Я хочу создать Dataframe (он же Dataset‹Row› в Spark 2.1) с помощью createDataframe(), все работает хорошо, когда я передаю ему параметр List‹Row›, но он выдает исключение, когда я передаю JavaRDD‹Row›.
[Код]
SparkSession ss = SparkSession.builder().appName("Spark Test").master("local[4]").getOrCreate();
List<Row> data = Arrays.asList(
RowFactory.create(Arrays.asList("a", "b", "c")),
RowFactory.create(Arrays.asList("A", "B", "C"))
);
StructType schema = new StructType(new StructField[]{
DataTypes.createStructField("col_1", DataTypes.createArrayType(DataTypes.StringType), false)
});
Когда я пробую этот код, все работает хорошо
ss.createDataFrame(data, schema).show();
+---------+
| col_1|
+---------+
|[a, b, c]|
|[A, B, C]|
+---------+
Но когда я передаю JavaRDD в качестве первого параметра, возникает исключение
JavaRDD<Row> rdd = JavaSparkContext.fromSparkContext(ss.sparkContext()).parallelize(data);
ss.createDataFrame(rdd, schema).show(); // throws exception
[Исключение]
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 1.0 failed 1 times, most recent failure: Lost task 2.0 in stage 1.0 (TID 3, localhost, executor driver): java.lang.RuntimeException: Error while encoding: java.lang.RuntimeException: java.util.Arrays$ArrayList is not a valid external type for schema of array<string>
mapobjects(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object)), StringType), true), validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, col_1), ArrayType(StringType,true))) AS col_1#0
+- mapobjects(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object)), StringType), true), validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, col_1), ArrayType(StringType,true)))
:- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(lambdavariable(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object)), StringType), true)
: +- validateexternaltype(lambdavariable(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object)), StringType)
: +- lambdavariable(MapObjects_loopValue0, MapObjects_loopIsNull1, ObjectType(class java.lang.Object))
+- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, col_1), ArrayType(StringType,true))
+- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, col_1)
+- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
+- input[0, org.apache.spark.sql.Row, true]
at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.toRow(ExpressionEncoder.scala:293)
at org.apache.spark.sql.SparkSession$$anonfun$3.apply(SparkSession.scala:547)
at org.apache.spark.sql.SparkSession$$anonfun$3.apply(SparkSession.scala:547)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:232)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.RuntimeException: java.util.Arrays$ArrayList is not a valid external type for schema of array<string>
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown Source)
at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.toRow(ExpressionEncoder.scala:290)
... 17 more
Любая помощь будет оценена