SPARQL query: Who discovered the most asteroids?

Karima Rafes

Who discovered the most asteroids?

Sample query

Reuse these data in your code

Query, endpoint and code for reusing the same data

Endpoint:

https://query.wikidata.org/sparql

Query:

PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20

Howto write a query SPARQL? (in French)

{{#sparql:PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20
| endpoint = https://query.wikidata.org/sparql
| chart=bordercloud.visualization.DataTable
| options=
| log=2
}}

Howto install LinkedWiki in my wiki? Howto insert this graph in my wiki?

Test this script in a new tab.

<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 rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language \"[AUTO_LANGUAGE],en\" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20`;

   // $('#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>

Test this script in a new tab.

<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 rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language \"[AUTO_LANGUAGE],en\" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20`};

    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>

Test this script in a new tab (Careful, several charts need a API key).
Howto insert this graph in my html page?

<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: &lt;http://www.bigdata.com/rdf#&gt;
PREFIX rdfs: &lt;http://www.w3.org/2000/01/rdf-schema#&gt;
PREFIX wd: &lt;http://www.wikidata.org/entity/&gt;
PREFIX wdt: &lt;http://www.wikidata.org/prop/direct/&gt;
PREFIX wikibase: &lt;http://wikiba.se/ontology#&gt;
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language &quot;[AUTO_LANGUAGE],en&quot; .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20"
    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='en'
   />

<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 rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20""")
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 rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20"
# 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 rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20
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 rdfs: <http://www.w3.org/2000/01/rdf-schema#> '...
'PREFIX wd: <http://www.wikidata.org/entity/> '...
'PREFIX wdt: <http://www.wikidata.org/prop/direct/> '...
'PREFIX wikibase: <http://wikiba.se/ontology#> '...
'#added before 2016-10 '...
'SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count) '...
'WHERE '...
'{ '...
'	?asteroid wdt:P31 wd:Q3863 . '...
'	?asteroid wdt:P61 ?discoverer . '...
'	SERVICE wikibase:label { '...
'		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . '...
'		?discoverer rdfs:label ?name '...
'	} '...
'} '...
'GROUP BY ?discoverer ?name '...
'ORDER BY DESC(?count) '...
'LIMIT 20 '];

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 rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
#added before 2016-10
SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count)
WHERE
{
	?asteroid wdt:P31 wd:Q3863 .
	?asteroid wdt:P61 ?discoverer .
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
		?discoverer rdfs:label ?name
	}
}
GROUP BY ?discoverer ?name
ORDER BY DESC(?count)
LIMIT 20
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 rdfs: <http://www.w3.org/2000/01/rdf-schema#> \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"
                    + "#added before 2016-10 \n"
                    + "SELECT ?discoverer ?name (COUNT(?asteroid) AS ?count) \n"
                    + "WHERE \n"
                    + "{ \n"
                    + "	?asteroid wdt:P31 wd:Q3863 . \n"
                    + "	?asteroid wdt:P61 ?discoverer . \n"
                    + "	SERVICE wikibase:label { \n"
                    + "		bd:serviceParam wikibase:language \"[AUTO_LANGUAGE],en\" . \n"
                    + "		?discoverer rdfs:label ?name \n"
                    + "	} \n"
                    + "} \n"
                    + "GROUP BY ?discoverer ?name \n"
                    + "ORDER BY DESC(?count) \n"
                    + "LIMIT 20 \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

You can use the SPARQL clients in Java : BorderCloud/SPARQL-JAVA or RDF4J

Table view

Simple view on the data

Reuse these data in your code

Query, endpoint and code for reusing the same data