Add DataCite usage example

docs/app-eg.rst

@@ -69,6 +69,8 @@ Data source examples and metric measurements
    set <https://github.com/dspinellis/alexandria3k/tree/main/examples/crossref-standalone>`__
 -  `Report metrics associated with ORCID
    data <https://github.com/dspinellis/alexandria3k/tree/main/examples/orcid>`__
+-  `Report metrics associated with DataCite
+   data <https://github.com/dspinellis/alexandria3k/tree/main/examples/datacite>`__
 -  `Report research organization registry
    metrics <https://github.com/dspinellis/alexandria3k/tree/main/examples/ror-metrics>`__
 

examples/Makefile

@@ -17,6 +17,7 @@ export ROR?=$(TOP_DIR)/tests/data/ror.zip
 export DOAJ?=$(TOP_DIR)/tests/data/doaj.csv
 export JOURNAL_NAMES?=$(TOP_DIR)/tests/data/titleFile.csv
 export PUBMED_DIR?=$(TOP_DIR)/tests/data/pubmed-sample
+export DATACITE?=$(TOP_DIR)/tests/data/datacite.tar.gz
 
 # Use source code tree implementation
 export A3K?=$(TOP_DIR)/bin/a3k

examples/README.md

@@ -45,6 +45,7 @@ The following examples are available.
 ### Data source examples and metric measurements
 * [Report metrics associated with the Crossref data set](crossref-standalone)
 * [Report metrics associated with ORCID data](orcid)
+* [Report metrics associated with DataCite data](datacite)
 * [Report research organization registry metrics](ror-metrics)
 
 ### Impact and productivitycalculations

examples/common/Makefile

@@ -12,6 +12,7 @@ USPTO_DIR?=../common/uspto-data
 ORCID_SUMMARIES?=../common/ORCID_2022_10_summaries.tar.gz
 ROR?=../common/ror-v1.17.1-2022-12-16.zip
 PUBMED_DIR?=../common/pubmed
+DATACITE=../common/datacite.tar.gz
 
 V?=1
 TIME?=time
@@ -36,6 +37,9 @@ $(ORCID_SUMMARIES):
 $(ROR):
 	curl -L 'https://zenodo.org/record/7448410/files/v1.17.1-2022-12-16-ror-data.zip?download=1' >$@
 
+$(DATACITE):
+	echo "Download the DataCite Public Data File as datacite.tar.gz from https://datafiles.datacite.org/"
+
 # TODO when using this Makefile: Add rule in including Makefile named
 # "populate" to populate the database with required data
 

examples/datacite/.gitignore

@@ -0,0 +1,8 @@
+.depend
+.depend.all
+nohup.out
+populate
+reports
+rolap
+simple-rolap
+tables

examples/datacite/Makefile

@@ -0,0 +1,14 @@
+#
+# Calculate DataCite table metrics
+#
+
+export MAINDB?=datacite
+export DEPENDENCIES=populate
+
+include ../common/Makefile
+
+# Populate database with DataCite data
+populate: $(DATACITE)
+	$(TIME) $(A3K) --progress \
+	  populate "$(MAINDB).db" datacite "$(DATACITE)"
+	touch $@

examples/datacite/README.md

@@ -0,0 +1,254 @@
+# DataCite metrics
+Populate a database with all DataCite data and report corresponding
+metrics as well as the codes used in the employed schemes.
+
+Below are the metrics and schemes results
+as obtained from the 2023 DataCite Public Data File.
+For schemes only the first ten values with the highest occurrence are listed.
+
+## Metrics
+
+| Value | Count |
+|:------|------:|
+|contributor\_affiliations|3635578|
+|contributor\_name\_identifiers|4576444|
+|creator\_affiliations|22560989|
+|creator\_name\_identifiers|12830187|
+|work\_contributors|24236641|
+|work\_creators|202655948|
+|work\_dates|81364966|
+|work\_descriptions|41259535|
+|work\_funding\_references|2305529|
+|work\_geo\_locations|19969035|
+|work\_related\_identifiers|483494659|
+|work\_rights|26632935|
+|work\_subjects|117682396|
+|work\_titles|57359160|
+|works|52863283|
+
+
+## dc\_contributor\_name\_identifiers.name\_identifier\_scheme
+
+| Value | Count |
+|:------|------:|
+|ORCID|1649199|
+|ROR|782619|
+|VIAF|589092|
+|GRID|200583|
+|GND|169558|
+|ISNI|90200|
+|BNF|87558|
+|LCCN|87558|
+|NKC|87558|
+|SUDOC|87558|
+
+## dc\_creator\_name\_identifiers.scheme\_uri
+
+| Value | Count |
+|:------|------:|
+|https://orcid.org|9385742|
+|(none)|2601705|
+|https://orcid.org/|200060|
+|https://d-nb.info/gnd/|86161|
+|(none)|83605|
+|http://orcid.org/|52468|
+|https://www.jacow.org/|31388|
+|http://isni.org/isni/|30290|
+|http://lccn.loc.gov/|29186|
+|https://aleph.nkp.cz/F/?func=find-c&local\_base=aut&CON\_LNG=ENG&ccl\_term=ica=|29186|
+
+## dc\_work\_contributors.contributor\_type
+
+| Value | Count |
+|:------|------:|
+|ContactPerson|5952672|
+|Other|3854570|
+|DataManager|3635356|
+|HostingInstitution|2358178|
+|Researcher|2260431|
+|DataCollector|1777541|
+|Funder|683551|
+|Distributor|564472|
+|Editor|518802|
+|(none)|460972|
+
+## dc\_work\_creators.name\_type
+
+| Value | Count |
+|:------|------:|
+|Personal|155758469|
+|(none)|41788325|
+|Organizational|5109154|
+
+## dc\_work\_dates.date\_type
+
+| Value | Count |
+|:------|------:|
+|Issued|33869505|
+|Updated|18217771|
+|Created|10375387|
+|Available|8191381|
+|Submitted|4422420|
+|Accepted|3138445|
+|Collected|2968553|
+|Copyrighted|108668|
+|Valid|44016|
+|Withdrawn|13512|
+
+## dc\_work\_descriptions.description\_type
+
+| Value | Count |
+|:------|------:|
+|Abstract|29843289|
+|Other|9688729|
+|SeriesInformation|1040621|
+|Methods|250449|
+|TechnicalInfo|244637|
+|TableOfContents|119599|
+|(none)|72210|
+|abstract|1|
+
+## dc\_work\_funding\_references.funder\_identifier\_type
+
+| Value | Count |
+|:------|------:|
+|Crossref Funder ID|985694|
+|(none)|691805|
+|ROR|426936|
+|GRID|168655|
+|ISNI|29975|
+|Other|2377|
+|"Other">China Geological Survey project|36|
+|Fondation Martine Aublet|20|
+|Fondation Martine Aublet (Paris, France)|16|
+|Fondation Martine Aublet (Paris, France).|2|
+
+## dc\_work\_related\_identifiers.related\_identifier\_type
+
+| Value | Count |
+|:------|------:|
+|DOI|456179995|
+|URL|14859234|
+|IGSN|9538696|
+|LSID|799059|
+|EISSN|745896|
+|ISSN|414258|
+|ISBN|303769|
+|Handle|295596|
+|LISSN|130048|
+|PMID|71231|
+
+## dc\_work\_related\_identifiers.relation\_type
+
+| Value | Count |
+|:------|------:|
+|References|431691310|
+|IsPartOf|13049632|
+|IsIdenticalTo|11390034|
+|IsSupplementTo|3944418|
+|IsVersionOf|3906323|
+|HasMetadata|3680959|
+|HasPart|2840517|
+|IsCitedBy|2684860|
+|HasVersion|2656100|
+|IsSourceOf|2118187|
+
+## dc\_work\_related\_identifiers.scheme\_type
+
+| Value | Count |
+|:------|------:|
+|(none)|480269100|
+|DwC-A|1611524|
+|XML|1611524|
+|http://datacite.org/schema/kernel-3|1965|
+|text/html|201|
+|xsd|201|
+|Text|64|
+|XSD|43|
+|Knowledge|34|
+|DATA ACCES|1|
+
+## dc\_work\_rights.rights\_identifier
+
+| Value | Count |
+|:------|------:|
+|(none)|15617810|
+|cc-by-4.0|5859089|
+|cc-by-nc-4.0|1696788|
+|cc0-1.0|1566760|
+|cc-by-sa-4.0|668028|
+|cc-by-3.0|335076|
+|cc-by-nc-nd-4.0|202084|
+|cc-by-nc-sa-4.0|106664|
+|cc-by-1.0|83510|
+|openaccess|54315|
+
+## dc\_work\_rights.rights\_identifier\_scheme
+
+| Value | Count |
+|:------|------:|
+|(none)|15705417|
+|SPDX|10818162|
+|info:eu-repo-Access-Terms vocabulary|54315|
+|(none)|52238|
+|Creative Commons|2105|
+|creativecommons|399|
+|b2share.legacy|181|
+|spdx|74|
+|custom|43|
+|Local Contexts|1|
+
+## dc\_works.identifier\_type
+
+| Value | Count |
+|:------|------:|
+|(none)|45955613|
+|DOI|4437411|
+|URL|1318449|
+|EISSN|619787|
+|Handle|192467|
+|ISSN|149125|
+|LISSN|130011|
+|ISBN|58286|
+|URN|2008|
+|arXiv|66|
+
+## dc\_work\_subjects.subject\_scheme
+
+| Value | Count |
+|:------|------:|
+|(none)|76872398|
+|Fields of Science and Technology (FOS)|16338295|
+|Parameter|4964564|
+|arXiv|3858253|
+|FOR|3763252|
+|LCSH|1401406|
+|Method|954884|
+|ddc|741879|
+|Project|407320|
+|keyword|394498|
+
+## dc\_work\_subjects.value\_uri
+
+| Value | Count |
+|:------|------:|
+|(none)|116832029|
+|http://id.loc.gov/authorities/subjects/sh85009003|176266|
+|http://www.oecd.org/science/inno/38235147.pdf|25620|
+|(none)|19432|
+|http://www.narcis.nl/classfication/D37000|5274|
+|https://core.tdar.org/browse/geographic-keyword/2810/southwestern-colorado|5013|
+|https://core.tdar.org/browse/geographic-keyword/84604/southwestern-us|5012|
+|https://core.tdar.org/browse/temporal-keyword/78/basketmaker-iii|4509|
+|https://core.tdar.org/browse/material-type/1/ceramic|3824|
+|http://astrothesaurus.org/uat/1469|3763|
+
+## dc\_work\_titles.title\_type
+
+| Value | Count |
+|:------|------:|
+|(none)|53091171|
+|Subtitle|3366476|
+|TranslatedTitle|449793|
+|AlternativeTitle|282511|
+|Other|169209|

examples/datacite/metrics.sql

@@ -0,0 +1,32 @@
+-- Output metrics of a fully-populated DataCite database
+
+SELECT "works" AS type,
+  (SELECT Count(*) FROM dc_works) AS records UNION
+SELECT "work_rights" AS type,
+  (SELECT Count(*) FROM dc_work_rights) AS records UNION
+SELECT "creator_name_identifiers" AS type,
+  (SELECT Count(*) FROM dc_creator_name_identifiers) AS records UNION
+SELECT "work_creators" AS type,
+  (SELECT Count(*) FROM dc_work_creators) AS records UNION
+SELECT "work_titles" AS type,
+  (SELECT Count(*) FROM dc_work_titles) AS records UNION
+SELECT "creator_affiliations" AS type,
+  (SELECT Count(*) FROM dc_creator_affiliations) AS records UNION
+SELECT "work_funding_references" AS type,
+  (SELECT Count(*) FROM dc_work_funding_references) AS records UNION
+SELECT "work_geo_locations" AS type,
+  (SELECT Count(*) FROM dc_work_geo_locations) AS records UNION
+SELECT "work_dates" AS type,
+  (SELECT Count(*) FROM dc_work_dates) AS records UNION
+SELECT "work_contributors" AS type,
+  (SELECT Count(*) FROM dc_work_contributors) AS records UNION
+SELECT "contributor_affiliations" AS type,
+  (SELECT Count(*) FROM dc_contributor_affiliations) AS records UNION
+SELECT "work_related_identifiers" AS type,
+  (SELECT Count(*) FROM dc_work_related_identifiers) AS records UNION
+SELECT "contributor_name_identifiers" AS type,
+  (SELECT Count(*) FROM dc_contributor_name_identifiers) AS records UNION
+SELECT "work_subjects" AS type,
+  (SELECT Count(*) FROM dc_work_subjects) AS records UNION
+SELECT "work_descriptions" AS type,
+  (SELECT Count(*) FROM dc_work_descriptions) AS records;

examples/datacite/schemes.sql

@@ -0,0 +1,35 @@
+-- Show the values used in the employed DataCite schemes
+
+SELECT "dc_work_funding_references.funder_identifier_type" AS field, funder_identifier_type AS name, Count(*) AS value FROM dc_work_funding_references GROUP BY funder_identifier_type UNION
+
+SELECT "dc_works.identifier_type" AS field, identifier_type AS name, Count(*) AS value FROM dc_works GROUP BY identifier_type UNION
+
+SELECT "dc_work_creators.name_type" AS field, name_type AS name, Count(*) AS value FROM dc_work_creators GROUP BY name_type UNION
+
+SELECT "dc_creator_name_identifiers.scheme_uri" AS field, scheme_uri AS name, Count(*) AS value FROM dc_creator_name_identifiers GROUP BY scheme_uri UNION
+
+SELECT "dc_work_contributors.contributor_type" AS field, contributor_type AS name, Count(*) AS value FROM dc_work_contributors GROUP BY contributor_type UNION
+
+SELECT "dc_contributor_name_identifiers.name_identifier_scheme" AS field, name_identifier_scheme AS name, Count(*) AS value FROM dc_contributor_name_identifiers GROUP BY name_identifier_scheme UNION
+
+SELECT "dc_work_titles.title_type" AS field, title_type AS name, Count(*) AS value FROM dc_work_titles GROUP BY title_type UNION
+
+SELECT "dc_work_subjects.subject_scheme" AS field, subject_scheme AS name, Count(*) AS value FROM dc_work_subjects GROUP BY subject_scheme UNION
+
+SELECT "dc_work_subjects.value_uri" AS field, value_uri AS name, Count(*) AS value FROM dc_work_subjects GROUP BY value_uri UNION
+
+SELECT "dc_work_dates.date_type" AS field, date_type AS name, Count(*) AS value FROM dc_work_dates GROUP BY date_type UNION
+
+SELECT "dc_work_related_identifiers.related_identifier_type" AS field, related_identifier_type AS name, Count(*) AS value FROM dc_work_related_identifiers GROUP BY related_identifier_type UNION
+
+SELECT "dc_work_related_identifiers.relation_type" AS field, relation_type AS name, Count(*) AS value FROM dc_work_related_identifiers GROUP BY relation_type UNION
+
+SELECT "dc_work_related_identifiers.scheme_type" AS field, scheme_type AS name, Count(*) AS value FROM dc_work_related_identifiers GROUP BY scheme_type UNION
+
+SELECT "dc_work_rights.rights_identifier_scheme" AS field, rights_identifier_scheme AS name, Count(*) AS value FROM dc_work_rights GROUP BY rights_identifier_scheme UNION
+
+SELECT "dc_work_rights.rights_identifier" AS field, rights_identifier AS name, Count(*) AS value FROM dc_work_rights GROUP BY rights_identifier UNION
+
+SELECT "dc_work_descriptions.description_type" AS field, description_type AS name, Count(*) AS value FROM dc_work_descriptions GROUP BY description_type UNION
+
+SELECT "dc_work_funding_references.funder_identifier_type" AS field, funder_identifier_type AS name, Count(*) AS value FROM dc_work_funding_references GROUP BY funder_identifier_type;