使用 flatten 以及 array 而不是 arrays_zip 然后使用 element_at 函数从每个元素中获取项。

val df = spark.read("/home/user/test.csv").csv.options("header", "true")

df.groupBy(col("id"),col("date")).
agg(flatten(array(collect_list(col("item1")),collect_list(col("item2")),collect_list(col("item3")))).alias("it")).
withColumn("item1",element_at(col("it"),1)).
withColumn("item2",element_at(col("it"),2)).
withColumn("item3",element_at(col("it"),3)).
drop("it").
show()
//+---+----+-----+-----+-----+
//| id|date|item1|item2|item3|
//+---+----+-----+-----+-----+
//|  0|   1|  111|  222|  333|
//|  1|   1|  111|  222|  333|
//+---+----+-----+-----+-----+
``` `2.Using groupBy and first(col,ignoreNulls=true)` ```
df.groupBy(col("id"),col("date")).
agg(first(col("item1")).alias("item1"),first(col("item2"),true).alias("item2"),first(col("item3"),true).alias("item3")).
show()
//+---+----+-----+-----+-----+
//| id|date|item1|item2|item3|
//+---+----+-----+-----+-----+
//|  0|   1|  111|  222|  333|
//|  1|   1|  111|  222|  333|
//+---+----+-----+-----+-----+
``` `SQL:` ```
df.createOrReplaceTempView("tmp")

//using first
spark.sql("select id,date,first(item1,true) as item1,first(item2,true) as item2,first(item3,true) as item3 from tmp group by id,date").show()

//using max
spark.sql("select id,date,max(item1) as item1,max(item2) as item2,max(item3) as item3 from tmp group by id,date").show()

//using flatten array
spark.sql("select id,date, element_at(tmp,1)item1, element_at(tmp,2)item2, element_at(tmp,3)item3 from (select id,date,flatten(array(collect_list(item1),collect_list(item2),collect_list(item3))) as tmp from tmp group by id,date)t").show()
//+---+----+-----+-----+-----+
//| id|date|item1|item2|item3|
//+---+----+-----+-----+-----+
//|  0|   1|  111|  222|  333|
//|  1|   1|  111|  222|  333|
//+---+----+-----+-----+-----+
``` `Dynamic way:` ```
val df = spark.read("/home/user/test.csv").csv.options("header", "true")

val df1=df.groupBy(col("id"),col("date")).agg(flatten(array(collect_list(col("item1")),collect_list(col("item2")),collect_list(col("item3")))).alias("it"))

val len=df1.agg(max(size(col("it")))).collect()(0)(0).toString.toInt

spark.range(len).collect().foldLeft(df1)((df,len) => df.withColumn(s"item${len+1}",col("it")(len))).
drop("it").
show()
//+---+----+-----+-----+-----+
//| id|date|item1|item2|item3|
//+---+----+-----+-----+-----+
//|  0|   1|  111|  222|  333|
//|  1|   1|  111|  222|  333|
//+---+----+-----+-----+-----+