Created
November 22, 2016 16:04
-
-
Save evbruno/808d891ef21633aff9a9e27f4ef43d41 to your computer and use it in GitHub Desktop.
Flight Delay computing with Spark
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// ref: https://github.com/evbruno/flight_delay_akka_streams | |
// ref: https://github.com/evbruno/flight_delay_java8 | |
// 0 : load | |
val flightText = sc.textFile("/tmp/2008.csv").cache | |
case class FlightEvent( | |
year: String, | |
month: String, | |
dayOfMonth: String, | |
dayOfWeek: String, | |
uniqueCarrier: String, | |
flightNum: String, | |
arrDelayMins: Int) | |
val flights = flightText.map(s => s.split(",")).filter(c => c(0) != "Year").map( s => | |
FlightEvent( | |
year = s(0), | |
month = s(1), | |
dayOfMonth = s(2), | |
dayOfWeek = s(3), | |
flightNum = s(9), | |
uniqueCarrier = s(8), | |
arrDelayMins = scala.util.Try(s(14).toInt).getOrElse(0) | |
) | |
).cache | |
val delayedFlights = flights.filter(_.arrDelayMins > 0) | |
delayedFlights.count // res3: Long = 2979504 | |
// 1a : SQL | |
val sqlContext = new org.apache.spark.sql.SQLContext(sc) | |
import sqlContext.implicits._ | |
val newDF = delayedFlights.toDF | |
newDF.registerTempTable("flights") | |
val df = sqlContext.sql("select uniqueCarrier, count(1), avg(arrDelayMins) from flights group by uniqueCarrier") | |
df.show | |
// 1b : Dataframes/RDDs | |
newDF.printSchema | |
newDF.show(10) | |
newDF.groupBy("uniqueCarrier").show(21) | |
newDF.groupBy("uniqueCarrier").avg("uniqueCarrier").show(21) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment