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

[Enrichment Step] get rid of hive

This commit is contained in:
Miriam Baglioni 2022-04-13 17:46:22 +02:00
parent d205bf78d8
commit 7501e823ed
6 changed files with 168 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep0.java Normal file
View File

@ -0,0 +1,90 @@
package eu.dnetlib.dhp.orcidtoresultfromsemrel;
import static eu.dnetlib.dhp.PropagationConstant.*;
import static eu.dnetlib.dhp.PropagationConstant.readPath;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.gson.Gson;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import scala.Tuple2;
public class PrepareResultOrcidAssociationStep0 implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareResultOrcidAssociationStep0.class);
public static void main(String[] args) throws Exception {
String jsonConf = IOUtils
.toString(
PrepareResultOrcidAssociationStep0.class
.getResourceAsStream(
"/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult0_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConf);
parser.parseArgument(args);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final List<String> allowedsemrel = Arrays
.stream(parser.get("allowedsemrels").split(";"))
.map(s -> s.toLowerCase())
.collect(Collectors.toList());
log.info("allowedSemRel: {}", new Gson().toJson(allowedsemrel));
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
selectRelations(
spark, inputPath, outputPath, allowedsemrel);
});
}
private static void selectRelations(SparkSession spark, String inputPath, String outputPath,
List<String> allowedsemrel) {
readPath(spark, inputPath, Relation.class)
.filter(
(FilterFunction<Relation>) r -> !r.getDataInfo().getDeletedbyinference()
&& allowedsemrel.contains(r.getRelClass().toLowerCase()))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
}
}

21
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java
View File

@ -53,7 +53,7 @@ public class PrepareResultOrcidAssociationStep1 {
String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
final String outputPath = parser.get("workingPath");
log.info("outputPath: {}", outputPath);
final String resultClassName = parser.get("resultTableName");
@ -76,15 +76,6 @@ public class PrepareResultOrcidAssociationStep1 {
SparkConf conf = new SparkConf();
String inputRelationPath = inputPath + "/relation";
log.info("inputRelationPath: {}", inputRelationPath);
String inputResultPath = inputPath + "/" + resultType;
log.info("inputResultPath: {}", inputResultPath);
String outputResultPath = outputPath + "/" + resultType;
log.info("outputResultPath: {}", outputResultPath);
runWithSparkSession(
conf,
isSparkSessionManaged,
@ -112,12 +103,14 @@ public class PrepareResultOrcidAssociationStep1 {
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/relationSubset");
.json(outputPath + "/" + resultType + "/relationSubset");
Dataset<Relation> relation = readPath(spark, outputPath + "/relationSubset", Relation.class);
log.info("Reading Graph table from: {}", inputResultPath);
final String resultOutputPath = outputPath + "/resultSubset/" + resultType;
readPath(spark, inputResultPath, resultClazz)
.filter(
(FilterFunction<R>) r -> !r.getDataInfo().getDeletedbyinference() && !r.getDataInfo().getInvisible())
@ -135,11 +128,11 @@ public class PrepareResultOrcidAssociationStep1 {
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/resultSubset");
.json(resultOutputPath);
Dataset<R> result = readPath(spark, outputPath + "/resultSubset", resultClazz);
Dataset<R> result = readPath(spark, resultOutputPath, resultClazz);
result.foreach((ForeachFunction<R>) r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
// result.foreach((ForeachFunction<R>) r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
result
.joinWith(relation, result.col("id").equalTo(relation.col("source")))

2
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java
View File

@ -52,7 +52,7 @@ public class PrepareResultOrcidAssociationStep2 {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
// removeOutputDir(spark, outputPath);
mergeInfo(spark, inputPath, outputPath);
});
}

26
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult0_parameters.json Normal file
View File

@ -0,0 +1,26 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName":"as",
"paramLongName":"allowedsemrels",
"paramDescription": "the allowed sematinc relations for propagation",
"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
}
]

4
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json
View File

@ -18,8 +18,8 @@
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},

54
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml
View File

@ -14,7 +14,7 @@
</property>
</parameters>
<start to="reset_outputpath"/>
<start to="fork_prepare_assoc_step1"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@ -80,7 +80,37 @@
<error to="Kill"/>
</action>
<join name="copy_wait" to="fork_prepare_assoc_step1"/>
<join name="copy_wait" to="prepare_relations"/>
<action name="prepare_relations">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>ORCIDPropagation-PreparePhase0-SelectRELATIONS</name>
<class>eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep0</class>
<jar>dhp-enrichment-${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.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/relationSubset</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<fork name="fork_prepare_assoc_step1">
<path start="join_prepare_publication"/>
@ -113,7 +143,7 @@
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/preparedInfo/targetOrcidAssoc</arg>
<arg>--workingPath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--allowedpids</arg><arg>${allowedpids}</arg>
</spark>
@ -141,7 +171,7 @@
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/preparedInfo/targetOrcidAssoc</arg>
<arg>--workingPath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--allowedpids</arg><arg>${allowedpids}</arg>
</spark>
@ -169,7 +199,7 @@
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/preparedInfo/targetOrcidAssoc</arg>
<arg>--workingPath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--allowedpids</arg><arg>${allowedpids}</arg>
</spark>
@ -197,7 +227,7 @@
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/preparedInfo/targetOrcidAssoc</arg>
<arg>--workingPath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--allowedpids</arg><arg>${allowedpids}</arg>
</spark>
@ -225,8 +255,8 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/orcidprop/preparedInfo/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/preparedInfo/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop//mergedOrcidAssoc</arg>
</spark>
<ok to="fork-join-exec-propagation"/>
<error to="Kill"/>
@ -261,7 +291,7 @@
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
@ -291,7 +321,7 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
@ -321,7 +351,7 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
@ -351,7 +381,7 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>