如何从键值映射、spark数据帧中提取值

import org.apache.spark.sql.functions._
import spark.implicits._
val m = Seq(Array("A -> abc"), Array("B -> 0.11856755943424617"), Array("C -> kqcams"))

val df = m.toDF("map_data")
df.show
// Simulate your data I think.

val df2 = df.withColumn("xxx", split(concat_ws("",$"map_data"), "-> ")).select($"xxx".getItem(1).as("map_val")).drop("xxx")
df2.show(false)

结果:

+--------------------+
|            map_data|
+--------------------+
|          [A -> abc]|
|[B -> 0.118567559...|
|       [C -> kqcams]|
+--------------------+

+-------------------+
|map_val            |
+-------------------+
|abc                |
|0.11856755943424617|
|kqcams             |
+-------------------+

scala v2.3 api , sql v2.3 api 或 pyspark v2.4 api map_values

在pyspark中,scala将非常类似。
spark ):

from pyspark.sql import functions as F

df = (
    spark.read.json(sc.parallelize(["""[
        {"key": ["3pea"],    "value": ["3PEA"] },
        {"key": ["barello"], "value": ["BA"]   }
    ]"""]))
    .select(F.map_from_arrays(F.col("key"), F.col("value")).alias("symbols") )
)

df.printSchema()
df.show()

root
 |-- symbols: map (nullable = true)
 |    |-- key: string
 |    |-- value: string (valueContainsNull = true)

+---------------+
|        symbols|
+---------------+
| [3pea -> 3PEA]|
|[barello -> BA]|
+---------------+

df.select((F.map_values(F.col("symbols"))[0]).alias("map_vals")).show()

+--------+
|map_vals|
+--------+
|    3PEA|
|      BA|
+--------+