Spark ML - Binary Classification Evaluator

See the Spark ML Documentation BinaryClassificationEvaluator

ml_binary_classification_eval(predicted_tbl_spark, label, score,
  metric = "areaUnderROC")

Arguments

predicted_tbl_spark

The result of running sdf_predict

label

Name of column string specifying which column contains the true, indexed labels (ie 0 / 1)

score

Name of column contains the scored probability of a success (ie 1)

metric

The classification metric - one of: areaUnderRoc (default) or areaUnderPR (not available in Spark 2.X)

Value

area under the specified curve