samplers

class ParquetSampler extends Sampler[GenericRecord]

Sampler for Parquet files.
Sampler for Parquet files.
Records are represented as Avro GenericRecord. Only head mode is supported.

def sampleAvro[T <: GenericRecord](coll: SCollection[T], fraction: Double, schema: ⇒ Schema, fields: Seq[String], seed: Option[Int], distribution: Option[SampleDistribution], distributionFields: Seq[String], precision: Precision, maxKeySize: Int, byteEncoding: ByteEncoding)(implicit arg0: ClassTag[T], arg1: Coder[T]): SCollection[T]
def sampleProto[T <: AbstractMessage](coll: SCollection[T], fraction: Double, fields: Seq[String], seed: Option[Int], distribution: Option[SampleDistribution], distributionFields: Seq[String], precision: Precision, maxKeySize: Int, byteEncoding: ByteEncoding)(implicit arg0: ClassTag[T]): SCollection[T]
def sampleTableRow(coll: SCollection[TableRow], fraction: Double, schema: TableSchema, fields: Seq[String], seed: Option[Int], distribution: Option[SampleDistribution], distributionFields: Seq[String], precision: Precision, maxKeySize: Int, byteEncoding: ByteEncoding): SCollection[TableRow]