def prop_has_range_or_comment(prop_value):
'''
Function to check whether the property has 'range' or 'comment' attribute associated with it.
'''
# return (0, 0)
has_comment = 0
has_range = 0
prop = prop_value['prop']
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select distinct ?prop ?value where {
<""" + prop + """> ?prop ?value }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
prop = result["prop"]["value"]
if "range" in prop:
has_range = 1
if "comment" in prop:
has_comment = 1
return (has_range, has_comment)
def taller4_parte3(request):
numero3 = 79
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?lat
WHERE { <http://dbpedia.org/resource/Colombia> geo:lat ?lat }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
a = 2
#print (result["lat"]["value"]).decode(string)
lat = (result["lat"]["value"])
print lat
#Trae los valores de longitud
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?long
WHERE { <http://dbpedia.org/resource/Colombia> geo:long ?long }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
a = 2
#print (result["long"]["value"])
longit = (result["long"]["value"])
print longit
return render(request, "taller4_parte3.html", {
"longit": longit,
"lat": lat
})
def prop_has_range_or_comment(prop_value):
'''
Function to check whether the property has 'range' or 'comment' attribute associated with it.
'''
# return (0, 0)
has_comment = 0
has_range = 0
prop = prop_value['prop']
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select distinct ?prop ?value where {
<""" + prop + """> ?prop ?value }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
prop = result["prop"]["value"]
if "range" in prop:
has_range = 1
if "comment" in prop:
has_comment = 1
return (has_range, has_comment)
def total_one_degree_paths(res1, res2):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select count(distinct ?var3) as ?cnt where
{
{
SELECT distinct ?var3
WHERE {
<http://dbpedia.org/resource/""" + res1 + """> ?prop1 ?var3 .
<""" + res2 + """> ?pr ?var3.
}
}
UNION
{
SELECT distinct ?var3
WHERE {
<http://dbpedia.org/resource/""" + res1 + """> ?prop1 ?var3 .
?var3 ?prop <""" + res2 + """> .
}
}
}
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
return result["cnt"]["value"]
def get_distractors(resource, resource_type):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select ?similar (count(?p) as ?similarity) where {
values ?res {<http://dbpedia.org/resource/""" + resource + """>}
?similar ?p ?o ; a <""" + resource_type + """> .
?res ?p ?o .
}
group by ?similar ?res
having (count(?p) > 1)
order by desc(?similarity)
LIMIT 30
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
del similar_resources[:]
for result in results["results"]["bindings"]:
res = result["similar"]["value"]
value = result["similarity"]["value"]
similar_resources.append([res, int(value), 0, 0])
def get_distractors(resource, resource_type):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select ?similar (count(?p) as ?similarity) where {
values ?res {<http://dbpedia.org/resource/""" + resource + """>}
?similar ?p ?o ; a <""" + resource_type + """> .
?res ?p ?o .
}
group by ?similar ?res
having (count(?p) > 1)
order by desc(?similarity)
LIMIT 30
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
del similar_resources[:]
for result in results["results"]["bindings"]:
res = result["similar"]["value"]
value = result["similarity"]["value"]
similar_resources.append([res, int(value), 0, 0])
def total_one_degree_paths(res1, res2):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select count(distinct ?var3) as ?cnt where
{
{
SELECT distinct ?var3
WHERE {
<http://dbpedia.org/resource/""" + res1 + """> ?prop1 ?var3 .
<""" + res2 + """> ?pr ?var3.
}
}
UNION
{
SELECT distinct ?var3
WHERE {
<http://dbpedia.org/resource/""" + res1 + """> ?prop1 ?var3 .
?var3 ?prop <""" + res2 + """> .
}
}
}
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
return result["cnt"]["value"]
def get_results(endpoint_url, query):
user_agent = "WDQS-example Python/%s.%s" % (sys.version_info[0],
sys.version_info[1])
# TODO adjust user agent; see https://w.wiki/CX6
sparql = SPARQLWrapper(endpoint_url, agent=user_agent)
sparql.setQuery(query)
sparql.setReturnFormat(JSON)
return sparql.query().convert()
def query_wikidata_service(searchterm, language_code):
query = """SELECT ?item ?itemLabel ?subclass_of ?subclass_ofLabel ?category_of ?category_ofLabel
?instance_of ?instance_ofLabel WHERE { SERVICE wikibase:mwapi { bd:serviceParam wikibase:api "EntitySearch" .
bd:serviceParam wikibase:endpoint "www.wikidata.org" . bd:serviceParam mwapi:search '""" + searchterm + """' .
bd:serviceParam mwapi:language '""" + language_code + """' . bd:serviceParam wikibase:limit 1 .
?item wikibase:apiOutputItem mwapi:item .} SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
OPTIONAL { ?item (wdt:P279) ?subclass_of.} OPTIONAL { ?item (wdt:P910) ?category_of.}
OPTIONAL { ?item (wdt:P31) ?instance_of.}}"""
url = 'https://query.wikidata.org/sparql'
sparql = SPARQLWrapper(url)
sparql.setQuery(query)
sparql.setReturnFormat(JSON)
return sparql.query().convert()
def get_similar_resources(resource):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select distinct ?prop ?value
where {
<http://dbpedia.org/resource/""" + resource + """> ?prop ?value }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
resource_type = get_resource_type(results)
get_distractors(resource, resource_type)
# Alchemy API Part starts
abstract = get_abstract(results)
concepts = alchemy_concepts(abstract)
for concept in concepts:
for res in similar_resources:
if concept[0] == res[0]:
res[2] = concept[1]
for res in similar_resources:
res[3] = int(total_one_degree_paths(resource, res[0]))
similar_resources.sort(key=lambda x: (-x[2], -x[1], -x[3]))
# Alchemy API part ends
tot_val = len(similar_resources)
tot = '"total": "' + str(tot_val) + '", '
ans = '{' + tot + ' "error": "0" , "resources": ['
res = ""
i = 1
for x in similar_resources:
res += """
{
"rank": \"""" + str(i) + """\",
"dbpedia": \"""" + x[0] + """\",
"similarity": \"""" + str(x[1]) + """\",
"alchemy": \"""" + str(x[2]) + """\",
"paths": \"""" + str(x[3]) + """\"
},"""
i += 1
ans += res
ans = ans[0:-1]
ans += ']}'
json_obj = json.loads(ans, strict=False)
ans = json.dumps(json_obj, indent=4)
print ans
def get_similar_resources(resource):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select distinct ?prop ?value
where {
<http://dbpedia.org/resource/""" + resource + """> ?prop ?value }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
resource_type = get_resource_type(results)
get_distractors(resource, resource_type)
# Alchemy API Part starts
abstract = get_abstract(results)
concepts = alchemy_concepts(abstract)
for concept in concepts:
for res in similar_resources:
if concept[0] == res[0]:
res[2] = concept[1]
for res in similar_resources:
res[3] = int(total_one_degree_paths(resource, res[0]))
similar_resources.sort(key=lambda x: (-x[2], -x[1], -x[3]))
# Alchemy API part ends
tot_val = len(similar_resources)
tot = '"total": "' + str(tot_val) + '", '
ans = '{' + tot + ' "error": "0" , "resources": ['
res = ""
i = 1
for x in similar_resources:
res += """
{
"rank": \"""" + str(i) + """\",
"dbpedia": \"""" + x[0] + """\",
"similarity": \"""" + str(x[1]) + """\",
"alchemy": \"""" + str(x[2]) + """\",
"paths": \"""" + str(x[3]) + """\"
},"""
i += 1
ans += res
ans = ans[0:-1]
ans += ']}'
json_obj = json.loads(ans, strict=False)
ans = json.dumps(json_obj, indent=4)
print ans
def get_sparql_dataframe(service, query):
"""
Helper function to convert SPARQL results into a Pandas data frame.
"""
sparql = SPARQLWrapper(service)
sparql.setQuery(query)
sparql.setReturnFormat(JSON)
result = sparql.query()
processed_results = json.load(result.response)
cols = processed_results['head']['vars']
out = []
for row in processed_results['results']['bindings']:
item = []
for c in cols:
item.append(row.get(c, {}).get('value'))
out.append(item)
return pd.DataFrame(out, columns=cols)
def total_pages_for_type(resource_type):
'''
Function which returns the total number of resources belonging to given resource type.
'''
freq = 0
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
SELECT COUNT(DISTINCT ?entity)
WHERE { ?entity <http://dbpedia.org/ontology/wikiPageID> ?value.
?entity <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <""" + resource_type + """> }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
freq = int(result["callret-0"]["value"])
return freq
def total_pages_for_type(resource_type):
'''
Function which returns the total number of resources belonging to given resource type.
'''
freq = 0
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
SELECT COUNT(DISTINCT ?entity)
WHERE { ?entity <http://dbpedia.org/ontology/wikiPageID> ?value.
?entity <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <""" + resource_type + """> }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
freq = int(result["callret-0"]["value"])
return freq
def count_freq(resource_type, prop):
'''
Function which counts how many times has the property appeared w.r.t. the resource type.
'''
freq = 0
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
SELECT COUNT(DISTINCT ?entity)
WHERE { ?entity <""" + prop + """> ?value.
?entity <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <""" + resource_type + """> }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
freq = int(result["callret-0"]["value"])
return freq
def count_freq(resource_type, prop):
'''
Function which counts how many times has the property appeared w.r.t. the resource type.
'''
freq = 0
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
SELECT COUNT(DISTINCT ?entity)
WHERE { ?entity <""" + prop + """> ?value.
?entity <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <""" + resource_type + """> }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
freq = int(result["callret-0"]["value"])
return freq
#!/usr/bin/env python3
from SPARQLWrapper import *
import os
import os.path as path
import json
import glob
import time
#BaseUrl="http://buda1.bdrc.io:13180/fuseki/bdrcrw/"
BaseUrl="http://localhost:13180/fuseki/bdrcrw/"
QueryEndpoint = SPARQLWrapper(BaseUrl+"query")
QueryEndpoint.setRequestMethod(POSTDIRECTLY)
QueryEndpoint.setMethod(POST)
QueryEndpoint.setReturnFormat(JSON)
UpdateEndpoint = SPARQLWrapper(BaseUrl+"update")
UpdateEndpoint.setRequestMethod(POSTDIRECTLY)
UpdateEndpoint.setMethod(POST)
ThisPath = os.path.dirname(os.path.abspath(__file__))
def get_all_tests(testgroupname, specifictest=None):
grouppath = path.join(ThisPath, testgroupname)
res = []
if specifictest is not None:
res.append(path.join(grouppath, specifictest))
return res
for dirname in sorted(glob.glob(grouppath+"/*")):
if path.isdir(dirname):
res.append(dirname)
return res
sparql = SPARQLWrapper("http://mmisw.org/sparql")
queryString = """
PREFIX ioos: <http://mmisw.org/ont/ioos/parameter/>
SELECT DISTINCT ?parameter ?definition ?unit ?property ?value
WHERE {?parameter a ioos:Parameter .
?parameter ?property ?value .
?parameter ioos:Term ?term .
?parameter ioos:Definition ?definition .
?parameter ioos:Units ?unit .
FILTER (regex(str(?property), "(exactMatch|closeMatch)", "i") && regex(str(?value), "temperature", "i") )
}
ORDER BY ?parameter
"""
sparql.setQuery(queryString)
sparql.setReturnFormat(JSON)
j = sparql.query().convert()
j.keys()
j["head"]["vars"]
# In[64]:
j
dict = j
print j
# In[38]:
#!/usr/bin/env python3
from SPARQLWrapper import *
import os
import os.path as path
import json
import glob
import time
#BaseUrl="http://buda1.bdrc.io:13180/fuseki/bdrcrw/"
BaseUrl = "http://localhost:13180/fuseki/corerw/"
QueryEndpoint = SPARQLWrapper(BaseUrl + "query")
QueryEndpoint.setRequestMethod(POSTDIRECTLY)
QueryEndpoint.setMethod(POST)
QueryEndpoint.setReturnFormat(JSON)
UpdateEndpoint = SPARQLWrapper(BaseUrl + "update")
UpdateEndpoint.setRequestMethod(POSTDIRECTLY)
UpdateEndpoint.setMethod(POST)
ThisPath = os.path.dirname(os.path.abspath(__file__))
def get_all_tests(testgroupname, specifictest=None):
grouppath = path.join(ThisPath, testgroupname)
res = []
if specifictest is not None:
res.append(path.join(grouppath, specifictest))
return res
for dirname in sorted(glob.glob(grouppath + "/*")):
if path.isdir(dirname):
res.append(dirname)
?director foaf:name ?directorname.
?movies dbpedia2:genre ?theloaiphim.
?movies dbpedia2:distributor ?producer.
OPTIONAL{
?movies dbpedia2:award ?giaithuong;
dbpedia2:language ?ngonngu.
?director foaf:depiction ?anh.
}
FILTER(!isLiteral(?film_title) || langMatches(lang(?film_title), "EN"))
}
ORDER BY(?quocgia )
""")
sparql.setReturnFormat(XML)
results = sparql.query().convert()
#Print all statements in dataGraph
for stmt in results:
graph.add(stmt)
# Iterate over triples in store and print them out.
print("--- printing raw triples ---")
for s, p, o in graph:
print((s.encode("utf-8",
errors='replace'), p.encode("utf-8", errors='replace'),
o.encode("utf-8", errors='replace')))
# For each foaf:Person in the store print out its mbox property.
# Bind a few prefix, namespace pairs for more readable output
graph.bind("dc", DC)
graph.bind("foaf", FOAF)
?historian rdfs:label ?historian_label .
?historian wdt:P19 ?birthplace .
?birthplace rdfs:label ?birthplace_label .
FILTER (langMatches(lang(?birthplace_label), "EN"))
FILTER (langMatches(lang(?historian_label), "EN"))
}
"""
#wikidata_endpoint = "https://query.wikidata.org/" o questo?
# set the endpoint
sparql_wd = SPARQLWrapper(wikidata_endpoint)
# set the query
sparql_wd.setQuery(birthplace_query)
# set the returned format
sparql_wd.setReturnFormat(JSON)
# get the results
results = sparql_wd.query().convert()
for result in results["results"]["bindings"]:
historian_uri = result["historian"]["value"]
if "historian_label" in result:
historian_label = result["historian_label"]["value"]
print(historian_label + ":", historian_uri)
if "birthplace" in result:
birthplace = result["birthplace"]["value"]
if "birthplace_label" in result:
birthplace_label = result["birthplace_label"]["value"]
print("born in:", birthplace, birthplace_label)
#se ci stanno sia URI CHE LABEL DEL NOME nel grph
g.add((URIRef(historian_uri), URIRef(wdt.P19), URIRef(birthplace)))
g.add((URIRef(birthplace), RDFS.label, Literal(birthplace_label)))
from SPARQLWrapper import *
from owlready2 import *
import os
sparql_endpoint = "http://localhost:9999/bigdata/sparql"
query = '''
describe ?child ?superParent
where {
hint:Query hint:describeMode "CBD".
?child rdfs:subClassOf* ?super .
?super rdfs:subClassOf* ?superParent .
}
values ?super {<http://hadatac.org/ont/chear#ATIDU>}
'''
sparql_wrapper = SPARQLWrapper(sparql_endpoint)
sparql_wrapper.setQuery(query)
sparql_wrapper.setReturnFormat(RDF)
results = sparql_wrapper.query().convert()
results.serialize('output.owl', format="pretty-xml")
print("Writing results to a rdf-xml file")
def start(resource):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select distinct ?prop ?value
where {
<http://dbpedia.org/resource/""" + resource + """> ?prop ?value }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
resource_type = get_resource_type(results)
total_pages = total_pages_for_type(resource_type)
for result in results["results"]["bindings"]:
prop = result["prop"]["value"]
value = result["value"]["value"]
cleaned_property_label = get_label(prop)
if "ontology" not in prop and "property" not in prop and "subject" not in prop:
continue
prop_info = dict.fromkeys(parameter_list, 0)
prop_info['score'] = 0
prop_info['value'] = []
if "xml:lang" not in result["value"] or 'en' in result["value"]["xml:lang"]:
prop_value = {}
prop_value['prop'] = prop
prop_value['value'] = value
if prop in prop_val_count:
prop_val_count[prop] += 1
else:
normalized_label = cleaned_property_label.lower().replace(
' ', '')
if normalized_label in normalized_labels:
continue
normalized_labels.append(normalized_label)
prop_val_count[prop] = 1
if prop in ans_dict:
ans_dict[prop].setdefault('value', []).append(value)
continue
prop_info['label'] = cleaned_property_label
prop_info.setdefault('value', []).append(value)
prop_info['blacklisted'] = 0
'''
if prop_info['blacklisted']:
ans_dict[prop] = prop_info
continue
'''
google_autosuggest = google_autocomplete_ranker(
resource, cleaned_property_label)
prop_info['is_onto'] = is_onto(prop)
prop_info['special_char'] = doesnt_contain_special_chars(
cleaned_property_label)
prop_info['no_of_words'] = no_of_words(cleaned_property_label)
range_comment = prop_has_range_or_comment(prop_value)
prop_info['has_range'] = range_comment[0]
prop_info['has_comment'] = range_comment[1]
prop_info['value_relevant'] = value_relevant(prop_value)
prop_info['special_datatype'] = is_special_datatype(result)
prop_info['google_keypress'] = google_autosuggest[0]
prop_info['google_location'] = google_autosuggest[1]
prop_info['is_of_relation'] = 0
prop_info['frequency'] = count_freq(
resource_type, prop) / float(total_pages)
ans_dict[prop] = prop_info
#handle_is_of_relations(resource, resource_type, total_pages)
for prop, count in prop_val_count.iteritems():
ans_dict[prop]['total_values'] = (1.0 - 1.0 / count)
#score = raw_input("Enter score for: " + prop + " (from 1-5) \n")
ans_dict[prop]['score'] = 0
def handle_is_of_relations(resource, resource_type, total_pages):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select ?prop ?value where {
?value ?prop <http://dbpedia.org/resource/""" + resource + """> }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
prop = result["prop"]["value"]
value = result["value"]["value"]
cleaned_property_label = get_label(prop)
if blacklisted(cleaned_property_label):
continue
if "ontology" not in prop and "property" not in prop and "subject" not in prop:
continue
if prop in ans_dict:
ans_dict[prop].setdefault('value', []).append(value)
prop_val_count[prop] += 1
ans_dict[prop]['is_of_relation'] = 1
continue
prop_info = dict.fromkeys(parameter_list, 0)
prop_info['score'] = 0
prop_info['value'] = []
if "xml:lang" not in result["value"] or 'en' in result["value"]["xml:lang"]:
prop_value = {}
prop_value['prop'] = prop
prop_value['value'] = value
if prop in prop_val_count:
prop_val_count[prop] += 1
else:
prop_val_count[prop] = 1
cleaned_property_label = get_label(prop)
prop_info['label'] = cleaned_property_label
prop_info.setdefault('value', []).append(value)
prop_info['blacklisted'] = 0
'''
if prop_info['blacklisted']:
ans_dict[prop] = prop_info
continue
'''
google_autosuggest = google_autocomplete_ranker(
resource, cleaned_property_label)
prop_info['is_onto'] = is_onto(prop)
prop_info['special_char'] = doesnt_contain_special_chars(
cleaned_property_label)
prop_info['no_of_words'] = no_of_words(cleaned_property_label)
range_comment = prop_has_range_or_comment(prop_value)
prop_info['has_range'] = range_comment[0]
prop_info['has_comment'] = range_comment[1]
prop_info['value_relevant'] = value_relevant(prop_value)
prop_info['special_datatype'] = is_special_datatype(result)
prop_info['google_keypress'] = google_autosuggest[0]
prop_info['google_location'] = google_autosuggest[1]
prop_info['is_of_relation'] = 1
prop_info['frequency'] = count_freq(
resource_type, prop) / float(total_pages)
ans_dict[prop] = prop_info
def handle_is_of_relations(resource, resource_type, total_pages):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select ?prop ?value where {
?value ?prop <http://dbpedia.org/resource/""" + resource + """> }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
prop = result["prop"]["value"]
value = result["value"]["value"]
cleaned_property_label = get_label(prop)
if blacklisted(cleaned_property_label):
continue
if "ontology" not in prop and "property" not in prop and "subject" not in prop:
continue
if prop in ans_dict:
ans_dict[prop].setdefault('value', []).append(value)
prop_val_count[prop] += 1
ans_dict[prop]['is_of_relation'] = 1
continue
prop_info = dict.fromkeys(parameter_list, 0)
prop_info['score'] = 0
prop_info['value'] = []
if "xml:lang" not in result["value"] or 'en' in result["value"][
"xml:lang"]:
prop_value = {}
prop_value['prop'] = prop
prop_value['value'] = value
if prop in prop_val_count:
prop_val_count[prop] += 1
else:
prop_val_count[prop] = 1
cleaned_property_label = get_label(prop)
prop_info['label'] = cleaned_property_label
prop_info.setdefault('value', []).append(value)
prop_info['blacklisted'] = 0
'''
if prop_info['blacklisted']:
ans_dict[prop] = prop_info
continue
'''
google_autosuggest = google_autocomplete_ranker(
resource, cleaned_property_label)
prop_info['is_onto'] = is_onto(prop)
prop_info['special_char'] = doesnt_contain_special_chars(
cleaned_property_label)
prop_info['no_of_words'] = no_of_words(cleaned_property_label)
range_comment = prop_has_range_or_comment(prop_value)
prop_info['has_range'] = range_comment[0]
prop_info['has_comment'] = range_comment[1]
prop_info['value_relevant'] = value_relevant(prop_value)
prop_info['special_datatype'] = is_special_datatype(result)
prop_info['google_keypress'] = google_autosuggest[0]
prop_info['google_location'] = google_autosuggest[1]
prop_info['is_of_relation'] = 1
prop_info['frequency'] = count_freq(resource_type,
prop) / float(total_pages)
ans_dict[prop] = prop_info
PREFIX dbpedia:<http://dbpedia.org/resource>
PREFIX dbpedia-this: <http://dbpedia.org/ontology/>
select ?spouse ?spouseName where {
<http://dbpedia.org/resource/Napoleon> <http://dbpedia.org/ontology/spouse> ?spouse .
?spouse rdfs:label ?spouseName.
filter( langMatches(lang(?spouseName),"en") )
} limit 5""") # ...... .
'''
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?label
WHERE { <http://dbpedia.org/resource/Asturias> rdfs:label ?label }
""")
'''
print "spouse: ----------------------"
'''
#for row in sparql:
# print("%s knows %s" % row)
print '\n\n*** N3 Example'
sparql.setReturnFormat(N3)
results = sparql.query().convert()
print results
'''
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
#print results
for result in results["results"]["bindings"]:
#print result["spouse"]["value"]," ",get_name_from_uri(result["spouse"]["value"])
print result["spouse"]["value"], " ", result["spouseName"]["value"]
############### till here #########################
def start(resource):
sparql = SPARQLWrapper("http://dbpedia.org/sparql")
query1 = """
select distinct ?prop ?value
where {
<http://dbpedia.org/resource/""" + resource + """> ?prop ?value }
"""
sparql.setQuery(query1)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
resource_type = get_resource_type(results)
total_pages = total_pages_for_type(resource_type)
for result in results["results"]["bindings"]:
prop = result["prop"]["value"]
value = result["value"]["value"]
cleaned_property_label = get_label(prop)
if "ontology" not in prop and "property" not in prop and "subject" not in prop:
continue
prop_info = dict.fromkeys(parameter_list, 0)
prop_info['score'] = 0
prop_info['value'] = []
if "xml:lang" not in result["value"] or 'en' in result["value"][
"xml:lang"]:
prop_value = {}
prop_value['prop'] = prop
prop_value['value'] = value
if prop in prop_val_count:
prop_val_count[prop] += 1
else:
normalized_label = cleaned_property_label.lower().replace(
' ', '')
if normalized_label in normalized_labels:
continue
normalized_labels.append(normalized_label)
prop_val_count[prop] = 1
if prop in ans_dict:
ans_dict[prop].setdefault('value', []).append(value)
continue
prop_info['label'] = cleaned_property_label
prop_info.setdefault('value', []).append(value)
prop_info['blacklisted'] = 0
'''
if prop_info['blacklisted']:
ans_dict[prop] = prop_info
continue
'''
google_autosuggest = google_autocomplete_ranker(
resource, cleaned_property_label)
prop_info['is_onto'] = is_onto(prop)
prop_info['special_char'] = doesnt_contain_special_chars(
cleaned_property_label)
prop_info['no_of_words'] = no_of_words(cleaned_property_label)
range_comment = prop_has_range_or_comment(prop_value)
prop_info['has_range'] = range_comment[0]
prop_info['has_comment'] = range_comment[1]
prop_info['value_relevant'] = value_relevant(prop_value)
prop_info['special_datatype'] = is_special_datatype(result)
prop_info['google_keypress'] = google_autosuggest[0]
prop_info['google_location'] = google_autosuggest[1]
prop_info['is_of_relation'] = 0
prop_info['frequency'] = count_freq(resource_type,
prop) / float(total_pages)
ans_dict[prop] = prop_info
#handle_is_of_relations(resource, resource_type, total_pages)
for prop, count in prop_val_count.iteritems():
ans_dict[prop]['total_values'] = (1.0 - 1.0 / count)
#score = raw_input("Enter score for: " + prop + " (from 1-5) \n")
ans_dict[prop]['score'] = 0
?s a <http://dbpedia.org/ontology/SoccerPlayer>.
?s <http://www.w3.org/2000/01/rdf-schema#label> ?label .
?s <http://dbpedia.org/ontology/team> ?team.
?team <http://www.w3.org/2000/01/rdf-schema#label> ?teamlabel .
?s <http://dbpedia.org/ontology/birthPlace> ?birthPlace .
?birthPlace <http://www.w3.org/2000/01/rdf-schema#label> ?bpLabel.
?s <http://dbpedia.org/ontology/height> ?height .
?s <http://dbpedia.org/ontology/number> ?number .
FILTER(langMatches(lang(?label), "EN")) .
FILTER(langMatches(lang(?teamlabel), "EN")) .
FILTER(langMatches(lang(?bpLabel), "EN")) .
}
""")
try:
sparql.setReturnFormat('json')
ret = sparql.query()
soccerDict = ret.convert()
except ValueError as ve:
print(ve)
######################### making the table ####################3
auxDict = soccerDict["results"]["bindings"]
soccer = pd.DataFrame()
for columns in soccerDict["head"]["vars"]:
print(columns)
soccer[columns] = [out[columns]["value"] for out in auxDict]
auxArr = [
list(soccer[soccer.label == val].iloc[0]) for val in soccer.label.unique()
PREFIX dbpedia:<http://dbpedia.org/resource>
PREFIX dbpedia-this: <http://dbpedia.org/ontology/>
select ?spouse ?spouseName where {
<http://dbpedia.org/resource/Napoleon> <http://dbpedia.org/ontology/spouse> ?spouse .
?spouse rdfs:label ?spouseName.
filter( langMatches(lang(?spouseName),"en") )
} limit 5"""
) #filter( langMatches(lang(?spouseName),"en") ) ...... ?spouse rdfs:label ?spouseName .
print "spouse: ----------------------"
print " Output w/o format "
res = sparql.query()
print '\n\n*** N3 Example'
sparql.setReturnFormat(N3)
results = sparql.query().convert()
print results
print '\n\n*** JSON Example'
sparql.setReturnFormat(JSON)
res = sparql.query()
print res.print_results()
results = sparql.query().convert()
#print results
print "\nby using variables explicitly"
for result in results["results"]["bindings"]:
print result["spouse"]["value"], " ", result["spouseName"]["value"]
print '\n\n*** XML Example'
sparql.setReturnFormat(XML)
