我想在火花中实现这样的事情。以下代码片段来自Pig Latin。无论如何我可以用Spark做同样的事情吗?
A = load 'student' AS (name:chararray,age:int,gpa:float);
DESCRIBE A;
A: {name: chararray,age: int,gpa: float} DUMP A; (John,18,4.0F)
(Mary,19,3.8F) (Bill,20,3.9F) (Joe,18,3.8F)
B = GROUP A BY age;
Result: (18,{(John,18,4.0F),(Joe,18,3.8F)}) (19,{(Mary,19,3.8F)})
(20,{(Bill,20,3.9F)})
感谢。
答案 0 :(得分:0)
按年龄划分名单很容易。我相信Spark API不允许您以相同的方式收集完整的行并获得完整的行列表。
// Input data
val df = {
import org.apache.spark.sql._
import org.apache.spark.sql.types._
import scala.collection.JavaConverters._
import java.time.LocalDate
val simpleSchema = StructType(
StructField("name", StringType) ::
StructField("age", IntegerType) ::
StructField("gpa", FloatType) :: Nil)
val data = List(
Row("John", 18, 4.0f),
Row("Mary", 19, 3.8f),
Row("Bill", 20, 3.9f),
Row("Joe", 18, 3.8f)
)
spark.createDataFrame(data.asJava, simpleSchema)
}
df.show()
val df2 = df.groupBy(col("age")).agg(collect_list(col("name")))
df2.show()