如何在spark sql聚合中添加三个整数列

Question

val df = sqlContext.phoenixTableAsDataFrame(
  Metadata.tables(A.Test), Seq("ID", "date", "col1", "col2","col3"),
  predicate = Some("\"date\" = " + date), zkUrl = Some(zkURL))

val df1 = df.groupBy($"ID", $"date").agg(
  sum($"col1" + $"col2" + $"col3").alias("col4"))

ID,date,col1,col2,col3
1,2017-01-01,5,10,12
2,2017-01-01,6,9,17
3,2017-01-01,2,3,7
4,2017-01-01,5,11,13

ID,date,col4 
1,2017-01-01,27
2,2017-01-01,32
3,2017-01-01,12
4,2017-01-01,29

Answer 1

我用下面的代码得到了一个正确的结果：

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, Row}
import org.apache.spark.sql.functions.{col, sum}
import org.apache.spark.sql.types.{IntegerType,  StructField, StructType}

  val rowsRdd: RDD[Row] = spark.sparkContext.parallelize(
    Seq(
      Row(1, 1, 5, 10, 12 ),
      Row(2, 1, 6, 9,  17 ),
      Row(3, 1, 2, 3,  7),
      Row(4, 1, 5, 11, 13)

    )
  )

  val schema: StructType = new StructType()
    .add(StructField("id",    IntegerType,  false))
    .add(StructField("date",  IntegerType, false))
    .add(StructField("col1",  IntegerType, false))
    .add(StructField("col2",  IntegerType, false))
    .add(StructField("col3",  IntegerType, false))
  val df0: DataFrame = spark.createDataFrame(rowsRdd, schema)

  val df = df0.groupBy(col("id"), col("date")).agg(sum(col("col1") + col("col2") + col("col3")).alias("col4")).sort("id")

  df.show()

结果是：

+---+----+----+
| id|date|col4|
+---+----+----+
|  1|   1|  27|
|  2|   1|  32|
|  3|   1|  12|
|  4|   1|  29|
+---+----+----+

这是你需要的吗？