Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add chist_era project mining #1303

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

add chist_era project mining #1303

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6570c8e
add chest_era project mining
johnfouf Sep 13, 2021
88d7ab7
Update projects.sql
johnfouf Sep 14, 2021
c029265
tokenize acronyms + chistera without whitespaces
johnfouf Sep 15, 2021
c555b92
drop chistera without whitespace
johnfouf Sep 15, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions ...dnetlib/iis/wf/referenceextraction/project/main_sqlite/oozie_app/lib/scripts/projects.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,14 @@ regexprmatches("support|project|grant|fund|thanks|agreement|research|acknowledge
--DFG

union all
-- CHIST-ERA
select jdict('documentId', docid, 'projectId', id, 'confidenceLevel', 0.8, 'textsnippet', (prev||" <<< "||middle||" >>> "||next)) as C1, docid, id, fundingclass1, grantid from
(setschema 'docid,prev,middle,next' select c1, textwindow2s(comprspaces(lower(keywords(c2))),10,2,10,"\bchist era\b") from pubs where c2 is not null), grants
where (regexprmatches("\b"||keywords(lower(acronym))||"\b", prev||" "||middle||" "||next) or grantid = "unidentified") and fundingclass1 = "CHIST-ERA" group by docid, id

union all


-- Canadian funders
select jdict('documentId', docid, 'projectId', id, 'confidenceLevel', 0.8, 'textsnippet', textsnippet) as C1, docid, id, fundingclass1, grantid
from (
Expand Down Expand Up @@ -255,6 +263,7 @@ select jdict('documentId', docid, 'projectId', id, 'confidenceLevel', sqroot(min
)
) where confidence > 0.16) group by docid,id);

delete from output_table where fundingClass1="CHIST-ERA" and grantid="unidentified" and docid in (select docid from output_table where grantid!="unidentified");
delete from matched_undefined_miur_only where docid in (select docid from output_table where fundingClass1="MIUR");
delete from matched_undefined_wt_only where docid in (select docid from output_table where fundingClass1="WT");
delete from matched_undefined_gsri where docid in (select docid from output_table where fundingClass1="GSRI");
Expand Down