROC
val auROC = metrics.areaUnderROC
println(s"Area under ROC = $auROC")



// 多分类下的模型评估。
// Compute raw scores on the test set
val predictionAndLabels = test.map { case LabeledPoint(label, features) =>
  val prediction = model.predict(features)
  (prediction, label)
}

// Instantiate metrics object
val metrics = new MulticlassMetrics(predictionAndLabels)

// Confusion matrix
println("Confusion matrix:")
println(metrics.confusionMatrix)

// Overall Statistics
val accuracy = metrics.accuracy
println("Summary Statistics")
println(s"Accuracy = $accuracy")

// Precision by label
val labels = metrics.labels
labels.foreach { l =>
  println(s"Precision($l) = " + metrics.precision(l))
}

// Recall by label
labels.foreach { l =>
  println(s"Recall($l) = " + metrics.recall(l))
}

// False positive rate by label
labels.foreach { l =>
  println(s"FPR($l) = " + metrics.falsePositiveRate(l))
}

// F-measure by label
labels.foreach { l =>
  println(s"F1-Score($l) = " + metrics.fMeasure(l))
}

// Weighted stats
println(s"Weighted precision: ${metrics.weightedPrecision}")
println(s"Weighted recall: ${metrics.weightedRecall}")
println(s"Weighted F1 score: ${metrics.weightedFMeasure}")
println(s"Weighted false positive rate: ${metrics.weightedFalsePositiveRate}")


# 多标签下的模型评估。
import org.apache.spark.mllib.evaluation.MultilabelMetrics
import org.apache.spark.rdd.RDD

val scoreAndLabels: RDD[(Array[Double], Array[Double])] = sc.parallelize(
  Seq((Array(0.0, 1.0), Array(0.0, 2.0)),
    (Array(0.0, 2.0), Array(0.0, 1.0)),
    (Array.empty[Double], Array(0.0)),
    (Array(2.0), Array(2.0)),
    (Array(2.0, 0.0), Array(2.0, 0.0)),
    (Array(0.0, 1.0, 2.0), Array(0.0, 1.0)),
    (Array(1.0), Array(1.0, 2.0))), 2)

// Instantiate metrics object
val metrics = new MultilabelMetrics(scoreAndLabels)

// Summary stats
println(s"Recall = ${metrics.recall}")
println(s"Precision = ${metrics.precision}")
println(s"F1 measure = ${metrics.f1Measure}")
println(s"Accuracy = ${metrics.accuracy}")

// Individual label stats
metrics.labels.foreach(label =>
  println(s"Class $label precision = ${metrics.precision(label)}"))
metrics.labels.foreach(label => println(s"Class $label recall = ${metrics.recall(label)}"))
metrics.labels.foreach(label => println(s"Class $label F1-score = ${metrics.f1Measure(label)}"))

// Micro stats
println(s"Micro recall = ${metrics.microRecall}")
println(s"Micro precision = ${metrics.microPrecision}")
println(s"Micro F1 measure = ${metrics.microF1Measure}")

// Hamming loss
println(s"Hamming loss = ${metrics.hammingLoss}")

// Subset accuracy
println(s"Subset accuracy = ${metrics.subsetAccuracy}")