【sparkSQL】DataFrame的常用操作

scala> import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.SparkSession

scala> val spark=SparkSession.builder().getOrCreate()
spark: org.apache.spark.sql.SparkSession = org.apache.spark.sql.SparkSession@2bdab835

//使支持RDDs转换为DataFrames及后续sql操作
scala> import spark.implicits._
import spark.implicits._

scala> val df = spark.read.json("file:///usr/local/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|
+----+-------+

// 打印模式信息
scala> df.printSchema()
root
 |-- age: long (nullable = true)
 |-- name: string (nullable = true)

// 选择多列
scala> df.select(df("name"),df("age")+1).show()
+-------+---------+
|   name|(age + 1)|
+-------+---------+
|Michael|     null|
|   Andy|       31|
| Justin|       20|
+-------+---------+

// 条件过滤
scala> df.filter(df("age") > 20 ).show()
+---+----+
|age|name|
+---+----+
| 30|Andy|
+---+----+

// 分组聚合
scala> df.groupBy("age").count().show()
+----+-----+
| age|count|
+----+-----+
|  19|    1|
|null|    1|
|  30|    1|
+----+-----+

// 排序
scala> df.sort(df("age").desc).show()
+----+-------+
| age|   name|
+----+-------+
|  30|   Andy|
|  19| Justin|
|null|Michael|
+----+-------+

//多列排序
scala> df.sort(df("age").desc, df("name").asc).show()
+----+-------+
| age|   name|
+----+-------+
|  30|   Andy|
|  19| Justin|
|null|Michael|
+----+-------+

//对列进行重命名
scala> df.select(df("name").as("username"),df("age")).show()
+--------+----+
|username| age|
+--------+----+
| Michael|null|
|    Andy|  30|
|  Justin|  19|
+--------+----+

//使用spark sql语句
scala>df.createTempView("table1")
scala> spark.sql("select * from table1 limit 10")

以上是我们常用的dataframe的基础操作

具体见一下博客

https://blog.csdn.net/dabokele/article/details/52802150

SparkSQL官网

http://spark.apache.org/docs/1.6.2/api/scala/index.html#org.apache.spark.sql.DataFrame