Scala Spark取出DataFrame中列中的值

Scala Spark取出DataFrame中列中的值

scala> val df = Seq(
     |     ("one", 2.0),
     |     ("two", 1.5),
     |     ("three", 8.0)
     |   ).toDF("id", "val")
df: org.apache.spark.sql.DataFrame = [id: string, val: double]

scala> df.show()
+-----+---+
|   id|val|
+-----+---+
|  one|2.0|
|  two|1.5|
|three|8.0|
+-----+---+


scala> df.select("id").collect().map(_(0)).toList
res6: List[Any] = List(one, two, three)

scala> df.select("id").rdd.map(_(0)).collect.toList 
res7: List[Any] = List(one, two, three)                                         

scala> df.select("id").map(_.getString(0)).collect.toList 
res8: List[String] = List(one, two, three)