D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 12 Projects 2 Releases 2 Wiki Activity

[ENRICHMENT][BETA] Use of community API in enrichment process AND addition to tagging result for communities through projects #359

Merged
claudio.atzori merged 22 commits from propagationapi into beta 2023-11-30 14:20:34 +01:00
Conversation 0 Commits 22 Files Changed 103 +9 -6
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit a5a89a702f - Show all commits

15
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml
View File

@ -90,14 +90,16 @@
<class>eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet</class> <class>eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar> <jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts> <spark-opts>
--executor-cores=4 --executor-cores=6
--executor-memory=10G --executor-memory=5G
--spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg> <arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
@ -117,14 +119,15 @@
<class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class> <class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar> <jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts> <spark-opts>
--executor-cores=${sparkExecutorCores} --executor-cores=6
--executor-memory=${sparkExecutorMemory} --executor-memory=5G
--spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts> </spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg> <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>