andreas.czerniak
/
BrBETA_dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

mergin with branch beta

This commit is contained in:
Miriam Baglioni 2021-11-11 08:59:53 +01:00
parent df7ee77c7a 6477a40670
commit 6d3c4c4abe
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkConvertRDDtoDataset.scala
View File

@ -59,7 +59,12 @@ object SparkConvertRDDtoDataset {
log.info("Converting Relation") log.info("Converting Relation")
val rddRelation =spark.sparkContext.textFile(s"$sourcePath/relation").map(s => mapper.readValue(s, classOf[Relation])).filter(r=> r.getSource.startsWith("50") && r.getTarget.startsWith("50")) val relationSemanticFilter = List("cites", "iscitedby","merges", "ismergedin")
val rddRelation =spark.sparkContext.textFile(s"$sourcePath/relation")
.map(s => mapper.readValue(s, classOf[Relation]))
.filter(r=> r.getSource.startsWith("50") && r.getTarget.startsWith("50"))
.filter(r => !relationSemanticFilter.exists(k => k.equalsIgnoreCase(r.getRelClass)))
spark.createDataset(rddRelation).as[Relation].write.mode(SaveMode.Overwrite).save(s"$relPath") spark.createDataset(rddRelation).as[Relation].write.mode(SaveMode.Overwrite).save(s"$relPath")