dimitris.pierrakos
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

Merge branch 'beta' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta

This commit is contained in:
Alessia Bardi 2022-06-10 17:29:15 +02:00
parent 68bd58d6a4 b229c6e7af
commit 922c6d66ef
9 changed files with 111 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkEoscTag.java
View File

@ -95,13 +95,14 @@ public class SparkEoscTag {
if (containsCriteriaNotebook(s)) { if (containsCriteriaNotebook(s)) {
sbject.add(EOSC_NOTEBOOK); sbject.add(EOSC_NOTEBOOK);
if (sbject.stream().anyMatch(sb -> sb.getValue().equals("EOSC Jupyter Notebook"))){ if (sbject.stream().anyMatch(sb -> sb.getValue().equals("EOSC Jupyter Notebook"))) {
sbject = sbject.stream().map(sb -> { sbject = sbject.stream().map(sb -> {
if (sb.getValue().equals("EOSC Jupyter Notebook")){ if (sb.getValue().equals("EOSC Jupyter Notebook")) {
return null; return null;
} }
return sb; return sb;
}).filter(Objects::nonNull).collect(Collectors.toList()); }).filter(Objects::nonNull).collect(Collectors.toList());
s.setSubject(sbject);
} }
} }
if (containsCriteriaGalaxy(s)) { if (containsCriteriaGalaxy(s)) {

19
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java
View File

@ -102,21 +102,28 @@ public class SparkCountryPropagationJob {
private static <R extends Result> MapFunction<Tuple2<R, ResultCountrySet>, R> getCountryMergeFn() { private static <R extends Result> MapFunction<Tuple2<R, ResultCountrySet>, R> getCountryMergeFn() {
return t -> { return t -> {
Optional.ofNullable(t._2()).ifPresent(r -> { Optional.ofNullable(t._2()).ifPresent(r -> {
t._1().getCountry().addAll(merge(t._1().getCountry(), r.getCountrySet())); if (Optional.ofNullable(t._1().getCountry()).isPresent())
t._1().getCountry().addAll(merge(t._1().getCountry(), r.getCountrySet()));
else
t._1().setCountry(merge(null, t._2().getCountrySet()));
}); });
return t._1(); return t._1();
}; };
} }
private static List<Country> merge(List<Country> c1, List<CountrySbs> c2) { private static List<Country> merge(List<Country> c1, List<CountrySbs> c2) {
HashSet<String> countries = c1 HashSet<String> countries = new HashSet<>();
.stream() if (Optional.ofNullable(c1).isPresent()) {
.map(Qualifier::getClassid) countries = c1
.collect(Collectors.toCollection(HashSet::new)); .stream()
.map(Qualifier::getClassid)
.collect(Collectors.toCollection(HashSet::new));
}
HashSet<String> finalCountries = countries;
return c2 return c2
.stream() .stream()
.filter(c -> !countries.contains(c.getClassid())) .filter(c -> !finalCountries.contains(c.getClassid()))
.map(c -> getCountry(c.getClassid(), c.getClassname())) .map(c -> getCountry(c.getClassid(), c.getClassname()))
.collect(Collectors.toList()); .collect(Collectors.toList());
} }

21
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/bulktag/EOSCTagJobTest.java
View File

@ -132,7 +132,7 @@ public class EOSCTagJobTest {
Assertions Assertions
.assertEquals( .assertEquals(
2, tmp 1, tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4")) .filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect() .collect()
.get(0) .get(0)
@ -326,7 +326,7 @@ public class EOSCTagJobTest {
Assertions Assertions
.assertEquals( .assertEquals(
2, 1,
tmp tmp
.filter( .filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow"))) s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow")))
@ -352,21 +352,12 @@ public class EOSCTagJobTest {
Assertions Assertions
.assertEquals( .assertEquals(
6, tmp 5, tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11")) .filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect() .collect()
.get(0) .get(0)
.getSubject() .getSubject()
.size()); .size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions Assertions
.assertEquals( .assertEquals(
@ -394,7 +385,7 @@ public class EOSCTagJobTest {
Assertions Assertions
.assertEquals( .assertEquals(
2, 1,
orp orp
.filter( .filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow"))) s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow")))
@ -438,14 +429,14 @@ public class EOSCTagJobTest {
Assertions Assertions
.assertEquals( .assertEquals(
3, orp 2, orp
.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72")) .filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72"))
.collect() .collect()
.get(0) .get(0)
.getSubject() .getSubject()
.size()); .size());
Assertions Assertions
.assertTrue( .assertFalse(
orp orp
.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72")) .filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72"))
.collect() .collect()

2
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/jupyter/software/software_10.json
View File

File diff suppressed because one or more lines are too long

32
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql
View File

@ -80,4 +80,34 @@ where reltype='resultResult'
and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE
and r1.resulttype.classname != 'other' and r1.resulttype.classname != 'other'
and r2.resulttype.classname != 'other' and r2.resulttype.classname != 'other'
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE; and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE;
create table ${stats_db_name}.result_citations_oc stored as parquet as
select substr(target, 4) as id, count(distinct substr(source, 4)) as citations
from ${openaire_db_name}.relation rel
join ${openaire_db_name}.result r1 on rel.source=r1.id
join ${openaire_db_name}.result r2 on r2.id=rel.target
where relClass='Cites' and rel.datainfo.provenanceaction.classid = 'sysimport:crosswalk:opencitations'
and reltype='resultResult'
and r1.resulttype.classname!=r2.resulttype.classname
and r1.datainfo.deletedbyinference=false and r1.datainfo.invisible = FALSE
and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE
and r1.resulttype.classname != 'other'
and r2.resulttype.classname != 'other'
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE
group by substr(target, 4);
create table ${stats_db_name}.result_references_oc stored as parquet as
select substr(source, 4) as id, count(distinct substr(target, 4)) as references
from ${openaire_db_name}.relation rel
join ${openaire_db_name}.result r1 on rel.source=r1.id
join ${openaire_db_name}.result r2 on r2.id=rel.target
where relClass='Cites' and rel.datainfo.provenanceaction.classid = 'sysimport:crosswalk:opencitations'
and reltype='resultResult'
and r1.resulttype.classname!=r2.resulttype.classname
and r1.datainfo.deletedbyinference=false and r1.datainfo.invisible = FALSE
and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE
and r1.resulttype.classname != 'other'
and r2.resulttype.classname != 'other'
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE
group by substr(source, 4);

48
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql
View File

@ -82,31 +82,31 @@ on r.id= tmp.id;
compute stats indi_funded_result_with_fundref; compute stats indi_funded_result_with_fundref;
create table indi_result_org_country_collab stored as parquet as -- create table indi_result_org_country_collab stored as parquet as
with tmp as -- with tmp as
(select o.id as id, o.country , ro.id as result,r.type from organization o -- (select o.id as id, o.country , ro.id as result,r.type from organization o
join result_organization ro on o.id=ro.organization -- join result_organization ro on o.id=ro.organization
join result r on r.id=ro.id where o.country <> 'UNKNOWN') -- join result r on r.id=ro.id where o.country <> 'UNKNOWN')
select o1.id org1,o2.country country2, o1.type, count(distinct o1.result) as collaborations -- select o1.id org1,o2.country country2, o1.type, count(distinct o1.result) as collaborations
from tmp as o1 -- from tmp as o1
join tmp as o2 on o1.result=o2.result -- join tmp as o2 on o1.result=o2.result
where o1.id<>o2.id and o1.country<>o2.country -- where o1.id<>o2.id and o1.country<>o2.country
group by o1.id, o1.type,o2.country; -- group by o1.id, o1.type,o2.country;
--
-- compute stats indi_result_org_country_collab;
compute stats indi_result_org_country_collab; -- create table indi_result_org_collab stored as parquet as
-- with tmp as
create table indi_result_org_collab stored as parquet as -- (select o.id, ro.id as result,r.type from organization o
with tmp as -- join result_organization ro on o.id=ro.organization
(select o.id, ro.id as result,r.type from organization o -- join result r on r.id=ro.id)
join result_organization ro on o.id=ro.organization -- select o1.id org1,o2.id org2, o1.type, count(distinct o1.result) as collaborations
join result r on r.id=ro.id) -- from tmp as o1
select o1.id org1,o2.id org2, o1.type, count(distinct o1.result) as collaborations -- join tmp as o2 on o1.result=o2.result
from tmp as o1 -- where o1.id<>o2.id
join tmp as o2 on o1.result=o2.result -- group by o1.id, o2.id, o1.type;
where o1.id<>o2.id --
group by o1.id, o2.id, o1.type; -- compute stats indi_result_org_collab;
compute stats indi_result_org_collab;
create table indi_funder_country_collab stored as parquet as create table indi_funder_country_collab stored as parquet as
with tmp as (select funder, project, country from organization_projects op with tmp as (select funder, project, country from organization_projects op

50
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql
View File

@ -18,28 +18,45 @@ create table TARGET.result stored as parquet as
select * from SOURCE.result r where exists (select 1 from SOURCE.result_concepts rc where rc.id=r.id) select * from SOURCE.result r where exists (select 1 from SOURCE.result_concepts rc where rc.id=r.id)
union all union all
select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in ( select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in (
'openorgs____::759d59f05d77188faee99b7493b46805', 'openorgs____::b84450f9864182c67b8611b5593f4250', --"Athena Research and Innovation Center In Information Communication & Knowledge Technologies', --ARC"
'openorgs____::b84450f9864182c67b8611b5593f4250', 'openorgs____::d41cf6bd4ab1b1362a44397e0b95c975', --National Research Council
'openorgs____::d41cf6bd4ab1b1362a44397e0b95c975', 'openorgs____::d2a09b9d5eabb10c95f9470e172d05d2', --??? Not exists ??
'openorgs____::eadc8da90a546e98c03f896661a2e4d4', 'openorgs____::d169c7407dd417152596908d48c11460', --Masaryk University
'openorgs____::d2a09b9d5eabb10c95f9470e172d05d2', 'openorgs____::1ec924b1759bb16d0a02f2dad8689b21', --University of Belgrade
'openorgs____::d169c7407dd417152596908d48c11460', 'openorgs____::2fb1e47b4612688d9de9169d579939a7', --University of Helsinki
'openorgs____::1ec924b1759bb16d0a02f2dad8689b21', 'openorgs____::759d59f05d77188faee99b7493b46805', --University of Minho
'openorgs____::2fb1e47b4612688d9de9169d579939a7', 'openorgs____::cad284878801b9465fa51a95b1d779db', --Universidad Politécnica de Madrid
'openorgs____::759d59f05d77188faee99b7493b46805', 'openorgs____::eadc8da90a546e98c03f896661a2e4d4', --University of Göttingen
'openorgs____::cad284878801b9465fa51a95b1d779db', 'openorgs____::c0286313e36479eff8676dba9b724b40', --National and Kapodistrian University of Athens
'openorgs____::eadc8da90a546e98c03f896661a2e4d4', -- 'openorgs____::c80a8243a5e5c620d7931c88d93bf17a', --Université Paris Diderot
'openorgs____::c0286313e36479eff8676dba9b724b40' 'openorgs____::c08634f0a6b0081c3dc6e6c93a4314f3', --Bielefeld University
-- ,'openorgs____::c80a8243a5e5c620d7931c88d93bf17a' -- Paris Diderot 'openorgs____::6fc85e4a8f7ecaf4b0c738d010e967ea', --University of Southern Denmark
) )) foo; 'openorgs____::3d6122f87f9a97a99d8f6e3d73313720', --Humboldt-Universität zu Berlin
'openorgs____::16720ada63d0fa8ca41601feae7d1aa5', --TU Darmstadt
'openorgs____::ccc0a066b56d2cfaf90c2ae369df16f5', --KU Leuven
'openorgs____::4c6f119632adf789746f0a057ed73e90', --University of the Western Cape
'openorgs____::ec3665affa01aeafa28b7852c4176dbd', --Rudjer Boskovic Institute
'openorgs____::5f31346d444a7f06a28c880fb170b0f6', --Ghent University
'openorgs____::2dbe47117fd5409f9c61620813456632', --University of Luxembourg
'openorgs____::6445d7758d3a40c4d997953b6632a368' --National Institute of Informatics (NII)
) )) foo;
compute stats TARGET.result; compute stats TARGET.result;
create table TARGET.result_citations stored as parquet as select * from SOURCE.result_citations orig where exists (select 1 from TARGET.result r where r.id=orig.id); create table TARGET.result_citations stored as parquet as select * from SOURCE.result_citations orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_citations; compute stats TARGET.result_citations;
create table TARGET.result_references_oc stored as parquet as select * from SOURCE.result_references_oc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_references_oc;
create table TARGET.result_citations_oc stored as parquet as select * from SOURCE.result_citations_oc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_citations_oc;
create table TARGET.result_classifications stored as parquet as select * from SOURCE.result_classifications orig where exists (select 1 from TARGET.result r where r.id=orig.id); create table TARGET.result_classifications stored as parquet as select * from SOURCE.result_classifications orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_classifications; compute stats TARGET.result_classifications;
create table TARGET.result_apc stored as parquet as select * from SOURCE.result_apc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_apc;
create table TARGET.result_concepts stored as parquet as select * from SOURCE.result_concepts orig where exists (select 1 from TARGET.result r where r.id=orig.id); create table TARGET.result_concepts stored as parquet as select * from SOURCE.result_concepts orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_concepts; compute stats TARGET.result_concepts;
@ -90,11 +107,6 @@ compute stats TARGET.result_sources;
create table TARGET.result_topics stored as parquet as select * from SOURCE.result_topics orig where exists (select 1 from TARGET.result r where r.id=orig.id); create table TARGET.result_topics stored as parquet as select * from SOURCE.result_topics orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_topics; compute stats TARGET.result_topics;
create table TARGET.result_apc stored as parquet as select * from SOURCE.result_apc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_apc;
create view TARGET.foo1 as select * from SOURCE.result_result rr where rr.source in (select id from TARGET.result); create view TARGET.foo1 as select * from SOURCE.result_result rr where rr.source in (select id from TARGET.result);
create view TARGET.foo2 as select * from SOURCE.result_result rr where rr.target in (select id from TARGET.result); create view TARGET.foo2 as select * from SOURCE.result_result rr where rr.target in (select id from TARGET.result);
create table TARGET.result_result STORED AS PARQUET as select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou; create table TARGET.result_result STORED AS PARQUET as select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou;

1
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql
View File

@ -127,6 +127,7 @@ CREATE TABLE ${stats_db_name}.result_organization STORED AS PARQUET AS
SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization
FROM ${openaire_db_name}.relation r FROM ${openaire_db_name}.relation r
WHERE r.reltype = 'resultOrganization' WHERE r.reltype = 'resultOrganization'
and r.target like '50|%'
and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false; and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false;
CREATE TABLE ${stats_db_name}.result_projects STORED AS PARQUET AS CREATE TABLE ${stats_db_name}.result_projects STORED AS PARQUET AS

2
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql
View File

@ -93,7 +93,7 @@ where d.datainfo.deletedbyinference=false and d.datainfo.invisible=false;
CREATE TABLE ${stats_db_name}.datasource_organizations STORED AS PARQUET AS CREATE TABLE ${stats_db_name}.datasource_organizations STORED AS PARQUET AS
SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization
FROM ${openaire_db_name}.relation r FROM ${openaire_db_name}.relation r
WHERE r.reltype = 'datasourceOrganization' and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false; WHERE r.reltype = 'datasourceOrganization' and r.datainfo.deletedbyinference = false and r.target like '20|%' and r.datainfo.invisible=false;
-- datasource sources: -- datasource sources:
-- where the datasource info have been collected from. -- where the datasource info have been collected from.