Merge pull request '[beta] OpenAIRE Affiliation Inference' (#452) from affRoFromRawString into beta

Reviewed-on: #452
This commit is contained in:
Claudio Atzori 2024-07-17 10:24:39 +02:00
commit c99f92efaa
7 changed files with 39 additions and 13 deletions

View File

@ -42,6 +42,9 @@ public class Constants {
public static final String NULL = "NULL"; public static final String NULL = "NULL";
public static final String NA = "N/A"; public static final String NA = "N/A";
public static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b";
public static final String WEB_CRAWL_NAME = "Web Crawl";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private Constants() { private Constants() {

View File

@ -41,9 +41,9 @@ public class PrepareAffiliationRelations implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareAffiliationRelations.class); private static final Logger log = LoggerFactory.getLogger(PrepareAffiliationRelations.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String ID_PREFIX = "50|doi_________::"; private static final String ID_PREFIX = "50|doi_________::";
public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:bipinference"; public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:openaireinference";
public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by BIP!"; public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by OpenAIRE";
public static final String BIP_INFERENCE_PROVENANCE = "bip:affiliation:crossref"; public static final String BIP_INFERENCE_PROVENANCE = "openaire:affiliation";
public static <I extends Result> void main(String[] args) throws Exception { public static <I extends Result> void main(String[] args) throws Exception {
@ -71,6 +71,9 @@ public class PrepareAffiliationRelations implements Serializable {
final String dataciteInputPath = parser.get("dataciteInputPath"); final String dataciteInputPath = parser.get("dataciteInputPath");
log.info("dataciteInputPath: {}", dataciteInputPath); log.info("dataciteInputPath: {}", dataciteInputPath);
final String webcrawlInputPath = parser.get("webCrawlInputPath");
log.info("webcrawlInputPath: {}", webcrawlInputPath);
final String outputPath = parser.get("outputPath"); final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath); log.info("outputPath: {}", outputPath);
@ -102,10 +105,16 @@ public class PrepareAffiliationRelations implements Serializable {
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations( JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
spark, dataciteInputPath, collectedFromDatacite); spark, dataciteInputPath, collectedFromDatacite);
List<KeyValue> collectedFromWebCrawl = OafMapperUtils
.listKeyValues(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME);
JavaPairRDD<Text, Text> webCrawlRelations = prepareAffiliationRelations(
spark, webcrawlInputPath, collectedFromWebCrawl);
crossrefRelations crossrefRelations
.union(pubmedRelations) .union(pubmedRelations)
.union(openAPCRelations) .union(openAPCRelations)
.union(dataciteRelations) .union(dataciteRelations)
.union(webCrawlRelations)
.saveAsHadoopFile( .saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class); outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);

View File

@ -21,6 +21,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.Constants;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction; import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelConstants;
@ -29,6 +30,7 @@ import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils; import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner; import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
import eu.dnetlib.dhp.schema.oaf.utils.PidType; import eu.dnetlib.dhp.schema.oaf.utils.PidType;
import io.netty.util.Constant;
import scala.Tuple2; import scala.Tuple2;
/** /**
@ -44,8 +46,7 @@ public class CreateActionSetFromWebEntries implements Serializable {
private static final String PMID_PREFIX = "50|pmid________::"; private static final String PMID_PREFIX = "50|pmid________::";
private static final String PMCID_PREFIX = "50|pmc_________::"; private static final String PMCID_PREFIX = "50|pmc_________::";
private static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b";
private static final String WEB_CRAWL_NAME = "Web Crawl";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(String[] args) throws Exception { public static void main(String[] args) throws Exception {
@ -214,7 +215,7 @@ public class CreateActionSetFromWebEntries implements Serializable {
ModelConstants.IS_AUTHOR_INSTITUTION_OF, ModelConstants.IS_AUTHOR_INSTITUTION_OF,
Arrays Arrays
.asList( .asList(
OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)), OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)),
OafMapperUtils OafMapperUtils
.dataInfo( .dataInfo(
false, null, false, false, false, null, false, false,
@ -233,7 +234,7 @@ public class CreateActionSetFromWebEntries implements Serializable {
ModelConstants.HAS_AUTHOR_INSTITUTION, ModelConstants.HAS_AUTHOR_INSTITUTION,
Arrays Arrays
.asList( .asList(
OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)), OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)),
OafMapperUtils OafMapperUtils
.dataInfo( .dataInfo(
false, null, false, false, false, null, false, false,

View File

@ -28,7 +28,13 @@
"paramLongName": "dataciteInputPath", "paramLongName": "dataciteInputPath",
"paramDescription": "the path to get the input data from Datacite", "paramDescription": "the path to get the input data from Datacite",
"paramRequired": true "paramRequired": true
}, },{
"paramName": "wip",
"paramLongName": "webCrawlInputPath",
"paramDescription": "the path to get the input data from Web Crawl",
"paramRequired": true
}
,
{ {
"paramName": "o", "paramName": "o",
"paramLongName": "outputPath", "paramLongName": "outputPath",

View File

@ -17,6 +17,10 @@
<name>dataciteInputPath</name> <name>dataciteInputPath</name>
<description>the path where to find the inferred affiliation relations from Datacite</description> <description>the path where to find the inferred affiliation relations from Datacite</description>
</property> </property>
<property>
<name>webCrawlInputPath</name>
<description>the path where to find the inferred affiliation relations from webCrawl</description>
</property>
<property> <property>
<name>outputPath</name> <name>outputPath</name>
<description>the path where to store the actionset</description> <description>the path where to store the actionset</description>
@ -112,7 +116,7 @@
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg> <arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg> <arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
<arg>--dataciteInputPath</arg><arg>${dataciteInputPath}</arg> <arg>--dataciteInputPath</arg><arg>${dataciteInputPath}</arg>
<arg>--webCrawlInputPath</arg><arg>${webCrawlInputPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg> <arg>--outputPath</arg><arg>${outputPath}</arg>
</spark> </spark>
<ok to="End"/> <ok to="End"/>

View File

@ -88,6 +88,7 @@ public class PrepareAffiliationRelationsTest {
"-pubmedInputPath", crossrefAffiliationRelationPath, "-pubmedInputPath", crossrefAffiliationRelationPath,
"-openapcInputPath", crossrefAffiliationRelationPath, "-openapcInputPath", crossrefAffiliationRelationPath,
"-dataciteInputPath", crossrefAffiliationRelationPath, "-dataciteInputPath", crossrefAffiliationRelationPath,
"-webCrawlInputPath", crossrefAffiliationRelationPath,
"-outputPath", outputPath "-outputPath", outputPath
}); });
@ -104,7 +105,7 @@ public class PrepareAffiliationRelationsTest {
// ); // );
// } // }
// count the number of relations // count the number of relations
assertEquals(80, tmp.count()); assertEquals(120, tmp.count());
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class)); Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
dataset.createOrReplaceTempView("result"); dataset.createOrReplaceTempView("result");
@ -115,7 +116,7 @@ public class PrepareAffiliationRelationsTest {
// verify that we have equal number of bi-directional relations // verify that we have equal number of bi-directional relations
Assertions Assertions
.assertEquals( .assertEquals(
40, execVerification 60, execVerification
.filter( .filter(
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'") "relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
.collectAsList() .collectAsList()
@ -123,7 +124,7 @@ public class PrepareAffiliationRelationsTest {
Assertions Assertions
.assertEquals( .assertEquals(
40, execVerification 60, execVerification
.filter( .filter(
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'") "relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
.collectAsList() .collectAsList()

View File

@ -5,3 +5,5 @@
{"DOI":"10.1061\/(asce)0733-9372(2002)128:7(575)","Matchings":[{"RORid":"https:\/\/ror.org\/04j198w64","Confidence":0.82}]} {"DOI":"10.1061\/(asce)0733-9372(2002)128:7(575)","Matchings":[{"RORid":"https:\/\/ror.org\/04j198w64","Confidence":0.82}]}
{"DOI":"10.1061\/(asce)0733-9372(2002)128:7(588)","Matchings":[{"RORid":"https:\/\/ror.org\/03m8km719","Confidence":0.8660254038},{"RORid":"https:\/\/ror.org\/02aze4h65","Confidence":0.87}]} {"DOI":"10.1061\/(asce)0733-9372(2002)128:7(588)","Matchings":[{"RORid":"https:\/\/ror.org\/03m8km719","Confidence":0.8660254038},{"RORid":"https:\/\/ror.org\/02aze4h65","Confidence":0.87}]}
{"DOI":"10.1161\/hy0202.103001","Matchings":[{"RORid":"https:\/\/ror.org\/057xtrt18","Confidence":0.7071067812}]} {"DOI":"10.1161\/hy0202.103001","Matchings":[{"RORid":"https:\/\/ror.org\/057xtrt18","Confidence":0.7071067812}]}
{"DOI": "10.1080/13669877.2015.1042504", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/03265fv13"}]}
{"DOI": "10.1007/3-540-47984-8_14", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/00a0n9e72"}]}