1
0
Fork 0

[personEntity] removed the deletedbyinference results (not indexed, but still in the graph). Changed the writing mode: append instead of overwrite

This commit is contained in:
Miriam Baglioni 2024-10-24 09:57:20 +02:00
parent aac5eb3499
commit c921cf7ee0
8 changed files with 153 additions and 11 deletions

View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.actionmanager.personentity;
package eu.dnetlib.dhp.common.person;
import java.util.Arrays;
import java.util.Iterator;

View File

@ -1,12 +1,9 @@
package eu.dnetlib.dhp.actionmanager.personentity;
package eu.dnetlib.dhp.common.person;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;
import eu.dnetlib.dhp.schema.oaf.Relation;
public class Coauthors implements Serializable {
private List<String> coauthors;

View File

@ -13,6 +13,8 @@ import java.sql.SQLException;
import java.util.*;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.common.person.CoAuthorshipIterator;
import eu.dnetlib.dhp.common.person.Coauthors;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;

View File

@ -48,12 +48,7 @@
<groupId>io.github.classgraph</groupId>
<artifactId>classgraph</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-aggregation</artifactId>
<version>1.2.5-SNAPSHOT</version>
<scope>compile</scope>
</dependency>
</dependencies>

View File

@ -0,0 +1,21 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
}
]

View File

@ -0,0 +1 @@
sourcePath=/tmp/miriam/13_graph_copy

View File

@ -0,0 +1,58 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
</property>
<property>
<name>spark2EventLogDir</name>
<value>/user/spark/spark2ApplicationHistory</value>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
</property>
<property>
<name>sparkExecutorNumber</name>
<value>4</value>
</property>
<property>
<name>sparkDriverMemory</name>
<value>15G</value>
</property>
<property>
<name>sparkExecutorMemory</name>
<value>5G</value>
</property>
<property>
<name>sparkExecutorCores</name>
<value>4</value>
</property>
<property>
<name>spark2MaxExecutors</name>
<value>50</value>
</property>
</configuration>

View File

@ -0,0 +1,68 @@
<workflow-app name="person_propagation" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="reset_outputpath">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="extract_person_relation_from_graph"/>
<error to="Kill"/>
</action>
<action name="extract_person_relation_from_graph">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>personPropagation</name>
<class>eu.dnetlib.dhp.person.SparkExtractPersonRelations</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/relation</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>