Description
LinearSVC should fail fast if the input dataset contains invalid values.
import org.apache.spark.ml.feature._ import org.apache.spark.ml.linalg._ import org.apache.spark.ml.classification._ import org.apache.spark.ml.clustering._ val df = sc.parallelize(Seq(LabeledPoint(1.0, Vectors.dense(1.0, Double.NaN)), LabeledPoint(0.0, Vectors.dense(Double.PositiveInfinity, 2.0)))).toDF() val svc = new LinearSVC() val model = svc.fit(df) scala> model.intercept res0: Double = NaN scala> model.coefficients res1: org.apache.spark.ml.linalg.Vector = [NaN,NaN]