Multiclass SVM for digit recognition

DigitRecognition.scala

// using https://github.com/Bekbolatov/spark/commit/463d73323d5f08669d5ae85dc9791b036637c966
import org.apache.spark.mllib.classification.SVMMultiClassWithSGD
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.linalg.Vectors
import breeze.linalg.DenseVector

val digits_train = sc.textFile("/data/pendigits.tra").map(line => DenseVector(line.split(",").map(_.trim().toDouble))).map( v => LabeledPoint(v(-1),Vectors.dense(v(0 to 15).toArray))).cache()

val digits_test = sc.textFile("/data/pendigits.tes").map(line => DenseVector(line.split(",").map(_.trim().toDouble))).map( v => LabeledPoint(v(-1),Vectors.dense(v(0 to 15).toArray)))


val model = SVMMultiClassWithSGD.train(digits_train, 100)

val predictionAndLabel = digits_test.map(p => (model.predict(p.features), p.label))
val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / digits_test.count()

val scoreAndLabels = digits_test.map { point =>
  val score = model.predict(point.features)
  (score, point.label)
}

scoreAndLabels.take(5)