理解 Spark SQL(二)-- SQLContext 和 HiveContext

scala> val df = spark.read.JSON("file:///opt/spark/examples/src/main/resources/people.json")
df: org.apache.spark.sql.DataFrame = [age: bigint, name: string]
scala> df.show()
+----+-------+
| age|   name|
+----+-------+
|null|Michael|
|  30|   Andy|
|  19| Justin|
+----+-------+
scala> df.select("name").show()
+-------+
|   name|
+-------+
|Michael|
|   Andy|
| Justin|
+-------+
scala> df.select(df("name"), df("age") + 1).show()
+-------+---------+
|   name|(age + 1)|
+-------+---------+
|Michael|     null|
|   Andy|       31|
| Justin|       20|
+-------+---------+
scala> df.filter(df("age")> 21).show()
+---+----+
|age|name|
+---+----+
| 30|Andy|
+---+----+
scala> df.groupBy("age").count().show()
+----+-----+
| age|count|
+----+-----+
|  19|    1|
|null|    1|
|  30|    1|
+----+-----+
scala>

来源: http://www.bubuko.com/infodetail-3298288.html