au.csiro.variantspark.output.CSVFeatureSink2.scala Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of variant-spark_2.11 Show documentation

Genomic variants interpretation toolkit

The newest version!

package au.csiro.variantspark.output

import au.csiro.variantspark.input.FeatureSource

/**
  * This only works for smallish datasets (used local files)
  */
case class CSVFeatureSink2(fileName: String) extends FeatureSink {

  def save(fs: FeatureSource) {
    val header = ("" :: fs.sampleNames).mkString(",")
    fs.features
      .map(f => (f.label :: f.valueAsStrings).mkString(","))
      .mapPartitionsWithIndex({
        case (i, it) =>
          if (i > 0) it else Some(header).iterator ++ it
      })
      .coalesce(1, true)
      .saveAsTextFile(fileName)
  }
}