${resume eq "rankings-start"} ${resume eq "impulse"} ${resume eq "rankings-iterative"} ${resume eq "format-results"} ${resume eq "map-ids"} ${resume eq "map-scores"} ${resume eq "start"} ${resume eq "projects-impact"}

${jobTracker}

${nameNode}

yarn-cluster cluster Openaire Ranking Graph Creation create_openaire_ranking_graph.py

--executor-memory 20G --executor-cores 4 --driver-memory 20G --master yarn --deploy-mode cluster --conf spark.sql.shuffle.partitions=7680 --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}

${openaireDataInput} ${currentYear} 7680 ${openaireGraphInputPath} ${wfAppPath}/create_openaire_ranking_graph.py#create_openaire_ranking_graph.py

${jobTracker}

${nameNode}

yarn-cluster cluster Spark CC CC.py

--executor-memory 18G --executor-cores 4 --driver-memory 10G --master yarn --deploy-mode cluster --conf spark.sql.shuffle.partitions=7680 --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}

${openaireGraphInputPath} 7680 ${wfAppPath}/CC.py#CC.py

${jobTracker}

${nameNode}

yarn-cluster cluster Spark RAM TAR.py

${openaireGraphInputPath} ${ramGamma} ${currentYear} RAM 7680 ${checkpointDir} ${wfAppPath}/TAR.py#TAR.py

${jobTracker}

${nameNode}

yarn-cluster cluster Spark Impulse CC.py

${openaireGraphInputPath} 7680 3 ${wfAppPath}/CC.py#CC.py

${jobTracker}

${nameNode}

yarn-cluster cluster Spark Pagerank PageRank.py

${openaireGraphInputPath} ${pageRankAlpha} ${convergenceError} ${checkpointDir} 7680 dfs ${wfAppPath}/PageRank.py#PageRank.py

${jobTracker}

${nameNode}

yarn-cluster cluster Spark AttRank AttRank.py

${openaireGraphInputPath} ${attrankAlpha} ${attrankBeta} ${attrankGamma} ${attrankRho} ${currentYear} ${attrankStartYear} ${convergenceError} ${checkpointDir} 7680 dfs ${wfAppPath}/AttRank.py#AttRank.py

${jobTracker}

${nameNode}

/usr/bin/bash get_ranking_files.sh /${workflowDataDir} ${wfAppPath}/get_ranking_files.sh#get_ranking_files.sh

${jobTracker}

${nameNode}

yarn-cluster cluster Format Ranking Results JSON format_ranking_results.py

--executor-memory 10G --executor-cores 4 --driver-memory 10G --master yarn --deploy-mode cluster --conf spark.sql.shuffle.partitions=7680 --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}

json-5-way ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['pr_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['attrank_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['cc_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['impulse_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['ram_file']} 7680 openaire ${wfAppPath}/format_ranking_results.py#format_ranking_results.py

${jobTracker}

${nameNode}

yarn-cluster cluster Format Ranking Results BiP! DB format_ranking_results.py

zenodo ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['pr_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['attrank_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['cc_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['impulse_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['ram_file']} 7680 openaire ${wfAppPath}/format_ranking_results.py#format_ranking_results.py

${jobTracker}

${nameNode}

yarn-cluster cluster Openaire-DOI synonym collection map_openaire_ids_to_dois.py

--executor-memory 18G --executor-cores 4 --driver-memory 15G --master yarn --deploy-mode cluster --conf spark.sql.shuffle.partitions=7680 --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}

${openaireDataInput} ${synonymFolder} ${wfAppPath}/map_openaire_ids_to_dois.py#map_openaire_ids_to_dois.py

${jobTracker}

${nameNode}

yarn-cluster cluster Mapping Openaire Scores to DOIs map_scores_to_dois.py

${synonymFolder} 7680 ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['pr_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['attrank_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['cc_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['impulse_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['ram_file']} ${wfAppPath}/map_scores_to_dois.py#map_scores_to_dois.py yarn cluster Produces the atomic action with the bip finder scores for publications eu.dnetlib.dhp.actionmanager.bipfinder.SparkAtomicActionScoreJob dhp-aggregation-${projectVersion}.jar

--executor-memory=${sparkExecutorMemory} --executor-cores=${sparkExecutorCores} --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}

--inputPath${bipScorePath} --outputPath${actionSetOutputPath}/results/ --targetEntityresult

${jobTracker}

${nameNode}

yarn-cluster cluster Project Impact Indicators projects_impact.py

${openaireDataInput}/relations ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['pr_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['attrank_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['cc_file']} ${nameNode}/${workflowDataDir}/${wf:actionData('get-file-names')['impulse_file']} 7680 ${projectImpactIndicatorsOutput} ${wfAppPath}/projects_impact.py#projects_impact.py yarn cluster Produces the atomic action with the bip finder scores for projects eu.dnetlib.dhp.actionmanager.bipfinder.SparkAtomicActionScoreJob dhp-aggregation-${projectVersion}.jar

--inputPath${projectImpactIndicatorsOutput} --outputPath${actionSetOutputPath}/projects/ --targetEntityproject PageRank failed, error message[${wf:errorMessage(wf:lastErrorNode())}] AttRank failed, error message[${wf:errorMessage(wf:lastErrorNode())}] CC failed, error message[${wf:errorMessage(wf:lastErrorNode())}] Impulse failed, error message[${wf:errorMessage(wf:lastErrorNode())}] RAM failed, error message[${wf:errorMessage(wf:lastErrorNode())}] Creation of openaire-graph failed, error message[${wf:errorMessage(wf:lastErrorNode())}] Synonym collection failed, error message[${wf:errorMessage(wf:lastErrorNode())}] Mapping scores to DOIs failed, error message[${wf:errorMessage(wf:lastErrorNode())}] Deleting output path for actionsets failed, error message[${wf:errorMessage(wf:lastErrorNode())}] ActionSet creation for results failed, error message[${wf:errorMessage(wf:lastErrorNode())}] Calculating project impact indicators failed, error message[${wf:errorMessage(wf:lastErrorNode())}] ActionSet creation for projects failed, error message[${wf:errorMessage(wf:lastErrorNode())}]