Sparql query example added

teams/team3/create_rdf_test.py

@@ -0,0 +1,84 @@
+import csv
+
+prefixe_url_siren = "https://api.insee.fr/siret/"
+
+predicate_name = "rdfs:label"
+predicate_long = "sx:longitude"
+predicate_lat = "sx:latitude"
+predicate_purpose = "org:purpose"
+
+SIREN = "SIREN"
+NIC = "NIC"
+APEN = "APEN700"
+NOMEN_LONG = "NOMEN_LONG"
+LOGITUDE = "longitude"
+latitude = "latitude"
+prefix_siret = "https://api.insee.fr/entreprises/sirene/siret/"
+
+prefix_ape = "http://id.insee.fr/codes/nafr2/sousClasse/";
+
+def addChevrons( string ):
+   return "<" + string + ">"
+
+def create_line_string( predicate, object ):
+   return "\t" + predicate + " \"" + object.replace('"','')  + "\" ; \n"
+
+def create_line_url( predicate, object ):
+   return "\t" + predicate + addChevrons(object.replace('"',''))  + " ; \n"
+
+
+def create_point(siret, lat, long):
+    pointName = "%sPoint"%(siret)
+    point ="\tgeo:hasGeometry ex:%s .\n"%(pointName)
+    point += "ex:%s a sf:Point;\n"%(pointName)
+    point += "\tgeo:asWKT \"POINT(%s %s)\"^^geo:wktLiteral.\n"%(long, lat)
+    return point
+
+
+#with open('geo-sirene_rdf.ttl', 'w') as output:
+
+with open('geo-sirene_35_rdf.ttl', 'w', encoding="utf8") as output:
+#on écrit les prefixe
+    output.write("@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema> .\n")
+    output.write("@prefix  sx: <http://www.w3.org/2003/01/geo/wgs84_pos> .\n")
+    output.write("@prefix  xsd: <http://www.w3.org/2001/XMLSchema#> .\n")
+    output.write("@prefix  rdf:<https://www.w3.org/1999/02/22-rdf-syntax-ns> .\n")
+    output.write("@prefix  geo: <http://www.opengis.net/ont/geosparql#> .\n")
+    output.write("@prefix  ex: <http://www.example.org/POI#> .\n")
+    output.write("@prefix  sf: <http://www.opengis.net/ont/sf#> .\n")
+    output.write("@prefix  org: <http://www.w3.org/ns/org#> .\n")
+
+
+
+    #with open('geo_sirene.csv', 'r', encoding="utf8") as csvfile:
+    with open('geo-sirene_35.csv', 'r', encoding="utf8") as csvfile:
+        csvreader = csv.reader(csvfile, delimiter=',', quotechar='"')
+        # tableau de résultat
+
+        headers = next(csvreader)
+
+        indice_SIREN =  headers.index(SIREN)
+        indice_NIC =  headers.index(NIC)
+        indice_NOMEN_LONG =  headers.index(NOMEN_LONG)
+        indice_LOGITUDE =  headers.index(LOGITUDE)
+        indice_latitude =  headers.index(latitude)
+        indice_APEN =  headers.index(APEN)
+
+        i=0
+        for row in csvreader:
+            siret = row[indice_SIREN]+row[indice_NIC]
+            output.write(addChevrons(prefix_siret+siret)+"\n")
+            output.write("\trdf:type org:OrganizationalUnit ;\n ")
+
+            better_apen = row[indice_APEN][:2]+"."+row[indice_APEN][2:]
+            output.write(create_line_string(predicate_name,row[indice_NOMEN_LONG]))
+            output.write(create_line_url(predicate_purpose,prefix_ape+better_apen))
+            output.write(create_point(siret, row[indice_latitude], row[indice_LOGITUDE] ))
+
+            i+=1
+
+            if (i%100==0):
+                print(i)
+
+
+

teams/team3/readme.md

@@ -18,9 +18,28 @@ ex:00708077300034Point a sf:Point;
 * First we download [this file](https://www.insee.fr/fr/statistiques/2520034) containing french population grid data
 * Then we use [QGIS](https://qgis.org/) to convert it to ShapeFile and change projection from EPSG:3035 to EPSG:4326
 * Then we export it from shapefile to CSV
-* We use a [Java tool to convert it to RDF](https://github.com/alicela/CensusGrid-LOS) hacked from 
-* 
+* We use a [Java tool to convert it to RDF](https://github.com/alicela/CensusGrid-LOS) hacked from [this one](https://github.com/LOS-ESSnet/POP5/blob/master/src/main/java/eu/europa/ec/eurostat/los/pop5/DataSetModelMaker.java)
 ## Converting organization data (SIRENE)
 * We use [this repository](http://data.cquest.org/geo_sirene/last/)  containing files with added geolocalization information that has been produced [this way](https://www.insee.fr/fr/information/2509465) and this way
-* We use a Python conversion script to convert it
-* This Python script can be modified to add variables using [the W3C Organization Ontology](https://www.w3.org/TR/vocab-org/)
+* We use a [Python script](https://github.com/trblft/Paris-Hackathon/blob/master/teams/team3/create_rdf_test.py) to convert it
+* This Python script can be modified to add variables using [the W3C Organization Ontology](https://www.w3.org/TR/vocab-org/)
+# Querying the GraphDB sparql endpoints
+```
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+PREFIX geo-pos: <http://www.w3.org/2003/01/geo/wgs84_pos>
+PREFIX gn: <http://www.geonames.org/ontology#>
+PREFIX omgeo: <http://www.ontotext.com/owlim/geo#>
+PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
+select (sum(xsd:double(?pop)) as ?pop_totale) where {
+    # On sélectionne la position de l'entreprise VINOUZE
+    ?e rdfs:label "VINOUZE" .
+    ?e geo-pos:long ?lon .
+    ?e geo-pos:lat ?lat .
+    # On récupère la population des carreaux statistiques dont le centroide est à moins d'1 km
+    SERVICE <http://census_sparl_endpoint/repositories/census-point> 
+    {
+	?c omgeo:nearby(?lat ?lon "1km") .
+    	?c gn:population ?pop .
+    }
+}
+```