Lab Solutions: Difference between revisions

From info216
No edit summary
(Added proposed solution for Lab 12 - OWL 2)
 
(62 intermediate revisions by 5 users not shown)
Line 1: Line 1:
This page will be updated with Python examples related to the lectures and labs. We will add more examples after each lab has ended. The first examples will use Python's RDFlib. We will introduce other relevant libraries later.
Here we will present suggested solutions after each lab. ''The page will be updated as the course progresses''


==Getting started==
=Getting started (Lab 1)=


<syntaxhighlight>
<syntaxhighlight>


from rdflib.collection import Collection
from rdflib import Graph, Namespace
from rdflib import Graph, Namespace, Literal, URIRef
 
from rdflib.namespace import RDF, FOAF, XSD
ex = Namespace('http://example.org/')


g = Graph()
g = Graph()
EX = Namespace('http://EXample.org/')
RL = Namespace('http://purl.org/vocab/relationship/')
DBO = Namespace('https://dbpedia.org/ontology/')
DBR = Namespace('https://dbpedia.org/page/')


g.namespace_manager.bind('exampleURI', EX)
g.bind("ex", ex)
g.namespace_manager.bind('relationship', RL)
 
g.namespace_manager.bind('dbpediaOntology', DBO)
# The Mueller Investigation was lead by Robert Mueller
g.namespace_manager.bind('dbpediaPage', DBR)
g.add((ex.MuellerInvestigation, ex.leadBy, ex.RobertMueller))
 
# It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, Michael Cohen, and Roger Stone.
g.add((ex.MuellerInvestigation, ex.involved, ex.PaulManafort))
g.add((ex.MuellerInvestigation, ex.involved, ex.RickGates))
g.add((ex.MuellerInvestigation, ex.involved, ex.GeorgePapadopoulos))
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelFlynn))
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelCohen))
g.add((ex.MuellerInvestigation, ex.involved, ex.RogerStone))


g.add((EX.Cade, RDF.type, FOAF.Person))
# Paul Manafort was business partner of Rick Gates
g.add((EX.Mary, RDF.type, FOAF.Person))
g.add((ex.PaulManafort, ex.businessPartner, ex.RickGates))
g.add((EX.Cade, RL.spouseOf, EX.Mary)) # a symmetrical relation from an established namespace
g.add((DBR.France, DBO.capital, DBR.Paris))
g.add((EX.Cade, FOAF.age, Literal(27)))
g.add((EX.Mary, FOAF.age, Literal('26', datatype=XSD.int)))
Collection (g, EX.MaryInterests, [EX.hiking, EX.choclate, EX.biology])
g.add((EX.Mary, EX.hasIntrest, EX.MaryInterests))
g.add((EX.Mary, RDF.type, EX.student))
g.add((DBO.capital, EX.range, EX.city))
g.add((EX.Mary, RDF.type, EX.kind))
g.add((EX.Cade, RDF.type, EX.kindPerson))


#hobbies = ['hiking', 'choclate', 'biology']
# He was campaign chairman for Donald Trump
#for i in hobbies:
g.add((ex.PaulManafort, ex.campaignChairman, ex.DonaldTrump))
#    g.add((EX.Mary, FOAF.interest, EX[i]))


print(g.serialize(format="turtle"))
# He was charged with money laundering, tax evasion, and foreign lobbying.
</syntaxhighlight>
g.add((ex.PaulManafort, ex.chargedWith, ex.MoneyLaundering))
g.add((ex.PaulManafort, ex.chargedWith, ex.TaxEvasion))
g.add((ex.PaulManafort, ex.chargedWith, ex.ForeignLobbying))
 
# He was convicted for bank and tax fraud.
g.add((ex.PaulManafort, ex.convictedOf, ex.BankFraud))
g.add((ex.PaulManafort, ex.convictedOf, ex.TaxFraud))


==RDFlib==
# He pleaded guilty to conspiracy.
<syntaxhighlight>
g.add((ex.PaulManafort, ex.pleadGuiltyTo, ex.Conspiracy))


from rdflib.namespace import RDF, XSD, FOAF
# He was sentenced to prison.
from rdflib import Graph, Namespace, Literal, BNode
g.add((ex.PaulManafort, ex.sentencedTo, ex.Prison))
from rdflib.collection import Collection


# He negotiated a plea agreement.
g.add((ex.PaulManafort, ex.negotiated, ex.PleaAgreement))


g = Graph()
# Rick Gates was charged with money laundering, tax evasion and foreign lobbying.
ex = Namespace('http://example.org/')
g.add((ex.RickGates, ex.chargedWith, ex.MoneyLaundering))
schema = Namespace("https://schema.org/")
g.add((ex.RickGates, ex.chargedWith, ex.TaxEvasion))
dbp = Namespace("https://dbpedia.org/resource/")
g.add((ex.RickGates, ex.chargedWith, ex.ForeignLobbying))


g.bind("ex", ex)
# He pleaded guilty to conspiracy and lying to FBI.
g.bind("dbp", dbp)
g.add((ex.RickGates, ex.pleadGuiltyTo, ex.Conspiracy))
g.bind("schema", schema)
g.add((ex.RickGates, ex.pleadGuiltyTo, ex.LyingToFBI))


address = BNode()
# Use the serialize method of rdflib.Graph to write out the model in different formats (on screen or to file)
degree = BNode()
print(g.serialize(format="ttl")) # To screen
#g.serialize("lab1.ttl", format="ttl") # To file


# from lab 1
# Loop through the triples in the model to print out all triples that have pleading guilty as predicate
g.add((ex.Cade, FOAF.name, Literal("Cade Tracey", datatype=XSD.string)))
for subject, object in g[ : ex.pleadGuiltyTo :]:
g.add((ex.Mary, FOAF.name, Literal("Mary", datatype=XSD.string)))
    print(subject, ex.pleadGuiltyTo, object)
g.add((ex.Cade, RDF.type, FOAF.Person))
g.add((ex.Mary, RDF.type, FOAF.Person))
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Cade, ex.married, ex.Mary))
g.add((ex.Cade, FOAF.age, Literal('27', datatype=XSD.int)))
g.add((ex.Mary, FOAF.age, Literal('26', datatype=XSD.int)))
g.add((ex.Paris, RDF.type, ex.City))
g.add((ex.France, ex.Capital, ex.Paris))
g.add((ex.Mary, FOAF.interest, ex.hiking))
g.add((ex.Mary, FOAF.interest, ex.Chocolate))
g.add((ex.Mary, FOAF.interest, ex.biology))
g.add((ex.France, ex.City, ex.Paris))
g.add((ex.Mary, ex.Characterostic, ex.kind))
g.add((ex.Cade, ex.Characterostic, ex.kind))
g.add((ex.France, RDF.type, ex.Country))
g.add((ex.Cade, schema.address, address))


# BNode address
# --- IF you have more time tasks ---
g.add((address, RDF.type, schema.PostalAdress))
g.add((address, schema.streetAddress, Literal('1516 Henry Street')))
g.add((address, schema.addresCity, dbp.Berkeley))
g.add((address, schema.addressRegion, dbp.California))
g.add((address, schema.postalCode, Literal('94709')))
g.add((address, schema.addressCountry, dbp.United_States))


# More info about Cade
# Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week
g.add((ex.Cade, ex.Degree, degree))
g.add((degree, ex.Field, dbp.Biology))
g.add((degree, RDF.type, dbp.Bachelors_degree))
g.add((degree, ex.Universety, dbp.University_of_California))
g.add((degree, ex.year, Literal('2001', datatype=XSD.gYear)))


# Emma
#Write a method (function) that submits your model for rendering and saves the returned image to file.
emma_degree = BNode()
import requests
g.add((ex.Emma, FOAF.name, Literal("Emma Dominguez", datatype=XSD.string)))
import shutil
g.add((ex.Emma, RDF.type, FOAF.Person))
g.add((ex.Emma, ex.Degree, emma_degree))
g.add((degree, ex.Field, dbp.Chemistry))
g.add((degree, RDF.type, dbp.Masters_degree))
g.add((degree, ex.Universety, dbp.University_of_Valencia))
g.add((degree, ex.year, Literal('2015', datatype=XSD.gYear)))


# Address
def graphToImage(graphInput):
emma_address = BNode()
    data = {"rdf":graphInput, "from":"ttl", "to":"png"}
g.add((ex.Emma, schema.address, emma_address))
    link = "http://www.ldf.fi/service/rdf-grapher"
g.add((emma_address, RDF.type, schema.PostalAdress))
    response = requests.get(link, params = data, stream=True)
g.add((emma_address, schema.streetAddress,
    # print(response.content)
      Literal('Carrer de la Guardia Civil 20')))
    print(response.raw)
g.add((emma_address, schema.addressRegion, dbp.Valencia))
    with open("lab1.png", "wb") as file:
g.add((emma_address, schema.postalCode, Literal('46020')))
        shutil.copyfileobj(response.raw, file)
g.add((emma_address, schema.addressCountry, dbp.Spain))


b = BNode()
graph = g.serialize(format="ttl")
g.add((ex.Emma, ex.visit, b))
graphToImage(graph)
Collection(g, b,
          [dbp.Portugal, dbp.Italy, dbp.France, dbp.Germany, dbp.Denmark, dbp.Sweden])


</syntaxhighlight>
</syntaxhighlight>


==SPARQL - Blazegraph==
=RDF programming with RDFlib (Lab 2)=
 
<syntaxhighlight>
<syntaxhighlight>
PREFIX ex: <http://example.org/>
from rdflib import Graph, Namespace, Literal, BNode, XSD, FOAF, RDF, URIRef
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
from rdflib.collection import Collection
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
 
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
g = Graph()
PREFIX xml: <http://www.w3.org/XML/1998/namespace>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>


# Getting the graph created in the first lab
g.parse("lab1.ttl", format="ttl")


#select all triplets in graph
ex = Namespace("http://example.org/")
SELECT ?s ?p ?o
WHERE {
    ?s ?p ?o .
}
#select the interestes of Cade
SELECT ?cadeInterest
WHERE {
    ex:Cade ex:interest ?cadeInterest .
}
#select the country and city where Emma lives
SELECT ?emmaCity ?emmaCountry
WHERE {
    ex:Emma ex:address ?address .
  ?address ex:city ?emmaCity .
  ?address ex:country ?emmaCountry .
}
#select the people who are over 26 years old
SELECT ?person ?age
WHERE {
    ?person ex:age ?age .
  FILTER(?age > 26) .   
}
#select people who graduated with Bachelor
SELECT ?person ?degree
WHERE {
    ?person ex:degree ?degree .
  ?degree ex:degreeLevel "Bachelor" .
         
}
# delete cades photography interest
DELETE DATA
{
    ex:Cade ex:interest ex:Photography .
}


# delete and insert university of valencia
g.bind("ex", ex)
DELETE { ?s ?p ex:University_of_Valencia }
g.bind("foaf", FOAF)
INSERT { ?s ?p ex:Universidad_de_Valencia }
WHERE  { ?s ?p ex:University_of_Valencia }


#check if the deletion worked
# --- Michael Cohen ---
SELECT ?s ?o2
# Michael Cohen was Donald Trump's attorney.
WHERE  {
g.add((ex.MichaelCohen, ex.attorneyTo, ex.DonaldTrump))
  ?s ex:degree ?o .
# He pleaded guilty for lying to Congress.
  ?o ex:degreeSource ?o2 .
g.add((ex.MichaelCohen, ex.pleadGuiltyTo, ex.LyingToCongress))
      }
#describe sergio
DESCRIBE ex:Sergio ?o
WHERE {
  ex:Sergio ?p ?o .
  ?o ?p2 ?o2 .
  }
</syntaxhighlight>


==SPARQL - RDFlib==
# --- Michael Flynn ---
<syntaxhighlight>
# Michael Flynn was adviser to Donald Trump.
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE
g.add((ex.MichaelFlynn, ex.adviserTo, ex.DonaldTrump))
# He pleaded guilty for lying to the FBI.
g.add((ex.MichaelFlynn, ex.pleadGuiltyTo, ex.LyingToFBI))
# He negotiated a plea agreement.
g.add((ex.MichaelFlynn, ex.negotiated, ex.PleaAgreement))


namespace = "lab4"
# Change your graph so it represents instances of lying as blank nodes.
sparql = SPARQLWrapper("http://10.111.21.183:9999/blazegraph/namespace/"+ namespace + "/sparql")
# Remove the triples that will be duplicated
g.remove((ex.Michael_Flynn, ex.pleadGuiltyTo, ex.LyingToFBI))
g.remove((ex.Michael_Flynn, ex.negoiated, ex.PleaBargain))
g.remove((ex.Rick_Gates, ex.pleadGuiltyTo, ex.LyingToFBI))
g.remove((ex.Rick_Gates, ex.pleadGuiltyTo, ex.Conspiracy))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.ForeignLobbying))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
g.remove((ex.Michael_Cohen, ex.pleadGuiltyTo, ex.LyingToCongress))


# Print out Cades interests
# --- Michael Flynn ---
sparql.setQuery("""
FlynnLying = BNode()
    PREFIX ex: <http://example.org/>
g.add((FlynnLying, ex.crime, ex.LyingToFBI))
    SELECT * WHERE {
g.add((FlynnLying, ex.pleadGulityOn, Literal("2017-12-1", datatype=XSD.date)))
    ex:Cade ex:interest ?interest.
g.add((FlynnLying, ex.liedAbout, Literal("His communications with a former Russian ambassador during the presidential transition", datatype=XSD.string)))
    }
g.add((FlynnLying, ex.pleaBargain, Literal("true", datatype=XSD.boolean)))
""")
g.add((ex.Michael_Flynn, ex.pleadGuiltyTo, FlynnLying))
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print(result["interest"]["value"])


# Print Emmas city and country
# --- Rick Gates ---
sparql.setQuery("""
GatesLying = BNode()
    PREFIX ex: <http://example.org/>
Crimes = BNode()
    SELECT ?emmaCity ?emmaCountry
Charged = BNode()
    WHERE {
Collection(g, Crimes, [ex.LyingToFBI, ex.Conspiracy])
        ex:Emma ex:address ?address .
Collection(g, Charged, [ex.ForeignLobbying, ex.MoneyLaundering, ex.TaxEvasion])
        ?address ex:city ?emmaCity .
g.add((GatesLying, ex.crime, Crimes))
        ?address ex:country ?emmaCountry .
g.add((GatesLying, ex.chargedWith, Charged))
        }
g.add((GatesLying, ex.pleadGulityOn, Literal("2018-02-23", datatype=XSD.date)))
""")
g.add((GatesLying, ex.pleaBargain, Literal("true", datatype=XSD.boolean)))
sparql.setReturnFormat(JSON)
g.add((ex.Rick_Gates, ex.pleadGuiltyTo, GatesLying))
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print("Emma's city is "+result["emmaCity"]["value"]+" and Emma's country is " + result["emmaCountry"]["value"])


#Select the people who are over 26 years old
# --- Michael Cohen ---
sparql.setQuery("""
CohenLying = BNode()
    PREFIX ex: <http://example.org/>
g.add((CohenLying, ex.crime, ex.LyingToCongress))
    SELECT ?person ?age
g.add((CohenLying, ex.liedAbout, ex.TrumpRealEstateDeal))
    WHERE {
g.add((CohenLying, ex.prosecutorsAlleged, Literal("In an August 2017 letter Cohen sent to congressional committees investigating Russian election interference, he falsely stated that the project ended in January 2016", datatype=XSD.string)))
        ?person ex:age ?age .
g.add((CohenLying, ex.mullerInvestigationAlleged, Literal("Cohen falsely stated that he had never agreed to travel to Russia for the real estate deal and that he did not recall any contact with the Russian government about the project", datatype=XSD.string)))
        FILTER(?age > 26) .
g.add((CohenLying, ex.pleadGulityOn, Literal("2018-11-29", datatype=XSD.date)))
        }
g.add((CohenLying, ex.pleaBargain, Literal("true", datatype=XSD.boolean)))
        """)
g.add((ex.Michael_Cohen, ex.pleadGuiltyTo, CohenLying))
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print("All people who are over 26 years old: "+result["person"]["value"])


#Select people who graduated with Bachelor
print(g.serialize(format="ttl"))
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT ?person ?degree
    WHERE {
        ?person ex:degree ?degree .
        ?degree ex:degreeLevel "Bachelor" .
        }
        """)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print("People who graduated with Bachelor: "+result["person"]["value"])


#Delete cades photography interest
#Save (serialize) your graph to a Turtle file.
sparql.setQuery("""
# g.serialize("lab2.ttl", format="ttl")
    PREFIX ex: <http://example.org/>
    DELETE DATA {
        ex:Cade ex:interest ex:Photography .
        }
        """)
sparql.setMethod(POST)
results = sparql.query()
print(results.response.read())


# Print out Cades interests again
#Add a few triples to the Turtle file with more information about Donald Trump.
sparql.setQuery("""
'''
    PREFIX ex: <http://example.org/>
ex:Donald_Trump ex:address [ ex:city ex:Palm_Beach ;
    SELECT * WHERE {
            ex:country ex:United_States ;
    ex:Cade ex:interest ?interest.
            ex:postalCode 33480 ;
    }
            ex:residence ex:Mar_a_Lago ;
""")
            ex:state ex:Florida ;
sparql.setReturnFormat(JSON)
            ex:streetName "1100 S Ocean Blvd"^^xsd:string ] ;
sparql.setMethod(GET)
    ex:previousAddress [ ex:city ex:Washington_DC ;
results = sparql.query().convert()
            ex:country ex:United_States ;
for result in results["results"]["bindings"]:
            ex:phoneNumber "1 202 456 1414"^^xsd:integer ;
     print(result["interest"]["value"])
            ex:postalCode "20500"^^xsd:integer ;
            ex:residence ex:The_White_House ;
            ex:streetName "1600 Pennsylvania Ave."^^xsd:string ];
    ex:marriedTo ex:Melania_Trump;
     ex:fatherTo (ex:Ivanka_Trump ex:Donald_Trump_Jr ex: ex:Tiffany_Trump ex:Eric_Trump ex:Barron_Trump).
'''


# Check university names
#Read (parse) the Turtle file back into a Python program, and check that the new triples are there
sparql.setQuery("""
def serialize_Graph():
    PREFIX ex: <http://example.org/>
    newGraph = Graph()
    SELECT ?s ?o2
    newGraph.parse("lab2.ttl")
    WHERE  {
     print(newGraph.serialize())
        ?s ex:degree ?o .
        ?o ex:degreeSource ?o2 .
      }
    """)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
     print(result["o2"]["value"])


#Don't need this to run until after adding the triples above to the ttl file
# serialize_Graph()


#Delete and insert university of valencia
#Write a method (function) that starts with Donald Trump prints out a graph depth-first to show how the other graph nodes are connected to him
sparql.setQuery("""
visited_nodes = set()
    PREFIX ex: <http://example.org/>
    DELETE { ?s ?p ex:University_of_Valencia }
    INSERT { ?s ?p ex:Universidad_de_Valencia }
    WHERE  { ?s ?p ex:University_of_Valencia }
        """)
sparql.setMethod(POST)
results = sparql.query()
print(results.response.read())


# Check university names again
def create_Tree(model, nodes):
sparql.setQuery("""
    #Traverse the model breadth-first to create the tree.
     PREFIX ex: <http://example.org/>
    global visited_nodes
     SELECT ?s ?o2
    tree = Graph()
     WHERE  {
     children = set()
         ?s ex:degree ?o .
     visited_nodes |= set(nodes)
         ?o ex:degreeSource ?o2 .
     for s, p, o in model:
      }
         if s in nodes and o not in visited_nodes:
    """)
            tree.add((s, p, o))
sparql.setReturnFormat(JSON)
            visited_nodes.add(o)
sparql.setMethod(GET)
            children.add(o)
results = sparql.query().convert()
         if o in nodes and s not in visited_nodes:
for result in results["results"]["bindings"]:
            invp = URIRef(f'{p}_inv') #_inv represents inverse of
    print(result["o2"]["value"])
            tree.add((o, invp, s))
            visited_nodes.add(s)
            children.add(s)
    if len(children) > 0:
        children_tree = create_Tree(model, children)
        for triple in children_tree:
            tree.add(triple)
    return tree


#Insert Sergio
def print_Tree(tree, root, indent=0):
sparql.setQuery("""
     #Print the tree depth-first.
     PREFIX ex: <http://example.org/>
     print(str(root))
     PREFIX foaf: <http://xmlns.com/foaf/0.1/>
     for s, p, o in tree:
     INSERT DATA {
         if s==root:
        ex:Sergio a foaf:Person ;
            print('    '*indent + '  ' + str(p), end=' ')
         ex:address [ a ex:Address ;
             print_Tree(tree, o, indent+1)
                ex:city ex:Valenciay ;
      
                ex:country ex:Spain ;
tree = create_Tree(g, [ex.Donald_Trump])
                ex:postalCode "46021"^^xsd:string ;
print_Tree(tree, ex.Donald_Trump)
                ex:state ex:California ;
</syntaxhighlight>
                ex:street "4_Carrer_del_Serpis"^^xsd:string ] ;
        ex:degree [ ex:degreeField ex:Computer_science ;
                ex:degreeLevel "Master"^^xsd:string ;
                ex:degreeSource ex:University_of_Valencia ;
                ex:year "2008"^^xsd:gYear ] ;
        ex:expertise ex:Big_data,
             ex:Semantic_technologies,
            ex:Machine_learning;
        foaf:name "Sergio_Pastor"^^xsd:string .
        }
     """)
sparql.setMethod(POST)
results = sparql.query()
print(results.response.read())
sparql.setMethod(GET)


# Describe Sergio
=SPARQL (Lab 3-4)=
sparql.setReturnFormat(TURTLE)
===List all triples===
sparql.setQuery("""
<syntaxhighlight lang="SPARQL">
    PREFIX ex: <http://example.org/>
SELECT ?s ?p ?o
    DESCRIBE ex:Sergio ?o
WHERE {?s ?p ?o .}
    WHERE {
</syntaxhighlight>
        ex:Sergio ?p ?o .
        ?o ?p2 ?o2 .
    }
    """)
results = sparql.query().convert()
print(results.serialize(format='turtle'))


# Construct that any city is in the country in an address
===List the first 100 triples===
sparql.setQuery("""
<syntaxhighlight lang="SPARQL">
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>  
SELECT ?s ?p ?o
    PREFIX ex: <http://example.org/>
WHERE {?s ?p ?o .}
    CONSTRUCT {?city ex:locatedIn ?country}
LIMIT 100
    Where {
</syntaxhighlight>
        ?s rdf:type ex:Address .
        ?s ex:city ?city .
        ?s ex:country ?country.
        }
    """)
sparql.setReturnFormat(TURTLE)
results = sparql.query().convert()
print(results.serialize(format='turtle'))


===Count the number of triples===
<syntaxhighlight lang="SPARQL">
SELECT (COUNT(*) as ?count)
WHERE {?s ?p ?o .}
</syntaxhighlight>
</syntaxhighlight>
==Web APIs and JSON-LD==


<syntaxhighlight>
===Count the number of indictments===
import requests
<syntaxhighlight lang="SPARQL">
from rdflib import FOAF, Namespace, Literal, RDF, Graph, TURTLE
PREFIX ns1: <http://example.org#>


r = requests.get('http://api.open-notify.org/astros.json').json()
SELECT (COUNT(?ind) as ?amount)
g = Graph()
WHERE {
EX = Namespace('http://EXample.org/')
  ?s ns1:outcome ?ind;
g.bind("ex", EX)
      ns1:outcome ns1:indictment.
}
</syntaxhighlight>


for item in r['people']:
===List the names of everyone who pleaded guilty, along with the name of the investigation===
    craft = item['craft'].replace(" ","_")
<syntaxhighlight lang="SPARQL">
    person = item['name'].replace(" ","_")
PREFIX ns1: <http://example.org#>
    g.add((EX[person], EX.onCraft, EX[craft]))
    g.add((EX[person], RDF.type, FOAF.Person))
    g.add((EX[person], FOAF.name, Literal(item['name'])))
    g.add((EX[craft], FOAF.name, Literal(item['craft'])))
res = g.query("""
    CONSTRUCT {?person1 foaf:knows ?person2}
    WHERE {
        ?person1 ex:onCraft ?craft .
        ?person2 ex:onCraft ?craft .
        }
""")


for triplet in res:
SELECT ?name ?invname
    # (we don't need to add that they know themselves)
WHERE {
    if (triplet[0] != triplet[2]):
  ?s ns1:name ?name;
        g.add((triplet))
      ns1:investigation ?invname;
       
      ns1:outcome ns1:guilty-plea .
print(g.serialize(format="turtle"))
}
</syntaxhighlight>
</syntaxhighlight>


==Semantic lifting - CSV==
===List the names of everyone who were convicted, but who had their conviction overturned by which president===
<syntaxhighlight>
<syntaxhighlight lang="SPARQL">
import pandas as pd
PREFIX ns1: <http://example.org#>
from rdflib import Graph, Namespace, URIRef, Literal
from rdflib.namespace import RDF, XSD


ex = Namespace("http://example.org/")
SELECT ?name ?president
dbr = Namespace("http://dbpedia.org/resource/")
WHERE {
dbp = Namespace("https://dbpedia.org/property/")
  ?s ns1:name ?name;
dbpage = Namespace("https://dbpedia.org/page/")
      ns1:president ?president;
sem = Namespace("http://semanticweb.cs.vu.nl/2009/11/sem/")
      ns1:outcome ns1:conviction;
tl = Namespace("http://purl.org/NET/c4dm/timeline.owl#")
      ns1:overturned ns1:true.
}
</syntaxhighlight>


g = Graph()
===For each investigation, list the number of indictments made===
g.bind("ex", ex)
<syntaxhighlight lang="SPARQL">
g.bind("dbr", dbr)
PREFIX ns1: <http://example.org#>
g.bind("dbp", dbp)
g.bind("dbpage", dbpage)
g.bind("sem", sem)
g.bind("tl", tl)


df = pd.read_csv("russia-investigations.csv")
SELECT ?invs (COUNT(?invs) as ?count)
# We need to correct the type of the columns in the DataFrame, as Pandas assigns an incorrect type when it reads the file (for me at least). We use .astype("str") to convert the content of the columns to a string.
WHERE {
df["name"] = df["name"].astype("str")
  ?s ns1:investigation ?invs;
df["type"] = df["type"].astype("str")
      ns1:outcome ns1:indictment .
}
GROUP BY ?invs
</syntaxhighlight>


# iterrows creates an iterable object (list of rows)
===For each investigation with multiple indictments, list the number of indictments made===
for index, row in df.iterrows():
<syntaxhighlight lang="SPARQL">
investigation = URIRef(ex + row['investigation'])
PREFIX ns1: <http://example.org#>
investigation_start = Literal(row['investigation-start'], datatype=XSD.date)
investigation_end = Literal(row['investigation-end'], datatype=XSD.date)
investigation_days = Literal(row['investigation-days'], datatype=XSD.integer)


name = Literal(row['name'], datatype=XSD.string)
SELECT ?invs (COUNT(?invs) as ?count)
name_underscore = URIRef(dbpage + row['name'].replace(" ","_"))
WHERE {
investigation_result = URIRef(ex + row['investigation']+ "_investigation_" + row['name'].replace(" ","_"))
  ?s ns1:investigation ?invs;
indictment_days = Literal(row['indictment-days'], datatype=XSD.integer)
      ns1:outcome ns1:indictment .
type = URIRef(dbr + row['type'].replace(" ","_"))
}
cp_date = Literal(row['cp-date'], datatype=XSD.date)
GROUP BY ?invs
cp_days = Literal(row['cp-days'], datatype=XSD.duration)
HAVING(?count > 1)
overturned = Literal(row['overturned'], datatype=XSD.boolean)
</syntaxhighlight>
pardoned = Literal(row['pardoned'], datatype=XSD.boolean)
american = Literal(row['american'], datatype=XSD.boolean)
president = Literal(row['president'], datatype=XSD.string)
president_underscore = URIRef(dbr + row['president'].replace(" ","_"))


g.add((investigation, RDF.type, sem.Event))
===For each investigation with multiple indictments, list the number of indictments made, sorted with the most indictments first===
g.add((investigation, sem.hasBeginTimeStamp, investigation_start))
<syntaxhighlight lang="SPARQL">
g.add((investigation, sem.hasEndTimeStamp, investigation_end))
PREFIX ns1: <http://example.org#>
g.add((investigation, tl.duration, investigation_days))
g.add((investigation, dbp.president, president_underscore))
g.add((investigation, sem.hasSubEvent, investigation_result))


g.add((investigation_result, ex.resultType, type))
SELECT ?invs (COUNT(?invs) as ?count)
g.add((investigation_result, ex.objectOfInvestigation, name_underscore))
WHERE {
g.add((investigation_result, ex.isAmerican, american))
  ?s ns1:investigation ?invs;
g.add((investigation_result, ex.indictmentDuration, indictment_days))
      ns1:outcome ns1:indictment .
g.add((investigation_result, ex.caseSolved, cp_date))
}
g.add((investigation_result, ex.daysBeforeCaseSolved, cp_days))
GROUP BY ?invs
g.add((investigation_result, ex.overturned, overturned))
HAVING(?count > 1)
g.add((investigation_result, ex.pardoned, pardoned))
ORDER BY DESC(?count)
g.serialize("output.ttl",format="ttl")
</syntaxhighlight>
</syntaxhighlight>


==RDFS==
===For each president, list the numbers of convictions and of pardons made===
<syntaxhighlight lang="SPARQL">
PREFIX ns1: <http://example.org#>


SELECT ?president (COUNT(?outcome) as ?conviction) (COUNT(?pardon) as
?pardons)
WHERE {
  ?s ns1:president ?president;
      ns1:outcome ?outcome ;
      ns1:outcome ns1:conviction.
      OPTIONAL{
        ?s ns1:pardoned ?pardon .
        FILTER (?pardon = ns1:true)
      }
}
GROUP BY ?president
</syntaxhighlight>


===Rename mullerkg:name to something like muellerkg:person===


==Getting started==
<syntaxhighlight lang="SPARQL">
PREFIX ns1: <http://example.org#>


 
DELETE{?s ns1:name ?o}
===Printing the triples of the Graph in a readable way===
INSERT{?s ns1:person ?o}
<syntaxhighlight>
WHERE {?s ns1:name ?o}
# The turtle format has the purpose of being more readable for humans.
print(g.serialize(format="turtle"))
</syntaxhighlight>
</syntaxhighlight>


===Coding Tasks Lab 1===
===Update the graph so all the investigated person and president nodes become the subjects in foaf:name triples with the corresponding strings===
<syntaxhighlight>
from rdflib import Graph, Namespace, URIRef, BNode, Literal
from rdflib.namespace import RDF, FOAF, XSD
 
g = Graph()
ex = Namespace("http://example.org/")


g.add((ex.Cade, ex.married, ex.Mary))
<syntaxhighlight lang="SPARQL">
g.add((ex.France, ex.capital, ex.Paris))
PREFIX ns1: <http://example.org#>
g.add((ex.Cade, ex.age, Literal("27", datatype=XSD.integer)))
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
g.add((ex.Mary, ex.age, Literal("26", datatype=XSD.integer)))
g.add((ex.Mary, ex.interest, ex.Hiking))
g.add((ex.Mary, ex.interest, ex.Chocolate))
g.add((ex.Mary, ex.interest, ex.Biology))
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Paris, RDF.type, ex.City))
g.add((ex.Paris, ex.locatedIn, ex.France))
g.add((ex.Cade, ex.characteristic, ex.Kind))
g.add((ex.Mary, ex.characteristic, ex.Kind))
g.add((ex.Mary, RDF.type, FOAF.Person))
g.add((ex.Cade, RDF.type, FOAF.Person))


# OR
#Persons
INSERT {?person foaf:name ?name}
WHERE {
      ?investigation ns1:person ?person .
      BIND(REPLACE(STR(?person), STR(ns1:), "") AS ?name)
}


g = Graph()
#Presidents
INSERT {?president foaf:name ?name}
WHERE {
      ?investigation ns1:president ?president .
      BIND(REPLACE(STR(?president), STR(ns1:), "") AS ?name)
}
</syntaxhighlight>


ex = Namespace('http://example.org/')
===Use INSERT DATA updates to add these triples===


g.add((ex.Cade, FOAF.name, Literal("Cade", datatype=XSD.string)))
<syntaxhighlight lang="SPARQL">
g.add((ex.Mary, FOAF.name, Literal("Mary", datatype=XSD.string)))
PREFIX ns1: <http://example.org#>
g.add((ex.Cade, RDF.type, FOAF.Person))
g.add((ex.Mary, RDF.type, FOAF.Person))
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Cade, ex.Married, ex.Mary))
g.add((ex.Cade, FOAF.age, Literal('27', datatype=XSD.int)))
g.add((ex.Mary, FOAF.age, Literal('26', datatype=XSD.int)))
g.add((ex.Paris, RDF.type, ex.City))
g.add((ex.France, ex.Capital, ex.Paris))
g.add((ex.Mary, FOAF.interest, ex.hiking))
g.add((ex.Mary, FOAF.interest, ex.Chocolate))
g.add((ex.Mary, FOAF.interest, ex.biology))
g.add((ex.France, ex.City, ex.Paris))
g.add((ex.Mary, ex.characteristic, ex.kind))
g.add((ex.Cade, ex.characteristic, ex.kind))
g.add((ex.France, RDF.type, ex.Country))


INSERT DATA {
    ns1:George_Papadopoulos ns1:adviserTo ns1:Donald_Trump;
        ns1:pleadGuiltyTo ns1:LyingToFBI;
        ns1:sentencedTo ns1:Prison.


print(g.serialize(format="turtle"))
    ns1:Roger_Stone a ns1:Republican;
        ns1:adviserTo ns1:Donald_Trump;
        ns1:officialTo ns1:Trump_Campaign;
        ns1:interactedWith ns1:Wikileaks;
        ns1:providedTestimony ns1:House_Intelligence_Committee;
        ns1:clearedOf ns1:AllCharges.
}


#To test if added
SELECT ?p ?o
WHERE {ns1:Roger_Stone ?p ?o .}
</syntaxhighlight>
</syntaxhighlight>


==Basic RDF programming==
===Use DELETE DATA and then INSERT DATA updates to correct that Roger Stone was cleared of all charges===


===Different ways to create an address===
<syntaxhighlight lang="SPARQL">
PREFIX ns1: <http://example.org#>


<syntaxhighlight>
DELETE DATA {
      ns1:Roger_Stone ns1:clearedOf ns1:AllCharges .
}


from rdflib import Graph, Namespace, URIRef, BNode, Literal
INSERT DATA {
from rdflib.namespace import RDF, FOAF, XSD
      ns1:Roger_Stone ns1:indictedFor ns1:ObstructionOfJustice,
                                      ns1:WitnessTampering,
                                      ns1:FalseStatements.
}


g = Graph()
#The task specifically requested DELETE DATA & INSERT DATA, put below is
ex = Namespace("http://example.org/")
a more efficient solution


DELETE{ns1:Roger_Stone ns1:clearedOf ns1:AllCharges.}
INSERT{
  ns1:Roger_Stone ns1:indictedFor ns1:ObstructionOfJustice,
                                  ns1:WitnessTampering,
                                  ns1:FalseStatements.
}
WHERE{ns1:Roger_Stone ns1:clearedOf ns1:AllCharges.}
</syntaxhighlight>


# How to represent the address of Cade Tracey. From probably the worst solution to the best.
===Use a DESCRIBE query to show the updated information about Roger Stone===


# Solution 1 -
<syntaxhighlight lang="SPARQL">
# Make the entire address into one Literal. However, Generally we want to separate each part of an address into their own triples. This is useful for instance if we want to find only the streets where people live.
PREFIX ns1: <http://example.org#>


g.add((ex.Cade_Tracey, ex.livesIn, Literal("1516_Henry_Street, Berkeley, California 94709, USA")))
DESCRIBE ?o
WHERE {ns1:Roger_Stone ns1:indictedFor ?o .}
</syntaxhighlight>


===Use a CONSTRUCT query to create a new RDF group with triples only about Roger Stone===


# Solution 2 -
<syntaxhighlight lang="SPARQL">
# Seperate the different pieces information into their own triples
PREFIX ns1: <http://example.org#>


g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
CONSTRUCT {
g.add((ex.Cade_tracey, ex.city, Literal("Berkeley")))
  ns1:Roger_Stone ?p ?o.
g.add((ex.Cade_tracey, ex.state, Literal("California")))
  ?s ?p2 ns1:Roger_Stone.
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
}
g.add((ex.Cade_tracey, ex.country, Literal("USA")))
WHERE {
  ns1:Roger_Stone ?p ?o .
  ?s ?p2 ns1:Roger_Stone
}
</syntaxhighlight>


===Write a DELETE/INSERT statement to change one of the prefixes in your graph===


# Solution 3 - Some parts of the addresses can make more sense to be resources than Literals.
<syntaxhighlight lang="SPARQL">
# Larger concepts like a city or state are typically represented as resources rather than Literals, but this is not necesarilly a requirement in the case that you don't intend to say more about them.  
PREFIX ns1: <http://example.org#>
PREFIX dbp: <https://dbpedia.org/page/>


g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
DELETE {?s ns1:person ?o1}
g.add((ex.Cade_tracey, ex.city, ex.Berkeley))
INSERT {?s ns1:person ?o2}
g.add((ex.Cade_tracey, ex.state, ex.California))
WHERE{
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
  ?s ns1:person ?o1 .
g.add((ex.Cade_tracey, ex.country, ex.USA))
  BIND (IRI(replace(str(?o1), str(ns1:), str(dbp:)))  AS ?o2)
}


#This update changes the object in triples with ns1:person as the
predicate. It changes it's prefix of ns1 (which is the
"shortcut/shorthand" for example.org) to the prefix dbp (dbpedia.org)
</syntaxhighlight>


# Solution 4
===Write an INSERT statement to add at least one significant date to the Mueller investigation, with literal type xsd:date. Write a DELETE/INSERT statement to change the date to a string, and a new DELETE/INSERT statement to change it back to xsd:date. ===
# Grouping of the information into an Address. We can Represent the address concept with its own URI OR with a Blank Node.
# One advantage of this is that we can easily remove the entire address, instead of removing each individual part of the address.
# Solution 4 or 5 is how I would recommend to make addresses. Here, ex.CadeAddress could also be called something like ex.address1 or so on, if you want to give each address a unique ID.  


# Address URI - CadeAdress
<syntaxhighlight lang="SPARQL">
#Whilst this solution is not exactly what the task asks for, I feel like
this is more appropiate given the dataset. The following update
changes the objects that uses the cp_date as predicate from a URI, to a
literal with date as it's datatype


g.add((ex.Cade_Tracey, ex.address, ex.CadeAddress))
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
g.add((ex.CadeAddress, RDF.type, ex.Address))
PREFIX ns1: <http://example.org#>
g.add((ex.CadeAddress, ex.street, Literal("1516 Henry Street")))
g.add((ex.CadeAddress, ex.city, ex.Berkeley))
g.add((ex.CadeAddress, ex.state, ex.California))
g.add((ex.CadeAddress, ex.postalCode, Literal("94709")))
g.add((ex.CadeAddress, ex.country, ex.USA))


# OR
DELETE {?s ns1:cp_date ?o}
INSERT{?s ns1:cp_date ?o3}
WHERE{
  ?s ns1:cp_date ?o .
  BIND (replace(str(?o), str(ns1:), "")  AS ?o2)
  BIND (STRDT(STR(?o2), xsd:date) AS ?o3)
}


# Blank node for Address. 
#To test:
address = BNode()
g.add((ex.Cade_Tracey, ex.address, address))
g.add((address, RDF.type, ex.Address))
g.add((address, ex.street, Literal("1516 Henry Street", datatype=XSD.string)))
g.add((address, ex.city, ex.Berkeley))
g.add((address, ex.state, ex.California))
g.add((address, ex.postalCode, Literal("94709", datatype=XSD.string)))
g.add((address, ex.country, ex.USA))


PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX ns1: <http://example.org#>


# Solution 5 using existing vocabularies for address
SELECT ?s ?o
WHERE{
  ?s ns1:cp_date ?o.
  FILTER(datatype(?o) = xsd:date)
}


# (in this case https://schema.org/PostalAddress from schema.org).
#To change it to an integer, use the following code, and to change it
# Also using existing ontology for places like California. (like http://dbpedia.org/resource/California from dbpedia.org)
back to date, swap "xsd:integer" to "xsd:date"


schema = Namespace("https://schema.org/")
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
dbp = Namespace("https://dpbedia.org/resource/")
PREFIX ns1: <http://example.org#>


g.add((ex.Cade_Tracey, schema.address, ex.CadeAddress))
DELETE {?s ns1:cp_date ?o}
g.add((ex.CadeAddress, RDF.type, schema.PostalAddress))
INSERT{?s ns1:cp_date ?o2}
g.add((ex.CadeAddress, schema.streetAddress, Literal("1516 Henry Street")))
WHERE{
g.add((ex.CadeAddress, schema.addresCity, dbp.Berkeley))
  ?s ns1:cp_date ?o .
g.add((ex.CadeAddress, schema.addressRegion, dbp.California))
  BIND (STRDT(STR(?o), xsd:integer) AS ?o2)
g.add((ex.CadeAddress, schema.postalCode, Literal("94709")))
}
g.add((ex.CadeAddress, schema.addressCountry, dbp.United_States))


</syntaxhighlight>
</syntaxhighlight>


===Typed Literals===
=SPARQL Programming (Lab 5)=
 
<syntaxhighlight>
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace
from rdflib.namespace import XSD
g = Graph()
ex = Namespace("http://example.org/")


g.add((ex.Cade, ex.age, Literal(27, datatype=XSD.integer)))
from rdflib import Graph, Namespace, RDF, FOAF
g.add((ex.Cade, ex.gpa, Literal(3.3, datatype=XSD.float)))
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE
g.add((ex.Cade, FOAF.name, Literal("Cade Tracey", datatype=XSD.string)))
g.add((ex.Cade, ex.birthday, Literal("2006-01-01", datatype=XSD.date)))
</syntaxhighlight>


g = Graph()
g.parse("Russia_investigation_kg.ttl")


===Writing and reading graphs/files===
# ----- RDFLIB -----
ex = Namespace('http://example.org#')


<syntaxhighlight>
NS = {
  # Writing the graph to a file on your system. Possible formats = turtle, n3, xml, nt.
    '': ex,
g.serialize(destination="triples.txt", format="turtle")
    'rdf': RDF,
    'foaf': FOAF,
}


  # Parsing a local file
# Print out a list of all the predicates used in your graph.
parsed_graph = g.parse(location="triples.txt", format="turtle")
task1 = g.query("""
SELECT DISTINCT ?p WHERE{
    ?s ?p ?o .
}
""", initNs=NS)


  # Parsing a remote endpoint like Dbpedia
print(list(task1))
dbpedia_graph = g.parse("http://dbpedia.org/resource/Pluto")
</syntaxhighlight>


===Graph Binding===
# Print out a sorted list of all the presidents represented in your graph.
<syntaxhighlight>
task2 = g.query("""
#Graph Binding is useful for at least two reasons:
SELECT DISTINCT ?president WHERE{
#(1) We no longer need to specify prefixes with SPARQL queries if they are already binded to the graph.
    ?s :president ?president .
#(2) When serializing the graph, the serialization will show the correct expected prefix
}
# instead of default namespace names ns1, ns2 etc.
ORDER BY ?president
""", initNs=NS)


g = Graph()
print(list(task2))


ex = Namespace("http://example.org/")
# Create dictionary (Python dict) with all the represented presidents as keys. For each key, the value is a list of names of people indicted under that president.
dbp = Namespace("http://dbpedia.org/resource/")
task3_dic = {}
schema = Namespace("https://schema.org/")


g.bind("ex", ex)
task3 = g.query("""
g.bind("dbp", dbp)
SELECT ?president ?person WHERE{
g.bind("schema", schema)
    ?s :president ?president;
</syntaxhighlight>
      :name ?person;
      :outcome :indictment.
}
""", initNs=NS)


===Collection Example===
for president, person in task3:
    if president not in task3_dic:
        task3_dic[president] = [person]
    else:
        task3_dic[president].append(person)


<syntaxhighlight>
print(task3_dic)
from rdflib import Graph, Namespace
from rdflib.collection import Collection


# Use an ASK query to investigate whether Donald Trump has pardoned more than 5 people.


# Sometimes we want to add many objects or subjects for the same predicate at once.  
# This task is a lot trickier than it needs to be. As far as I'm aware RDFLib has no HAVING support, so a query like this:
# In these cases we can use Collection() to save some time.
task4 = g.query("""
# In this case I want to add all countries that Emma has visited at once.
ASK {
  SELECT (COUNT(?s) as ?count) WHERE{
    ?s :pardoned :true;
    :president :Bill_Clinton  .
    }
    HAVING (?count > 5)
}
""", initNs=NS)


b = BNode()
print(task4.askAnswer)
g.add((ex.Emma, ex.visit, b))
Collection(g, b,
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])


# OR
# Which works fine in Blazegraph and is a valid SPARQL query will always provide false in RDFLib cause it uses HAVING.
# Instead you have to use a nested SELECT query like below, where you use FILTER instead of HAVING. Donald Trump has no pardons,
# so I have instead chosen Bill Clinton with 13 to check if the query works.


g.add((ex.Emma, ex.visit, ex.EmmaVisits))
task4 = g.query("""
Collection(g, ex.EmmaVisits,
    ASK{
     [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])
        SELECT ?count WHERE{{
          SELECT (COUNT(?s) as ?count) WHERE{
            ?s :pardoned :true;
                  :president :Bill_Clinton  .
                }}
        FILTER (?count > 5)
        }
     }
""", initNs=NS)


</syntaxhighlight>
print(task4.askAnswer)


==SPARQL==
# Use a DESCRIBE query to create a new graph with information about Donald Trump. Print out the graph in Turtle format.


Also see the [[SPARQL Examples]] page!
# By all accounts, it seems DESCRIBE querires are yet to be implemented in RDFLib, but they are attempting to implement it:
 
# https://github.com/RDFLib/rdflib/pull/2221 <--- Issue and proposed solution rasied
===Querying a local ("in memory") graph===
# https://github.com/RDFLib/rdflib/commit/2325b4a81724c1ccee3a131067db4fbf9b4e2629 <--- Solution commited to RDFLib
 
# This solution does not work. However, this proposed solution should work if DESCRIBE is implemented in RDFLib
Example contents of the file family.ttl:
@prefix rex: <http://example.org/royal#> .
@prefix fam: <http://example.org/family#> .
rex:IngridAlexandra fam:hasParent rex:HaakonMagnus .
rex:SverreMagnus fam:hasParent rex:HaakonMagnus .
rex:HaakonMagnus fam:hasParent rex:Harald .
rex:MarthaLouise fam:hasParent rex:Harald .
rex:HaakonMagnus fam:hasSister rex:MarthaLouise .


import rdflib
# task5 = g.query("""  
# DESCRIBE :Donald_Trump
g = rdflib.Graph()
# """, initNs=NS)
g.parse("family.ttl", format='ttl')
qres = g.query("""
PREFIX fam: <http://example.org/family#>
    SELECT ?child ?sister WHERE {
        ?child fam:hasParent ?parent .
        ?parent fam:hasSister ?sister .
    }""")
for row in qres:
    print("%s has aunt %s" % row)


With a prepared query, you can write the query once, and then bind some of the variables each time you use it:
# print(task5.serialize())
import rdflib
g = rdflib.Graph()
g.parse("family.ttl", format='ttl')
q = rdflib.plugins.sparql.prepareQuery(
        """SELECT ?child ?sister WHERE {
                  ?child fam:hasParent ?parent .
                  ?parent fam:hasSister ?sister .
        }""",
        initNs = { "fam": "http://example.org/family#"})
sm = rdflib.URIRef("http://example.org/royal#SverreMagnus")
for row in g.query(q, initBindings={'child': sm}):
        print(row)


===Select all contents of lists (rdfllib.Collection)===
# ----- SPARQLWrapper -----
<syntaxhighlight>


# rdflib.Collection has a different interntal structure so it requires a slightly more advance query. Here I am selecting all places that Emma has visited.
SERVER = 'http://localhost:7200' #Might need to replace this
REPOSITORY = 'Labs' #Replace with your repository name


PREFIX ex:  <http://example.org/>
# Query Endpoint
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
sparql = SPARQLWrapper(f'{SERVER}/repositories/{REPOSITORY}')
# Update Endpoint
sparqlUpdate = SPARQLWrapper(f'{SERVER}/repositories/{REPOSITORY}/statements')


SELECT ?visit
# Ask whether there was an ongoing indictment on the date 1990-01-01.
WHERE {
sparql.setQuery("""
  ex:Emma ex:visit/rdf:rest*/rdf:first ?visit
    PREFIX ns1: <http://example.org#>
}
    ASK {
</syntaxhighlight>
        SELECT ?end ?start
        WHERE{
            ?s ns1:investigation_end ?end;
              ns1:investigation_start ?start;
              ns1:outcome ns1:indictment.
            FILTER(?start <= "1990-01-01"^^xsd:date && ?end >= "1990-01-01"^^xsd:date)
    }
    }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
print(f"Are there any investigation on the 1990-01-01: {results['boolean']}")


# List ongoing indictments on that date 1990-01-01.
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    SELECT ?s
    WHERE{
        ?s ns1:investigation_end ?end;
          ns1:investigation_start ?start;
          ns1:outcome ns1:indictment.
        FILTER(?start <= "1990-01-01"^^xsd:date && ?end >= "1990-01-01"^^xsd:date)
    }
""")


===Using parameters/variables in rdflib queries===
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


<syntaxhighlight>
print("The ongoing investigations on the 1990-01-01 are:")
from rdflib import Graph, Namespace, URIRef
for result in results["results"]["bindings"]:
from rdflib.plugins.sparql import prepareQuery
    print(result["s"]["value"])


g = Graph()
# Describe investigation number 100 (muellerkg:investigation_100).
ex = Namespace("http://example.org/")
sparql.setQuery("""
g.bind("ex", ex)
    PREFIX ns1: <http://example.org#>
    DESCRIBE ns1:investigation_100
""")


g.add((ex.Cade, ex.livesIn, ex.France))
sparql.setReturnFormat(TURTLE)
g.add((ex.Anne, ex.livesIn, ex.Norway))
results = sparql.query().convert()
g.add((ex.Sofie, ex.livesIn, ex.Sweden))
g.add((ex.Per, ex.livesIn, ex.Norway))
g.add((ex.John, ex.livesIn, ex.USA))


print(results)


def find_people_from_country(country):
# Print out a list of all the types used in your graph.
        country = URIRef(ex + country)
sparql.setQuery("""
        q = prepareQuery(
    PREFIX ns1: <http://example.org#>
        """
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
        PREFIX ex: <http://example.org/>
        SELECT ?person WHERE {
        ?person ex:livesIn ?country.
        }
        """)


         capital_result = g.query(q, initBindings={'country': country})
    SELECT DISTINCT ?types
    WHERE{
         ?s rdf:type ?types .  
    }
""")


        for row in capital_result:
sparql.setReturnFormat(JSON)
            print(row)
results = sparql.query().convert()


find_people_from_country("Norway")
rdf_Types = []
</syntaxhighlight>


===SELECTING data from Blazegraph via Python===
for result in results["results"]["bindings"]:
<syntaxhighlight>
    rdf_Types.append(result["types"]["value"])


from SPARQLWrapper import SPARQLWrapper, JSON
print(rdf_Types)


# This creates a server connection to the same URL that contains the graphic interface for Blazegraph.  
# Update the graph to that every resource that is an object in a muellerkg:investigation triple has the rdf:type muellerkg:Investigation.
# You also need to add "sparql" to end of the URL like below.
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


sparql = SPARQLWrapper("http://localhost:9999/blazegraph/sparql")
    INSERT{
        ?invest rdf:type ns1:Investigation .
    }
    WHERE{
        ?s ns1:investigation ?invest .
}"""


# SELECT all triples in the database.
sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


#To Test
sparql.setQuery("""
sparql.setQuery("""
     SELECT DISTINCT ?p WHERE {
     prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    ?s ?p ?o.
    PREFIX ns1: <http://example.org#>
 
    ASK{
        ns1:watergate rdf:type ns1:Investigation.
     }
     }
""")
""")
sparql.setReturnFormat(JSON)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()
print(results['boolean'])


for result in results["results"]["bindings"]:
# Update the graph to that every resource that is an object in a muellerkg:person triple has the rdf:type muellerkg:IndictedPerson.
     print(result["p"]["value"])
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
 
    INSERT{
        ?person rdf:type ns1:IndictedPerson .
    }
    WHERE{
        ?s ns1:name ?person .
}"""
 
sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()
 
#To test, run the query in the above task, replacing the ask query with e.g. ns1:Deborah_Gore_Dean rdf:type ns1:IndictedPerson
 
# Update the graph so all the investigation nodes (such as muellerkg:watergate) become the subject in a dc:title triple with the corresponding string (watergate) as the literal.
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX dc: <http://purl.org/dc/elements/1.1/>
 
    INSERT{
        ?invest dc:title ?investString.
    }
     WHERE{
        ?s ns1:investigation ?invest .
        BIND (replace(str(?invest), str(ns1:), "")  AS ?investString)
}"""
 
sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


# SELECT all interests of Cade
#Same test as above, replace it with e.g. ns1:watergate dc:title "watergate"


# Print out a sorted list of all the indicted persons represented in your graph.
sparql.setQuery("""
sparql.setQuery("""
     PREFIX ex: <http://example.org/>
     PREFIX ns1: <http://example.org#>
     SELECT DISTINCT ?interest WHERE {
    PREFIX foaf: <http://xmlns.com/foaf/0.1/>
     ex:Cade ex:interest ?interest.
 
     SELECT ?name
    WHERE{
     ?s  ns1:name ?name;
            ns1:outcome ns1:indictment.
     }
     }
    ORDER BY ?name
""")
""")
sparql.setReturnFormat(JSON)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()
names = []


for result in results["results"]["bindings"]:
for result in results["results"]["bindings"]:
     print(result["interest"]["value"])
     names.append(result["name"]["value"])
</syntaxhighlight>


===Updating data from Blazegraph via Python===
print(names)
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, POST, DIGEST


namespace = "kb"
# Print out the minimum, average and maximum indictment days for all the indictments in the graph.
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql")


sparql.setMethod(POST)
sparql.setQuery("""
sparql.setQuery("""
     PREFIX ex: <http://example.org/>
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
     INSERT DATA{
     PREFIX ns1: <http://example.org#>
    ex:Cade ex:interest ex:Mathematics.
 
     }
     SELECT (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
        ?s  ns1:indictment_days ?days;
            ns1:outcome ns1:indictment.
      
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
    BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
}
""")
""")


results = sparql.query()
sparql.setReturnFormat(JSON)
print(results.response.read())
results = sparql.query().convert()


for result in results["results"]["bindings"]:
    print(f'The longest an investigation lasted was: {result["max"]["value"]}')
    print(f'The shortest an investigation lasted was: {result["min"]["value"]}')
    print(f'The average investigation lasted: {result["avg"]["value"]}')


</syntaxhighlight>
# Print out the minimum, average and maximum indictment days for all the indictments in the graph per investigation.
===Retrieving data from Wikidata with SparqlWrapper===
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, JSON
 
sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
# In the query I want to select all the Vitamins in wikidata.


sparql.setQuery("""
sparql.setQuery("""
     SELECT ?nutrient ?nutrientLabel WHERE
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
{
    PREFIX ns1: <http://example.org#>
  ?nutrient wdt:P279 wd:Q34956.
 
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
     SELECT ?investigation (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
}
    ?s  ns1:indictment_days ?days;
        ns1:outcome ns1:indictment;
        ns1:investigation ?investigation.
   
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
    BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
    }
    GROUP BY ?investigation
""")
""")


Line 865: Line 824:


for result in results["results"]["bindings"]:
for result in results["results"]["bindings"]:
     print(result["nutrient"]["value"], "   ", result["nutrientLabel"]["value"])
     print(f'{result["investigation"]["value"]} - min: {result["min"]["value"]}, max: {result["max"]["value"]}, avg: {result["avg"]["value"]}')
 
</syntaxhighlight>
</syntaxhighlight>


=Wikidata SPARQL (Lab 6)=
===Use a DESCRIBE query to retrieve some triples about your entity===


More examples can be found in the example section on the official query service here: https://query.wikidata.org/.
<syntaxhighlight lang="SPARQL">
DESCRIBE wd:Q42 LIMIT 100
</syntaxhighlight>
 
===Use a SELECT query to retrieve the first 100 triples about your entity===
 
<syntaxhighlight lang="SPARQL">
SELECT * WHERE {
  wd:Q42 ?p ?o .
} LIMIT 100
</syntaxhighlight>


===Download from BlazeGraph===
===Write a local SELECT query that embeds a SERVICE query to retrieve the first 100 triples about your entity to your local machine===


<syntaxhighlight>
<syntaxhighlight lang="SPARQL">
"""
PREFIX wd: <http://www.wikidata.org/entity/>
Dumps a database to a local RDF file.
You need to install the SPARQLWrapper package first...
"""


import datetime
SELECT * WHERE {
from SPARQLWrapper import SPARQLWrapper, RDFXML
    SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
        SELECT * WHERE {
            wd:Q42 ?p ?o .
        } LIMIT 100
    }
}
</syntaxhighlight>


# your namespace, the default is 'kb'
===Change the SELECT query to an INSERT query that adds the Wikidata triples your local repository===
ns = 'kb'


# the SPARQL endpoint
<syntaxhighlight lang="SPARQL">
endpoint = 'http://info216.i2s.uib.no/bigdata/namespace/' + ns + '/sparql'
PREFIX wd: <http://www.wikidata.org/entity/>


# - the endpoint just moved, the old one was:
INSERT {
# endpoint = 'http://i2s.uib.no:8888/bigdata/namespace/' + ns + '/sparql'
    wd:Q42 ?p ?o .
} WHERE {
    SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
        SELECT * WHERE {
            wd:Q42 ?p ?o .
        } LIMIT 100
    }
}
</syntaxhighlight>


# create wrapper
===Use a FILTER statement to only SELECT primary triples in this sense.===
wrapper = SPARQLWrapper(endpoint)


# prepare the SPARQL update
<syntaxhighlight lang="SPARQL">
wrapper.setQuery('CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }')
PREFIX wd: <http://www.wikidata.org/entity/>
wrapper.setReturnFormat(RDFXML)


# execute the SPARQL update and convert the result to an rdflib.Graph
SELECT * WHERE {
graph = wrapper.query().convert()
    wd:Q42 ?p ?o .
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (STRSTARTS(STR(?o), STR(wd:)))
} LIMIT 100
</syntaxhighlight>


# the destination file, with code to make it timestamped
===Use Wikidata's in-built SERVICE wikibase:label to get labels for all the object resources===
destfile = 'rdf_dumps/slr-kg4news-' + datetime.datetime.now().strftime('%Y%m%d-%H%M') + '.rdf'


# serialize the result to file
<syntaxhighlight lang="SPARQL">
graph.serialize(destination=destfile, format='ttl')
PREFIX wd: <http://www.wikidata.org/entity/>


# report and quit
SELECT ?p ?oLabel WHERE {
print('Wrote %u triples to file %s .' %
    wd:Q42 ?p ?o .
      (len(res), destfile))
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (STRSTARTS(STR(?o), STR(wd:)))
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
} LIMIT 100
</syntaxhighlight>
</syntaxhighlight>


===Query Dbpedia with SparqlWrapper===
===Edit your query (by relaxing the FILTER expression) so it also returns triples where the object has DATATYPE xsd:string.===


<syntaxhighlight>
<syntaxhighlight lang="SPARQL">
from SPARQLWrapper import SPARQLWrapper, JSON
PREFIX wd: <http://www.wikidata.org/entity/>


sparql = SPARQLWrapper("http://dbpedia.org/sparql")
SELECT ?p ?oLabel ?o WHERE {
    wd:Q42 ?p ?o .
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (
      STRSTARTS(STR(?o), STR(wd:)) ||  # comment out this whole line to see only string literals!
      DATATYPE(?o) = xsd:string
    )
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
} LIMIT 100
</syntaxhighlight>


sparql.setQuery("""
===Relax the FILTER expression again so it also returns triples with these three predicates (rdfs:label, skos:altLabel and schema:description) ===
    PREFIX dbr: <http://dbpedia.org/resource/>
    PREFIX dbo: <http://dbpedia.org/ontology/>
    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
    SELECT ?comment
    WHERE {
    dbr:Barack_Obama rdfs:comment ?comment.
    FILTER (langMatches(lang(?comment),"en"))
    }
""")


sparql.setReturnFormat(JSON)
<syntaxhighlight lang="SPARQL">
results = sparql.query().convert()
PREFIX wd: <http://www.wikidata.org/entity/>


for result in results["results"]["bindings"]:
SELECT ?p ?oLabel ?o WHERE {
     print(result["comment"]["value"])
    wd:Q42 ?p ?o .
     FILTER (
      (STRSTARTS(STR(?p), STR(wdt:)) &&  # comment out these three lines to see only fingerprint literals!
      STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
      ||
      (?p IN (rdfs:label, skos:altLabel, schema:description) &&
      DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
    )
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
} LIMIT 100
</syntaxhighlight>
</syntaxhighlight>


==Lifting CSV to RDF==
===Try to restrict the FILTER expression again so that, when the predicate is rdfs:label, skos:altLabel and schema:description, the object must have LANG "en" ===


<syntaxhighlight>
<syntaxhighlight lang="SPARQL">
from rdflib import Graph, Literal, Namespace, URIRef
PREFIX wikibase: <http://wikiba.se/ontology#>
from rdflib.namespace import RDF, FOAF, RDFS, OWL
PREFIX bd: <http://www.bigdata.com/rdf#>
import pandas as pd
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX schema: <http://schema.org/>
 
SELECT * WHERE {
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
    SELECT ?p ?oLabel ?o WHERE {
        wd:Q42 ?p ?o .
 
        FILTER (
          (STRSTARTS(STR(?p), STR(wdt:)) &&
          STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
          ||
          (?p IN (rdfs:label, skos:altLabel, schema:description) &&
          DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
        )


g = Graph()
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
ex = Namespace("http://example.org/")
g.bind("ex", ex)


# Load the CSV data as a pandas Dataframe.
    } LIMIT 100
csv_data = pd.read_csv("task1.csv")
  }
}
</syntaxhighlight>


# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
===Change the SELECT query to an INSERT query that adds the Wikidata triples your local repository ===
csv_data = csv_data.replace(to_replace=" ", value="_", regex=True)


# Here I mark all missing/empty data as "unknown". This makes it easy to delete triples containing this later.
<syntaxhighlight lang="SPARQL">
csv_data = csv_data.fillna("unknown")
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX schema: <http://schema.org/>


# Loop through the CSV data, and then make RDF triples.
INSERT {
for index, row in csv_data.iterrows():
  wd:Q42 ?p ?o .
    # The names of the people act as subjects.
  ?o rdfs:label ?oLabel .
    subject = row['Name']
} WHERE {
    # Create triples: e.g. "Cade_Tracey - age - 27"
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
     g.add((URIRef(ex + subject), URIRef(ex + "age"), Literal(row["Age"])))
     SELECT ?p ?oLabel ?o WHERE {
    g.add((URIRef(ex + subject), URIRef(ex + "married"), URIRef(ex + row["Spouse"])))
        wd:Q42 ?p ?o .
    g.add((URIRef(ex + subject), URIRef(ex + "country"), URIRef(ex + row["Country"])))


    # If We want can add additional RDF/RDFS/OWL information e.g
        FILTER (
    g.add((URIRef(ex + subject), RDF.type, FOAF.Person))
          (STRSTARTS(STR(?p), STR(wdt:)) &&
          STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
          ||
          (?p IN (rdfs:label, skos:altLabel, schema:description) &&
          DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
        )


# I remove triples that I marked as unknown earlier.
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
g.remove((None, None, URIRef("http://example.org/unknown")))


# Clean printing of the graph.
    } LIMIT 500
print(g.serialize(format="turtle").decode())
  }
}
</syntaxhighlight>
</syntaxhighlight>


===CSV file for above example===
==If you have more time ==
===You must therefore REPLACE all wdt: prefixes of properties with wd: prefixes and BIND the new URI AS a new variable, for example ?pw. ===
 
<syntaxhighlight lang="SPARQL">
PREFIX wd: <http://www.wikidata.org/entity/>
 
SELECT ?pwLabel ?oLabel WHERE {
    wd:Q42 ?p ?o .
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (STRSTARTS(STR(?o), STR(wd:)))
    BIND (IRI(REPLACE(STR(?p), STR(wdt:), STR(wd:))) AS ?pw)


<syntaxhighlight>
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
"Name","Age","Spouse","Country"
"Cade Tracey","26","Mary Jackson","US"
} LIMIT 100
"Bob Johnson","21","","Canada"
"Mary Jackson","25","","France"
"Phil Philips","32","Catherine Smith","Japan"
</syntaxhighlight>
</syntaxhighlight>


===Now you can go back to the SELECT statement that returned primary triples with only resource objects (not literal objects or fingerprints). Extend it so it also includes primary triples "one step out", i.e., triples where the subjects are objects of triples involving your reference entity. ===
<syntaxhighlight lang="SPARQL">
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX schema: <http://schema.org/>
INSERT {
  wd:Q42 ?p1 ?o1 .
  ?o1 rdfs:label ?o1Label .
  ?o1 ?p2 ?o2 .
  ?o2 rdfs:label ?o2Label .
} WHERE {
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
    SELECT ?p1 ?o1Label ?o1 ?p2 ?o2Label ?o2 WHERE {
        wd:Q42 ?p1 ?o1 .
        ?o1 ?p2 ?o2 .
        FILTER (
          STRSTARTS(STR(?p1), STR(wdt:)) &&
          STRSTARTS(STR(?o1), STR(wd:)) &&
          STRSTARTS(STR(?p2), STR(wdt:)) &&
          STRSTARTS(STR(?o2), STR(wd:))
        )
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
    } LIMIT 500
  }
}
</syntaxhighlight>


=Coding Tasks Lab 6=
=CSV to RDF (Lab 7)=
<syntaxhighlight>
import pandas as pd


<syntaxhighlight lang="Python">


from rdflib import Graph, Namespace, URIRef, Literal, BNode
#Imports
from rdflib.namespace import RDF, XSD
import re
from pandas import *
from numpy import nan
from rdflib import Graph, Namespace, URIRef, Literal, RDF, XSD, FOAF
from spotlight import SpotlightException, annotate


SERVER = "https://api.dbpedia-spotlight.org/en/annotate"
# Test around with the confidence, and see how many names changes depending on the confidence.
# However, be aware that anything lower than this (0.83) it will replace James W. McCord and other names that includes James with LeBron James
CONFIDENCE = 0.83


ex = Namespace("http://example.org/")
# This function uses DBpedia Spotlight, which was not a part of the CSV lab this year. 
sem = Namespace("http://semanticweb.cs.vu.nl/2009/11/sem/")
def annotate_entity(entity, filters={'types': 'DBpedia:Person'}):
annotations = []
try:
annotations = annotate(address=SERVER, text=entity, confidence=CONFIDENCE, filters=filters)
except SpotlightException as e:
print(e)
return annotations


g = Graph()
g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)
g.bind("ex", ex)
g.bind("sem", sem)


#Pandas' read_csv function to load russia-investigation.csv
df = read_csv("russia-investigation.csv")
#Replaces all instances of nan to None type with numpy's nan
df = df.replace(nan, None)
#Function that prepares the values to be added to the graph as a URI (ex infront) or Literal
def prepareValue(row):
if row == None: #none type
value = Literal(row)
elif isinstance(row, str) and re.match(r'\d{4}-\d{2}-\d{2}', row): #date
value = Literal(row, datatype=XSD.date)
elif isinstance(row, bool): #boolean value (true / false)
value = Literal(row, datatype=XSD.boolean)
elif isinstance(row, int): #integer
value = Literal(row, datatype=XSD.integer)
elif isinstance(row, str): #string
value = URIRef(ex + row.replace('"', '').replace(" ", "_").replace(",","").replace("-", "_"))
elif isinstance(row, float): #float
value = Literal(row, datatype=XSD.float)
return value
#Convert the non-semantic CSV dataset into a semantic RDF
def csv_to_rdf(df):
for index, row in df.iterrows():
id = URIRef(ex + "Investigation_" + str(index))
investigation = prepareValue(row["investigation"])
investigation_start = prepareValue(row["investigation-start"])
investigation_end = prepareValue(row["investigation-end"])
investigation_days = prepareValue(row["investigation-days"])
indictment_days = prepareValue(row["indictment-days "])
cp_date = prepareValue(row["cp-date"])
cp_days = prepareValue(row["cp-days"])
overturned = prepareValue(row["overturned"])
pardoned = prepareValue(row["pardoned"])
american = prepareValue(row["american"])
outcome = prepareValue(row["type"])
name_ex = prepareValue(row["name"])
president_ex = prepareValue(row["president"])
#Spotlight Search
name = annotate_entity(str(row['name']))
president = annotate_entity(str(row['president']).replace(".", ""))
#Adds the tripples to the graph
g.add((id, RDF.type, ex.Investigation))
g.add((id, ex.investigation, investigation))
g.add((id, ex.investigation_start, investigation_start))
g.add((id, ex.investigation_end, investigation_end))
g.add((id, ex.investigation_days, investigation_days))
g.add((id, ex.indictment_days, indictment_days))
g.add((id, ex.cp_date, cp_date))
g.add((id, ex.cp_days, cp_days))
g.add((id, ex.overturned, overturned))
g.add((id, ex.pardoned, pardoned))
g.add((id, ex.american, american))
g.add((id, ex.outcome, outcome))


# Removing unwanted characters
#Spotlight search
df = pd.read_csv('russia-investigation.csv')
#Name
# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
try:
df = df.replace(to_replace=" ", value="_", regex=True)
g.add((id, ex.person, URIRef(name[0]["URI"])))
# This may seem odd, but in the data set we have a name like this:("Scooter"). So we have to remove quotation marks
except:
df = df.replace(to_replace=f'"', value="", regex=True)
g.add((id, ex.person, name_ex))
# # Here I mark all missing/empty data as "unknown". This makes it easy to delete triples containing this later.
df = df.fillna("unknown")


# Loop through the CSV data, and then make RDF triples.
#President
for index, row in df.iterrows():
try:
    name = row['investigation']
g.add((id, ex.president, URIRef(president[0]["URI"])))
    investigation = URIRef(ex + name)
except:
    g.add((investigation, RDF.type, sem.Event))
g.add((id, ex.president, president_ex))
    investigation_start = row["investigation-start"]
    g.add((investigation, sem.hasBeginTimeStamp, Literal(
        investigation_start, datatype=XSD.datetime)))
    investigation_end = row["investigation-end"]
    g.add((investigation, sem.hasEndTimeStamp, Literal(
        investigation_end, datatype=XSD.datetime)))
    investigation_end = row["investigation-days"]
    g.add((investigation, sem.hasXSDDuration, Literal(
        investigation_end, datatype=XSD.Days)))
    person = row["name"]
    person = URIRef(ex + person)
    g.add((investigation, sem.Actor, person))
    result = row['type']
    g.add((investigation, sem.hasSubEvent, Literal(result, datatype=XSD.string)))
    overturned = row["overturned"]
    g.add((investigation, ex.overtuned, Literal(overturned, datatype=XSD.boolean)))
    pardoned = row["pardoned"]
    g.add((investigation, ex.pardon, Literal(pardoned, datatype=XSD.boolean)))


g.serialize("output.ttl", format="ttl")
csv_to_rdf(df)
print(g.serialize(format="turtle"))
print(g.serialize())
g.serialize("lab7.ttl", format="ttl")


</syntaxhighlight>
</syntaxhighlight>
<!--
==Lifting XML to RDF==
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF, XSD, RDFS
import xml.etree.ElementTree as ET


g = Graph()
=JSON-LD (Lab 8)=
ex = Namespace("http://example.org/TV/")
== Task 1) Basic JSON-LD ==
prov = Namespace("http://www.w3.org/ns/prov#")
 
g.bind("ex", ex)
<syntaxhighlight lang="JSON-LD">
g.bind("prov", prov)


tree = ET.parse("tv_shows.xml")
{
root = tree.getroot()
    "@context": {
        "@base": "http://example.org/",
        "edges": "http://example.org/triple",
        "start": "http://example.org/source",
        "rel": "http://exaxmple.org/predicate",
        "end": "http://example.org/object",
        "Person" : "http://example.org/Person",
        "birthday" : {
            "@id" : "http://example.org/birthday",
            "@type" : "xsd:date"
        },
        "nameEng" : {
            "@id" : "http://example.org/en/name",
            "@language" : "en"
        },
        "nameFr" : {
            "@id" : "http://example.org/fr/name",
            "@language" : "fr"
        },
        "nameCh" : {
            "@id" : "http://example.org/ch/name",
            "@language" : "ch"
        },
        "age" : {
            "@id" : "http://example.org/age",
            "@type" : "xsd:int"
        },
        "likes" : "http://example.org/games/likes",
        "haircolor" : "http://example.org/games/haircolor"
    },
    "@graph": [
        {
            "@id": "people/Jeremy",
            "@type": "Person",
            "birthday" : "1987.1.1",
            "nameEng" : "Jeremy",
            "age" : 26
        },
        {
            "@id": "people/Tom",
            "@type": "Person"
        },
        {
            "@id": "people/Ju",
            "@type": "Person",
            "birthday" : "2001.1.1",
            "nameCh" : "Ju",
            "age" : 22,
            "likes" : "bastketball"
        },
        {
            "@id": "people/Louis",
            "@type": "Person",
            "birthday" : "1978.1.1",
            "haircolor" : "Black",
            "nameFr" : "Louis",
            "age" : 45
        },
        {"edges" : [
        {
            "start" : "people/Jeremy",
            "rel" : "knows",
            "end" : "people/Tom"
        },
        {
            "start" : "people/Tom",
            "rel" : "knows",
            "end" : "people/Louis"
        },
        {
            "start" : "people/Louis",
            "rel" : "teaches",
            "end" : "people/Ju"
        },
        {
            "start" : "people/Ju",
            "rel" : "plays",
            "end" : "people/Jeremy"
        },
        {
            "start" : "people/Ju",
            "rel" : "plays",
            "end" : "people/Tom"
        }
        ]}
    ]
}


for tv_show in root.findall('tv_show'):
    show_id = tv_show.attrib["id"]
    title = tv_show.find("title").text


    g.add((URIRef(ex + show_id), ex.title, Literal(title, datatype=XSD.string)))
</syntaxhighlight>
    g.add((URIRef(ex + show_id), RDF.type, ex.TV_Show))


    for actor in tv_show.findall("actor"):
== Task 2 & 3) Retrieving JSON-LD from ConceptNet / Programming JSON-LD in Python ==
        first_name = actor.find("firstname").text
        last_name = actor.find("lastname").text
        full_name = first_name + "_" + last_name
       
        g.add((URIRef(ex + show_id), ex.stars, URIRef(ex + full_name)))
        g.add((URIRef(ex + full_name), ex.starsIn, URIRef(title)))
        g.add((URIRef(ex + full_name), RDF.type, ex.Actor))


print(g.serialize(format="turtle").decode())
<syntaxhighlight lang="Python">
</syntaxhighlight>
 
import rdflib


CN_BASE = 'http://api.conceptnet.io/c/en/'


==RDFS==
g = rdflib.Graph()
g.parse(CN_BASE+'indictment', format='json-ld')


===RDFS-plus (OWL) Properties===
# To download JSON object:
<syntaxhighlight>
g.add((ex.married, RDF.type, OWL.SymmetricProperty))
g.add((ex.married, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.livesWith, RDF.type, OWL.ReflexiveProperty))
g.add((ex.livesWith, RDF.type, OWL.SymmetricProperty))
g.add((ex.sibling, RDF.type, OWL.TransitiveProperty))
g.add((ex.sibling, RDF.type, OWL.SymmetricProperty))
g.add((ex.sibling, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.hasFather, RDF.type, OWL.FunctionalProperty))
g.add((ex.hasFather, RDF.type, OWL.AsymmetricProperty))
g.add((ex.hasFather, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.fatherOf, RDF.type, OWL.AsymmetricProperty))
g.add((ex.fatherOf, RDF.type, OWL.IrreflexiveProperty))


# Sometimes there is no definite answer, and it comes down to how we want to model our properties
import json
# e.g is livesWith a transitive property? Usually yes, but we can also want to specify that a child lives with both of her divorced parents.
import requests
# which means that: (mother livesWith child % child livesWith father) != mother livesWith father. Which makes it non-transitive.
</syntaxhighlight>


===RDFS inference with RDFLib===
json_obj = requests.get(CN_BASE+'indictment').json()
You can use the OWL-RL package to add inference capabilities to RDFLib. It can be installed using the pip install command:
<syntaxhighlight>
pip install owlrl
</syntaxhighlight>
Or download it from [https://github.com/RDFLib/OWL-RL GitHub] and copy the ''owlrl'' subfolder into your project folder next to your Python files.


[https://owl-rl.readthedocs.io/en/latest/owlrl.html OWL-RL documentation.]
# To change the @context:


Example program to get you started. In this example we are creating the graph using sparql.update, but it is also possible to parse the data from a file.
context = {
<syntaxhighlight>
    "@base": "http://ex.org/",
import rdflib.plugins.sparql.update
    "edges": "http://ex.org/triple/",
import owlrl.RDFSClosure
    "start": "http://ex.org/s/",
    "rel": "http://ex.org/p/",
    "end": "http://ex.org/o/",
    "label": "http://ex.org/label"
}
json_obj['@context'] = context
json_str = json.dumps(json_obj)


g = rdflib.Graph()
g = rdflib.Graph()
g.parse(data=json_str, format='json-ld')


ex = rdflib.Namespace('http://example.org#')
# To extract triples (here with labels):
g.bind('', ex)


g.update("""
r = g.query("""
PREFIX ex: <http://example.org#>
        SELECT ?s ?sLabel ?p ?o ?oLabel WHERE {
PREFIX owl: <http://www.w3.org/2002/07/owl#>
            ?edge
INSERT DATA {
                <http://ex.org/s/> ?s ;
    ex:Socrates rdf:type ex:Man .
                <http://ex.org/p/> ?p ;
    ex:Man rdfs:subClassOf ex:Mortal .
                <http://ex.org/o/> ?o .
}""")
            ?s <http://ex.org/label> ?sLabel .
            ?o <http://ex.org/label> ?oLabel .
}
        """, initNs={'cn': CN_BASE})
print(r.serialize(format='txt').decode())
 
# Construct a new graph:


rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
r = g.query("""
# RDF_Semantics parameters:
        CONSTRUCT {
# - graph (rdflib.Graph) – The RDF graph to be extended.
            ?s ?p ?o .
# - axioms (bool) – Whether (non-datatype) axiomatic triples should be added or not.
            ?s <http://ex.org/label> ?sLabel .
# - daxioms (bool) – Whether datatype axiomatic triples should be added or not.
            ?o <http://ex.org/label> ?oLabel .
# - rdfs (bool) – Whether RDFS inference is also done (used in subclassed only).
        } WHERE {
# For now, you will in most cases use all False in RDFS_Semtantics.
            ?edge <http://ex.org/s/> ?s ;
                  <http://ex.org/p/> ?p ;
                  <http://ex.org/o/> ?o .
            ?s <http://ex.org/label> ?sLabel .
            ?o <http://ex.org/label> ?oLabel .
}
        """, initNs={'cn': CN_BASE})


# Generates the closure of the graph - generates the new entailed triples, but does not add them to the graph.
print(r.graph.serialize(format='ttl'))
rdfs.closure()
# Adds the new triples to the graph and empties the RDFS triple-container.
rdfs.flush_stored_triples()


# Ask-query to check whether a new triple has been generated from the entailment.
b = g.query("""
PREFIX ex: <http://example.org#>
ASK {
    ex:Socrates rdf:type ex:Mortal .
}
""")
print('Result: ' + bool(b))
</syntaxhighlight>
</syntaxhighlight>


===Language tagged RDFS labels===
=SHACL (Lab 9)=
<syntaxhighlight>
 
from rdflib import Graph, Namespace, Literal
<syntaxhighlight lang="Python">
from rdflib.namespace import RDFS
 
from pyshacl import validate
from rdflib import Graph
 
data_graph = Graph()
# parses the Turtle example from the task
data_graph.parse("data_graph.ttl")
 
prefixes = """
@prefix ex: <http://example.org/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix sh: <http://www.w3.org/ns/shacl#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
"""
 
shape_graph = """
ex:PUI_Shape
    a sh:NodeShape ;
    sh:targetClass ex:PersonUnderInvestigation ;
    sh:property [
        sh:path foaf:name ;
        sh:minCount 1 ; #Every person under investigation has exactly one name.
        sh:maxCount 1 ; #Every person under investigation has exactly one name.
        sh:datatype rdf:langString ; #All person names must be language-tagged
    ] ;
    sh:property [
        sh:path ex:chargedWith ;
        sh:nodeKind sh:IRI ; #The object of a charged with property must be a URI.
        sh:class ex:Offense ; #The object of a charged with property must be an offense.
    ] .
 
# --- If you have more time tasks ---
ex:User_Shape rdf:type sh:NodeShape;
    sh:targetClass ex:Indictment;
    # The only allowed values for ex:american are true, false or unknown.
    sh:property [
        sh:path ex:american;
        sh:pattern "(true|false|unknown)" ;
    ];
   
    # The value of a property that counts days must be an integer.
    sh:property [
        sh:path ex:indictment_days;
        sh:datatype xsd:integer;
    ]; 
    sh:property [
        sh:path ex:investigation_days;
        sh:datatype xsd:integer;
    ];
   
    # The value of a property that indicates a start date must be xsd:date.
    sh:property [
        sh:path ex:investigation_start;
        sh:datatype xsd:date;
    ];
 
    # The value of a property that indicates an end date must be xsd:date or unknown (tip: you can use sh:or (...) ).
    sh:property [
        sh:path ex:investigation_end;
        sh:or (
        [ sh:datatype xsd:date ]
        [ sh:hasValue "unknown" ]
    )];
   
    # Every indictment must have exactly one FOAF name for the investigated person.
    sh:property [
        sh:path foaf:name;
        sh:minCount 1;
        sh:maxCount 1;
    ];
   
    # Every indictment must have exactly one investigated person property, and that person must have the type ex:PersonUnderInvestigation.
    sh:property [
        sh:path ex:investigatedPerson ;
        sh:minCount 1 ;
        sh:maxCount 1 ;
        sh:class ex:PersonUnderInvestigation ;
        sh:nodeKind sh:IRI ;
    ] ;
 
    # No URI-s can contain hyphens ('-').
    sh:property [
        sh:path ex:outcome ;
        sh:nodeKind sh:IRI ;
        sh:pattern "^[^-]*$" ;
    ] ;


g = Graph()
    # Presidents must be identified with URIs.
ex = Namespace("http://example.org/")
    sh:property [
        sh:path ex:president ;
        sh:minCount 1 ;
        sh:class ex:President ;
        sh:nodeKind sh:IRI ;
    ] .
"""


g.add((ex.France, RDFS.label, Literal("Frankrike", lang="no")))
shacl_graph = Graph()
g.add((ex.France, RDFS.label, Literal("France", lang="en")))
# parses the contents of a shape_graph you made in the previous task
g.add((ex.France, RDFS.label, Literal("Francia", lang="es")))
shacl_graph.parse(data=prefixes+shape_graph)


# uses pySHACL's validate method to apply the shape_graph constraints to the data_graph
results = validate(
    data_graph,
    shacl_graph=shacl_graph,
    inference='both'
)


</syntaxhighlight>
# prints out the validation result
boolean_value, results_graph, results_text = results


==OWL==
# print(boolean_value)
===Basic inference with RDFLib===
print(results_graph.serialize(format='ttl'))
# print(results_text)


You can use the OWL-RL package again as for Lecture 5.
#Write a SPARQL query to print out each distinct sh:resultMessage in the results_graph
distinct_messages = """
PREFIX sh: <http://www.w3.org/ns/shacl#>


Instead of:  
SELECT DISTINCT ?message WHERE {
<syntaxhighlight>
    [] sh:result / sh:resultMessage ?message .
# The next three lines add inferred triples to g.
}
rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
"""
rdfs.closure()
messages = results_graph.query(distinct_messages)
rdfs.flush_stored_triples()
for row in messages:
</syntaxhighlight>
    print(row.message)
you can write this to get both RDFS and basic RDFS Plus / OWL inference:
<syntaxhighlight>
# The next three lines add inferred triples to g.
owl = owlrl.CombinedClosure.RDFS_OWLRL_Semantics(g, False, False, False)
owl.closure()
owl.flush_stored_triples()
</syntaxhighlight>


Example updates and queries:
#each sh:resultMessage in the results_graph once, along with the number of times that message has been repeated in the results
<syntaxhighlight>
count_messages = """
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX sh: <http://www.w3.org/ns/shacl#>  
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX ex: <http://example.org#>


INSERT DATA {
SELECT ?message (COUNT(?node) AS ?num_messages) WHERE {
     ex:Socrates ex:hasWife ex:Xanthippe .
     [] sh:result ?result .
     ex:hasHusband owl:inverseOf ex:hasWife .
     ?result sh:resultMessage ?message ;
            sh:focusNode ?node .
}
}
GROUP BY ?message
ORDER BY DESC(?count) ?message
"""
messages = results_graph.query(count_messages)
for row in messages:
    print("COUNT    MESSAGE")
    print(row.num_messages, "      ", row.message)
</syntaxhighlight>
</syntaxhighlight>


<syntaxhighlight>
=RDFS (Lab 10)=
ASK {
 
  ex:Xanthippe ex:hasHusband ex:Socrates .
<syntaxhighlight lang="Python">
}
 
</syntaxhighlight>
import owlrl
from rdflib import Graph, RDF, Namespace, Literal, XSD, FOAF, RDFS
from rdflib.collection import Collection
 
g = Graph()
ex = Namespace('http://example.org/')
 
g.bind("ex", ex)
g.bind("foaf", FOAF)


<syntaxhighlight>
ASK {
  ex:Socrates ^ex:hasHusband ex:Xanthippe .
}
</syntaxhighlight>


<syntaxhighlight>
NS = {
INSERT DATA {
     'ex': ex,
     ex:hasWife rdfs:subPropertyOf ex:hasSpouse .
    'rdf': RDF,
     ex:hasSpouse rdf:type owl:SymmetricProperty .
     'rdfs': RDFS,
    'foaf': FOAF,
}
}
</syntaxhighlight>


<syntaxhighlight>
#Write a small function that computes the RDFS closure on your graph.
ASK {
def flush():
  ex:Socrates ex:hasSpouse ex:Xanthippe .
    engine = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
}
    engine.closure()
</syntaxhighlight>
    engine.flush_stored_triples()


<syntaxhighlight>
#Rick Gates was charged with money laundering and tax evasion.
ASK {
g.add((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
  ex:Socrates ^ex:hasSpouse ex:Xanthippe .
g.add((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
}
</syntaxhighlight>


#When one thing that is charged with another thing,
g.add((ex.chargedWith, RDFS.domain, ex.PersonUnderInvestigation))  #the first thing (subject) is a person under investigation and
g.add((ex.chargedWith, RDFS.range, ex.Offense))  #the second thing (object) is an offense.


#Write a SPARQL query that checks the RDF type(s) of Rick Gates and money laundering in your RDF graph.
print(g.query('ASK {ex:Rick_Gates rdf:type ex:PersonUnderInvestigation}', initNs=NS).askAnswer)
print(g.query('ASK {ex:MoneyLaundering rdf:type ex:Offense}', initNs=NS).askAnswer)
flush()
print(g.query('ASK {ex:Rick_Gates rdf:type ex:PersonUnderInvestigation}', initNs=NS).askAnswer)
print(g.query('ASK {ex:MoneyLaundering rdf:type ex:Offense}', initNs=NS).askAnswer)


#A person under investigation is a FOAF person
g.add((ex.PersonUnderInvestigation, RDFS.subClassOf, FOAF.Person))
print(g.query('ASK {ex:Rick_Gates rdf:type foaf:Person}', initNs=NS).askAnswer)
flush()
print(g.query('ASK {ex:Rick_Gates rdf:type foaf:Person}', initNs=NS).askAnswer)


#Paul Manafort was convicted for tax evasion.
g.add((ex.Paul_Manafort, ex.convictedFor, ex.TaxEvasion))
#the first thing is also charged with the second thing
g.add((ex.convictedFor, RDFS.subPropertyOf, ex.chargedWith))
flush()
print(g.query('ASK {ex:Paul_Manafort ex:chargedWith ex:TaxEvasion}', initNs=NS).askAnswer)


print(g.serialize())


===XML Data for above example===
<syntaxhighlight>
<data>
    <tv_show id="1050">
        <title>The_Sopranos</title>
        <actor>
            <firstname>James</firstname>
            <lastname>Gandolfini</lastname>
        </actor>
    </tv_show>
    <tv_show id="1066">
        <title>Seinfeld</title>
        <actor>
            <firstname>Jerry</firstname>
            <lastname>Seinfeld</lastname>
        </actor>
        <actor>
            <firstname>Julia</firstname>
            <lastname>Louis-dreyfus</lastname>
        </actor>
        <actor>
            <firstname>Jason</firstname>
            <lastname>Alexander</lastname>
        </actor>
    </tv_show>
</data>
</syntaxhighlight>
</syntaxhighlight>


==Lifting HTML to RDF==
=OWL 1 (Lab 11)=
<syntaxhighlight>
<syntaxhighlight lang="Python">
from bs4 import BeautifulSoup as bs, NavigableString
 
from rdflib import Graph, URIRef, Namespace
from rdflib import Graph, RDFS, Namespace, RDF, FOAF, BNode, OWL, URIRef, Literal, XSD
from rdflib.namespace import RDF
from rdflib.collection import Collection
import owlrl


g = Graph()
g = Graph()
ex = Namespace("http://example.org/")
ex = Namespace('http://example.org/')
schema = Namespace('http://schema.org/')
dbr = Namespace('https://dbpedia.org/page/')
 
g.bind("ex", ex)
g.bind("ex", ex)
# g.bind("schema", schema)
g.bind("foaf", FOAF)
# Donald Trump and Robert Mueller are two different persons.
g.add((ex.Donald_Trump, OWL.differentFrom, ex.Robert_Mueller))
# Actually, all the names mentioned in connection with the Mueller investigation refer to different people.
b1 = BNode()
b2 = BNode()
Collection(g, b2, [ex.Robert_Mueller, ex.Paul_Manafort, ex.Rick_Gates, ex.George_Papadopoulos, ex.Michael_Flynn, ex.Michael_Cohen, ex.Roger_Stone, ex.Donald_Trump])
g.add((b1, RDF.type, OWL.AllDifferent))
g.add((b1, OWL.distinctMembers, b2))
# All these people are foaf:Persons as well as schema:Persons
g.add((FOAF.Person, OWL.equivalentClass, schema.Person))
# Tax evation is a kind of bank and tax fraud.
g.add((ex.TaxEvation, RDFS.subClassOf, ex.BankFraud))
g.add((ex.TaxEvation, RDFS.subClassOf, ex.TaxFraud))
# The Donald Trump involved in the Mueller investigation is dbpedia:Donald_Trump and not dbpedia:Donald_Trump_Jr.
g.add((ex.Donald_Trump, OWL.sameAs, dbr.Donald_Trump))
g.add((ex.Donald_Trump, OWL.differentFrom, URIRef(dbr + "Donald_Trump_Jr.")))
# Congress, FBI and the Mueller investigation are foaf:Organizations.
g.add((ex.Congress, RDF.type, FOAF.Organization))
g.add((ex.FBI, RDF.type, FOAF.Organization))
g.add((ex.Mueller_Investigation, RDF.type, FOAF.Organization))


html = open("tv_shows.html").read()
# Nothing can be both a person and an organization.
html = bs(html, features="html.parser")
g.add((FOAF.Person, OWL.disjointWith, FOAF.Organization))


shows = html.find_all('li', attrs={'class': 'show'})
# Leading an organization is a way of being involved in an organization.
for show in shows:
g.add((ex.leading, RDFS.subPropertyOf, ex.involved))
    title = show.find("h3").text
    actors = show.find('ul', attrs={'class': 'actor_list'})
    for actor in actors:
        if isinstance(actor, NavigableString):
            continue
        else:
            actor = actor.text.replace(" ", "_")
            g.add((URIRef(ex + title), ex.stars, URIRef(ex + actor)))
            g.add((URIRef(ex + actor), RDF.type, ex.Actor))


    g.add((URIRef(ex + title), RDF.type, ex.TV_Show))
# Being a campaign manager or an advisor for is a way of supporting someone.
g.add((ex.campaignManagerTo, RDFS.subPropertyOf, ex.supports))
g.add((ex.advisorTo, RDFS.subPropertyOf, ex.supports))


# Donald Trump is a politician and a Republican.
g.add((ex.Donald_Trump, RDF.type, ex.Politician))
g.add((ex.Donald_Trump, RDF.type, ex.Republican))
# A Republican politician is both a politician and a Republican.
g.add((ex.RepublicanPolitician, RDFS.subClassOf, ex.Politician))
g.add((ex.RepublicanPolitician, RDFS.subClassOf, ex.Republican))
#hasBusinessPartner
g.add((ex.Paul_Manafort, ex.hasBusinessPartner, ex.Rick_Gates))
g.add((ex.hasBusinessPartner, RDF.type, OWL.SymmetricProperty))
g.add((ex.hasBusinessPartner, RDF.type, OWL.IrreflexiveProperty))
#adviserTo
g.add((ex.Michael_Flynn, ex.adviserTo, ex.Donald_Trump))
g.add((ex.adviserTo, RDF.type, OWL.IrreflexiveProperty))
# Not necessarily asymmetric as it's not a given that they couldn't be advisors to each other 
#wasLyingTo
g.add((ex.Rick_Gates_Lying, ex.wasLyingTo, ex.FBI))
g.add((ex.wasLyingTo, RDF.type, OWL.IrreflexiveProperty))
# Not asymmetric as the subject and object could lie to each other; also in this context, the FBI can lie to you
#presidentOf
g.add((ex.Donald_Trump, ex.presidentOf, ex.USA))
g.add((ex.presidentOf, RDF.type, OWL.AsymmetricProperty))
g.add((ex.presidentOf, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.presidentOf, RDF.type, OWL.FunctionalProperty)) #can only be president of one country
#not inversefunctionalproperty as Bosnia has 3 presidents https://www.culturalworld.org/do-any-countries-have-more-than-one-president.htm
#hasPresident
g.add((ex.USA, ex.hasPresident, ex.Donald_Trump))
g.add((ex.hasPresident, RDF.type, OWL.AsymmetricProperty))
g.add((ex.hasPresident, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.hasPresident, RDF.type, OWL.InverseFunctionalProperty)) #countries do not share their president with another
#not functionalproperty as a country (Bosnia) can have more than one president
#Closure
owlrl.DeductiveClosure(owlrl.OWLRL_Semantics).expand(g)
#Serialization
print(g.serialize(format="ttl"))
# g.serialize("lab8.xml", format="xml") #serializes to XML file


print(g.serialize(format="turtle").decode())
</syntaxhighlight>
</syntaxhighlight>


===HTML code for the example above===
=OWL 2 (Lab 12)=
<syntaxhighlight>
<syntaxhighlight lang="Python">
<!DOCTYPE html>
 
<html>
@prefix : <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
<head>
@prefix dc: <http://purl.org/dc/terms#> .
    <meta charset="utf-8">
@prefix io: <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
    <title></title>
@prefix dbr: <http://dbpedia.org/resource/> .
</head>
@prefix owl: <http://www.w3.org/2002/07/owl#> .
<body>
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
    <div class="tv_shows">
@prefix xml: <http://www.w3.org/XML/1998/namespace> .
        <ul>
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
            <li class="show">
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
                <h3>The_Sopranos</h3>
@prefix prov: <http://www.w3.org/ns/prov#> .
                <div class="irrelevant_data"></div>
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
                <ul class="actor_list">
@base <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
                    <li>James Gandolfini</li>
 
                </ul>
<http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology> rdf:type owl:Ontology .
            </li>
 
            <li class="show">
#################################################################
                <h3>Seinfeld</h3>
#    Object Properties
                <div class="irrelevant_data"></div>
#################################################################
                <ul class="actor_list">
 
                    <li >Jerry Seinfeld</li>
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#indictedIn
                    <li>Jason Alexander</li>
io:indictedIn rdf:type owl:ObjectProperty ;
                    <li>Julia Louis-Dreyfus</li>
              rdfs:subPropertyOf io:involvedIn ;
                </ul>
              rdfs:domain io:InvestigatedPerson ;
            </li>
              rdfs:range io:Investigation .
        </ul>
 
    </div>
 
</body>
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#investigating
</html>
io:investigating rdf:type owl:ObjectProperty ;
</syntaxhighlight>
                rdfs:subPropertyOf io:involvedIn ;
                rdfs:domain io:Investigator ;
                rdfs:range io:Investigation .
 
 
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#involvedIn
io:involvedIn rdf:type owl:ObjectProperty ;
              rdfs:domain foaf:Person ;
              rdfs:range io:Investigation .
 
 
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#leading
io:leading rdf:type owl:ObjectProperty ;
          rdfs:subPropertyOf io:investigating ;
          rdfs:domain io:InvestigationLeader ;
          rdfs:range io:Investigation .
 
 
#################################################################
#    Data properties
#################################################################
 
###  http://purl.org/dc/elements/1.1/description
<http://purl.org/dc/elements/1.1/description> rdf:type owl:DatatypeProperty ;
                                              rdfs:domain io:Investigation ;
                                              rdfs:range xsd:string .
 
 
###  http://www.w3.org/ns/prov#endedAtTime
prov:endedAtTime rdf:type owl:DatatypeProperty ,
                          owl:FunctionalProperty ;
                rdfs:domain io:Investigation ;
                rdfs:range xsd:dateTime .
 
 
###  http://www.w3.org/ns/prov#startedAtTime
prov:startedAtTime rdf:type owl:DatatypeProperty ,
                            owl:FunctionalProperty ;
                  rdfs:domain io:Investigation ;
                  rdfs:range xsd:dateTime .
 
 
###  http://xmlns.com/foaf/0.1/name
foaf:name rdf:type owl:DatatypeProperty ;
          rdfs:domain foaf:Person ;
          rdfs:range xsd:string .
 
 
###  http://xmlns.com/foaf/0.1/title
foaf:title rdf:type owl:DatatypeProperty ;
          rdfs:domain io:Investigation ;
          rdfs:range xsd:string .
 
 
#################################################################
#    Classes
#################################################################
 
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#InvestigatedPerson
io:InvestigatedPerson rdf:type owl:Class ;
                      rdfs:subClassOf io:Person ;
                      owl:disjointWith io:Investigator .
 
 
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Investigation
io:Investigation rdf:type owl:Class .
 
 
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#InvestigationLeader
io:InvestigationLeader rdf:type owl:Class ;
                      rdfs:subClassOf io:Investigator .
 
 
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Investigator
io:Investigator rdf:type owl:Class ;
                rdfs:subClassOf io:Person .


==Web APIs with JSON==
<syntaxhighlight>
import requests
import json
import pprint


# Retrieve JSON data from API service URL. Then load it with the json library as a json object.
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Person
url = "http://api.geonames.org/postalCodeLookupJSON?postalcode=46020&#country=ES&username=demo"
io:Person rdf:type owl:Class ;
data = requests.get(url).content.decode("utf-8")
          rdfs:subClassOf foaf:Person .
data = json.loads(data)
pprint.pprint(data)
</syntaxhighlight>




==JSON-LD==
###  http://xmlns.com/foaf/0.1/Person
foaf:Person rdf:type owl:Class .


<syntaxhighlight>
import rdflib


g = rdflib.Graph()
#################################################################
#    Individuals
#################################################################


example = """
###  http://dbpedia.org/resource/Donald_Trump
{
dbr:Donald_Trump rdf:type owl:NamedIndividual ;
  "@context": {
                foaf:name "Donald Trump" .
    "name": "http://xmlns.com/foaf/0.1/name",
    "homepage": {
      "@id": "http://xmlns.com/foaf/0.1/homepage",
      "@type": "@id"
    }
  },
  "@id": "http://me.markus-lanthaler.com/",
  "name": "Markus Lanthaler",
  "homepage": "http://www.markus-lanthaler.com/"
}
"""


# json-ld parsing automatically deals with @contexts
g.parse(data=example, format='json-ld')


# serialisation does expansion by default
###  http://dbpedia.org/resource/Elizabeth_Prelogar
for line in g.serialize(format='json-ld').decode().splitlines():
dbr:Elizabeth_Prelogar rdf:type owl:NamedIndividual ;
    print(line)
                      io:investigating <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
                      foaf:name "Elizabeth Prelogar" .


# by supplying a context object, serialisation can do compaction
context = {
    "foaf": "http://xmlns.com/foaf/0.1/"
}
for line in g.serialize(format='json-ld', context=context).decode().splitlines():
    print(line)
</syntaxhighlight>


###  http://dbpedia.org/resource/Michael_Flynn
dbr:Michael_Flynn rdf:type owl:NamedIndividual ;
                  foaf:name "Michael Flynn" .


<div class="credits" style="text-align: right; direction: ltr; margin-left: 1em;">''INFO216, UiB, 2017-2020. All code examples are [https://creativecommons.org/choose/zero/ CC0].'' </div>


==OWL - Complex Classes and Restrictions==
###  http://dbpedia.org/resource/Paul_Manafort
<syntaxhighlight>
dbr:Paul_Manafort rdf:type owl:NamedIndividual ;
import owlrl
                  io:indictedIn <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
from rdflib import Graph, Literal, Namespace, BNode
                  foaf:name "Paul Manafort" .
from rdflib.namespace import RDF, OWL, RDFS
from rdflib.collection import Collection


g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)
g.bind("owl", OWL)


# a Season is either Autumn, Winter, Spring, Summer
###  http://dbpedia.org/resource/Robert_Mueller
seasons = BNode()
dbr:Robert_Mueller rdf:type owl:NamedIndividual ;
Collection(g, seasons, [ex.Winter, ex.Autumn, ex.Spring, ex.Summer])
                  io:leading <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
g.add((ex.Season, OWL.oneOf, seasons))
                  foaf:name "Robert Mueller" .


# A Parent is a Father or Mother
b = BNode()
Collection(g, b, [ex.Father, ex.Mother])
g.add((ex.Parent, OWL.unionOf, b))


# A Woman is a person who has the "female" gender
###  http://dbpedia.org/resource/Roger_Stone
br = BNode()
dbr:Roger_Stone rdf:type owl:NamedIndividual ;
g.add((br, RDF.type, OWL.Restriction))
                foaf:name "Roger Stone" .
g.add((br, OWL.onProperty, ex.gender))
g.add((br, OWL.hasValue, ex.Female))
bi = BNode()
Collection(g, bi, [ex.Person, br])
g.add((ex.Woman, OWL.intersectionOf, bi))


# A vegetarian is a Person who only eats vegetarian food
br = BNode()
g.add((br, RDF.type, OWL.Restriction))
g.add((br, OWL.onProperty, ex.eats))
g.add((br, OWL.allValuesFrom, ex.VeganFood))
bi = BNode()
Collection(g, bi, [ex.Person, br])
g.add((ex.Vegetarian, OWL.intersectionOf, bi))


# A vegetarian is a Person who can not eat meat.
###  http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)
br = BNode()
<http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> rdf:type owl:NamedIndividual ;
g.add((br, RDF.type, OWL.Restriction))
                                                                        foaf:title "Mueller Investigation" .
g.add((br, OWL.onProperty, ex.eats))
g.add((br, OWL.QualifiedCardinality, Literal(0)))
g.add((br, OWL.onClass, ex.Meat))
bi = BNode()
Collection(g, bi, [ex.Person, br])
g.add((ex.Vegetarian, OWL.intersectionOf, bi))


# A Worried Parent is a parent who has at least one sick child
br = BNode()
g.add((br, RDF.type, OWL.Restriction))
g.add((br, OWL.onProperty, ex.hasChild))
g.add((br, OWL.QualifiedMinCardinality, Literal(1)))
g.add((br, OWL.onClass, ex.Sick))
bi = BNode()
Collection(g, bi, [ex.Parent, br])
g.add((ex.WorriedParent, OWL.intersectionOf, bi))


# using the restriction above, If we now write...:
#################################################################
g.add((ex.Bob, RDF.type, ex.Parent))
#    General axioms
g.add((ex.Bob, ex.hasChild, ex.John))
#################################################################
g.add((ex.John, RDF.type, ex.Sick))
# ...we can infer with owl reasoning that Bob is a worried Parent even though we didn't specify it ourselves because Bob fullfills the restriction and Parent requirements.


</syntaxhighlight>
[ rdf:type owl:AllDifferent ;
  owl:distinctMembers ( dbr:Donald_Trump
                        dbr:Elizabeth_Prelogar
                        dbr:Michael_Flynn
                        dbr:Paul_Manafort
                        dbr:Robert_Mueller
                        dbr:Roger_Stone
                      )
] .


==Protege-OWL reasoning with HermiT==


[[:File:DL-reasoning-RoyalFamily-final.owl.txt | Example file]] from Lecture 13 about OWL-DL, rules and reasoning.
###  Generated by the OWL API (version 4.5.25.2023-02-15T19:15:49Z) https://github.com/owlcs/owlapi


-->
</syntaxhighlight>

Latest revision as of 12:44, 27 April 2024

Here we will present suggested solutions after each lab. The page will be updated as the course progresses

Getting started (Lab 1)

from rdflib import Graph, Namespace

ex = Namespace('http://example.org/')

g = Graph()

g.bind("ex", ex)

# The Mueller Investigation was lead by Robert Mueller
g.add((ex.MuellerInvestigation, ex.leadBy, ex.RobertMueller))

# It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, Michael Cohen, and Roger Stone.
g.add((ex.MuellerInvestigation, ex.involved, ex.PaulManafort))
g.add((ex.MuellerInvestigation, ex.involved, ex.RickGates))
g.add((ex.MuellerInvestigation, ex.involved, ex.GeorgePapadopoulos))
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelFlynn))
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelCohen))
g.add((ex.MuellerInvestigation, ex.involved, ex.RogerStone))

# Paul Manafort was business partner of Rick Gates
g.add((ex.PaulManafort, ex.businessPartner, ex.RickGates))

# He was campaign chairman for Donald Trump
g.add((ex.PaulManafort, ex.campaignChairman, ex.DonaldTrump))

# He was charged with money laundering, tax evasion, and foreign lobbying.
g.add((ex.PaulManafort, ex.chargedWith, ex.MoneyLaundering))
g.add((ex.PaulManafort, ex.chargedWith, ex.TaxEvasion))
g.add((ex.PaulManafort, ex.chargedWith, ex.ForeignLobbying))

# He was convicted for bank and tax fraud.
g.add((ex.PaulManafort, ex.convictedOf, ex.BankFraud))
g.add((ex.PaulManafort, ex.convictedOf, ex.TaxFraud))

# He pleaded guilty to conspiracy.
g.add((ex.PaulManafort, ex.pleadGuiltyTo, ex.Conspiracy))

# He was sentenced to prison.
g.add((ex.PaulManafort, ex.sentencedTo, ex.Prison))

# He negotiated a plea agreement.
g.add((ex.PaulManafort, ex.negotiated, ex.PleaAgreement))

# Rick Gates was charged with money laundering, tax evasion and foreign lobbying.
g.add((ex.RickGates, ex.chargedWith, ex.MoneyLaundering))
g.add((ex.RickGates, ex.chargedWith, ex.TaxEvasion))
g.add((ex.RickGates, ex.chargedWith, ex.ForeignLobbying))

# He pleaded guilty to conspiracy and lying to FBI.
g.add((ex.RickGates, ex.pleadGuiltyTo, ex.Conspiracy))
g.add((ex.RickGates, ex.pleadGuiltyTo, ex.LyingToFBI))

# Use the serialize method of rdflib.Graph to write out the model in different formats (on screen or to file)
print(g.serialize(format="ttl")) # To screen
#g.serialize("lab1.ttl", format="ttl") # To file

# Loop through the triples in the model to print out all triples that have pleading guilty as predicate
for subject, object in g[ : ex.pleadGuiltyTo :]:
    print(subject, ex.pleadGuiltyTo, object)

# --- IF you have more time tasks ---

# Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week 

#Write a method (function) that submits your model for rendering and saves the returned image to file.
import requests
import shutil

def graphToImage(graphInput):
    data = {"rdf":graphInput, "from":"ttl", "to":"png"}
    link = "http://www.ldf.fi/service/rdf-grapher"
    response = requests.get(link, params = data, stream=True)
    # print(response.content)
    print(response.raw)
    with open("lab1.png", "wb") as file:
        shutil.copyfileobj(response.raw, file)

graph = g.serialize(format="ttl")
graphToImage(graph)

RDF programming with RDFlib (Lab 2)

from rdflib import Graph, Namespace, Literal, BNode, XSD, FOAF, RDF, URIRef
from rdflib.collection import Collection

g = Graph()

# Getting the graph created in the first lab
g.parse("lab1.ttl", format="ttl")

ex = Namespace("http://example.org/")

g.bind("ex", ex)
g.bind("foaf", FOAF)

# --- Michael Cohen ---
# Michael Cohen was Donald Trump's attorney.
g.add((ex.MichaelCohen, ex.attorneyTo, ex.DonaldTrump))
# He pleaded guilty for lying to Congress.
g.add((ex.MichaelCohen, ex.pleadGuiltyTo, ex.LyingToCongress))

# --- Michael Flynn ---
# Michael Flynn was adviser to Donald Trump.
g.add((ex.MichaelFlynn, ex.adviserTo, ex.DonaldTrump))
# He pleaded guilty for lying to the FBI.
g.add((ex.MichaelFlynn, ex.pleadGuiltyTo, ex.LyingToFBI))
# He negotiated a plea agreement.
g.add((ex.MichaelFlynn, ex.negotiated, ex.PleaAgreement))

# Change your graph so it represents instances of lying as blank nodes.
# Remove the triples that will be duplicated
g.remove((ex.Michael_Flynn, ex.pleadGuiltyTo, ex.LyingToFBI)) 
g.remove((ex.Michael_Flynn, ex.negoiated, ex.PleaBargain))
g.remove((ex.Rick_Gates, ex.pleadGuiltyTo, ex.LyingToFBI))
g.remove((ex.Rick_Gates, ex.pleadGuiltyTo, ex.Conspiracy))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.ForeignLobbying))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
g.remove((ex.Michael_Cohen, ex.pleadGuiltyTo, ex.LyingToCongress))

# --- Michael Flynn ---
FlynnLying = BNode() 
g.add((FlynnLying, ex.crime, ex.LyingToFBI))
g.add((FlynnLying, ex.pleadGulityOn, Literal("2017-12-1", datatype=XSD.date)))
g.add((FlynnLying, ex.liedAbout, Literal("His communications with a former Russian ambassador during the presidential transition", datatype=XSD.string)))
g.add((FlynnLying, ex.pleaBargain, Literal("true", datatype=XSD.boolean)))
g.add((ex.Michael_Flynn, ex.pleadGuiltyTo, FlynnLying))

# --- Rick Gates ---
GatesLying = BNode()
Crimes = BNode()
Charged = BNode()
Collection(g, Crimes, [ex.LyingToFBI, ex.Conspiracy])
Collection(g, Charged, [ex.ForeignLobbying, ex.MoneyLaundering, ex.TaxEvasion])
g.add((GatesLying, ex.crime, Crimes))
g.add((GatesLying, ex.chargedWith, Charged))
g.add((GatesLying, ex.pleadGulityOn, Literal("2018-02-23", datatype=XSD.date)))
g.add((GatesLying, ex.pleaBargain, Literal("true", datatype=XSD.boolean)))
g.add((ex.Rick_Gates, ex.pleadGuiltyTo, GatesLying))

# --- Michael Cohen ---
CohenLying = BNode()
g.add((CohenLying, ex.crime, ex.LyingToCongress))
g.add((CohenLying, ex.liedAbout, ex.TrumpRealEstateDeal))
g.add((CohenLying, ex.prosecutorsAlleged, Literal("In an August 2017 letter Cohen sent to congressional committees investigating Russian election interference, he falsely stated that the project ended in January 2016", datatype=XSD.string)))
g.add((CohenLying, ex.mullerInvestigationAlleged, Literal("Cohen falsely stated that he had never agreed to travel to Russia for the real estate deal and that he did not recall any contact with the Russian government about the project", datatype=XSD.string)))
g.add((CohenLying, ex.pleadGulityOn, Literal("2018-11-29", datatype=XSD.date)))
g.add((CohenLying, ex.pleaBargain, Literal("true", datatype=XSD.boolean)))
g.add((ex.Michael_Cohen, ex.pleadGuiltyTo, CohenLying))

print(g.serialize(format="ttl"))

#Save (serialize) your graph to a Turtle file.
# g.serialize("lab2.ttl", format="ttl")

#Add a few triples to the Turtle file with more information about Donald Trump.
'''
ex:Donald_Trump ex:address [ ex:city ex:Palm_Beach ;
            ex:country ex:United_States ;
            ex:postalCode 33480 ;
            ex:residence ex:Mar_a_Lago ;
            ex:state ex:Florida ;
            ex:streetName "1100 S Ocean Blvd"^^xsd:string ] ;
    ex:previousAddress [ ex:city ex:Washington_DC ;
            ex:country ex:United_States ;
            ex:phoneNumber "1 202 456 1414"^^xsd:integer ;
            ex:postalCode "20500"^^xsd:integer ;
            ex:residence ex:The_White_House ;
            ex:streetName "1600 Pennsylvania Ave."^^xsd:string ];
    ex:marriedTo ex:Melania_Trump;
    ex:fatherTo (ex:Ivanka_Trump ex:Donald_Trump_Jr ex: ex:Tiffany_Trump ex:Eric_Trump ex:Barron_Trump).
'''

#Read (parse) the Turtle file back into a Python program, and check that the new triples are there
def serialize_Graph():
    newGraph = Graph()
    newGraph.parse("lab2.ttl")
    print(newGraph.serialize())

#Don't need this to run until after adding the triples above to the ttl file
# serialize_Graph() 

#Write a method (function) that starts with Donald Trump prints out a graph depth-first to show how the other graph nodes are connected to him
visited_nodes = set()

def create_Tree(model, nodes):
    #Traverse the model breadth-first to create the tree.
    global visited_nodes
    tree = Graph()
    children = set()
    visited_nodes |= set(nodes)
    for s, p, o in model:
        if s in nodes and o not in visited_nodes:
            tree.add((s, p, o))
            visited_nodes.add(o)
            children.add(o)
        if o in nodes and s not in visited_nodes:
            invp = URIRef(f'{p}_inv') #_inv represents inverse of
            tree.add((o, invp, s))
            visited_nodes.add(s)
            children.add(s)
    if len(children) > 0:
        children_tree = create_Tree(model, children)
        for triple in children_tree:
            tree.add(triple)
    return tree

def print_Tree(tree, root, indent=0):
    #Print the tree depth-first.
    print(str(root))
    for s, p, o in tree:
        if s==root:
            print('    '*indent + '  ' + str(p), end=' ')
            print_Tree(tree, o, indent+1)
    
tree = create_Tree(g, [ex.Donald_Trump])
print_Tree(tree, ex.Donald_Trump)

SPARQL (Lab 3-4)

List all triples

SELECT ?s ?p ?o
WHERE {?s ?p ?o .}

List the first 100 triples

SELECT ?s ?p ?o
WHERE {?s ?p ?o .}
LIMIT 100

Count the number of triples

SELECT (COUNT(*) as ?count)
WHERE {?s ?p ?o .}

Count the number of indictments

PREFIX ns1: <http://example.org#>

SELECT (COUNT(?ind) as ?amount)
WHERE {
   ?s ns1:outcome ?ind;
      ns1:outcome ns1:indictment.
}

List the names of everyone who pleaded guilty, along with the name of the investigation

PREFIX ns1: <http://example.org#>

SELECT ?name ?invname
WHERE {
   ?s ns1:name ?name;
      ns1:investigation ?invname;
      ns1:outcome ns1:guilty-plea .
}

List the names of everyone who were convicted, but who had their conviction overturned by which president

PREFIX ns1: <http://example.org#>

SELECT ?name ?president
WHERE {
   ?s ns1:name ?name;
      ns1:president ?president;
      ns1:outcome ns1:conviction;
      ns1:overturned ns1:true.
}

For each investigation, list the number of indictments made

PREFIX ns1: <http://example.org#>

SELECT ?invs (COUNT(?invs) as ?count)
WHERE {
   ?s ns1:investigation ?invs;
      ns1:outcome ns1:indictment .
}
GROUP BY ?invs

For each investigation with multiple indictments, list the number of indictments made

PREFIX ns1: <http://example.org#>

SELECT ?invs (COUNT(?invs) as ?count)
WHERE {
   ?s ns1:investigation ?invs;
      ns1:outcome ns1:indictment .
}
GROUP BY ?invs
HAVING(?count > 1)

For each investigation with multiple indictments, list the number of indictments made, sorted with the most indictments first

PREFIX ns1: <http://example.org#>

SELECT ?invs (COUNT(?invs) as ?count)
WHERE {
   ?s ns1:investigation ?invs;
      ns1:outcome ns1:indictment .
}
GROUP BY ?invs
HAVING(?count > 1)
ORDER BY DESC(?count)

For each president, list the numbers of convictions and of pardons made

PREFIX ns1: <http://example.org#>

SELECT ?president (COUNT(?outcome) as ?conviction) (COUNT(?pardon) as
?pardons)
WHERE {
   ?s ns1:president ?president;
      ns1:outcome ?outcome ;
      ns1:outcome ns1:conviction.
      OPTIONAL{
         ?s ns1:pardoned ?pardon .
         FILTER (?pardon = ns1:true)
      }
}
GROUP BY ?president

Rename mullerkg:name to something like muellerkg:person

PREFIX ns1: <http://example.org#>

DELETE{?s ns1:name ?o}
INSERT{?s ns1:person ?o}
WHERE {?s ns1:name ?o}

Update the graph so all the investigated person and president nodes become the subjects in foaf:name triples with the corresponding strings

PREFIX ns1: <http://example.org#>
PREFIX foaf: <http://xmlns.com/foaf/0.1/>

#Persons
INSERT {?person foaf:name ?name}
WHERE {
      ?investigation ns1:person ?person .
      BIND(REPLACE(STR(?person), STR(ns1:), "") AS ?name)
}

#Presidents
INSERT {?president foaf:name ?name}
WHERE {
      ?investigation ns1:president ?president .
      BIND(REPLACE(STR(?president), STR(ns1:), "") AS ?name)
}

Use INSERT DATA updates to add these triples

PREFIX ns1: <http://example.org#>

INSERT DATA {
     ns1:George_Papadopoulos ns1:adviserTo ns1:Donald_Trump;
         ns1:pleadGuiltyTo ns1:LyingToFBI;
         ns1:sentencedTo ns1:Prison.

     ns1:Roger_Stone a ns1:Republican;
         ns1:adviserTo ns1:Donald_Trump;
         ns1:officialTo ns1:Trump_Campaign;
         ns1:interactedWith ns1:Wikileaks;
         ns1:providedTestimony ns1:House_Intelligence_Committee;
         ns1:clearedOf ns1:AllCharges.
}

#To test if added
SELECT ?p ?o
WHERE {ns1:Roger_Stone ?p ?o .}

Use DELETE DATA and then INSERT DATA updates to correct that Roger Stone was cleared of all charges

PREFIX ns1: <http://example.org#>

DELETE DATA {
      ns1:Roger_Stone ns1:clearedOf ns1:AllCharges .
}

INSERT DATA {
      ns1:Roger_Stone ns1:indictedFor ns1:ObstructionOfJustice,
                                      ns1:WitnessTampering,
                                      ns1:FalseStatements.
}

#The task specifically requested DELETE DATA & INSERT DATA, put below is
a more efficient solution

DELETE{ns1:Roger_Stone ns1:clearedOf ns1:AllCharges.}
INSERT{
   ns1:Roger_Stone ns1:indictedFor ns1:ObstructionOfJustice,
                                   ns1:WitnessTampering,
                                   ns1:FalseStatements.
}
WHERE{ns1:Roger_Stone ns1:clearedOf ns1:AllCharges.}

Use a DESCRIBE query to show the updated information about Roger Stone

PREFIX ns1: <http://example.org#>

DESCRIBE ?o
WHERE {ns1:Roger_Stone ns1:indictedFor ?o .}

Use a CONSTRUCT query to create a new RDF group with triples only about Roger Stone

PREFIX ns1: <http://example.org#>

CONSTRUCT {
   ns1:Roger_Stone ?p ?o.
   ?s ?p2 ns1:Roger_Stone.
}
WHERE {
   ns1:Roger_Stone ?p ?o .
   ?s ?p2 ns1:Roger_Stone
}

Write a DELETE/INSERT statement to change one of the prefixes in your graph

PREFIX ns1: <http://example.org#>
PREFIX dbp: <https://dbpedia.org/page/>

DELETE {?s ns1:person ?o1}
INSERT {?s ns1:person ?o2}
WHERE{
   ?s ns1:person ?o1 .
   BIND (IRI(replace(str(?o1), str(ns1:), str(dbp:)))  AS ?o2)
}

#This update changes the object in triples with ns1:person as the
predicate. It changes it's prefix of ns1 (which is the
"shortcut/shorthand" for example.org) to the prefix dbp (dbpedia.org)

Write an INSERT statement to add at least one significant date to the Mueller investigation, with literal type xsd:date. Write a DELETE/INSERT statement to change the date to a string, and a new DELETE/INSERT statement to change it back to xsd:date.

#Whilst this solution is not exactly what the task asks for, I feel like
this is more appropiate given the dataset. The following update
changes the objects that uses the cp_date as predicate from a URI, to a
literal with date as it's datatype

PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX ns1: <http://example.org#>

DELETE {?s ns1:cp_date ?o}
INSERT{?s ns1:cp_date ?o3}
WHERE{
   ?s ns1:cp_date ?o .
   BIND (replace(str(?o), str(ns1:), "")  AS ?o2)
   BIND (STRDT(STR(?o2), xsd:date) AS ?o3)
}

#To test:

PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX ns1: <http://example.org#>

SELECT ?s ?o
WHERE{
   ?s ns1:cp_date ?o.
   FILTER(datatype(?o) = xsd:date)
}

#To change it to an integer, use the following code, and to change it
back to date, swap "xsd:integer" to "xsd:date"

PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX ns1: <http://example.org#>

DELETE {?s ns1:cp_date ?o}
INSERT{?s ns1:cp_date ?o2}
WHERE{
   ?s ns1:cp_date ?o .
   BIND (STRDT(STR(?o), xsd:integer) AS ?o2)
}

SPARQL Programming (Lab 5)

from rdflib import Graph, Namespace, RDF, FOAF
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE

g = Graph()
g.parse("Russia_investigation_kg.ttl")

# ----- RDFLIB -----
ex = Namespace('http://example.org#')

NS = {
    '': ex,
    'rdf': RDF,
    'foaf': FOAF,
}

# Print out a list of all the predicates used in your graph.
task1 = g.query("""
SELECT DISTINCT ?p WHERE{
    ?s ?p ?o .
}
""", initNs=NS)

print(list(task1))

# Print out a sorted list of all the presidents represented in your graph.
task2 = g.query("""
SELECT DISTINCT ?president WHERE{
    ?s :president ?president .
}
ORDER BY ?president
""", initNs=NS)

print(list(task2))

# Create dictionary (Python dict) with all the represented presidents as keys. For each key, the value is a list of names of people indicted under that president.
task3_dic = {}

task3 = g.query("""
SELECT ?president ?person WHERE{
    ?s :president ?president;
       :name ?person;
       :outcome :indictment.
}
""", initNs=NS)

for president, person in task3:
    if president not in task3_dic:
        task3_dic[president] = [person]
    else:
        task3_dic[president].append(person)

print(task3_dic)

# Use an ASK query to investigate whether Donald Trump has pardoned more than 5 people.

# This task is a lot trickier than it needs to be. As far as I'm aware RDFLib has no HAVING support, so a query like this:
task4 = g.query("""
ASK {
  	SELECT (COUNT(?s) as ?count) WHERE{
    	?s :pardoned :true;
   	   :president :Bill_Clinton  .
    }
    HAVING (?count > 5)
}
""", initNs=NS)

print(task4.askAnswer)

# Which works fine in Blazegraph and is a valid SPARQL query will always provide false in RDFLib cause it uses HAVING. 
# Instead you have to use a nested SELECT query like below, where you use FILTER instead of HAVING. Donald Trump has no pardons,
# so I have instead chosen Bill Clinton with 13 to check if the query works. 

task4 = g.query("""
    ASK{
        SELECT ?count WHERE{{
  	        SELECT (COUNT(?s) as ?count) WHERE{
    	        ?s :pardoned :true;
                   :president :Bill_Clinton  .
                }}
        FILTER (?count > 5) 
        }
    }
""", initNs=NS)

print(task4.askAnswer)

# Use a DESCRIBE query to create a new graph with information about Donald Trump. Print out the graph in Turtle format.

# By all accounts, it seems DESCRIBE querires are yet to be implemented in RDFLib, but they are attempting to implement it:
# https://github.com/RDFLib/rdflib/pull/2221 <--- Issue and proposed solution rasied
# https://github.com/RDFLib/rdflib/commit/2325b4a81724c1ccee3a131067db4fbf9b4e2629 <--- Solution commited to RDFLib
# This solution does not work. However, this proposed solution should work if DESCRIBE is implemented in RDFLib

# task5 = g.query(""" 
# DESCRIBE :Donald_Trump
# """, initNs=NS)

# print(task5.serialize())

# ----- SPARQLWrapper -----

SERVER = 'http://localhost:7200' #Might need to replace this
REPOSITORY = 'Labs' #Replace with your repository name

# Query Endpoint
sparql = SPARQLWrapper(f'{SERVER}/repositories/{REPOSITORY}') 
# Update Endpoint
sparqlUpdate = SPARQLWrapper(f'{SERVER}/repositories/{REPOSITORY}/statements')

# Ask whether there was an ongoing indictment on the date 1990-01-01.
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    ASK {
        SELECT ?end ?start
        WHERE{
            ?s ns1:investigation_end ?end;
               ns1:investigation_start ?start;
               ns1:outcome ns1:indictment.
            FILTER(?start <= "1990-01-01"^^xsd:date && ?end >= "1990-01-01"^^xsd:date) 
	    }
    }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
print(f"Are there any investigation on the 1990-01-01: {results['boolean']}")

# List ongoing indictments on that date 1990-01-01.
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    SELECT ?s
    WHERE{
        ?s ns1:investigation_end ?end;
           ns1:investigation_start ?start;
           ns1:outcome ns1:indictment.
        FILTER(?start <= "1990-01-01"^^xsd:date && ?end >= "1990-01-01"^^xsd:date) 
    }
""")

sparql.setReturnFormat(JSON)
results = sparql.query().convert()

print("The ongoing investigations on the 1990-01-01 are:")
for result in results["results"]["bindings"]:
    print(result["s"]["value"])

# Describe investigation number 100 (muellerkg:investigation_100).
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    DESCRIBE ns1:investigation_100
""")

sparql.setReturnFormat(TURTLE)
results = sparql.query().convert()

print(results)

# Print out a list of all the types used in your graph.
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>

    SELECT DISTINCT ?types
    WHERE{
        ?s rdf:type ?types . 
    }
""")

sparql.setReturnFormat(JSON)
results = sparql.query().convert()

rdf_Types = []

for result in results["results"]["bindings"]:
    rdf_Types.append(result["types"]["value"])

print(rdf_Types)

# Update the graph to that every resource that is an object in a muellerkg:investigation triple has the rdf:type muellerkg:Investigation.
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>

    INSERT{
        ?invest rdf:type ns1:Investigation .
    }
    WHERE{
        ?s ns1:investigation ?invest .
}"""

sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()

#To Test
sparql.setQuery("""
    prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX ns1: <http://example.org#>

    ASK{
        ns1:watergate rdf:type ns1:Investigation.
    }
""")

sparql.setReturnFormat(JSON)
results = sparql.query().convert()
print(results['boolean'])

# Update the graph to that every resource that is an object in a muellerkg:person triple has the rdf:type muellerkg:IndictedPerson.
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>

    INSERT{
        ?person rdf:type ns1:IndictedPerson .
    }
    WHERE{
        ?s ns1:name ?person .
}"""

sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()

#To test, run the query in the above task, replacing the ask query with e.g. ns1:Deborah_Gore_Dean rdf:type ns1:IndictedPerson

# Update the graph so all the investigation nodes (such as muellerkg:watergate) become the subject in a dc:title triple with the corresponding string (watergate) as the literal.
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX dc: <http://purl.org/dc/elements/1.1/>

    INSERT{
        ?invest dc:title ?investString.
    }
    WHERE{
        ?s ns1:investigation ?invest .
        BIND (replace(str(?invest), str(ns1:), "")  AS ?investString)
}"""

sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()

#Same test as above, replace it with e.g. ns1:watergate dc:title "watergate"

# Print out a sorted list of all the indicted persons represented in your graph.
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    PREFIX foaf: <http://xmlns.com/foaf/0.1/>

    SELECT ?name
    WHERE{
    ?s  ns1:name ?name;
            ns1:outcome ns1:indictment.
    }
    ORDER BY ?name
""")

sparql.setReturnFormat(JSON)
results = sparql.query().convert()

names = []

for result in results["results"]["bindings"]:
    names.append(result["name"]["value"])

print(names)

# Print out the minimum, average and maximum indictment days for all the indictments in the graph.

sparql.setQuery("""
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    PREFIX ns1: <http://example.org#>

    SELECT (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
        ?s  ns1:indictment_days ?days;
            ns1:outcome ns1:indictment.
    
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
    BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
}
""")

sparql.setReturnFormat(JSON)
results = sparql.query().convert()

for result in results["results"]["bindings"]:
    print(f'The longest an investigation lasted was: {result["max"]["value"]}')
    print(f'The shortest an investigation lasted was: {result["min"]["value"]}')
    print(f'The average investigation lasted: {result["avg"]["value"]}')

# Print out the minimum, average and maximum indictment days for all the indictments in the graph per investigation.

sparql.setQuery("""
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    PREFIX ns1: <http://example.org#>

    SELECT ?investigation (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
    ?s  ns1:indictment_days ?days;
        ns1:outcome ns1:indictment;
        ns1:investigation ?investigation.
    
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
    BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
    }
    GROUP BY ?investigation
""")

sparql.setReturnFormat(JSON)
results = sparql.query().convert()

for result in results["results"]["bindings"]:
    print(f'{result["investigation"]["value"]} - min: {result["min"]["value"]}, max: {result["max"]["value"]}, avg: {result["avg"]["value"]}')

Wikidata SPARQL (Lab 6)

Use a DESCRIBE query to retrieve some triples about your entity

DESCRIBE wd:Q42 LIMIT 100

Use a SELECT query to retrieve the first 100 triples about your entity

SELECT * WHERE {
  wd:Q42 ?p ?o .
} LIMIT 100

Write a local SELECT query that embeds a SERVICE query to retrieve the first 100 triples about your entity to your local machine

PREFIX wd: <http://www.wikidata.org/entity/>

SELECT * WHERE {
    SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
        SELECT * WHERE {
            wd:Q42 ?p ?o .
        } LIMIT 100
    }
}

Change the SELECT query to an INSERT query that adds the Wikidata triples your local repository

PREFIX wd: <http://www.wikidata.org/entity/>

INSERT {
    wd:Q42 ?p ?o .
} WHERE {
    SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
        SELECT * WHERE {
            wd:Q42 ?p ?o .
        } LIMIT 100
    }
}

Use a FILTER statement to only SELECT primary triples in this sense.

PREFIX wd: <http://www.wikidata.org/entity/>

SELECT * WHERE {
    wd:Q42 ?p ?o .
 
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (STRSTARTS(STR(?o), STR(wd:)))
} LIMIT 100

Use Wikidata's in-built SERVICE wikibase:label to get labels for all the object resources

PREFIX wd: <http://www.wikidata.org/entity/>

SELECT ?p ?oLabel WHERE {
    wd:Q42 ?p ?o .
 
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (STRSTARTS(STR(?o), STR(wd:)))
 
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
 
} LIMIT 100

Edit your query (by relaxing the FILTER expression) so it also returns triples where the object has DATATYPE xsd:string.

PREFIX wd: <http://www.wikidata.org/entity/>

SELECT ?p ?oLabel ?o WHERE {
    wd:Q42 ?p ?o .
 
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (
      STRSTARTS(STR(?o), STR(wd:)) ||  # comment out this whole line to see only string literals!
      DATATYPE(?o) = xsd:string
    )
 
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
 
} LIMIT 100

Relax the FILTER expression again so it also returns triples with these three predicates (rdfs:label, skos:altLabel and schema:description)

PREFIX wd: <http://www.wikidata.org/entity/>

SELECT ?p ?oLabel ?o WHERE {
    wd:Q42 ?p ?o .
 
    FILTER (
      (STRSTARTS(STR(?p), STR(wdt:)) &&  # comment out these three lines to see only fingerprint literals!
       STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
      ||
      (?p IN (rdfs:label, skos:altLabel, schema:description) &&
       DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
    )
 
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
 
} LIMIT 100

Try to restrict the FILTER expression again so that, when the predicate is rdfs:label, skos:altLabel and schema:description, the object must have LANG "en"

PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX schema: <http://schema.org/>

SELECT * WHERE {
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
    SELECT ?p ?oLabel ?o WHERE {
        wd:Q42 ?p ?o .

        FILTER (
          (STRSTARTS(STR(?p), STR(wdt:)) &&
           STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
          ||
          (?p IN (rdfs:label, skos:altLabel, schema:description) &&
           DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
        )

        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }

    } LIMIT 100
  }
}

Change the SELECT query to an INSERT query that adds the Wikidata triples your local repository

PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX schema: <http://schema.org/>

INSERT {
  wd:Q42 ?p ?o .
  ?o rdfs:label ?oLabel .
} WHERE {
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
    SELECT ?p ?oLabel ?o WHERE {
        wd:Q42 ?p ?o .

        FILTER (
          (STRSTARTS(STR(?p), STR(wdt:)) &&
           STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
          ||
          (?p IN (rdfs:label, skos:altLabel, schema:description) &&
           DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
        )

        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }

    } LIMIT 500
  }
}

If you have more time

You must therefore REPLACE all wdt: prefixes of properties with wd: prefixes and BIND the new URI AS a new variable, for example ?pw.

PREFIX wd: <http://www.wikidata.org/entity/>

SELECT ?pwLabel ?oLabel WHERE {
    wd:Q42 ?p ?o .
 
    FILTER (STRSTARTS(STR(?p), STR(wdt:)))
    FILTER (STRSTARTS(STR(?o), STR(wd:)))
 
    BIND (IRI(REPLACE(STR(?p), STR(wdt:), STR(wd:))) AS ?pw)

    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
 
} LIMIT 100

Now you can go back to the SELECT statement that returned primary triples with only resource objects (not literal objects or fingerprints). Extend it so it also includes primary triples "one step out", i.e., triples where the subjects are objects of triples involving your reference entity.

PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX bd: <http://www.bigdata.com/rdf#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX schema: <http://schema.org/>

INSERT {
  wd:Q42 ?p1 ?o1 .
  ?o1 rdfs:label ?o1Label .
  ?o1 ?p2 ?o2 .
  ?o2 rdfs:label ?o2Label .
} WHERE {
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
    SELECT ?p1 ?o1Label ?o1 ?p2 ?o2Label ?o2 WHERE {
        wd:Q42 ?p1 ?o1 .
        ?o1 ?p2 ?o2 .

        FILTER (
           STRSTARTS(STR(?p1), STR(wdt:)) &&
           STRSTARTS(STR(?o1), STR(wd:)) &&
           STRSTARTS(STR(?p2), STR(wdt:)) &&
           STRSTARTS(STR(?o2), STR(wd:))
        )

        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }

    } LIMIT 500
  }
}

CSV to RDF (Lab 7)

#Imports
import re
from pandas import *
from numpy import nan
from rdflib import Graph, Namespace, URIRef, Literal, RDF, XSD, FOAF
from spotlight import SpotlightException, annotate

SERVER = "https://api.dbpedia-spotlight.org/en/annotate"
# Test around with the confidence, and see how many names changes depending on the confidence.
# However, be aware that anything lower than this (0.83) it will replace James W. McCord and other names that includes James with LeBron James
CONFIDENCE = 0.83 

# This function uses DBpedia Spotlight, which was not a part of the CSV lab this year.  
def annotate_entity(entity, filters={'types': 'DBpedia:Person'}):
	annotations = []
	try:
		annotations = annotate(address=SERVER, text=entity, confidence=CONFIDENCE, filters=filters)
	except SpotlightException as e:
		print(e)
	return annotations

g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)

#Pandas' read_csv function to load russia-investigation.csv
df = read_csv("russia-investigation.csv")
#Replaces all instances of nan to None type with numpy's nan
df = df.replace(nan, None)

#Function that prepares the values to be added to the graph as a URI (ex infront) or Literal
def prepareValue(row):
	if row == None: #none type
		value = Literal(row)
	elif isinstance(row, str) and re.match(r'\d{4}-\d{2}-\d{2}', row): #date
		value = Literal(row, datatype=XSD.date)
	elif isinstance(row, bool): #boolean value (true / false)
		value = Literal(row, datatype=XSD.boolean)
	elif isinstance(row, int): #integer
		value = Literal(row, datatype=XSD.integer)
	elif isinstance(row, str): #string
		value = URIRef(ex + row.replace('"', '').replace(" ", "_").replace(",","").replace("-", "_"))
	elif isinstance(row, float): #float
		value = Literal(row, datatype=XSD.float)

	return value

#Convert the non-semantic CSV dataset into a semantic RDF 
def csv_to_rdf(df):
	for index, row in df.iterrows():
		id = URIRef(ex + "Investigation_" + str(index))
		investigation = prepareValue(row["investigation"])
		investigation_start = prepareValue(row["investigation-start"])
		investigation_end = prepareValue(row["investigation-end"])
		investigation_days = prepareValue(row["investigation-days"])
		indictment_days = prepareValue(row["indictment-days "])
		cp_date = prepareValue(row["cp-date"])
		cp_days = prepareValue(row["cp-days"])
		overturned = prepareValue(row["overturned"])
		pardoned = prepareValue(row["pardoned"])
		american = prepareValue(row["american"])
		outcome = prepareValue(row["type"])
		name_ex = prepareValue(row["name"])
		president_ex = prepareValue(row["president"])

		#Spotlight Search
		name = annotate_entity(str(row['name']))
		president = annotate_entity(str(row['president']).replace(".", ""))
		
		#Adds the tripples to the graph
		g.add((id, RDF.type, ex.Investigation))
		g.add((id, ex.investigation, investigation))
		g.add((id, ex.investigation_start, investigation_start))
		g.add((id, ex.investigation_end, investigation_end))
		g.add((id, ex.investigation_days, investigation_days))
		g.add((id, ex.indictment_days, indictment_days))
		g.add((id, ex.cp_date, cp_date))
		g.add((id, ex.cp_days, cp_days))
		g.add((id, ex.overturned, overturned))
		g.add((id, ex.pardoned, pardoned))
		g.add((id, ex.american, american))
		g.add((id, ex.outcome, outcome))

		#Spotlight search
		#Name
		try:
			g.add((id, ex.person, URIRef(name[0]["URI"])))
		except:
			g.add((id, ex.person, name_ex))

		#President
		try:
			g.add((id, ex.president, URIRef(president[0]["URI"])))
		except:
			g.add((id, ex.president, president_ex))

csv_to_rdf(df)
print(g.serialize())
g.serialize("lab7.ttl", format="ttl")

JSON-LD (Lab 8)

Task 1) Basic JSON-LD

{
    "@context": {
        "@base": "http://example.org/",
        "edges": "http://example.org/triple",
        "start": "http://example.org/source",
        "rel": "http://exaxmple.org/predicate",
        "end": "http://example.org/object",
        "Person" : "http://example.org/Person",
        "birthday" : {
            "@id" : "http://example.org/birthday",
            "@type" : "xsd:date"
        },
        "nameEng" : {
            "@id" : "http://example.org/en/name",
            "@language" : "en"
        },
        "nameFr" : {
            "@id" : "http://example.org/fr/name",
            "@language" : "fr"
        },
        "nameCh" : {
            "@id" : "http://example.org/ch/name",
            "@language" : "ch"
        },
        "age" : {
            "@id" : "http://example.org/age",
            "@type" : "xsd:int"
        },
        "likes" : "http://example.org/games/likes",
        "haircolor" : "http://example.org/games/haircolor"
    },
    "@graph": [
        {
            "@id": "people/Jeremy",
            "@type": "Person",
            "birthday" : "1987.1.1",
            "nameEng" : "Jeremy",
            "age" : 26
        },
        {
            "@id": "people/Tom",
            "@type": "Person"
        },
        {
            "@id": "people/Ju",
            "@type": "Person",
            "birthday" : "2001.1.1",
            "nameCh" : "Ju",
            "age" : 22,
            "likes" : "bastketball"
        },
        {
            "@id": "people/Louis",
            "@type": "Person",
            "birthday" : "1978.1.1",
            "haircolor" : "Black",
            "nameFr" : "Louis",
            "age" : 45
        },
        {"edges" : [
        {
            "start" : "people/Jeremy",
            "rel" : "knows",
            "end" : "people/Tom"
        },
        {
            "start" : "people/Tom",
            "rel" : "knows",
            "end" : "people/Louis"
        },
        {
            "start" : "people/Louis",
            "rel" : "teaches",
            "end" : "people/Ju"
        },
        {
            "start" : "people/Ju",
            "rel" : "plays",
            "end" : "people/Jeremy"
        },
        {
            "start" : "people/Ju",
            "rel" : "plays",
            "end" : "people/Tom"
        }
        ]}
    ]
}

Task 2 & 3) Retrieving JSON-LD from ConceptNet / Programming JSON-LD in Python

import rdflib

CN_BASE = 'http://api.conceptnet.io/c/en/'

g = rdflib.Graph()
g.parse(CN_BASE+'indictment', format='json-ld')

# To download JSON object:

import json
import requests

json_obj = requests.get(CN_BASE+'indictment').json()

# To change the @context:

context = {
     "@base": "http://ex.org/",
     "edges": "http://ex.org/triple/",
     "start": "http://ex.org/s/",
     "rel": "http://ex.org/p/",
     "end": "http://ex.org/o/",
     "label": "http://ex.org/label"
}
json_obj['@context'] = context
json_str = json.dumps(json_obj)

g = rdflib.Graph()
g.parse(data=json_str, format='json-ld')

# To extract triples (here with labels):

r = g.query("""
         SELECT ?s ?sLabel ?p ?o ?oLabel WHERE {
             ?edge
                 <http://ex.org/s/> ?s ;
                 <http://ex.org/p/> ?p ;
                 <http://ex.org/o/> ?o .
             ?s <http://ex.org/label> ?sLabel .
             ?o <http://ex.org/label> ?oLabel .
}
         """, initNs={'cn': CN_BASE})
print(r.serialize(format='txt').decode())

# Construct a new graph:

r = g.query("""
         CONSTRUCT {
             ?s ?p ?o .
             ?s <http://ex.org/label> ?sLabel .
             ?o <http://ex.org/label> ?oLabel .
         } WHERE {
             ?edge <http://ex.org/s/> ?s ;
                   <http://ex.org/p/> ?p ;
                   <http://ex.org/o/> ?o .
             ?s <http://ex.org/label> ?sLabel .
             ?o <http://ex.org/label> ?oLabel .
}
         """, initNs={'cn': CN_BASE})

print(r.graph.serialize(format='ttl'))

SHACL (Lab 9)

from pyshacl import validate
from rdflib import Graph

data_graph = Graph()
# parses the Turtle example from the task
data_graph.parse("data_graph.ttl")

prefixes = """
@prefix ex: <http://example.org/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix sh: <http://www.w3.org/ns/shacl#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
"""

shape_graph = """
ex:PUI_Shape
    a sh:NodeShape ;
    sh:targetClass ex:PersonUnderInvestigation ;
    sh:property [
        sh:path foaf:name ;
        sh:minCount 1 ; #Every person under investigation has exactly one name. 
        sh:maxCount 1 ; #Every person under investigation has exactly one name.
        sh:datatype rdf:langString ; #All person names must be language-tagged
    ] ;
    sh:property [
        sh:path ex:chargedWith ;
        sh:nodeKind sh:IRI ; #The object of a charged with property must be a URI.
        sh:class ex:Offense ; #The object of a charged with property must be an offense.
    ] .

# --- If you have more time tasks ---
ex:User_Shape rdf:type sh:NodeShape;
    sh:targetClass ex:Indictment;
    # The only allowed values for ex:american are true, false or unknown.
    sh:property [
        sh:path ex:american;
        sh:pattern "(true|false|unknown)" ;
    ];
    
    # The value of a property that counts days must be an integer.
    sh:property [
        sh:path ex:indictment_days;
        sh:datatype xsd:integer;
    ];   
    sh:property [
        sh:path ex:investigation_days;
        sh:datatype xsd:integer;
    ];
    
    # The value of a property that indicates a start date must be xsd:date.
    sh:property [
        sh:path ex:investigation_start;
        sh:datatype xsd:date;
    ];

    # The value of a property that indicates an end date must be xsd:date or unknown (tip: you can use sh:or (...) ).
    sh:property [
        sh:path ex:investigation_end;
        sh:or (
         [ sh:datatype xsd:date ]
         [ sh:hasValue "unknown" ]
    )];
    
    # Every indictment must have exactly one FOAF name for the investigated person.
    sh:property [
        sh:path foaf:name;
        sh:minCount 1;
        sh:maxCount 1;
    ];
    
    # Every indictment must have exactly one investigated person property, and that person must have the type ex:PersonUnderInvestigation.
    sh:property [
        sh:path ex:investigatedPerson ;
        sh:minCount 1 ;
        sh:maxCount 1 ;
        sh:class ex:PersonUnderInvestigation ;
        sh:nodeKind sh:IRI ;
    ] ;

    # No URI-s can contain hyphens ('-').
    sh:property [
        sh:path ex:outcome ;
        sh:nodeKind sh:IRI ;
        sh:pattern "^[^-]*$" ;
    ] ;

    # Presidents must be identified with URIs.
    sh:property [
        sh:path ex:president ;
        sh:minCount 1 ;
        sh:class ex:President ;
        sh:nodeKind sh:IRI ;
    ] .
"""

shacl_graph = Graph()
# parses the contents of a shape_graph you made in the previous task
shacl_graph.parse(data=prefixes+shape_graph)

# uses pySHACL's validate method to apply the shape_graph constraints to the data_graph
results = validate(
    data_graph,
    shacl_graph=shacl_graph,
    inference='both'
)

# prints out the validation result
boolean_value, results_graph, results_text = results

# print(boolean_value)
print(results_graph.serialize(format='ttl'))
# print(results_text)

#Write a SPARQL query to print out each distinct sh:resultMessage in the results_graph
distinct_messages = """
PREFIX sh: <http://www.w3.org/ns/shacl#> 

SELECT DISTINCT ?message WHERE {
    [] sh:result / sh:resultMessage ?message .
}
"""
messages = results_graph.query(distinct_messages)
for row in messages:
    print(row.message)

#each sh:resultMessage in the results_graph once, along with the number of times that message has been repeated in the results
count_messages = """
PREFIX sh: <http://www.w3.org/ns/shacl#> 

SELECT ?message (COUNT(?node) AS ?num_messages) WHERE {
    [] sh:result ?result .
    ?result sh:resultMessage ?message ;
            sh:focusNode ?node .
}
GROUP BY ?message
ORDER BY DESC(?count) ?message
"""

messages = results_graph.query(count_messages)
for row in messages:
    print("COUNT    MESSAGE")
    print(row.num_messages, "      ", row.message)

RDFS (Lab 10)

import owlrl
from rdflib import Graph, RDF, Namespace, Literal, XSD, FOAF, RDFS
from rdflib.collection import Collection

g = Graph()
ex = Namespace('http://example.org/')

g.bind("ex", ex)
g.bind("foaf", FOAF)


NS = {
    'ex': ex,
    'rdf': RDF,
    'rdfs': RDFS,
    'foaf': FOAF,
}

#Write a small function that computes the RDFS closure on your graph.
def flush():
    engine = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
    engine.closure()
    engine.flush_stored_triples()

#Rick Gates was charged with money laundering and tax evasion.
g.add((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
g.add((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))

#When one thing that is charged with another thing,
g.add((ex.chargedWith, RDFS.domain, ex.PersonUnderInvestigation))  #the first thing (subject) is a person under investigation and
g.add((ex.chargedWith, RDFS.range, ex.Offense))  #the second thing (object) is an offense.

#Write a SPARQL query that checks the RDF type(s) of Rick Gates and money laundering in your RDF graph.
print(g.query('ASK {ex:Rick_Gates rdf:type ex:PersonUnderInvestigation}', initNs=NS).askAnswer)
print(g.query('ASK {ex:MoneyLaundering rdf:type ex:Offense}', initNs=NS).askAnswer)
flush()
print(g.query('ASK {ex:Rick_Gates rdf:type ex:PersonUnderInvestigation}', initNs=NS).askAnswer)
print(g.query('ASK {ex:MoneyLaundering rdf:type ex:Offense}', initNs=NS).askAnswer)

#A person under investigation is a FOAF person
g.add((ex.PersonUnderInvestigation, RDFS.subClassOf, FOAF.Person))
print(g.query('ASK {ex:Rick_Gates rdf:type foaf:Person}', initNs=NS).askAnswer)
flush()
print(g.query('ASK {ex:Rick_Gates rdf:type foaf:Person}', initNs=NS).askAnswer)

#Paul Manafort was convicted for tax evasion.
g.add((ex.Paul_Manafort, ex.convictedFor, ex.TaxEvasion))
#the first thing is also charged with the second thing
g.add((ex.convictedFor, RDFS.subPropertyOf, ex.chargedWith)) 
flush()
print(g.query('ASK {ex:Paul_Manafort ex:chargedWith ex:TaxEvasion}', initNs=NS).askAnswer)

print(g.serialize())

OWL 1 (Lab 11)

from rdflib import Graph, RDFS, Namespace, RDF, FOAF, BNode, OWL, URIRef, Literal, XSD
from rdflib.collection import Collection
import owlrl

g = Graph()
ex = Namespace('http://example.org/')
schema = Namespace('http://schema.org/')
dbr = Namespace('https://dbpedia.org/page/')

g.bind("ex", ex)
# g.bind("schema", schema)
g.bind("foaf", FOAF)

# Donald Trump and Robert Mueller are two different persons.
g.add((ex.Donald_Trump, OWL.differentFrom, ex.Robert_Mueller))

# Actually, all the names mentioned in connection with the Mueller investigation refer to different people.
b1 = BNode()
b2 = BNode()
Collection(g, b2, [ex.Robert_Mueller, ex.Paul_Manafort, ex.Rick_Gates, ex.George_Papadopoulos, ex.Michael_Flynn, ex.Michael_Cohen, ex.Roger_Stone, ex.Donald_Trump])
g.add((b1, RDF.type, OWL.AllDifferent))
g.add((b1, OWL.distinctMembers, b2))

# All these people are foaf:Persons as well as schema:Persons
g.add((FOAF.Person, OWL.equivalentClass, schema.Person))

# Tax evation is a kind of bank and tax fraud.
g.add((ex.TaxEvation, RDFS.subClassOf, ex.BankFraud))
g.add((ex.TaxEvation, RDFS.subClassOf, ex.TaxFraud))

# The Donald Trump involved in the Mueller investigation is dbpedia:Donald_Trump and not dbpedia:Donald_Trump_Jr.
g.add((ex.Donald_Trump, OWL.sameAs, dbr.Donald_Trump))
g.add((ex.Donald_Trump, OWL.differentFrom, URIRef(dbr + "Donald_Trump_Jr.")))

# Congress, FBI and the Mueller investigation are foaf:Organizations.
g.add((ex.Congress, RDF.type, FOAF.Organization))
g.add((ex.FBI, RDF.type, FOAF.Organization))
g.add((ex.Mueller_Investigation, RDF.type, FOAF.Organization))

# Nothing can be both a person and an organization.
g.add((FOAF.Person, OWL.disjointWith, FOAF.Organization))

# Leading an organization is a way of being involved in an organization.
g.add((ex.leading, RDFS.subPropertyOf, ex.involved))

# Being a campaign manager or an advisor for is a way of supporting someone.
g.add((ex.campaignManagerTo, RDFS.subPropertyOf, ex.supports))
g.add((ex.advisorTo, RDFS.subPropertyOf, ex.supports))

# Donald Trump is a politician and a Republican.
g.add((ex.Donald_Trump, RDF.type, ex.Politician))
g.add((ex.Donald_Trump, RDF.type, ex.Republican))

# A Republican politician is both a politician and a Republican.
g.add((ex.RepublicanPolitician, RDFS.subClassOf, ex.Politician))
g.add((ex.RepublicanPolitician, RDFS.subClassOf, ex.Republican))

#hasBusinessPartner
g.add((ex.Paul_Manafort, ex.hasBusinessPartner, ex.Rick_Gates))
g.add((ex.hasBusinessPartner, RDF.type, OWL.SymmetricProperty))
g.add((ex.hasBusinessPartner, RDF.type, OWL.IrreflexiveProperty))

#adviserTo
g.add((ex.Michael_Flynn, ex.adviserTo, ex.Donald_Trump))
g.add((ex.adviserTo, RDF.type, OWL.IrreflexiveProperty))
# Not necessarily asymmetric as it's not a given that they couldn't be advisors to each other  

#wasLyingTo
g.add((ex.Rick_Gates_Lying, ex.wasLyingTo, ex.FBI))
g.add((ex.wasLyingTo, RDF.type, OWL.IrreflexiveProperty))
# Not asymmetric as the subject and object could lie to each other; also in this context, the FBI can lie to you

#presidentOf
g.add((ex.Donald_Trump, ex.presidentOf, ex.USA))
g.add((ex.presidentOf, RDF.type, OWL.AsymmetricProperty))
g.add((ex.presidentOf, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.presidentOf, RDF.type, OWL.FunctionalProperty)) #can only be president of one country
#not inversefunctionalproperty as Bosnia has 3 presidents https://www.culturalworld.org/do-any-countries-have-more-than-one-president.htm

#hasPresident
g.add((ex.USA, ex.hasPresident, ex.Donald_Trump))
g.add((ex.hasPresident, RDF.type, OWL.AsymmetricProperty))
g.add((ex.hasPresident, RDF.type, OWL.IrreflexiveProperty))
g.add((ex.hasPresident, RDF.type, OWL.InverseFunctionalProperty)) #countries do not share their president with another
#not functionalproperty as a country (Bosnia) can have more than one president

#Closure
owlrl.DeductiveClosure(owlrl.OWLRL_Semantics).expand(g)

#Serialization
print(g.serialize(format="ttl"))
# g.serialize("lab8.xml", format="xml") #serializes to XML file

OWL 2 (Lab 12)

@prefix : <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
@prefix dc: <http://purl.org/dc/terms#> .
@prefix io: <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
@prefix dbr: <http://dbpedia.org/resource/> .
@prefix owl: <http://www.w3.org/2002/07/owl#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix xml: <http://www.w3.org/XML/1998/namespace> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix prov: <http://www.w3.org/ns/prov#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@base <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .

<http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology> rdf:type owl:Ontology .

#################################################################
#    Object Properties
#################################################################

###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#indictedIn
io:indictedIn rdf:type owl:ObjectProperty ;
              rdfs:subPropertyOf io:involvedIn ;
              rdfs:domain io:InvestigatedPerson ;
              rdfs:range io:Investigation .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#investigating
io:investigating rdf:type owl:ObjectProperty ;
                 rdfs:subPropertyOf io:involvedIn ;
                 rdfs:domain io:Investigator ;
                 rdfs:range io:Investigation .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#involvedIn
io:involvedIn rdf:type owl:ObjectProperty ;
              rdfs:domain foaf:Person ;
              rdfs:range io:Investigation .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#leading
io:leading rdf:type owl:ObjectProperty ;
           rdfs:subPropertyOf io:investigating ;
           rdfs:domain io:InvestigationLeader ;
           rdfs:range io:Investigation .


#################################################################
#    Data properties
#################################################################

###  http://purl.org/dc/elements/1.1/description
<http://purl.org/dc/elements/1.1/description> rdf:type owl:DatatypeProperty ;
                                              rdfs:domain io:Investigation ;
                                              rdfs:range xsd:string .


###  http://www.w3.org/ns/prov#endedAtTime
prov:endedAtTime rdf:type owl:DatatypeProperty ,
                          owl:FunctionalProperty ;
                 rdfs:domain io:Investigation ;
                 rdfs:range xsd:dateTime .


###  http://www.w3.org/ns/prov#startedAtTime
prov:startedAtTime rdf:type owl:DatatypeProperty ,
                            owl:FunctionalProperty ;
                   rdfs:domain io:Investigation ;
                   rdfs:range xsd:dateTime .


###  http://xmlns.com/foaf/0.1/name
foaf:name rdf:type owl:DatatypeProperty ;
          rdfs:domain foaf:Person ;
          rdfs:range xsd:string .


###  http://xmlns.com/foaf/0.1/title
foaf:title rdf:type owl:DatatypeProperty ;
           rdfs:domain io:Investigation ;
           rdfs:range xsd:string .


#################################################################
#    Classes
#################################################################

###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#InvestigatedPerson
io:InvestigatedPerson rdf:type owl:Class ;
                      rdfs:subClassOf io:Person ;
                      owl:disjointWith io:Investigator .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Investigation
io:Investigation rdf:type owl:Class .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#InvestigationLeader
io:InvestigationLeader rdf:type owl:Class ;
                       rdfs:subClassOf io:Investigator .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Investigator
io:Investigator rdf:type owl:Class ;
                rdfs:subClassOf io:Person .


###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Person
io:Person rdf:type owl:Class ;
          rdfs:subClassOf foaf:Person .


###  http://xmlns.com/foaf/0.1/Person
foaf:Person rdf:type owl:Class .


#################################################################
#    Individuals
#################################################################

###  http://dbpedia.org/resource/Donald_Trump
dbr:Donald_Trump rdf:type owl:NamedIndividual ;
                 foaf:name "Donald Trump" .


###  http://dbpedia.org/resource/Elizabeth_Prelogar
dbr:Elizabeth_Prelogar rdf:type owl:NamedIndividual ;
                       io:investigating <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
                       foaf:name "Elizabeth Prelogar" .


###  http://dbpedia.org/resource/Michael_Flynn
dbr:Michael_Flynn rdf:type owl:NamedIndividual ;
                  foaf:name "Michael Flynn" .


###  http://dbpedia.org/resource/Paul_Manafort
dbr:Paul_Manafort rdf:type owl:NamedIndividual ;
                  io:indictedIn <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
                  foaf:name "Paul Manafort" .


###  http://dbpedia.org/resource/Robert_Mueller
dbr:Robert_Mueller rdf:type owl:NamedIndividual ;
                   io:leading <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
                   foaf:name "Robert Mueller" .


###  http://dbpedia.org/resource/Roger_Stone
dbr:Roger_Stone rdf:type owl:NamedIndividual ;
                foaf:name "Roger Stone" .


###  http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)
<http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> rdf:type owl:NamedIndividual ;
                                                                        foaf:title "Mueller Investigation" .


#################################################################
#    General axioms
#################################################################

[ rdf:type owl:AllDifferent ;
  owl:distinctMembers ( dbr:Donald_Trump
                        dbr:Elizabeth_Prelogar
                        dbr:Michael_Flynn
                        dbr:Paul_Manafort
                        dbr:Robert_Mueller
                        dbr:Roger_Stone
                      )
] .


###  Generated by the OWL API (version 4.5.25.2023-02-15T19:15:49Z) https://github.com/owlcs/owlapi
Retrieved from "http://info216.wiki.uib.no/index.php?title=Lab_Solutions&oldid=2540"