KIryl Sultanau created SPARK-23178:
--------------------------------------
Summary: Kryo Unsafe problems with count distinct from cache
Key: SPARK-23178
URL: https://issues.apache.org/jira/browse/SPARK-23178
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 2.2.1, 2.2.0
Reporter: KIryl Sultanau
val spark = SparkSession
.builder
.appName("unsafe-issue")
.master("local[*]")
.config("spark.serializer",
"org.apache.spark.serializer.KryoSerializer")
.config("spark.kryo.unsafe", "true")
.config("spark.kryo.registrationRequired", "false")
.getOrCreate()
val devicesDF = spark.read.format("csv")
.option("header", "true")
.option("delimiter", "\t")
.load("/data/Devices.tsv").cache()
val gatewaysDF = spark.read.format("csv")
.option("header", "true")
.option("delimiter", "\t")
.load("/data/Gateways.tsv").cache()
val devJoinedDF = devicesDF.join(gatewaysDF, Seq("GatewayId"),
"inner").cache()
devJoinedDF.printSchema()
println(devJoinedDF.count())
println(devJoinedDF.select("DeviceId").distinct().count())
println(devJoinedDF.groupBy("DeviceId").count().filter("count>1").count())
println(devJoinedDF.groupBy("DeviceId").count().filter("count=1").count())
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
