在Scala、Spark和UDF中使用类型多态性展平要映射的映射序列

我有下面的函数，它将字符串映射序列展平为双精度。如何将类型字符串设置为双泛型

val flattenSeqOfMaps = udf { values: Seq[Map[String, Double]] => values.flatten.toMap }
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

谢谢

编辑1： 我用的是spark 2.3。我了解spark 2.4中的高阶函数

编辑2：我靠近了一点。我需要什么来代替f{in val=udf{f}。请比较joinMap类型签名和下面的Maps类型签名

scala> val joinMap = udf { values: Seq[Map[String, Double]] => values.flatten.toMap }
joinMap: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

scala> def f[S,D](values: Seq[Map[S, D]]): Map[S,D] = { values.flatten.toMap}
f: [S, D](values: Seq[Map[S,D]])Map[S,D]

scala> val flattenSeqOfMaps = udf { f _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(NullType,NullType,true),Some(List(ArrayType(MapType(NullType,NullType,true),true))))

编辑3：以下代码适用于我

scala> val flattenSeqOfMaps = udf { f[String,Double] _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

scala> def f[S,D](values: Seq[Map[S, D]]): Map[S,D] = { values.flatten.toMap}
f: [S, D](values: Seq[Map[S,D]])Map[S,D]

scala> val flattenSeqOfMaps = udf { f[String,Double] _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

---

而您可以将函数定义为

import scala.reflect.runtime.universe.TypeTag

def flattenSeqOfMaps[S : TypeTag, D: TypeTag] = udf { 
  values: Seq[Map[S, D]] => values.flatten.toMap
}

然后使用特定实例：

val df = Seq(Seq(Map("a" -> 1), Map("b" -> 1))).toDF("val")

val flattenSeqOfMapsStringInt = flattenSeqOfMaps[String, Int]

df.select($"val", flattenSeqOfMapsStringInt($"val") as "val").show

+----------+--------+ |瓦尔|瓦尔| +----------+--------+ |[a->1]，[b->1]|[a->1，b->1]| +----------+--------| 也可以使用内置函数，而不需要显式泛型：

import org.apache.spark.sql.functions.{expr, flatten, map_from_arrays}

def flattenSeqOfMaps_(col: String) = {
  val keys = flatten(expr(s"transform(`$col`, x -> map_keys(x))"))
  val values = flatten(expr(s"transform(`$col`, x -> map_values(x))"))
  map_from_arrays(keys, values)
}

df.select($"val", flattenSeqOfMaps_("val") as "val").show

+----------+--------+ |瓦尔|瓦尔| +----------+--------+ |[a->1]，[b->1]|[a->1，b->1]| +----------+--------+

---

而您可以将函数定义为

import scala.reflect.runtime.universe.TypeTag

def flattenSeqOfMaps[S : TypeTag, D: TypeTag] = udf { 
  values: Seq[Map[S, D]] => values.flatten.toMap
}

然后使用特定实例：

val df = Seq(Seq(Map("a" -> 1), Map("b" -> 1))).toDF("val")

val flattenSeqOfMapsStringInt = flattenSeqOfMaps[String, Int]

df.select($"val", flattenSeqOfMapsStringInt($"val") as "val").show

+----------+--------+ |瓦尔|瓦尔| +----------+--------+ |[a->1]，[b->1]|[a->1，b->1]| +----------+--------| 也可以使用内置函数，而不需要显式泛型：

import org.apache.spark.sql.functions.{expr, flatten, map_from_arrays}

def flattenSeqOfMaps_(col: String) = {
  val keys = flatten(expr(s"transform(`$col`, x -> map_keys(x))"))
  val values = flatten(expr(s"transform(`$col`, x -> map_values(x))"))
  map_from_arrays(keys, values)
}

df.select($"val", flattenSeqOfMaps_("val") as "val").show

+----------+--------+ |瓦尔|瓦尔| +----------+--------+ |[a->1]，[b->1]|[a->1，b->1]| +----------+--------+

---

下面的代码适用于我

scala> val flattenSeqOfMaps = udf { f[String,Double] _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

scala> def f[S,D](values: Seq[Map[S, D]]): Map[S,D] = { values.flatten.toMap}
f: [S, D](values: Seq[Map[S,D]])Map[S,D]

scala> val flattenSeqOfMaps = udf { f[String,Double] _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

---

下面的代码适用于我

scala> val flattenSeqOfMaps = udf { f[String,Double] _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

scala> def f[S,D](values: Seq[Map[S, D]]): Map[S,D] = { values.flatten.toMap}
f: [S, D](values: Seq[Map[S,D]])Map[S,D]

scala> val flattenSeqOfMaps = udf { f[String,Double] _}
flattenSeqOfMaps: org.apache.spark.sql.expressions.UserDefinedFunction = UserDefinedFunction(<function1>,MapType(StringType,DoubleType,false),Some(List(ArrayType(MapType(StringType,DoubleType,false),true))))

---

我的错。我没有提到spark 2.3版本。编辑问题，我的错。我没有提到spark 2.3版本。编辑问题。