评估指标与api

对2分类或者多分类模型的评估：

// 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")
// 评估指标：

val metricsml = new MulticlassMetrics(predictionAndLabels)
// Confusion matrix
println("Confusion matrix:")
println(metricsml.confusionMatrix)
// Overall Statistics
val accuracy = metricsml.accuracy
println("Summary Statistics")
println(s"Accuracy = $accuracy")

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

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

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

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

predictionAndLabels.take(30).foreach(println)