From 227e10f4b3ae28cb531b8b8863536e7484ae2c58 Mon Sep 17 00:00:00 2001 From: Antonis Lempesis Date: Fri, 5 Aug 2022 12:54:36 +0300 Subject: [PATCH] commenting out the collab indicators because they still fail --- .../scripts/step16-createIndicatorsTables.sql | 162 +++++++++--------- .../scripts/step20-createMonitorDB.sql | 2 +- 2 files changed, 82 insertions(+), 82 deletions(-) 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 index 25776316b..da344d132 100755 --- 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 @@ -84,87 +84,87 @@ from project_results r compute stats indi_funded_result_with_fundref; -create table indi_result_org_collab stored as parquet as -select o1.organization org1, o2.organization org2, count(distinct o1.id) as collaborations -from result_organization as o1 - join result_organization as o2 on o1.id=o2.id and o1.organization!=o2.organization -group by o1.organization, o2.organization; - -compute stats indi_result_org_collab; - -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; - -compute stats indi_result_org_country_collab; - -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) -select o1.id org1,o2.id org2, 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 -group by o1.id, o2.id, o1.type; - -compute stats indi_result_org_collab; - -create table indi_project_collab_org stored as parquet as -select o1.id org1,o2.id org2, count(distinct o1.project) as collaborations -from organization_projects as o1 - join organization_projects as o2 on o1.project=o2.project -where o1.id!=o2.id -group by o1.id, o2.id; - -compute stats indi_project_collab_org; - -create table indi_project_collab_org_country stored as parquet as - with tmp as - (select o.id organization, o.country , ro.project as project from organization o - join organization_projects ro on o.id=ro.id - and o.country <> 'UNKNOWN') -select o1.organization org1,o2.country country2, count(distinct o1.project) as collaborations -from tmp as o1 - join tmp as o2 on o1.project=o2.project -where o1.organization<>o2.organization and o1.country<>o2.country -group by o1.organization, o2.country; - -compute stats indi_project_collab_org_country; - -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; - -compute stats indi_funder_country_collab; - -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 country <> 'UNKNOWN') -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.country<>o2.country -group by o1.country, o2.country, o1.type; - -compute stats indi_result_country_collab; +-- create table indi_result_org_collab stored as parquet as +-- select o1.organization org1, o2.organization org2, count(distinct o1.id) as collaborations +-- from result_organization as o1 +-- join result_organization as o2 on o1.id=o2.id and o1.organization!=o2.organization +-- group by o1.organization, o2.organization; +-- +-- compute stats indi_result_org_collab; +-- +-- 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; +-- +-- compute stats indi_result_org_country_collab; +-- +-- 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) +-- select o1.id org1,o2.id org2, 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 +-- group by o1.id, o2.id, o1.type; +-- +-- compute stats indi_result_org_collab; +-- +-- create table indi_project_collab_org stored as parquet as +-- select o1.id org1,o2.id org2, count(distinct o1.project) as collaborations +-- from organization_projects as o1 +-- join organization_projects as o2 on o1.project=o2.project +-- where o1.id!=o2.id +-- group by o1.id, o2.id; +-- +-- compute stats indi_project_collab_org; +-- +-- create table indi_project_collab_org_country stored as parquet as +-- with tmp as +-- (select o.id organization, o.country , ro.project as project from organization o +-- join organization_projects ro on o.id=ro.id +-- and o.country <> 'UNKNOWN') +-- select o1.organization org1,o2.country country2, count(distinct o1.project) as collaborations +-- from tmp as o1 +-- join tmp as o2 on o1.project=o2.project +-- where o1.organization<>o2.organization and o1.country<>o2.country +-- group by o1.organization, o2.country; +-- +-- compute stats indi_project_collab_org_country; +-- +-- 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; +-- +-- compute stats indi_funder_country_collab; +-- +-- 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 country <> 'UNKNOWN') +-- 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.country<>o2.country +-- group by o1.country, o2.country, o1.type; +-- +-- compute stats indi_result_country_collab; ---- Sprint 4 ---- create table indi_pub_diamond stored as parquet as 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 cc6b69e34..5aca19f6e 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 @@ -170,7 +170,7 @@ 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_funder_country_collab as select * from SOURCE.indi_funder_country_collab; +-- 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;