def linkset_stats(linkset):
query = """
PREFIX void: <http://rdfs.org/ns/void#>
PREFIX bdb: <http://vocabularies.bridgedb.org/ops#>
PREFIX ll: <http://risis.eu/alignment/predicate/>
SELECT DISTINCT ?dataset ?datatype ?alignsMechanism ?total
(COUNT (DISTINCT ?RESOURCE) as ?subtotal)
(ROUND((COUNT(DISTINCT ?RESOURCE) / ?total)*10000) /100 as ?percentage)
{{
<{0}> ll:alignsMechanism ?alignsMechanism .
{{
<{0}>
bdb:subjectsDatatype ?datatype ;
void:subjectsTarget ?dataset .
graph <{0}>
{{
?RESOURCE ?p ?o .
}}
}}
UNION
{{
<{0}>
bdb:objectsDatatype ?datatype ;
void:objectsTarget ?dataset .
graph <{0}>
{{
?o ?p ?RESOURCE .
}}
}}
{{
SELECT (COUNT(DISTINCT ?RESOURCE) as ?total) ?dataset ?datatype
{{
graph ?dataset
{{
?RESOURCE a ?datatype .
}}
}} GROUP BY ?dataset ?datatype
}}
}} GROUP BY ?dataset ?datatype ?total ?alignsMechanism
""".format(linkset)
Qry.display_result(query=query, spacing=60, is_activated=True)
def properties(graph, datatype=None):
comment = "# " if datatype is None else ""
datatype = datatype if Ut.is_nt_format(datatype) is True else "<{}>".format(datatype)
graph = graph if Ut.is_nt_format(graph) is True else "<{}>".format(graph)
properties = """
# <http://www.w3.org/1999/02/22-rdf-syntax-ns#type>
SELECT DISTINCT ?predicate
WHERE
{{
GRAPH {}
{{
{}?subj {} ?type .
?subj ?predicate ?obj .
}}
}}
""".format(graph, comment, datatype)
print properties
Qr.display_result(query=properties, spacing=50, limit=0, is_activated=True)
def ds_stats(dataset, datatype, display=True, optional_label=True, graph_list=None):
# QUERY THAT COMPUTES STATISTICS OVER THE ALIGNMENTS INVOLVING A PARTICULAR DATASET
append = "#" if graph_list is None else ""
values = ""
# LIST OF GRAPHS
if graph_list is not None:
for alignment in graph_list:
values += " <{}>".format(alignment)
comment_opt_lbl = '' if optional_label else '#'
query = """
PREFIX void: <http://rdfs.org/ns/void#>
PREFIX bdb: <http://vocabularies.bridgedb.org/ops#>
PREFIX dataset: <http://risis.eu/dataset/>
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
PREFIX ll: <http://risis.eu/alignment/predicate/>
PREFIX skos: <{2}>
SELECT DISTINCT ?dataset ?alignsMechanism
(COUNT(DISTINCT ?RESOURCE) as ?total) ?subTotal
(ROUND((?subTotal / COUNT(DISTINCT ?RESOURCE) ) *10000)/100 as ?percentage) ?graph ?graph_uri
{{
{4}VALUES ?graph_uri {{ {5} }}
graph <{0}>
{{
?RESOURCE a <{1}> .
}}
# TO CHECK WHETHER THE SELECTED GRAPH IS RELATED TO THE SELECTED DATASET
#?graph_uri
# void:target*/(void:subjectsTarget|void:objectsTarget) <{0}> ;
# void:target*/(bdb:subjectsDatatype|bdb:objectsDatatype) <{1}> .
# DISPLYING THE USER UPDATED LABEL
{3}OPTIONAL
{{ graph ?rq
{{
?graph_uri skos:prefLabel ?label
}}
}}
BIND (IF(bound(?label), ?label , ?graph_uri) AS ?graph)
# 1. LINKSET WHERE SUBJECTS AND OBJECTS RESOURCES ARE IN THE SAME DATASET
{{
SELECT (count(DISTINCT ?RESOURCE) as ?subTotal) ?graph_uri ?dataset ?alignsMechanism
{{
?graph_uri
bdb:subjectsDatatype <{1}> ;
void:subjectsTarget <{0}> ;
void:objectsTarget ?dataset ;
ll:alignsMechanism ?alignsMechanism .
graph ?graph_uri
{{
{{ ?RESOURCE ?SING ?oResource. }}
UNION
{{ ?oResource ?SING ?RESOURCE . }}
}}
FILTER (<{0}> = ?dataset)
}} GROUP BY ?graph_uri ?dataset ?alignsMechanism
}}
UNION # 2. WHEN THE DATSET SELECTED IS THE SUBJECT
{{
SELECT (count(DISTINCT ?RESOURCE) as ?subTotal) ?graph_uri ?dataset ?alignsMechanism
{{
?graph_uri
bdb:subjectsDatatype <{1}> ;
void:subjectsTarget <{0}> ;
void:objectsTarget ?dataset ;
ll:alignsMechanism ?alignsMechanism .
graph ?graph_uri
{{
?RESOURCE ?SING ?oResource.
}}
FILTER (<{0}> != ?dataset)
}} GROUP BY ?graph_uri ?dataset ?alignsMechanism
}}
UNION # 3. WHEN THE DATASET SELECTED IS THE OBJECT
{{
SELECT (count(DISTINCT ?RESOURCE) as ?subTotal) ?graph_uri ?dataset ?alignsMechanism
{{
?graph_uri
bdb:objectsDatatype <{1}> ;
void:objectsTarget <{0}> ;
void:subjectsTarget ?dataset ;
ll:alignsMechanism ?alignsMechanism .
graph ?graph_uri
{{
?oResource ?SING ?RESOURCE .
}}
FILTER (<{0}> != ?dataset)
}} GROUP BY ?graph_uri ?dataset ?alignsMechanism
}}
UNION # 4. RUN THIS WHEN THE GRAPH IS A LENS AND WHEN SUBJECTS AND OBJECTS RESOURCES ARE IN THE SAME DATASET
{{
SELECT (count(DISTINCT ?RESOURCE) as ?subTotal) ?graph_uri ?dataset ?alignsMechanism
{{
?graph_uri
void:target ?linkset ;
ll:operator ?alignsMechanism .
?linkset
bdb:subjectsDatatype <{1}> ;
void:subjectsTarget <{0}> ;
void:objectsTarget ?dataset .
graph ?graph_uri
{{
{{ ?RESOURCE ?SING ?oResource. }}
UNION
{{ ?oResource ?SING ?RESOURCE . }}
}}
FILTER (<{0}> = ?dataset)
}} GROUP BY ?graph_uri ?dataset ?alignsMechanism
}}
UNION # 5. RUN THIS WHEN THE GRAPH IS A LENS AND WHEN THE SELECTED DATASET IS THE SUBJECT
{{
SELECT (count(DISTINCT ?RESOURCE) as ?subTotal) ?graph_uri ?dataset ?alignsMechanism
{{
?graph_uri
void:target+ ?linkset ;
ll:operator ?alignsMechanism .
?linkset
bdb:subjectsDatatype <{1}> ;
void:subjectsTarget <{0}> ;
void:objectsTarget ?dataset .
graph ?graph_uri
{{
?oResource ?SING ?RESOURCE .
}}
FILTER (<{0}> != ?dataset)
}} GROUP BY ?graph_uri ?dataset ?alignsMechanism
}}
UNION #6. RUN THIS WHEN THE GRAPH IS A LENS AND WHEN THE SELECTED DATASET IS THE OBJECT
{{
SELECT (count(DISTINCT ?RESOURCE) as ?subTotal) ?graph_uri ?dataset ?alignsMechanism
{{
?graph_uri
void:target+ ?linkset ;
ll:operator ?alignsMechanism .
?linkset
bdb:objectsDatatype <{1}> ;
void:objectsTarget <{0}> ;
void:subjectsTarget ?dataset .
graph ?graph_uri
{{
?oResource ?SING ?RESOURCE .
}}
FILTER (<{0}> != ?dataset)
}} GROUP BY ?graph_uri ?dataset ?alignsMechanism
}}
}}
GROUP BY ?graph ?subTotal ?dataset ?alignsMechanism ?graph_uri having (?subTotal > 0)
ORDER BY ?dataset ?alignsMechanism
""".format(dataset, datatype, Ns.skos, comment_opt_lbl, append, values)
# print query
if display is True:
Qry.display_result(query=query, spacing=100, is_activated=True)
return query
def visit_data():
# ETER
eter_query = """
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX pred: <http://risis.eu/eter_2014/ontology/predicate/>
SELECT *
{{
GRAPH <http://risis.eu/dataset/eter_2014>
{{
?entity rdf:type ?type ;
pred:ETER_ID_Year ?year ;
pred:Institution_Name ?name ;
pred:Geographic_coordinates__latitude ?lat ;
pred:Geographic_coordinates__longitude ?long .
OPTIONAL {{ ?entity pred:Total_number_of_full_professors ?professors .}}
OPTIONAL {{ ?entity pred:Total_academic_staff_FTE ?academic_staff_FTE . }}
OPTIONAL {{ ?entity pred:Total_academic_staff_HC ?academic_staff_HC }}
OPTIONAL {{ ?entity pred:Total_students_enrolled_at_ISCED_5 ?ISCED_5. }}
OPTIONAL {{ ?entity pred:Total_students_enrolled_at_ISCED_6 ?ISCED_6. }}
OPTIONAL {{ ?entity pred:Total_students_enrolled_at_ISCED_7 ?ISCED_7. }}
OPTIONAL {{ ?entity pred:Total_students_enrolled_at_ISCED_8 ?ISCED_8. }}
}}
}} LIMIT 50
""".format()
print eter_query
Qr.display_result(query=eter_query, spacing=50, limit=0, is_activated=True)
grid_query = """
PREFIX coord: <http://www.w3.org/2003/01/geo/wgs84_pos#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX pred: <http://www.grid.ac/ontology/>
SELECT *
{{
GRAPH <http://risis.eu/dataset/grid_20180208>
{{
?entity rdf:type ?type ;
rdfs:label ?name .
?entity pred:hasAddress/coord:long ?long .
?entity pred:hasAddress/coord:lat ?lat .
}}
}} LIMIT 50
""".format()
print grid_query
# Qr.display_result(query=grid_query, spacing=50, limit=0, is_activated=True)
orgreg_query = """
PREFIX pred: <http://risis.eu/orgreg_20170718/ontology/predicate/>
SELECT *
{{
GRAPH <http://risis.eu/dataset/orgreg_20170718>
{{
?entity pred:characteristicsOf/pred:Type_of_entity ?type ;
pred:Entity_current_name_English ?name .
?entity pred:locationOf/pred:Geographical_coordinates__latitude ?long .
?entity pred:locationOf/pred:Geographical_coordinates__longitude ?lat .
}}
}} LIMIT 500
""".format()
def coverage_query(merged_lens, dataset, distribution=True, minus=False, datasets_involve=False, activated=False):
if activated is False:
print "THE FUNCTION [coverage_query] IS NOT ACTIVATED."
return None
# FETCH ALL DATASETS INVOLVED IN THE LENS
if datasets_involve is True:
datasets_q = """
SELECT DISTINCT ?datasets
{{
{} void:target*/(void:subjectsTarget|void:objectsTarget) ?datasets.
}}
""".format(Ut.to_nt_format(merged_lens))
# print datasets_q
Qr.display_result(query=datasets_q, spacing=50, limit=50, is_activated=True)
if distribution is False:
distribution_str = ""
else:
print "\n>>> COMPUTING THE ORIGINAL DISTRIBUTION OF : {}".format(dataset)
distribution_str = "# "
if minus is True:
if distribution is True:
print ">>> WARNING: DISTRIBUTION MUST BE SET TO [FALSE] IF MINUS IS SET TO [TRUE]"
minus_str = ""
else:
if distribution is True:
print ">>> WARNING: FOR COVERAGE DISTRIBUTION, DISTRIBUTION MUST BE SET TO FALSE"
else:
print "\n>>> COVERAGE OF {}".format(dataset)
minus_str = "# "
query = """
PREFIX lens:<http://risis.eu/lens/>
PREFIX dataset:<http://risis.eu/dataset/>
PREFIX property:<http://risis.eu/orgreg_20170718/ontology/predicate/>
# SELECT DISTINCT ?entity ?country
SELECT ?country (count(DISTINCT ?entity) as ?total)
# SELECT ?country (count( ?country) as ?total)
{{
{{
SELECT DISTINCT ?entity
{{
{{
# ALL UNIVERSITIES IN ORGREG
GRAPH <{1}>
{{
?entity a <http://risis.eu/orgreg_20170718/ontology/class/University> .
}}
}}
{2}{3}MINUS # ==> FETCH ALL UNIVERSITIES IN THE ORGREG DATASET THAT ARE NOT FOUND
{2}{{
{2} # LINKS (ENTITIES) FOUND FOR THE SIX DATASETS
{2} BIND(<{0}> AS ?lens)
{2} {{ GRAPH ?lens {{ ?entity ?pred ?obj . }}}}
{2} UNION
{2} {{ GRAPH ?lens {{ ?subj ?pred ?entity . }}}}
{2}}}
}}
}}
# FETCHING THE COUNTRY FOR EACH ORGANIZATION
GRAPH <{1}>
{{
?entity a <http://risis.eu/orgreg_20170718/ontology/class/University> .
OPTIONAL {{ ?entity property:locationOf/property:Country_of_location ?_country. }}
BIND (IF(bound(?_country), ?_country , "NONE") AS ?country)
}}
}} GROUP BY ?country ORDER BY ?country
""".format(merged_lens, dataset, distribution_str, minus_str)
# print query
Qr.display_result(query=query, spacing=50, limit=50, is_activated=True)