axelfahy / networkanomalydetection Goto Github PK

hello Thanks nice job done ! but i got a runtime issue with the schema
kmeansSimple works well but kmeansOneHotEncoder exits :

Exception in thread "main" java.lang.IllegalArgumentException: Field "label" does not exist.
Available fields: duration, protocol_type, service, flag, src_bytes, dst_bytes, land, wrong_fragment, urgent, hot, num_failed_logins, logged_in, num_compromised, root_shell, su_attempted, num_root, num_file_creations, num_shells, num_access_files, num_outbound_cmds, is_host_login, is_guest_login, count, srv_count, serror_rate, srv_serror_rate, rerror_rate, srv_rerror_rate, same_srv_rate, diff_srv_rate, srv_diff_host_rate, dst_host_count, dst_host_srv_count, dst_host_same_srv_rate, dst_host_diff_srv_rate, dst_host_same_src_port_rate, dst_host_srv_diff_host_rate, dst_host_serror_rate, dst_host_srv_serror_rate, dst_host_rerror_rate, dst_host_srv_rerror_rate
at org.apache.spark.sql.types.StructType$$anonfun$apply$1.apply(StructType.scala:267)
at org.apache.spark.sql.types.StructType$$anonfun$apply$1.apply(StructType.scala:267)
at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
at scala.collection.AbstractMap.getOrElse(Map.scala:59)
at org.apache.spark.sql.types.StructType.apply(StructType.scala:266)
at org.apache.spark.ml.feature.StringIndexerBase$class.validateAndTransformSchema(StringIndexer.scala:85)
at org.apache.spark.ml.feature.StringIndexer.validateAndTransformSchema(StringIndexer.scala:109)
at org.apache.spark.ml.feature.StringIndexer.transformSchema(StringIndexer.scala:152)
at org.apache.spark.ml.Pipeline$$anonfun$transformSchema$4.apply(Pipeline.scala:184)
at org.apache.spark.ml.Pipeline$$anonfun$transformSchema$4.apply(Pipeline.scala:184)
at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57)
at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66)
at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:186)
at org.apache.spark.ml.Pipeline.transformSchema(Pipeline.scala:184)
at org.apache.spark.ml.PipelineStage.transformSchema(Pipeline.scala:74)
at org.apache.spark.ml.Pipeline.fit(Pipeline.scala:136)
at com.spark_batch_sample.examples.NetworkAnomalyDetection$RunClustering.kmeansOneHotEncoder(NetworkAnomalyDetection.scala:407)