SparkSQL小例子

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.types._
import org.apache.spark.sql.Row
import org.apache.spark.rdd.RDD

object PeopleDataStatisticSparkSQL {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("SparkSQL").setMaster("local");
    val sc = new SparkContext(conf)
    val peopleDataRDD = sc.textFile("/Users/lihu/Desktop/crawle/xingbie.txt")
    val sqlCtx = new SQLContext(sc)
    import sqlCtx.implicits._
    val shemaArray = Array("id", "gender", "height")
    val schema = StructType(shemaArray.map(StructField(_, StringType, true)))
    val rowRDD:RDD[Row] = peopleDataRDD.map(_.split(" ")).map(eachRow => Row(eachRow(0), eachRow(1), eachRow(2)))
    val peopleDF = sqlCtx.createDataFrame(rowRDD, schema)
    peopleDF.registerTempTable("people")
    println(sqlCtx.sql("select id from people where height > 180 and gender = ‘M‘").count())
    println(sqlCtx.sql("select id from people where height > 170 and gender = ‘F‘").count())
    println(peopleDF.filter(peopleDF("gender").equalTo("M")).filter(peopleDF("height") > 165).count())
    peopleDF.groupBy(peopleDF("gender")).count().show()
    peopleDF.filter(peopleDF("gender").equalTo("M")).filter(peopleDF("height") > 165).show(2)
    peopleDF.sort($"height".desc).take(3).foreach{row => println(row(0) + " " + row(1) + " " + row(2))}
    peopleDF.groupBy(peopleDF("gender")).agg(Map("height" -> "avg")).show()
    peopleDF.groupBy(peopleDF("gender")).agg(Map("height" -> "max")).show()
    peopleDF.groupBy(peopleDF("gender")).agg(Map("height" -> "min")).show()
  }
}