Repository: bigtop Updated Branches: refs/heads/master 5efdbfbfa -> 96a2a4aca
BIGTOP-2019. BigPetStore Spark isn't compiling due to changes in SQL API Project: http://git-wip-us.apache.org/repos/asf/bigtop/repo Commit: http://git-wip-us.apache.org/repos/asf/bigtop/commit/96a2a4ac Tree: http://git-wip-us.apache.org/repos/asf/bigtop/tree/96a2a4ac Diff: http://git-wip-us.apache.org/repos/asf/bigtop/diff/96a2a4ac Branch: refs/heads/master Commit: 96a2a4aca547d71eeab36094edff2159cc0bab4f Parents: 5efdbfb Author: RJ Nowling <[email protected]> Authored: Tue Sep 8 13:48:15 2015 -0500 Committer: RJ Nowling <[email protected]> Committed: Tue Sep 8 13:49:19 2015 -0500 ---------------------------------------------------------------------- .../spark/analytics/PetStoreStatistics.scala | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/bigtop/blob/96a2a4ac/bigtop-bigpetstore/bigpetstore-spark/src/main/scala/org/apache/bigpetstore/spark/analytics/PetStoreStatistics.scala ---------------------------------------------------------------------- diff --git a/bigtop-bigpetstore/bigpetstore-spark/src/main/scala/org/apache/bigpetstore/spark/analytics/PetStoreStatistics.scala b/bigtop-bigpetstore/bigpetstore-spark/src/main/scala/org/apache/bigpetstore/spark/analytics/PetStoreStatistics.scala index 2d376a4..e7e5b08 100644 --- a/bigtop-bigpetstore/bigpetstore-spark/src/main/scala/org/apache/bigpetstore/spark/analytics/PetStoreStatistics.scala +++ b/bigtop-bigpetstore/bigpetstore-spark/src/main/scala/org/apache/bigpetstore/spark/analytics/PetStoreStatistics.scala @@ -68,7 +68,7 @@ object PetStoreStatistics { def queryTxByMonth(sqlContext: SQLContext): Array[StatisticsTxByMonth] = { import sqlContext._ - val results: SchemaRDD = sql("SELECT count(*), month FROM Transactions GROUP BY month") + val results: DataFrame = sql("SELECT count(*), month FROM Transactions GROUP BY month") val transactionsByMonth = results.collect() for(x<-transactionsByMonth){ println(x) @@ -82,7 +82,7 @@ object PetStoreStatistics { def queryTxByProductZip(sqlContext: SQLContext): Array[StatisticsTxByProductZip] = { import sqlContext._ - val results: SchemaRDD = sql( + val results: DataFrame = sql( """SELECT count(*) c, productId, zipcode FROM Transactions t JOIN Stores s ON t.storeId = s.storeId @@ -104,7 +104,7 @@ GROUP BY productId, zipcode""") def queryTxByProduct(sqlContext: SQLContext): Array[StatisticsTxByProduct] = { import sqlContext._ - val results: SchemaRDD = sql( + val results: DataFrame = sql( """SELECT count(*) c, productId FROM Transactions GROUP BY productId""") val groupedProducts = results.collect() @@ -121,16 +121,17 @@ GROUP BY productId, zipcode""") val sqlContext = new org.apache.spark.sql.SQLContext(sc) import sqlContext._ + import sqlContext.implicits._ // Transform the Non-SparkSQL Calendar into a SparkSQL-friendly field. val mappableTransactions:RDD[TransactionSQL] = r._5.map { trans => trans.toSQL() } - r._1.registerTempTable("Locations") - r._2.registerTempTable("Stores") - r._3.registerTempTable("Customers") - r._4.registerTempTable("Product") - mappableTransactions.registerTempTable("Transactions") + r._1.toDF().registerTempTable("Locations") + r._2.toDF().registerTempTable("Stores") + r._3.toDF().registerTempTable("Customers") + r._4.toDF().registerTempTable("Product") + mappableTransactions.toDF().registerTempTable("Transactions") val txByMonth = queryTxByMonth(sqlContext)
