diff options
Diffstat (limited to 'examples/src/main/scala')
3 files changed, 6 insertions, 6 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 d1bda0ff84..1b019fbb51 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 @@ -35,8 +35,8 @@ object RDDRelation { import spark.implicits._ val df = spark.createDataFrame((1 to 100).map(i => Record(i, s"val_$i"))) - // Any RDD containing case classes can be registered as a table. The schema of the table is - // automatically inferred using scala reflection. + // Any RDD containing case classes can be used to create a temporary view. The schema of the + // view is automatically inferred using scala reflection. df.createOrReplaceTempView("records") // Once tables have been registered, you can run SQL queries over them. @@ -66,7 +66,7 @@ object RDDRelation { // Queries can be run using the DSL on parquet files just like the original RDD. parquetFile.where($"key" === 1).select($"value".as("a")).collect().foreach(println) - // These files can also be registered as tables. + // These files can also be used to create a temporary view. parquetFile.createOrReplaceTempView("parquetFile") spark.sql("SELECT * FROM parquetFile").collect().foreach(println) diff --git a/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala b/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala index a15cf5ded0..7293cb51b2 100644 --- a/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala +++ b/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala @@ -70,9 +70,9 @@ object HiveFromSpark { case Row(key: Int, value: String) => s"Key: $key, Value: $value" } - // You can also register RDDs as temporary tables within a HiveContext. + // You can also use RDDs to create temporary views within a HiveContext. val rdd = sc.parallelize((1 to 100).map(i => Record(i, s"val_$i"))) - rdd.toDF().registerTempTable("records") + rdd.toDF().createOrReplaceTempView("records") // Queries can then join RDD data with data stored in Hive. println("Result of SELECT *:") diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala index 688c5b23c2..787bbec73b 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala @@ -66,7 +66,7 @@ object SqlNetworkWordCount { // Convert RDD[String] to RDD[case class] to DataFrame val wordsDataFrame = rdd.map(w => Record(w)).toDF() - // Register as table + // Creates a temporary view using the DataFrame wordsDataFrame.createOrReplaceTempView("words") // Do word count on table using SQL and print it |