diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql index 2808d0a3a..9db5d3240 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql @@ -27,6 +27,23 @@ select * from stats_ext.rndexpediture; create view ${stats_db_name}.issn_gold_oa_dataset as select * from stats_ext.issn_gold_oa_dataset; +------------------------------------------------------------------------------------------------ +------------------------------------------------------------------------------------------------ +-- Usage statistics +------------------------------------------------------------------------------------------------ +------------------------------------------------------------------------------------------------ +create or replace view ${stats_db_name}.usage_stats as +select * from openaire_prod_usage_stats.usage_stats; + +create or replace view ${stats_db_name}.downloads_stats as +select * from openaire_prod_usage_stats.downloads_stats; + +create or replace view ${stats_db_name}.pageviews_stats as +select * from openaire_prod_usage_stats.pageviews_stats; + +create or replace view ${stats_db_name}.views_stats as +select * from openaire_prod_usage_stats.views_stats; + ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ -- Creation date of the database @@ -36,4 +53,4 @@ create table ${stats_db_name}.creation_date as select date_format(current_date(), 'dd-MM-yyyy') as date; -- -- ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS; --- ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS FOR COLUMNS; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql index 6e63e2836..a5839da11 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql @@ -14,7 +14,7 @@ LEFT OUTER JOIN ( SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference=false) d on p.datasource = d.id; + WHERE d.datainfo.deletedbyinference=false and d.datainfo.invisible = FALSE) d on p.datasource = d.id; CREATE TABLE IF NOT EXISTS ${stats_db_name}.dataset_sources STORED AS PARQUET as SELECT p.id, case when d.id is null then 'other' else p.datasource end as datasource @@ -25,7 +25,7 @@ LEFT OUTER JOIN ( SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference=false) d on p.datasource = d.id; + WHERE d.datainfo.deletedbyinference=false and d.datainfo.invisible = FALSE) d on p.datasource = d.id; CREATE TABLE IF NOT EXISTS ${stats_db_name}.software_sources STORED AS PARQUET as SELECT p.id, case when d.id is null then 'other' else p.datasource end as datasource @@ -36,7 +36,7 @@ LEFT OUTER JOIN ( SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference=false) d on p.datasource = d.id; + WHERE d.datainfo.deletedbyinference=false and d.datainfo.invisible = FALSE) d on p.datasource = d.id; CREATE TABLE IF NOT EXISTS ${stats_db_name}.otherresearchproduct_sources STORED AS PARQUET as SELECT p.id, case when d.id is null then 'other' else p.datasource end as datasource @@ -47,7 +47,7 @@ LEFT OUTER JOIN ( SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference=false) d on p.datasource = d.id; + WHERE d.datainfo.deletedbyinference=false and d.datainfo.invisible = FALSE) d on p.datasource = d.id; CREATE VIEW IF NOT EXISTS ${stats_db_name}.result_sources AS SELECT * FROM ${stats_db_name}.publication_sources @@ -67,4 +67,17 @@ from ( LATERAL VIEW explode(author) a as auth LATERAL VIEW explode(auth.pid) ap as auth_pid LATERAL VIEW explode(auth.pid.qualifier.classid) apt as author_pid_type - WHERE res.datainfo.deletedbyinference = FALSE and res.datainfo.invisible = FALSE and author_pid_type = 'orcid') as res \ No newline at end of file + WHERE res.datainfo.deletedbyinference = FALSE and res.datainfo.invisible = FALSE and author_pid_type = 'orcid') as res; + +create table ${stats_db_name}.result_result stored as parquet as +select substr(rel.source, 4) as source, substr(rel.target, 4) as target, relclass, subreltype +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 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; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql index e9c2e014c..c81ae5a6f 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql @@ -8,22 +8,22 @@ CREATE TABLE IF NOT EXISTS ${stats_db_name}.publication_licenses STORED AS PARQUET AS SELECT substr(p.id, 4) as id, licenses.value as type from ${openaire_db_name}.publication p LATERAL VIEW explode(p.instance.license) instances as licenses -where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false; +where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false and p.datainfo.invisible = FALSE; CREATE TABLE IF NOT EXISTS ${stats_db_name}.dataset_licenses STORED AS PARQUET AS SELECT substr(p.id, 4) as id, licenses.value as type from ${openaire_db_name}.dataset p LATERAL VIEW explode(p.instance.license) instances as licenses -where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false; +where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false and p.datainfo.invisible = FALSE; CREATE TABLE IF NOT EXISTS ${stats_db_name}.software_licenses STORED AS PARQUET AS SELECT substr(p.id, 4) as id, licenses.value as type from ${openaire_db_name}.software p LATERAL VIEW explode(p.instance.license) instances as licenses -where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false; +where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false and p.datainfo.invisible = FALSE; CREATE TABLE IF NOT EXISTS ${stats_db_name}.otherresearchproduct_licenses STORED AS PARQUET AS SELECT substr(p.id, 4) as id, licenses.value as type from ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.instance.license) instances as licenses -where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false; +where licenses.value is not null and licenses.value != '' and p.datainfo.deletedbyinference=false and p.datainfo.invisible = FALSE; CREATE VIEW IF NOT EXISTS ${stats_db_name}.result_licenses AS SELECT * FROM ${stats_db_name}.publication_licenses @@ -46,4 +46,17 @@ FROM ( LEFT OUTER JOIN ( SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference=false) d on o.datasource = d.id; \ No newline at end of file + WHERE d.datainfo.deletedbyinference=false and d.datainfo.invisible = FALSE) d on o.datasource = d.id; + +-- ANALYZE TABLE ${stats_db_name}.publication_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.organization_pids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.organization_pids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.organization_sources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.organization_sources COMPUTE STATISTICS FOR COLUMNS; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql index 58e7c7c11..cec22cd3e 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql @@ -9,22 +9,22 @@ CREATE TABLE IF NOT EXISTS ${stats_db_name}.publication_refereed STORED AS PARQUET as select substr(r.id, 4) as id, inst.refereed.classname as refereed from ${openaire_db_name}.publication r lateral view explode(r.instance) instances as inst -where r.datainfo.deletedbyinference=false; +where r.datainfo.deletedbyinference=false and r.datainfo.invisible = FALSE; CREATE TABLE IF NOT EXISTS ${stats_db_name}.dataset_refereed STORED AS PARQUET as select substr(r.id, 4) as id, inst.refereed.classname as refereed from ${openaire_db_name}.dataset r lateral view explode(r.instance) instances as inst -where r.datainfo.deletedbyinference=false; +where r.datainfo.deletedbyinference=false and r.datainfo.invisible = FALSE; CREATE TABLE IF NOT EXISTS ${stats_db_name}.software_refereed STORED AS PARQUET as select substr(r.id, 4) as id, inst.refereed.classname as refereed from ${openaire_db_name}.software r lateral view explode(r.instance) instances as inst -where r.datainfo.deletedbyinference=false; +where r.datainfo.deletedbyinference=false and r.datainfo.invisible = FALSE; CREATE TABLE IF NOT EXISTS ${stats_db_name}.otherresearchproduct_refereed STORED AS PARQUET as select substr(r.id, 4) as id, inst.refereed.classname as refereed from ${openaire_db_name}.otherresearchproduct r lateral view explode(r.instance) instances as inst -where r.datainfo.deletedbyinference=false; +where r.datainfo.deletedbyinference=false and r.datainfo.invisible = FALSE; CREATE VIEW IF NOT EXISTS ${stats_db_name}.result_refereed as select * from ${stats_db_name}.publication_refereed diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql old mode 100644 new mode 100755 index 0ea4a5adc..9f11fa49d --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql @@ -1,28 +1,29 @@ +---- Sprint 1 ---- create table indi_pub_green_oa stored as parquet as -select distinct p.id, coalesce(green_oa, 0) as green_oa +select distinct p.id, coalesce(green_oa, 0) as green_oa from publication p -left outer join ( -select p.id, 1 as green_oa +left outer join ( +select p.id, 1 as green_oa from publication p join result_instance ri on ri.id = p.id join datasource on datasource.id = ri.hostedby where datasource.type like '%Repository%' -and (ri.accessright = 'Open Access' -or ri.accessright = 'Embargo')) tmp +and (ri.accessright = 'Open Access' +or ri.accessright = 'Embargo' or ri.accessright = 'Open Source')) tmp on p.id= tmp.id; create table indi_pub_grey_lit stored as parquet as select distinct p.id, coalesce(grey_lit, 0) as grey_lit from publication p left outer join ( -select p.id, 1 as grey_lit +select p.id, 1 as grey_lit from publication p join result_classifications rt on rt.id = p.id -where rt.type not in ('Article','Part of book or chapter of book','Book','Doctoral thesis','Master thesis','Data Paper', 'Thesis', 'Bachelor thesis', 'Conference object') and +where rt.type not in ('Article','Part of book or chapter of book','Book','Doctoral thesis','Master thesis','Data Paper', 'Thesis', 'Bachelor thesis', 'Conference object') and not exists (select 1 from result_classifications rc where type ='Other literature type' and rc.id=p.id)) tmp on p.id=tmp.id; create table indi_pub_doi_from_crossref stored as parquet as -select distinct p.id, coalesce(doi_from_crossref, 0) as doi_from_crossref +select distinct p.id, coalesce(doi_from_crossref, 0) as doi_from_crossref from publication p left outer join (select ri.id, 1 as doi_from_crossref from result_instance ri @@ -33,7 +34,7 @@ on tmp.id=p.id; create table indi_pub_gold_oa stored as parquet as select distinct p.id, coalesce(gold_oa, 0) as gold_oa from publication p -left outer join ( +left outer join ( select p.id, 1 as gold_oa from publication p join result_instance ri on ri.id = p.id @@ -41,226 +42,56 @@ join datasource on datasource.id = ri.hostedby where datasource.id like '%doajarticles%') tmp on p.id= tmp.id; -create table indi_project_pubs_count stored as parquet as -select pr.id id, count(p.id) total_pubs from project_results pr -join publication p on p.id=pr.result -group by pr.id; - -create table indi_project_datasets_count stored as parquet as -select pr.id id, count(d.id) total_datasets from project_results pr -join dataset d on d.id=pr.result -group by pr.id; - -create table indi_project_software_count stored as parquet as -select pr.id id, count(s.id) total_software from project_results pr -join software s on s.id=pr.result -group by pr.id; - -create table indi_project_otherresearch_count stored as parquet as -select pr.id id, count(o.id) total_other from project_results pr -join otherresearchproduct o on o.id=pr.result -group by pr.id; - -create table indi_pub_avg_year_country_oa stored as parquet as -select year, country, round(OpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageOA, -round(NonOpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageNonOA - from - (SELECT year, country, SUM(CASE - WHEN bestlicence='Open Access' THEN 1 - ELSE 0 - END) AS OpenAccess, SUM(CASE - WHEN bestlicence<>'Open Access' THEN 1 - ELSE 0 - END) AS NonOpenAccess - FROM publication p - join result_organization ro on p.id=ro.id - join organization o on o.id=ro.organization - where cast(year as int)>=2003 and cast(year as int)<=2021 - group by year, country) tmp; - -create table indi_dataset_avg_year_country_oa stored as parquet as -select year, country, round(OpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageOA, -round(NonOpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageNonOA - from - (SELECT year, country, SUM(CASE - WHEN bestlicence='Open Access' THEN 1 - ELSE 0 - END) AS OpenAccess, SUM(CASE - WHEN bestlicence<>'Open Access' THEN 1 - ELSE 0 - END) AS NonOpenAccess - FROM dataset d - join result_organization ro on d.id=ro.id - join organization o on o.id=ro.organization - where cast(year as int)>=2003 and cast(year as int)<=2021 - group by year, country) tmp; - -create table indi_software_avg_year_country_oa stored as parquet as -select year, country, round(OpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageOA, -round(NonOpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageNonOA - from - (SELECT year, country, SUM(CASE - WHEN bestlicence='Open Access' THEN 1 - ELSE 0 - END) AS OpenAccess, SUM(CASE - WHEN bestlicence<>'Open Access' THEN 1 - ELSE 0 - END) AS NonOpenAccess - FROM software s - join result_organization ro on s.id=ro.id - join organization o on o.id=ro.organization - where cast(year as int)>=2003 and cast(year as int)<=2021 - group by year, country) tmp; - - -create table indi_other_avg_year_country_oa stored as parquet as -select year, country, round(OpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageOA, -round(NonOpenAccess/(OpenAccess+NonOpenAccess)*100,3) as averageNonOA - from - (SELECT year, country, SUM(CASE - WHEN bestlicence='Open Access' THEN 1 - ELSE 0 - END) AS OpenAccess, SUM(CASE - WHEN bestlicence<>'Open Access' THEN 1 - ELSE 0 - END) AS NonOpenAccess - FROM otherresearchproduct orp - join result_organization ro on orp.id=ro.id - join organization o on o.id=ro.organization - where cast(year as int)>=2003 and cast(year as int)<=2021 - group by year, country) tmp; - -create table indi_pub_avg_year_context_oa stored as parquet as -with total as -(select count(distinct pc.id) no_of_pubs, year, c.name name, sum(count(distinct pc.id)) over(PARTITION by year) as total from publication_concepts pc -join context c on pc.concept like concat('%',c.id,'%') -join publication p on p.id=pc.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by c.name, year ) -select year, name, round(no_of_pubs/total*100,3) averageofpubs -from total; - -create table indi_dataset_avg_year_context_oa stored as parquet as -with total as -(select count(distinct pc.id) no_of_pubs, year, c.name name, sum(count(distinct pc.id)) over(PARTITION by year) as total from dataset_concepts pc -join context c on pc.concept like concat('%',c.id,'%') -join dataset p on p.id=pc.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by c.name, year ) -select year, name, round(no_of_pubs/total*100,3) averageofdataset -from total; - -create table indi_software_avg_year_context_oa stored as parquet as -with total as -(select count(distinct pc.id) no_of_pubs, year, c.name name, sum(count(distinct pc.id)) over(PARTITION by year) as total from software_concepts pc -join context c on pc.concept like concat('%',c.id,'%') -join software p on p.id=pc.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by c.name, year ) -select year, name, round(no_of_pubs/total*100,3) averageofsoftware -from total; - -create table indi_other_avg_year_context_oa stored as parquet as -with total as -(select count(distinct pc.id) no_of_pubs, year, c.name name, sum(count(distinct pc.id)) over(PARTITION by year) as total from otherresearchproduct_concepts pc -join context c on pc.concept like concat('%',c.id,'%') -join otherresearchproduct p on p.id=pc.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by c.name, year ) -select year, name, round(no_of_pubs/total*100,3) averageofother -from total; - -create table indi_other_avg_year_content_oa stored as parquet as -with total as -(select count(distinct pd.id) no_of_pubs, year, d.type type, sum(count(distinct pd.id)) over(PARTITION by year) as total -from otherresearchproduct_datasources pd -join datasource d on datasource=d.id -join otherresearchproduct p on p.id=pd.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by d.type, year) -select year, type, round(no_of_pubs/total*100,3) averageOfOtherresearchproduct -from total; - -create table indi_software_avg_year_content_oa stored as parquet as -with total as -(select count(distinct pd.id) no_of_pubs, year, d.type type, sum(count(distinct pd.id)) over(PARTITION by year) as total -from software_datasources pd -join datasource d on datasource=d.id -join software p on p.id=pd.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by d.type, year) -select year, type, round(no_of_pubs/total*100,3) averageOfSoftware -from total; - -create table indi_dataset_avg_year_content_oa stored as parquet as -with total as -(select count(distinct pd.id) no_of_pubs, year, d.type type, sum(count(distinct pd.id)) over(PARTITION by year) as total -from dataset_datasources pd -join datasource d on datasource=d.id -join dataset p on p.id=pd.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by d.type, year) -select year, type, round(no_of_pubs/total*100,3) averageOfDatasets -from total; - -create table indi_pub_avg_year_content_oa stored as parquet as -with total as -(select count(distinct pd.id) no_of_pubs, year, d.type type, sum(count(distinct pd.id)) over(PARTITION by year) as total -from publication_datasources pd -join datasource d on datasource=d.id -join publication p on p.id=pd.id -where cast(year as int)>=2003 and cast(year as int)<=2021 -group by d.type, year) -select year, type, round(no_of_pubs/total*100,3) averageOfPubs -from total; - -create table indi_pub_has_cc_licence stored as parquet as -select distinct p.id, (case when lic='' or lic is null then 0 else 1 end) as has_cc_license -from publication p -left outer join (select p.id, license.type as lic from publication p -join publication_licenses as license on license.id = p.id +---- Sprint 2 ---- +create table indi_result_has_cc_licence stored as parquet as +select distinct r.id, (case when lic='' or lic is null then 0 else 1 end) as has_cc_license +from result r +left outer join (select r.id, license.type as lic from result r +join result_licenses as license on license.id = r.id where lower(license.type) LIKE '%creativecommons.org%' OR lower(license.type) LIKE '%cc-%') tmp -on p.id= tmp.id; +on r.id= tmp.id; -create table indi_pub_has_cc_licence_url stored as parquet as -select distinct p.id, (case when lic_host='' or lic_host is null then 0 else 1 end) as has_cc_license_url -from publication p -left outer join (select p.id, lower(parse_url(license.type, "HOST")) as lic_host -from publication p -join publication_licenses as license on license.id = p.id -WHERE lower(parse_url(license.type, 'HOST')) = 'creativecommons.org') tmp -on p.id= tmp.id; +create table indi_result_has_cc_licence_url stored as parquet as +select distinct r.id, case when lic_host='' or lic_host is null then 0 else 1 end as has_cc_license_url +from result r +left outer join (select r.id, lower(parse_url(license.type, "HOST")) as lic_host +from result r +join result_licenses as license on license.id = r.id +WHERE lower(parse_url(license.type, "HOST")) = "creativecommons.org") tmp +on r.id= tmp.id; create table indi_pub_has_abstract stored as parquet as select distinct publication.id, coalesce(abstract, 1) has_abstract from publication; -create table indi_with_orcid stored as parquet as +create table indi_result_with_orcid stored as parquet as select distinct r.id, coalesce(has_orcid, 0) as has_orcid -from result r -left outer join (select id, 1 as has_orcid from result_orcid) tmp -on r.id= tmp.id +from result r +left outer join (select id, 1 as has_orcid from result_orcid) tmp +on r.id= tmp.id; -create table indi_funded_result_with_fundref stored as parquet as + +---- Sprint 3 ---- +create table indi_funded_result_with_fundref stored as parquet as select distinct r.id, coalesce(fundref, 0) as fundref -from project_results r +from project_results r left outer join (select distinct id, 1 as fundref from project_results -where provenance='Harvested') tmp -on r.id= tmp.id +where provenance='Harvested') tmp +on r.id= tmp.id; -create table indi_result_org_country_collab stored as parquet as -with tmp as +create table indi_result_org_country_collab stored as parquet as +with tmp as (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 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 from tmp as o1 join tmp as o2 on o1.result=o2.result -where o1.id<>o2.id and o1.country<>o2.country -group by o1.id, o1.type,o2.country +where o1.id<>o2.id and o1.country<>o2.country +group by o1.id, o1.type,o2.country; -create table indi_result_org_collab stored as parquet as -with tmp as +create table indi_result_org_collab stored as parquet as +with tmp as (select o.id, ro.id as result,r.type from organization o join result_organization ro on o.id=ro.organization join result r on r.id=ro.id) @@ -268,15 +99,82 @@ select o1.id org1,o2.id org2, o1.type, count(distinct o1.result) as collaboratio from tmp as o1 join tmp as o2 on o1.result=o2.result where o1.id<>o2.id -group by o1.id, o2.id, o1.type +group by o1.id, o2.id, o1.type; -create table indi_result_org_country_collab stored as parquet as -with tmp as -(select o.id as id, o.country , ro.id as result,r.type from organization o +create table indi_funder_country_collab stored as parquet as +with tmp as (select funder, project, country from organization_projects op +join organization o on o.id=op.id +join project p on p.id=op.project +where country <> 'UNKNOWN') +select f1.funder, f1.country as country1, f2.country as country2, count(distinct f1.project) as collaborations +from tmp as f1 +join tmp as f2 on f1.project=f2.project +where f1.country<>f2.country +group by f1.funder, f2.country, f1.country; + +create table indi_result_country_collab stored as parquet as +with tmp as +(select country, ro.id as result,r.type from organization o join result_organization ro on o.id=ro.organization -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 +join result r on r.id=ro.id) +select o1.country country1, o2.country country2, o1.type, count(distinct o1.result) as collaborations from tmp as o1 join tmp as o2 on o1.result=o2.result -where o1.id<>o2.id and o1.country<>o2.country -group by o1.id, o1.type,o2.country +where o1.country<>o2.country +group by o1.country, o2.country, o1.type; + +---- Sprint 4 ---- +create table indi_pub_diamond stored as parquet as +select distinct pd.id, coalesce(in_diamond_journal, 0) as in_diamond_journal +from publication_datasources pd +left outer join ( +select pd.id, 1 as in_diamond_journal from publication_datasources pd +join datasource d on d.id=pd.datasource +join stats_ext.plan_s_jn ps where (ps.issn_print=d.issn_printed and ps.issn_online=d.issn_online) +and (ps.journal_is_in_doaj=true or ps.journal_is_oa=true) and ps.has_apc=false) tmp +on pd.id=tmp.id; + +create table indi_pub_hybrid stored as parquet as +select distinct pd.id, coalesce(is_hybrid, 0) as is_hybrid +from publication_datasources pd +left outer join ( +select pd.id, 1 as is_hybrid from publication_datasources pd +join datasource d on d.id=pd.datasource +join stats_ext.plan_s_jn ps where (ps.issn_print=d.issn_printed and ps.issn_online=d.issn_online) +and (ps.journal_is_in_doaj=false and ps.journal_is_oa=false)) tmp +on pd.id=tmp.id; + +create table indi_is_gold_oa stored as parquet as +(select distinct pd.id, coalesce(gold_oa, 0) as gold_oa +from publication_datasources pd +left outer join ( +select pd.id, 1 as gold_oa from publication_datasources pd +join datasource d on d.id=pd.datasource +join stats_ext.plan_s_jn ps on (ps.issn_print=d.issn_printed or ps.issn_online=d.issn_online) +where ps.journal_is_in_doaj is true or ps.journal_is_oa is true) tmp +on pd.id=tmp.id); + +create table indi_pub_in_transformative stored as parquet as +select distinct pd.id, coalesce(is_transformative, 0) as is_transformative +from publication pd +left outer join ( +select pd.id, 1 as is_transformative from publication_datasources pd +join datasource d on d.id=pd.datasource +join stats_ext.plan_s_jn ps where (ps.issn_print=d.issn_printed and ps.issn_online=d.issn_online) +and ps.is_transformative_journal=true) tmp +on pd.id=tmp.id; + +create table indi_pub_closed_other_open stored as parquet as +select distinct ri.id, coalesce(pub_closed_other_open, 0) as pub_closed_other_open from result_instance ri +left outer join +(select ri.id, 1 as pub_closed_other_open from result_instance ri +join publication p on p.id=ri.id +join datasource d on ri.hostedby=d.id +where d.type like '%Journal%' and ri.accessright='Closed Access' and +(p.bestlicence='Open Access' or p.bestlicence='Open Source')) tmp +on tmp.id=ri.id; + + +---- Sprint 5 ---- +create table indi_result_no_of_copies stored as parquet as +select id, count(id) as number_of_copies from result_instance group by id; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql index dfe6246ca..4ffbd384b 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql @@ -38,13 +38,13 @@ SELECT substr(p.id, 4) as id, case when size(p.description) > 0 then true else false end as abstract, 'publication' as type from ${openaire_db_name}.publication p -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_classifications STORED AS PARQUET AS SELECT substr(p.id, 4) as id, instancetype.classname as type from ${openaire_db_name}.publication p LATERAL VIEW explode(p.instance.instancetype) instances as instancetype -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_concepts STORED AS PARQUET AS SELECT substr(p.id, 4) as id, case @@ -53,45 +53,45 @@ SELECT substr(p.id, 4) as id, case when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept from ${openaire_db_name}.publication p LATERAL VIEW explode(p.context) contexts as context -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_datasources STORED AS PARQUET as SELECT p.id, case when d.id is null then 'other' else p.datasource end as datasource FROM ( SELECT substr(p.id, 4) as id, substr(instances.instance.hostedby.key, 4) as datasource from ${openaire_db_name}.publication p lateral view explode(p.instance) instances as instance - where p.datainfo.deletedbyinference = false) p + where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false) p LEFT OUTER JOIN ( SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference = false) d on p.datasource = d.id; + WHERE d.datainfo.deletedbyinference = false and d.datainfo.invisible=false) d on p.datasource = d.id; CREATE TABLE ${stats_db_name}.publication_languages STORED AS PARQUET AS select substr(p.id, 4) as id, p.language.classname as language FROM ${openaire_db_name}.publication p -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_oids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, oids.ids AS oid FROM ${openaire_db_name}.publication p LATERAL VIEW explode(p.originalid) oids AS ids -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_pids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, ppid.qualifier.classname AS type, ppid.value as pid FROM ${openaire_db_name}.publication p LATERAL VIEW explode(p.pid) pids AS ppid -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_topics STORED AS PARQUET as select substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS TYPE, subjects.subject.value AS topic FROM ${openaire_db_name}.publication p LATERAL VIEW explode(p.subject) subjects AS subject -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.publication_citations STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, xpath_string(citation.value, "//citation/id[@type='openaire']/@value") AS cites FROM ${openaire_db_name}.publication p lateral view explode(p.extrainfo) citations AS citation WHERE xpath_string(citation.value, "//citation/id[@type='openaire']/@value") != "" - and p.datainfo.deletedbyinference = false; \ No newline at end of file + and p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql index f4fb2a174..e75bdffc8 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql @@ -49,8 +49,10 @@ compute stats TARGET.result_greenoa; create table TARGET.result_languages stored as parquet as select * from SOURCE.result_languages orig where exists (select 1 from TARGET.result r where r.id=orig.id); compute stats TARGET.result_languages; -create table TARGET.result_licences stored as parquet as select * from SOURCE.result_licenses orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.result_licences; +create table TARGET.result_licenses stored as parquet as select * from SOURCE.result_licenses orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.result_licenses; + +create table TARGET.licenses_normalized as select * from SOURCE.licenses_normalized; create table TARGET.result_oids stored as parquet as select * from SOURCE.result_oids orig where exists (select 1 from TARGET.result r where r.id=orig.id); compute stats TARGET.result_oids; @@ -79,6 +81,13 @@ 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); compute stats TARGET.result_topics; +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 table TARGET.result_result as select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou; +drop view TARGET.foo1; +drop view TARGET.foo2; +compute stats TARGET.result_result; + -- datasources create view if not exists TARGET.datasource as select * from SOURCE.datasource; create view if not exists TARGET.datasource_oids as select * from SOURCE.datasource_oids; @@ -100,28 +109,12 @@ create view if not exists TARGET.project as select * from SOURCE.project; create view if not exists TARGET.project_oids as select * from SOURCE.project_oids; create view if not exists TARGET.project_organizations as select * from SOURCE.project_organizations; create view if not exists TARGET.project_resultcount as select * from SOURCE.project_resultcount; +create view if not exists TARGET.project_classification as select * from SOURCE.project_classification; create table TARGET.project_results stored as parquet as select id as result, project as id from TARGET.result_projects; compute stats TARGET.project_results; -- indicators -create view TARGET.indi_dataset_avg_year_content_oa as select * from SOURCE.indi_dataset_avg_year_content_oa orig; -create view TARGET.indi_dataset_avg_year_context_oa as select * from SOURCE.indi_dataset_avg_year_context_oa orig; -create view TARGET.indi_dataset_avg_year_country_oa as select * from SOURCE.indi_dataset_avg_year_country_oa orig; - -create view TARGET.indi_other_avg_year_content_oa as select * from SOURCE.indi_other_avg_year_content_oa orig; -create view TARGET.indi_other_avg_year_context_oa as select * from SOURCE.indi_other_avg_year_context_oa orig; -create view TARGET.indi_other_avg_year_country_oa as select * from SOURCE.indi_other_avg_year_country_oa orig; - -create view TARGET.indi_project_datasets_count as select * from SOURCE.indi_project_datasets_count orig; -create view TARGET.indi_project_otherresearch_count as select * from SOURCE.indi_project_otherresearch_count orig; -create view TARGET.indi_project_pubs_count as select * from SOURCE.indi_project_pubs_count orig; -create view TARGET.indi_project_software_count as select * from SOURCE.indi_project_software_count orig; - -create view TARGET.indi_pub_avg_year_content_oa as select * from SOURCE.indi_pub_avg_year_content_oa orig; -create view TARGET.indi_pub_avg_year_context_oa as select * from SOURCE.indi_pub_avg_year_context_oa orig; -create view TARGET.indi_pub_avg_year_country_oa as select * from SOURCE.indi_pub_avg_year_country_oa orig; - create table TARGET.indi_pub_green_oa stored as parquet as select * from SOURCE.indi_pub_green_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id); compute stats TARGET.indi_pub_green_oa; create table TARGET.indi_pub_grey_lit stored as parquet as select * from SOURCE.indi_pub_grey_lit orig where exists (select 1 from TARGET.result r where r.id=orig.id); @@ -132,14 +125,31 @@ create table TARGET.indi_pub_gold_oa stored as parquet as select * from SOURCE.i compute stats TARGET.indi_pub_gold_oa; create table TARGET.indi_pub_has_abstract stored as parquet as select * from SOURCE.indi_pub_has_abstract orig where exists (select 1 from TARGET.result r where r.id=orig.id); compute stats TARGET.indi_pub_has_abstract; -create table TARGET.indi_pub_has_cc_licence stored as parquet as select * from SOURCE.indi_pub_has_cc_licence orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.indi_pub_has_cc_licence; -create table TARGET.indi_pub_has_cc_licence_url stored as parquet as select * from SOURCE.indi_pub_has_cc_licence_url orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.indi_pub_has_cc_licence_url; +create table TARGET.indi_result_has_cc_licence stored as parquet as select * from SOURCE.indi_result_has_cc_licence orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_result_has_cc_licence; +create table TARGET.indi_result_has_cc_licence_url stored as parquet as select * from SOURCE.indi_result_has_cc_licence_url orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_result_has_cc_licence_url; -create view TARGET.indi_software_avg_year_content_oa as select * from SOURCE.indi_software_avg_year_content_oa orig; -create view TARGET.indi_software_avg_year_context_oa as select * from SOURCE.indi_software_avg_year_context_oa orig; -create view TARGET.indi_software_avg_year_country_oa as select * from SOURCE.indi_software_avg_year_country_oa orig; +create view TARGET.indi_funder_country_collab as select * from SOURCE.indi_funder_country_collab; + +create table TARGET.indi_result_with_orcid stored as parquet as select * from SOURCE.indi_result_with_orcid orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_result_with_orcid; +create table TARGET.indi_funded_result_with_fundref stored as parquet as select * from SOURCE.indi_funded_result_with_fundref orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_funded_result_with_fundref; +create table TARGET.indi_pub_diamond stored as parquet as select * from SOURCE.indi_pub_diamond orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_diamond; +create table TARGET.indi_pub_hybrid stored as parquet as select * from SOURCE.indi_pub_hybrid orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_hybrid; +create table TARGET.indi_pub_in_transformative stored as parquet as select * from SOURCE.indi_pub_in_transformative orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_in_transformative; +create table TARGET.indi_pub_closed_other_open stored as parquet as select * from SOURCE.indi_pub_closed_other_open orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_closed_other_open; + +create table TARGET.indi_result_no_of_copies stored as parquet as select * from SOURCE.indi_result_no_of_copies orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_result_no_of_copies; + +--- Usage statistics +create table TARGET.usage_stats stored as parquet as select * from SOURCE.usage_stats orig where exists (select 1 from TARGET.result r where r.id=orig.result_id); --denorm alter table TARGET.result rename to TARGET.res_tmp; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql index 4841944a2..eb97263a7 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql @@ -38,20 +38,20 @@ SELECT substr(d.id, 4) AS id, CASE WHEN SIZE(d.description) > 0 THEN TRUE ELSE FALSE end AS abstract, 'dataset' AS type FROM ${openaire_db_name}.dataset d -WHERE d.datainfo.deletedbyinference = FALSE; +WHERE d.datainfo.deletedbyinference = FALSE and d.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_citations STORED AS PARQUET AS SELECT substr(d.id, 4) AS id, xpath_string(citation.value, "//citation/id[@type='openaire']/@value") AS cites FROM ${openaire_db_name}.dataset d LATERAL VIEW explode(d.extrainfo) citations AS citation WHERE xpath_string(citation.value, "//citation/id[@type='openaire']/@value") != "" - and d.datainfo.deletedbyinference = false; + and d.datainfo.deletedbyinference = false and d.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_classifications STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, instancetype.classname AS type FROM ${openaire_db_name}.dataset p LATERAL VIEW explode(p.instance.instancetype) instances AS instancetype -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_concepts STORED AS PARQUET AS SELECT substr(p.id, 4) as id, case @@ -60,7 +60,7 @@ SELECT substr(p.id, 4) as id, case when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept from ${openaire_db_name}.dataset p LATERAL VIEW explode(p.context) contexts as context -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_datasources STORED AS PARQUET AS SELECT p.id, case when d.id IS NULL THEN 'other' ELSE p.datasource END AS datasource @@ -68,31 +68,31 @@ FROM ( SELECT substr(p.id, 4) as id, substr(instances.instance.hostedby.key, 4) AS datasource FROM ${openaire_db_name}.dataset p LATERAL VIEW explode(p.instance) instances AS instance - where p.datainfo.deletedbyinference = false) p + where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false) p LEFT OUTER JOIN ( SELECT substr(d.id, 4) id FROM ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference = false) d ON p.datasource = d.id; + WHERE d.datainfo.deletedbyinference = false and d.datainfo.invisible=false) d ON p.datasource = d.id; CREATE TABLE ${stats_db_name}.dataset_languages STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, p.language.classname AS language FROM ${openaire_db_name}.dataset p -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_oids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, oids.ids AS oid FROM ${openaire_db_name}.dataset p LATERAL VIEW explode(p.originalid) oids AS ids -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_pids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, ppid.qualifier.classname AS type, ppid.value AS pid FROM ${openaire_db_name}.dataset p LATERAL VIEW explode(p.pid) pids AS ppid -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.dataset_topics STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS type, subjects.subject.value AS topic FROM ${openaire_db_name}.dataset p LATERAL VIEW explode(p.subject) subjects AS subject -where p.datainfo.deletedbyinference = false; \ No newline at end of file +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql index 390a5e338..0d1f6323e 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql @@ -38,20 +38,20 @@ SELECT substr(s.id, 4) as id, CASE WHEN SIZE(s.description) > 0 THEN TRUE ELSE FALSE END AS abstract, 'software' as type from ${openaire_db_name}.software s -where s.datainfo.deletedbyinference = false; +where s.datainfo.deletedbyinference = false and s.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_citations STORED AS PARQUET AS SELECT substr(s.id, 4) as id, xpath_string(citation.value, "//citation/id[@type='openaire']/@value") AS cites FROM ${openaire_db_name}.software s LATERAL VIEW explode(s.extrainfo) citations as citation where xpath_string(citation.value, "//citation/id[@type='openaire']/@value") != "" - and s.datainfo.deletedbyinference = false; + and s.datainfo.deletedbyinference = false and s.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_classifications STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, instancetype.classname AS type FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.instance.instancetype) instances AS instancetype -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_concepts STORED AS PARQUET AS SELECT substr(p.id, 4) as id, case @@ -60,7 +60,7 @@ SELECT substr(p.id, 4) as id, case when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.context) contexts AS context -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_datasources STORED AS PARQUET AS SELECT p.id, CASE WHEN d.id IS NULL THEN 'other' ELSE p.datasource end as datasource @@ -68,31 +68,31 @@ FROM ( SELECT substr(p.id, 4) AS id, substr(instances.instance.hostedby.key, 4) AS datasource FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.instance) instances AS instance - where p.datainfo.deletedbyinference = false) p + where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false) p LEFT OUTER JOIN ( SELECT substr(d.id, 4) id FROM ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference = false) d ON p.datasource = d.id; + WHERE d.datainfo.deletedbyinference = false and d.datainfo.invisible=false) d ON p.datasource = d.id; CREATE TABLE ${stats_db_name}.software_languages STORED AS PARQUET AS select substr(p.id, 4) AS id, p.language.classname AS language FROM ${openaire_db_name}.software p -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_oids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, oids.ids AS oid FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.originalid) oids AS ids -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_pids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, ppid.qualifier.classname AS type, ppid.value AS pid FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.pid) pids AS ppid -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.software_topics STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS type, subjects.subject.value AS topic FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.subject) subjects AS subject -where p.datainfo.deletedbyinference = false; \ No newline at end of file +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql index 65c2f0c33..06b616d6a 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql @@ -37,19 +37,19 @@ SELECT substr(o.id, 4) AS id, CASE WHEN SIZE(o.description) > 0 THEN TRUE ELSE FALSE END AS abstract, 'other' AS type FROM ${openaire_db_name}.otherresearchproduct o -WHERE o.datainfo.deletedbyinference = FALSE; +WHERE o.datainfo.deletedbyinference = FALSE and o.datainfo.invisible=false; -- Otherresearchproduct_citations CREATE TABLE ${stats_db_name}.otherresearchproduct_citations STORED AS PARQUET AS SELECT substr(o.id, 4) AS id, xpath_string(citation.value, "//citation/id[@type='openaire']/@value") AS cites FROM ${openaire_db_name}.otherresearchproduct o LATERAL VIEW explode(o.extrainfo) citations AS citation WHERE xpath_string(citation.value, "//citation/id[@type='openaire']/@value") != "" - and o.datainfo.deletedbyinference = false; + and o.datainfo.deletedbyinference = false and o.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.otherresearchproduct_classifications STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, instancetype.classname AS type FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.instance.instancetype) instances AS instancetype -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.otherresearchproduct_concepts STORED AS PARQUET AS SELECT substr(p.id, 4) as id, case @@ -57,33 +57,33 @@ SELECT substr(p.id, 4) as id, case when contexts.context.id RLIKE '^[^::]+::[^::]+$' then concat(contexts.context.id, '::other') when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.context) contexts AS context -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.otherresearchproduct_datasources STORED AS PARQUET AS SELECT p.id, CASE WHEN d.id IS NULL THEN 'other' ELSE p.datasource END AS datasource FROM (SELECT substr(p.id, 4) AS id, substr(instances.instance.hostedby.key, 4) AS datasource from ${openaire_db_name}.otherresearchproduct p lateral view explode(p.instance) instances as instance - where p.datainfo.deletedbyinference = false) p + where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false) p LEFT OUTER JOIN(SELECT substr(d.id, 4) id from ${openaire_db_name}.datasource d - WHERE d.datainfo.deletedbyinference = false) d on p.datasource = d.id; + WHERE d.datainfo.deletedbyinference = false and d.datainfo.invisible=false) d on p.datasource = d.id; CREATE TABLE ${stats_db_name}.otherresearchproduct_languages STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, p.language.classname AS language FROM ${openaire_db_name}.otherresearchproduct p -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.otherresearchproduct_oids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, oids.ids AS oid FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.originalid) oids AS ids -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.otherresearchproduct_pids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, ppid.qualifier.classname AS type, ppid.value AS pid FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.pid) pids AS ppid -where p.datainfo.deletedbyinference = false; +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.otherresearchproduct_topics STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS type, subjects.subject.value AS topic FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.subject) subjects AS subject -where p.datainfo.deletedbyinference = false; \ No newline at end of file +where p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql index c75659c46..fd10ce2e4 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql @@ -5,24 +5,26 @@ ------------------------------------------------------ CREATE TABLE ${stats_db_name}.project_oids STORED AS PARQUET AS SELECT substr(p.id, 4) AS id, oids.ids AS oid -FROM ${openaire_db_name}.project p LATERAL VIEW explode(p.originalid) oids AS ids; +FROM ${openaire_db_name}.project p LATERAL VIEW explode(p.originalid) oids AS ids +where p.datainfo.deletedbyinference=false and p.datainfo.invisible=false; + CREATE TABLE ${stats_db_name}.project_organizations AS SELECT substr(r.source, 4) AS id, substr(r.target, 4) AS organization from ${openaire_db_name}.relation r WHERE r.reltype = 'projectOrganization' - and r.datainfo.deletedbyinference = false; + and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.project_results STORED AS PARQUET AS SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS result, r.datainfo.provenanceaction.classname as provenance FROM ${openaire_db_name}.relation r WHERE r.reltype = 'resultProject' - and r.datainfo.deletedbyinference = false; + and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false; create table ${stats_db_name}.project_classification STORED AS PARQUET as select substr(p.id, 4) as id, class.h2020programme.code, class.level1, class.level2, class.level3 from ${openaire_db_name}.project p lateral view explode(p.h2020classification) classifs as class -where p.datainfo.deletedbyinference=false and class.h2020programme is not null; +where p.datainfo.deletedbyinference=false and p.datainfo.invisible=false and class.h2020programme is not null; CREATE TABLE ${stats_db_name}.project_tmp ( @@ -72,7 +74,7 @@ SELECT substr(p.id, 4) AS id, p.code.value AS code, p.totalcost AS totalcost FROM ${openaire_db_name}.project p -WHERE p.datainfo.deletedbyinference = false; +WHERE p.datainfo.deletedbyinference = false and p.datainfo.invisible=false; create table ${stats_db_name}.funder STORED AS PARQUET as select distinct xpath_string(fund, '//funder/id') as id, diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql index 99fa47767..e1c36cbc0 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql @@ -127,7 +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 FROM ${openaire_db_name}.relation r WHERE r.reltype = 'resultOrganization' - and r.datainfo.deletedbyinference = false; + and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.result_projects STORED AS PARQUET AS select pr.result AS id, pr.id AS project, datediff(p.enddate, p.startdate) AS daysfromend, pr.provenance as provenance diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql index 33e1e3527..5b1d588d9 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql @@ -44,7 +44,7 @@ FROM ${openaire_db_name}.datasource d1 LATERAL VIEW EXPLODE(originalid) temp AS originalidd WHERE originalidd like "piwik:%") AS d2 ON d1.id = d2.id -WHERE d1.datainfo.deletedbyinference = FALSE; +WHERE d1.datainfo.deletedbyinference = FALSE and d1.datainfo.invisible=false; -- Updating temporary table with everything that is not based on results -> This is done with the following "dual" table. -- Creating a temporary dual table that will be removed after the following insert @@ -76,24 +76,26 @@ UPDATE ${stats_db_name}.datasource_tmp SET yearofvalidation=null WHERE yearofval CREATE TABLE ${stats_db_name}.datasource_languages STORED AS PARQUET AS SELECT substr(d.id, 4) AS id, langs.languages AS language -FROM ${openaire_db_name}.datasource d LATERAL VIEW explode(d.odlanguages.value) langs AS languages; +FROM ${openaire_db_name}.datasource d LATERAL VIEW explode(d.odlanguages.value) langs AS languages +where d.datainfo.deletedbyinference=false and d.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.datasource_oids STORED AS PARQUET AS SELECT substr(d.id, 4) AS id, oids.ids AS oid -FROM ${openaire_db_name}.datasource d LATERAL VIEW explode(d.originalid) oids AS ids; +FROM ${openaire_db_name}.datasource d LATERAL VIEW explode(d.originalid) oids AS ids +where d.datainfo.deletedbyinference=false and d.datainfo.invisible=false; CREATE TABLE ${stats_db_name}.datasource_organizations STORED AS PARQUET AS SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization FROM ${openaire_db_name}.relation r -WHERE r.reltype = 'datasourceOrganization' and r.datainfo.deletedbyinference = false; +WHERE r.reltype = 'datasourceOrganization' and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false; -- datasource sources: -- where the datasource info have been collected from. create table if not exists ${stats_db_name}.datasource_sources STORED AS PARQUET AS select substr(d.id, 4) as id, substr(cf.key, 4) as datasource from ${openaire_db_name}.datasource d lateral view explode(d.collectedfrom) cfrom as cf -where d.datainfo.deletedbyinference = false; +where d.datainfo.deletedbyinference = false and d.datainfo.invisible=false; CREATE OR REPLACE VIEW ${stats_db_name}.datasource_results AS SELECT datasource AS id, id AS result -FROM ${stats_db_name}.result_datasources; \ No newline at end of file +FROM ${stats_db_name}.result_datasources; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql index a1cb46185..c73aa811c 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql @@ -9,7 +9,7 @@ SELECT substr(o.id, 4) as id, o.legalshortname.value as legalshortname, o.country.classid as country FROM ${openaire_db_name}.organization o -WHERE o.datainfo.deletedbyinference = FALSE; +WHERE o.datainfo.deletedbyinference = FALSE and o.datainfo.invisible = FALSE; CREATE OR REPLACE VIEW ${stats_db_name}.organization_datasources AS SELECT organization AS id, id AS datasource