diff options
Diffstat (limited to 'examples')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala | 20 |
1 files changed, 10 insertions, 10 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala b/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala index 94b67cb29b..8ce4427c53 100644 --- a/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala +++ b/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala @@ -19,7 +19,7 @@ package org.apache.spark.examples.sql import org.apache.spark.{SparkConf, SparkContext} -import org.apache.spark.sql.{SaveMode, SQLContext} +import org.apache.spark.sql.{SaveMode, SparkSession} // One method for defining the schema of an RDD is to make a case class with the desired column // names and types. @@ -29,10 +29,10 @@ object RDDRelation { def main(args: Array[String]) { val sparkConf = new SparkConf().setAppName("RDDRelation") val sc = new SparkContext(sparkConf) - val sqlContext = new SQLContext(sc) + val spark = new SparkSession(sc) - // Importing the SQL context gives access to all the SQL functions and implicit conversions. - import sqlContext.implicits._ + // Importing the SparkSession gives access to all the SQL functions and implicit conversions. + import spark.implicits._ val df = sc.parallelize((1 to 100).map(i => Record(i, s"val_$i"))).toDF() // Any RDD containing case classes can be registered as a table. The schema of the table is @@ -41,15 +41,15 @@ object RDDRelation { // Once tables have been registered, you can run SQL queries over them. println("Result of SELECT *:") - sqlContext.sql("SELECT * FROM records").collect().foreach(println) + spark.sql("SELECT * FROM records").collect().foreach(println) // Aggregation queries are also supported. - val count = sqlContext.sql("SELECT COUNT(*) FROM records").collect().head.getLong(0) + val count = spark.sql("SELECT COUNT(*) FROM records").collect().head.getLong(0) println(s"COUNT(*): $count") - // The results of SQL queries are themselves RDDs and support all normal RDD functions. The + // The results of SQL queries are themselves RDDs and support all normal RDD functions. The // items in the RDD are of type Row, which allows you to access each column by ordinal. - val rddFromSql = sqlContext.sql("SELECT key, value FROM records WHERE key < 10") + val rddFromSql = spark.sql("SELECT key, value FROM records WHERE key < 10") println("Result of RDD.map:") rddFromSql.rdd.map(row => s"Key: ${row(0)}, Value: ${row(1)}").collect().foreach(println) @@ -61,14 +61,14 @@ object RDDRelation { df.write.mode(SaveMode.Overwrite).parquet("pair.parquet") // Read in parquet file. Parquet files are self-describing so the schema is preserved. - val parquetFile = sqlContext.read.parquet("pair.parquet") + val parquetFile = spark.read.parquet("pair.parquet") // Queries can be run using the DSL on parquet files just like the original RDD. parquetFile.where($"key" === 1).select($"value".as("a")).collect().foreach(println) // These files can also be registered as tables. parquetFile.registerTempTable("parquetFile") - sqlContext.sql("SELECT * FROM parquetFile").collect().foreach(println) + spark.sql("SELECT * FROM parquetFile").collect().foreach(println) sc.stop() } |