org.apache.spark.input.PortableDataStream Scala Examples

The following examples show how to use org.apache.spark.input.PortableDataStream. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: JsonUtils.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources.json

import org.apache.spark.input.PortableDataStream
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.catalyst.json.JSONOptions

object JsonUtils {
  
  def sample(json: RDD[PortableDataStream], options: JSONOptions): RDD[PortableDataStream] = {
    require(options.samplingRatio > 0,
      s"samplingRatio (${options.samplingRatio}) should be greater than 0")
    if (options.samplingRatio > 0.99) {
      json
    } else {
      json.sample(withReplacement = false, options.samplingRatio, 1)
    }
  }
}
Example 2
Source File: JsonUtils.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources.json

import org.apache.spark.input.PortableDataStream
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.catalyst.json.JSONOptions

object JsonUtils {
  
  def sample(json: RDD[PortableDataStream], options: JSONOptions): RDD[PortableDataStream] = {
    require(options.samplingRatio > 0,
      s"samplingRatio (${options.samplingRatio}) should be greater than 0")
    if (options.samplingRatio > 0.99) {
      json
    } else {
      json.sample(withReplacement = false, options.samplingRatio, 1)
    }
  }
}