История страницы

scala> val rdd = sc.parallelize(1 to 100)
rdd: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[0] at parallelize at <console>:24

scala> val df = rdd.toDF
df: org.apache.spark.sql.DataFrame = [value: int]

scala> df.printSchema
root
 |-- value: integer (nullable = false)


scala> df.show(2)
+-----+
|value|
+-----+
|    1|
|    2|
+-----+
only showing top 2 rows

scala> case class Person(id: Int, name: String)
defined class Person

scala> val persons = Seq(Person(1, "Ivan"), Person(2, "Petrov"), Person(3, "Sidorov")).toDF
persons: org.apache.spark.sql.DataFrame = [id: int, name: string]

scala> persons.select("name").show
+-------+
|   name|
+-------+
|   Ivan|
| Petrov|
|Sidorov|
+-------+


scala> persons.createGlobalTempView("persons")

scala> spark.sql("select id from global_temp.persons").show
+---+
| id|
+---+
|  1|
|  2|
|  3|
+---+