D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

8172_impact_indicators_workflow #284

Merged
miriam.baglioni merged 49 commits from 8172_impact_indicators_workflow into beta 2023-08-14 15:50:48 +02:00
Conversation 7 Commits 49 Files Changed 23 +21 -117
1 changed files with 21 additions and 117 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 12a57e1f58 - Show all commits

138
dhp-workflows/dhp-impact-indicators/src/main/resources/eu/dnetlib/dhp/oa/graph/impact_indicators/oozie_app/workflow.xml
View File

@ -46,7 +46,7 @@
<!-- Script name goes here -->
<jar>create_openaire_ranking_graph.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -57,16 +57,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkHighDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<!-- The openaire graph data from which to read relations and objects -->
<arg>${openaireDataInput}</arg>
@ -113,7 +104,7 @@
<!-- Script name goes here -->
<jar>CC.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -124,16 +115,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${openaireGraphInputPath}</arg>
<!-- number of partitions to be used on joins -->
@ -167,7 +149,7 @@
<!-- Script name goes here -->
<jar>TAR.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -178,16 +160,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${openaireGraphInputPath}</arg>
<arg>${ramGamma}</arg>
@ -228,7 +201,7 @@
<!-- Script name goes here -->
<jar>CC.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -239,16 +212,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${openaireGraphInputPath}</arg>
<!-- number of partitions to be used on joins -->
@ -296,7 +260,7 @@
<!-- Script name goes here -->
<jar>PageRank.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -307,16 +271,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${openaireGraphInputPath}</arg>
<arg>${pageRankAlpha}</arg>
@ -354,7 +309,7 @@
<!-- Script name goes here -->
<jar>AttRank.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -365,16 +320,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${openaireGraphInputPath}</arg>
<arg>${attrankAlpha}</arg>
@ -459,7 +405,7 @@
<!-- Script name goes here -->
<jar>format_ranking_results.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkNormalExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -470,16 +416,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkNormalExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>json-5-way</arg>
<!-- Input files must be identified dynamically -->
@ -520,7 +457,7 @@
<!-- Script name goes here -->
<jar>format_ranking_results.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkNormalExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -531,16 +468,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkNormalExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>zenodo</arg>
<!-- Input files must be identified dynamically -->
@ -588,7 +516,7 @@
<!-- Script name goes here -->
<jar>map_openaire_ids_to_dois.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -599,16 +527,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkHighDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${openaireDataInput}</arg>
<!-- number of partitions to be used on joins -->
@ -643,7 +562,7 @@
<!-- Script name goes here -->
<jar>map_scores_to_dois.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -654,16 +573,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkHighDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}</spark-opts>
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
<!-- Script arguments here -->
<arg>${synonymFolder}</arg>
<!-- Number of partitions -->
@ -739,18 +649,12 @@
<!-- Script name goes here -->
<jar>projects_impact.py</jar>
<!-- spark configuration options: I've taken most of them from an example from dhp workflows / Master value stolen from sandro -->
<<<<<<< HEAD
<spark-opts>
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
=======
<spark-opts>--executor-memory ${sparkHighExecutorMemory} --executor-cores ${sparkExecutorCores} --driver-memory ${sparkNormalDriverMemory}
--master yarn
--deploy-mode cluster
--conf spark.sql.shuffle.partitions=7680
>>>>>>> 4a905932a3db36c61570c24b9aa54283cd30abba
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}