Feedback

Creating synergies and interactions among the analysts and the “producers” of data. See details.

Reuse these data in your code

Query, endpoint and code for reusing the same data
https://query.wikidata.org/sparql
PREFIX bd: <http://www.bigdata.com/rdf#> 
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

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" }
}
ORDER BY DESC(?companiesPerM)
Howto write a query SPARQL? (in French)
{{#sparql:PREFIX bd: <http://www.bigdata.com/rdf#> 
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

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" }
}
ORDER BY DESC(?companiesPerM)
| 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#> \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\
\n\
# German states, ordered by the number of company headquarters per million inhabitants\n\
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)\n\
# Nested queries for correctness (don\'t count companies twice) and performance (aggregate before adding more data)\n\
# Limits states without population missing; company data in Wikidata is always incomplete\n\
# Note This query shows some not-so-easy nesting of DISTINCT (don\'t count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.\n\
SELECT\n\
	?state ?stateLabel\n\
	?companies\n\
	?population\n\
	(?companies/?population*1000000 AS ?companiesPerM)\n\
WHERE\n\
{\n\
	{ SELECT ?state (count(*) as ?companies) WHERE {\n\
		{SELECT DISTINCT ?company ?state WHERE {\n\
			?state wdt:P31 wd:Q1221156 .\n\
			?company wdt:P31/wdt:P279* wd:Q4830453 .\n\
			?company wdt:P159/wdt:P131* ?state .\n\
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don\'t count dissolved companies\n\
		} }\n\
	} GROUP BY ?state  }\n\
    ?state wdt:P1082 ?population\n\
	SERVICE wikibase:label { bd:serviceParam wikibase:language \"de\" }\n\
}\n\
ORDER BY DESC(?companiesPerM)"

   // $('#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 (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://io.datascience-paris-saclay.fr/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 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

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don&#039;t count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don&#039;t count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don&#039;t count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language &quot;de&quot; }
}
ORDER BY DESC(?companiesPerM)"
    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;'  />

<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 wd: <http://www.wikidata.org/entity/> 
PREFIX wdt: <http://www.wikidata.org/prop/direct/> 
PREFIX wikibase: <http://wikiba.se/ontology#> 
#added before 2016-10

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" }
}
ORDER BY DESC(?companiesPerM)""")
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 wd: <http://www.wikidata.org/entity/> 
PREFIX wdt: <http://www.wikidata.org/prop/direct/> 
PREFIX wikibase: <http://wikiba.se/ontology#> 
#added before 2016-10

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" }
}
ORDER BY DESC(?companiesPerM)"
# Step 2 - Use SPARQL package to submit query and save results to a data frame
qd <- SPARQL(endpoint,query)
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 wd: <http://www.wikidata.org/entity/> 
PREFIX wdt: <http://www.wikidata.org/prop/direct/> 
PREFIX wikibase: <http://wikiba.se/ontology#> 
#added before 2016-10

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" }
}
ORDER BY DESC(?companiesPerM)
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 wd: <http://www.wikidata.org/entity/>  '...
'PREFIX wdt: <http://www.wikidata.org/prop/direct/>  '...
'PREFIX wikibase: <http://wikiba.se/ontology#>  '...
'#added before 2016-10 '...
' '...
'# German states, ordered by the number of company headquarters per million inhabitants '...
'# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country) '...
'# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data) '...
'# Limits states without population missing; company data in Wikidata is always incomplete '...
'# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified. '...
'SELECT '...
'	?state ?stateLabel '...
'	?companies '...
'	?population '...
'	(?companies/?population*1000000 AS ?companiesPerM) '...
'WHERE '...
'{ '...
'	{ SELECT ?state (count(*) as ?companies) WHERE { '...
'		{SELECT DISTINCT ?company ?state WHERE { '...
'			?state wdt:P31 wd:Q1221156 . '...
'			?company wdt:P31/wdt:P279* wd:Q4830453 . '...
'			?company wdt:P159/wdt:P131* ?state . '...
'			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies '...
'		} } '...
'	} GROUP BY ?state  } '...
'    ?state wdt:P1082 ?population '...
'	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" } '...
'} '...
'ORDER BY DESC(?companiesPerM) '];

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 wd: <http://www.wikidata.org/entity/> 
PREFIX wdt: <http://www.wikidata.org/prop/direct/> 
PREFIX wikibase: <http://wikiba.se/ontology#> 
#added before 2016-10

# German states, ordered by the number of company headquarters per million inhabitants
# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country)
# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data)
# Limits states without population missing; company data in Wikidata is always incomplete
# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified.
SELECT
	?state ?stateLabel
	?companies
	?population
	(?companies/?population*1000000 AS ?companiesPerM)
WHERE
{
	{ SELECT ?state (count(*) as ?companies) WHERE {
		{SELECT DISTINCT ?company ?state WHERE {
			?state wdt:P31 wd:Q1221156 .
			?company wdt:P31/wdt:P279* wd:Q4830453 .
			?company wdt:P159/wdt:P131* ?state .
			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies
		} }
	} GROUP BY ?state  }
    ?state wdt:P1082 ?population
	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" }
}
ORDER BY DESC(?companiesPerM)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.Endpoint;
import java.util.ArrayList;
import java.util.HashMap;

public class Main {

    public static void main(String[] args) {
        try {
            Endpoint sp = new Endpoint("https://query.wikidata.org/sparql";, false);

            String querySelect = 'PREFIX bd: <http://www.bigdata.com/rdf#>  \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'
                    + ' \n'
                    + '# German states, ordered by the number of company headquarters per million inhabitants \n'
                    + '# Replace wd:Q1221156 (state of Germany) by anything else you care about, e.g., wd:Q6256 (country) \n'
                    + '# Nested queries for correctness (don't count companies twice) and performance (aggregate before adding more data) \n'
                    + '# Limits states without population missing; company data in Wikidata is always incomplete \n'
                    + '# Note This query shows some not-so-easy nesting of DISTINCT (don't count any company twice) and aggregate, in combination with arithmetic output evaluation functions. It is a hard query that may time out if modified. \n'
                    + 'SELECT \n'
                    + '	?state ?stateLabel \n'
                    + '	?companies \n'
                    + '	?population \n'
                    + '	(?companies/?population*1000000 AS ?companiesPerM) \n'
                    + 'WHERE \n'
                    + '{ \n'
                    + '	{ SELECT ?state (count(*) as ?companies) WHERE { \n'
                    + '		{SELECT DISTINCT ?company ?state WHERE { \n'
                    + '			?state wdt:P31 wd:Q1221156 . \n'
                    + '			?company wdt:P31/wdt:P279* wd:Q4830453 . \n'
                    + '			?company wdt:P159/wdt:P131* ?state . \n'
                    + '			FILTER NOT EXISTS{ ?company wdt:P576 ?date } # don't count dissolved companies \n'
                    + '		} } \n'
                    + '	} GROUP BY ?state  } \n'
                    + '    ?state wdt:P1082 ?population \n'
                    + '	SERVICE wikibase:label { bd:serviceParam wikibase:language "de" } \n'
                    + '} \n'
                    + 'ORDER BY DESC(?companiesPerM) \n';

            HashMap rs = sp.query(querySelect);
            printResult(rs,30);

        }catch(EndpointException eex) {
            System.out.println(eex);
            eex.printStackTrace();
        }
    }

    public static void printResult(HashMap rs , int size) {

      for (String variable : (ArrayList) rs.get("result").get("variables")) {
        System.out.print(String.format("%-"+size+"."+size+"s", variable ) + " | ");
      }
      System.out.print("\n");
      for (HashMap value : (ArrayList>) rs.get("result").get("rows")) {
        //System.out.print(value);
        /* for (String key : value.keySet()) {
         System.out.println(value.get(key));
         }*/
        for (String variable : (ArrayList) rs.get("result").get("variables")) {
          //System.out.println(value.get(variable));
          System.out.print(String.format("%-"+size+"."+size+"s", value.get(variable)) + " | ");
        }
        System.out.print("\n");
      }
    }
}
Project Github BorderCloud/SPARQL-JAVA
Very soon !
TODO