Я пытаюсь создать таблицу в spark (scala), а затем вставить значения из двух существующих фреймов данных, но я получил это исключение:
Exception in thread "main" org.apache.spark.sql.AnalysisException: Hive support is required to CREATE Hive TABLE (AS SELECT);;
'CreateTable `stat_type_predicate_percentage`, ErrorIfExists
Вот код:
case class stat_type_predicate_percentage (type1: Option[String], predicate: Option[String], outin: Option[INT], percentage: Option[FLOAT])
object LoadFiles1 {
def main(args: Array[String]) {
val sc = new SparkContext("local[*]", "LoadFiles1")
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
val warehouseLocation = new File("spark-warehouse").getAbsolutePath
val spark = SparkSession
.builder()
.appName("Spark Hive Example")
.config("spark.sql.warehouse.dir", warehouseLocation)
.enableHiveSupport()
.getOrCreate()
import sqlContext.implicits._
import org.apache.spark.sql._
import org.apache.spark.sql.Row;
import org.apache.spark.sql.types.{StructType,StructField,StringType};
//statistics
val create = spark.sql("CREATE TABLE stat_type_predicate_percentage (type1 String, predicate String, outin INT, percentage FLOAT) USING hive")
val insert1 = spark.sql("INSERT INTO stat_type_predicate_percentage SELECT types.type, res.predicate, 0, 1.0*COUNT(subject)/(SELECT COUNT(subject) FROM MappingBasedProperties AS resinner WHERE res.predicate = resinner.predicate) FROM MappingBasedProperties AS res, MappingBasedTypes AS types WHERE res.subject = types.resource GROUP BY res.predicate,types.type")
val select = spark.sql("SELECT * from stat_type_predicate_percentage" )
}
Как мне это решить?