https://query.wikidata.org/sparql
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel
Comment écrire une requête SPARQL ?
{{#sparql:PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel
| endpoint = https://query.wikidata.org/sparql
| chart=bordercloud.visualization.DataTable
| options=
| log=2
}}
Comment installer LinkedWiki dans mon wiki ?
Comment insérer ce graphique dans mon wiki ?
Tester ce script dans un nouvel onglet.
<html>
<head>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.4.1/jquery.min.js" async></script>
</head>
<body onload="testQuery();">
<script>
function testQuery(){
var endpoint = "https://query.wikidata.org/sparql";
var query = `PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won\'t help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language \"[AUTO_LANGUAGE],en\" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel`;
// $('#bodyContentResearch').append(queryDataset);
$.ajax({
url: endpoint,
dataType: 'json',
data: {
queryLn: 'SPARQL',
query: query ,
limit: 'none',
infer: 'true',
Accept: 'application/sparql-results+json'
},
success: displayResult,
error: displayError
});
}
function displayError(xhr, textStatus, errorThrown) {
console.log(textStatus);
console.log(errorThrown);
}
function displayResult(data) {
$.each(data.results.bindings, function(index, bs) {
console.log(bs);
$("body").append(JSON.stringify(bs) + "<hr/>");
});
}
</script>
</body>
</html>
Tester ce script dans un nouvel onglet.
<html>
<head>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.4.1/jquery.min.js" async></script>
</head>
<body onload="testQuery();">
<script>
function testQuery(){
var url = new URL("https://query.wikidata.org/sparql");
var params = {query:`PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won\'t help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language \"[AUTO_LANGUAGE],en\" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel`};
url.search = new URLSearchParams(params).toString();
var myHeaders = new Headers();
myHeaders.append("Accept", "application/sparql-results+json");
var requestOptions = {
method: 'GET',
headers: myHeaders,
redirect: 'follow'
};
fetch(url, requestOptions)
.then(response => response.json())
.then(result => displayResult(result))
.catch(error => displayError(error));
}
function displayError(error) {
console.log(error);
}
function displayResult(data) {
data.results.bindings.forEach(bs => {
console.log(bs);
$("body").append(JSON.stringify(bs) + "<hr/>");
});
}
</script>
</body>
</html>
Tester ce script dans un nouvel onglet (attention, plusieurs graphiques nécessitent une clé API).
Comment insérer ce graphique dans ma page HTML ?
<html>
<head>
<link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css" integrity="sha384-ggOyR0iXCbMQv3Xipma34MD+dH/1fQ784/j6cY/iJTQUOhcWr7x9JvoRxT2MZw1T" crossorigin="anonymous">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.9.0/css/all.min.css">
<script
src="https://code.jquery.com/jquery-3.4.1.min.js"
integrity="sha256-CSXorXvZcTkaix6Yvo6HppcZGetbYMGWSFlBw8HfCJo="
crossorigin="anonymous"> </script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.7/umd/popper.min.js" integrity="sha384-UO2eT0CpHqdSJQ6hJty5KVphtPhzWj9WO1clHTMGa3JDZwrnQq4sF86dIHNDz0W1" crossorigin="anonymous"> </script>
<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/js/bootstrap.min.js" integrity="sha384-JjSmVgyd0p3pXB1rRibZUAYoIIy6OrQ6VrjIEaFf/nJGzIxFDsf4x0xIM+B07jRM" crossorigin="anonymous"> </script>
<script type="text/javascript" src="https://bordercloud.github.io/sgvizler2/sgvizler2/sgvizler2.js" defer> </script>
<script type="text/javascript" src="https://linkedwiki.com/js/initExampleHTML.js" defer > </script>
</head>
<body style="margin:0;">
<div id="sgvzl_example_query"
data-sgvizler-endpoint="https://query.wikidata.org/sparql"
data-sgvizler-query="PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel"
data-sgvizler-chart='bordercloud.visualization.DataTable'
data-sgvizler-chart-options=''
data-sgvizler-endpoint_output_format='json'
data-sgvizler-log='2'
style='width:100%; height:auto;'
lang='fr'
/>
<script>
/*$(function() {
sgvizler2.containerDrawAll({
// Google Api key
googleApiKey : "GOOGLE_MAP_API_KEY",
// OpenStreetMap Access Token
// https://www.mapbox.com/api-documentation/#access-tokens
osmAccessToken : "OSM_MAP_API_KEY"
});
});*/
</script>
</body>
</html>
from SPARQLWrapper import SPARQLWrapper, JSON
sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
sparql.setQuery("""
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
print(result)
#print(result["label"]["value"])
Howto use SPARQL with Python ?
library(SPARQL) # SPARQL querying package
library(ggplot2)
# Step 1 - Set up preliminaries and define query
# Define the data.gov endpoint
endpoint <- "https://query.wikidata.org/sparql"
# create query statement
query <- "PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel"
# Step 2 - Use SPARQL package to submit query and save results to a data frame
qd <- SPARQL(endpoint,query,curl_args=list(useragent=R.version.string))
df <- qd$results
SPARQL with R in less than 5 minutes
#!/usr/bin/env ruby
#
# Install sparql for Ruby
# gem update --system
# gem install sparql
#
require 'sparql/client'
endpoint = "https://query.wikidata.org/sparql"
sparql = <<-EOT
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel
EOT
#For Wikidata, the method get is required
#For other SPARQL endpoints, the method post is prefered
client = SPARQL::Client.new(endpoint, :method => :get)
rows = client.query(sparql)
puts "Number of rows: #{rows.size}"
for row in rows
for key,val in row do
# print "#{key.to_s.ljust(10)}: #{val}\t"
print "#{key}: #{val}\t"
end
print "\n"
end
Doc Ruby for SPARQL 1.1
endpoint = 'https://query.wikidata.org/sparql';
query = ['PREFIX bd: <http://www.bigdata.com/rdf#> '...
'PREFIX p: <http://www.wikidata.org/prop/> '...
'PREFIX pq: <http://www.wikidata.org/prop/qualifier/> '...
'PREFIX ps: <http://www.wikidata.org/prop/statement/> '...
'PREFIX wd: <http://www.wikidata.org/entity/> '...
'PREFIX wdt: <http://www.wikidata.org/prop/direct/> '...
'PREFIX wikibase: <http://wikiba.se/ontology#> '...
' '...
'#defaultView:BarChart '...
'# male/female population _must_ not be added unqualified as total population (!) '...
'# this is an error and should be fixed at the item using P1540 and P1539 instead '...
'# (wrong query result may be a manifestation of such) '...
'SELECT ?year (AVG(?pop) AS ?population) ?countryLabel '...
' (COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen) '...
'WHERE '...
'{ '...
' ?country wdt:P31 wd:Q6256; '...
' p:P1082 ?popStatement . '...
' ?popStatement ps:P1082 ?pop; '...
' pq:P585 ?date . '...
' BIND(STR(YEAR(?date)) AS ?year) '...
' '...
' # IF multiple ?pop values per country per year exist, we prioritize by source '...
' # census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last '...
' # note wikibaserank won't help here each year may have multiple statements for ?pop value '...
' # rankprefered is used for the best value (or values) of the latest or current year '...
' # ranknormal may be justified for all of multiple ?pop values for a given year '...
' OPTIONAL { ?popStatement pq:P459 ?method. } '...
' OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ]. '...
' FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). } '...
' OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ]. '...
' FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). } '...
' OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ]. '...
' FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). } '...
' BIND(COALESCE( '...
' IF(BOUND(?census), ?census, 1/0), '...
' IF(BOUND(?other), ?other, 1/0), '...
' IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method). '...
' FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true)) '...
' # .. still need to group if multiple values per country per year exist and '...
' # - none is qualified with P459 '...
' # - multiple ?estimate or multiple ?census (>1 value from same source) '...
' # - ?other yields more than one source (>1 values are better than optionally '...
' # supplied estimate, but no census source available) '...
' '...
' SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" } '...
'} '...
'GROUP BY ?year ?countryLabel '...
'ORDER BY ?year ?countryLabel '];
url_head = strcat(endpoint,'?query=');
url_query = urlencode(query);
format = 'text/tab-separated-values';
url_tail = strcat('&format=', format);
url = strcat(url_head, url_query, url_tail);
% get the data from the endpoint
query_results = urlread(url);
% write the data to a file so that tdfread can parse it
fid = fopen('query_results.txt','w');
if fid>=0
fprintf(fid, '%s\n', query_results)
fclose(fid)
end
% this reads the tsv file into a struct
sparql_data = tdfread('query_results.txt')
Project Github MatlabSPARQL
<?php
require __DIR__ . '/../vendor/autoload.php';
use BorderCloud\SPARQL\SparqlClient;
$endpoint ="https://query.wikidata.org/sparql";
$sp_readonly = new SparqlClient();
$sp_readonly->setEndpointRead($endpoint);
$q = <<<EOD
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#defaultView:BarChart
# male/female population _must_ not be added unqualified as total population (!)
# this is an error and should be fixed at the item using P1540 and P1539 instead
# (wrong query result may be a manifestation of such)
SELECT ?year (AVG(?pop) AS ?population) ?countryLabel
(COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen)
WHERE
{
?country wdt:P31 wd:Q6256;
p:P1082 ?popStatement .
?popStatement ps:P1082 ?pop;
pq:P585 ?date .
BIND(STR(YEAR(?date)) AS ?year)
# IF multiple ?pop values per country per year exist, we prioritize by source
# census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last
# note wikibaserank won't help here each year may have multiple statements for ?pop value
# rankprefered is used for the best value (or values) of the latest or current year
# ranknormal may be justified for all of multiple ?pop values for a given year
OPTIONAL { ?popStatement pq:P459 ?method. }
OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ].
FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ].
FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). }
OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ].
FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). }
BIND(COALESCE(
IF(BOUND(?census), ?census, 1/0),
IF(BOUND(?other), ?other, 1/0),
IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method).
FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true))
# .. still need to group if multiple values per country per year exist and
# - none is qualified with P459
# - multiple ?estimate or multiple ?census (>1 value from same source)
# - ?other yields more than one source (>1 values are better than optionally
# supplied estimate, but no census source available)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" }
}
GROUP BY ?year ?countryLabel
ORDER BY ?year ?countryLabel
EOD;
$rows = $sp_readonly->query($q, 'rows');
$err = $sp_readonly->getErrors();
if ($err) {
print_r($err);
throw new Exception(print_r($err, true));
}
foreach ($rows["result"]["variables"] as $variable) {
printf("%-20.20s",$variable);
echo '|';
}
echo "\n";
foreach ($rows["result"]["rows"] as $row) {
foreach ($rows["result"]["variables"] as $variable) {
printf("%-20.20s", $row[$variable]);
echo '|';
}
echo "\n";
}
?>
Project Github BorderCloud/SPARQL
import com.bordercloud.sparql.*;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.HashMap;
public class Main {
public static void main(String[] args) {
try {
URI endpoint = new URI("https://query.wikidata.org/sparql");
String querySelect = "PREFIX bd: <http://www.bigdata.com/rdf#> \n"
+ "PREFIX p: <http://www.wikidata.org/prop/> \n"
+ "PREFIX pq: <http://www.wikidata.org/prop/qualifier/> \n"
+ "PREFIX ps: <http://www.wikidata.org/prop/statement/> \n"
+ "PREFIX wd: <http://www.wikidata.org/entity/> \n"
+ "PREFIX wdt: <http://www.wikidata.org/prop/direct/> \n"
+ "PREFIX wikibase: <http://wikiba.se/ontology#> \n"
+ " \n"
+ "#defaultView:BarChart \n"
+ "# male/female population _must_ not be added unqualified as total population (!) \n"
+ "# this is an error and should be fixed at the item using P1540 and P1539 instead \n"
+ "# (wrong query result may be a manifestation of such) \n"
+ "SELECT ?year (AVG(?pop) AS ?population) ?countryLabel \n"
+ " (COUNT(*) AS ?number_of_chosen_sources) (SAMPLE(?method) AS ?a_source_of_those_chosen) \n"
+ "WHERE \n"
+ "{ \n"
+ " ?country wdt:P31 wd:Q6256; \n"
+ " p:P1082 ?popStatement . \n"
+ " ?popStatement ps:P1082 ?pop; \n"
+ " pq:P585 ?date . \n"
+ " BIND(STR(YEAR(?date)) AS ?year) \n"
+ " \n"
+ " # IF multiple ?pop values per country per year exist, we prioritize by source \n"
+ " # census 1st, others 2nd, estimation(s) 3rd, unknown sources (none supplies P459) last \n"
+ " # note wikibaserank won\'t help here each year may have multiple statements for ?pop value \n"
+ " # rankprefered is used for the best value (or values) of the latest or current year \n"
+ " # ranknormal may be justified for all of multiple ?pop values for a given year \n"
+ " OPTIONAL { ?popStatement pq:P459 ?method. } \n"
+ " OPTIONAL { ?country p:P1082 [ pq:P585 ?d; pq:P459 ?estimate ]. \n"
+ " FILTER(STR(YEAR(?d)) = ?year). FILTER(?estimate = wd:Q791801). } \n"
+ " OPTIONAL { ?country p:P1082 [ pq:P585 ?e; pq:P459 ?census ]. \n"
+ " FILTER(STR(YEAR(?e)) = ?year). FILTER(?census = wd:Q39825). } \n"
+ " OPTIONAL { ?country p:P1082 [ pq:P585 ?f; pq:P459 ?other ]. \n"
+ " FILTER(STR(YEAR(?f)) = ?year). FILTER(?other != wd:Q39825 && ?other != wd:Q791801). } \n"
+ " BIND(COALESCE( \n"
+ " IF(BOUND(?census), ?census, 1/0), \n"
+ " IF(BOUND(?other), ?other, 1/0), \n"
+ " IF(BOUND(?estimate), ?estimate, 1/0) ) AS ?pref_method). \n"
+ " FILTER(IF(BOUND(?pref_method),?method = ?pref_method,true)) \n"
+ " # .. still need to group if multiple values per country per year exist and \n"
+ " # - none is qualified with P459 \n"
+ " # - multiple ?estimate or multiple ?census (>1 value from same source) \n"
+ " # - ?other yields more than one source (>1 values are better than optionally \n"
+ " # supplied estimate, but no census source available) \n"
+ " \n"
+ " SERVICE wikibase:label { bd:serviceParam wikibase:language \"[AUTO_LANGUAGE],en\" } \n"
+ "} \n"
+ "GROUP BY ?year ?countryLabel \n"
+ "ORDER BY ?year ?countryLabel \n";
SparqlClient sc = new SparqlClient(false);
sc.setEndpointRead(endpoint);
SparqlResult sr = sc.query(querySelect);
//sc.printLastQueryAndResult();
printResult(sr.getModel(),30);
} catch (URISyntaxException | SparqlClientException e) {
System.out.println(e);
e.printStackTrace();
}
}
public static void printResult(SparqlResultModel rs , int size) {
for (String variable : rs.getVariables()) {
System.out.print(String.format("%-"+size+"."+size+"s", variable ) + " | ");
}
System.out.print("\n");
for (HashMap row : rs.getRows()) {
for (String variable : rs.getVariables()) {
System.out.print(String.format("%-"+size+"."+size+"s", row.get(variable)) + " | ");
}
System.out.print("\n");
}
}
}
For example, with Gradle :
apply plugin: 'java'
apply plugin: 'application'
// This comes out to package + '.' + mainClassName
mainClassName = 'Main'
group 'org.example'
version '1.0-SNAPSHOT'
repositories {
mavenCentral()
}
dependencies {
compile "com.bordercloud:SPARQL-JAVA:[1.0,)"
}
Project Github BorderCloud/SPARQL-JAVA
Other SPARQL client :
RDF4J