|
|
(147 intermediate revisions by 7 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 (Lab 1)= |
| | |
| ==Lecture 1: Python, RDFlib, and PyCharm==
| |
| | |
| | |
| ===Printing the triples of the Graph in a readable way===
| |
| <syntaxhighlight> | | <syntaxhighlight> |
| # The turtle format has the purpose of being more readable for humans.
| |
| print(g.serialize(format="turtle").decode())
| |
| </syntaxhighlight>
| |
|
| |
|
| ===Coding Tasks Lab 1===
| | from rdflib import Graph, Namespace |
| <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))
| |
| g.add((ex.France, ex.capital, ex.Paris))
| |
| g.add((ex.Cade, ex.age, Literal("27", datatype=XSD.integer)))
| |
| 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))
| |
| | |
| </syntaxhighlight>
| |
| | |
| == Lab 1/2 - Different ways to create an address ==
| |
| | |
| <syntaxhighlight>
| |
|
| |
|
| from rdflib import Graph, Namespace, URIRef, BNode, Literal
| | ex = Namespace('http://example.org/') |
| from rdflib.namespace import RDF, FOAF, XSD
| |
|
| |
|
| g = Graph() | | g = Graph() |
| ex = Namespace("http://example.org/")
| |
|
| |
|
| |
| # How to represent the address of Cade Tracey. From probably the worst solution to the best.
| |
|
| |
| # Solution 1 -
| |
| # Make the entire address into one Literal. However, Generally we want to seperate 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.
| |
|
| |
| g.add((ex.Cade_Tracey, ex.livesIn, Literal("1516_Henry_Street, Berkeley, California 94709, USA")))
| |
|
| |
|
| |
| # Solution 2 -
| |
| # Seperate the different pieces information into their own triples
| |
|
| |
| g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
| |
| g.add((ex.Cade_tracey, ex.city, Literal("Berkeley")))
| |
| g.add((ex.Cade_tracey, ex.state, Literal("California")))
| |
| g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
| |
| g.add((ex.Cade_tracey, ex.country, Literal("USA")))
| |
|
| |
|
| |
| # Solution 3 - Some parts of the addresses can make more sense to be resources than Literals.
| |
| # 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.
| |
|
| |
| g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
| |
| g.add((ex.Cade_tracey, ex.city, ex.Berkeley))
| |
| g.add((ex.Cade_tracey, ex.state, ex.California))
| |
| g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
| |
| g.add((ex.Cade_tracey, ex.country, ex.USA))
| |
|
| |
|
| |
| # Solution 4
| |
| # 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
| |
|
| |
| g.add((ex.Cade_Tracey, ex.address, ex.CadeAddress))
| |
| g.add((ex.CadeAddress, RDF.type, ex.Address))
| |
| 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
| |
|
| |
| # Blank node for Address.
| |
| 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))
| |
|
| |
|
| |
| # Solution 5 using existing vocabularies for address
| |
|
| |
| # (in this case https://schema.org/PostalAddress from schema.org).
| |
| # Also using existing ontology for places like California. (like http://dbpedia.org/resource/California from dbpedia.org)
| |
|
| |
| schema = "https://schema.org/"
| |
| dbp = "https://dpbedia.org/resource/"
| |
|
| |
| g.add((ex.Cade_Tracey, schema.address, ex.CadeAddress))
| |
| g.add((ex.CadeAddress, RDF.type, schema.PostalAddress))
| |
| g.add((ex.CadeAddress, schema.streetAddress, Literal("1516 Henry Street")))
| |
| g.add((ex.CadeAddress, schema.addresCity, dbp.Berkeley))
| |
| g.add((ex.CadeAddress, schema.addressRegion, dbp.California))
| |
| g.add((ex.CadeAddress, schema.postalCode, Literal("94709")))
| |
| g.add((ex.CadeAddress, schema.addressCountry, dbp.United_States))
| |
|
| |
| </syntaxhighlight>
| |
|
| |
|
| |
| == Lab 2 - Collection Example ==
| |
|
| |
| <syntaxhighlight>
| |
| from rdflib import Graph, Namespace
| |
| from rdflib.collection import Collection
| |
|
| |
|
| |
| # Sometimes we want to add many objects or subjects for the same predicate at once.
| |
| # In these cases we can use Collection() to save some time.
| |
| # In this case I want to add all countries that Emma has visited at once.
| |
|
| |
| b = BNode()
| |
| g.add((ex.Emma, ex.visit, b))
| |
| Collection(g, b,
| |
| [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])
| |
|
| |
| # OR
| |
|
| |
| g.add((ex.Emma, ex.visit, ex.EmmaVisits))
| |
| Collection(g, ex.EmmaVisits,
| |
| [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])
| |
|
| |
| </syntaxhighlight>
| |
|
| |
| == Lab 3/4 - SPARQL queries from the lecture ==
| |
| <syntaxhighlight>
| |
| SELECT DISTINCT ?p WHERE {
| |
| ?s ?p ?o .
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
| <syntaxhighlight>
| |
| PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
| |
|
| |
| SELECT DISTINCT ?t WHERE {
| |
| ?s rdf:type ?t .
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
| <syntaxhighlight>
| |
| PREFIX owl: <http://www.w3.org/2002/07/owl#>
| |
| CONSTRUCT {
| |
| ?s owl:sameAs ?o2 .
| |
| } WHERE {
| |
| ?s owl:sameAs ?o .
| |
| FILTER(REGEX(STR(?o), "^http://www\\.", "s"))
| |
| BIND(URI(REPLACE(STR(?o), "^http://www\\.", "http://", "s")) AS ?o2)
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
| ==Lab 3/4 - SPARQL - Select all contents of lists (rdfllib.Collection)==
| |
| <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.
| |
|
| |
| PREFIX ex: <http://example.org/>
| |
| PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
| |
|
| |
| SELECT ?visit
| |
| WHERE {
| |
| ex:Emma ex:visit/rdf:rest*/rdf:first ?visit
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
|
| |
| == Lab 4/6 - SELECTING data from Blazegraph via Python ==
| |
| <syntaxhighlight>
| |
|
| |
| from SPARQLWrapper import SPARQLWrapper, JSON
| |
|
| |
| # This creates a server connection to the same URL that contains the graphic interface for Blazegraph.
| |
| # You also need to add "sparql" to end of the URL like below.
| |
|
| |
| sparql = SPARQLWrapper("http://localhost:9999/blazegraph/sparql")
| |
|
| |
| # SELECT all triples in the database.
| |
|
| |
| sparql.setQuery("""
| |
| SELECT DISTINCT ?p WHERE {
| |
| ?s ?p ?o.
| |
| }
| |
| """)
| |
| sparql.setReturnFormat(JSON)
| |
| results = sparql.query().convert()
| |
|
| |
| for result in results["results"]["bindings"]:
| |
| print(result["p"]["value"])
| |
|
| |
| # SELECT all interests of Cade
| |
|
| |
| sparql.setQuery("""
| |
| PREFIX ex: <http://example.org/>
| |
| SELECT DISTINCT ?interest WHERE {
| |
| ex:Cade ex:interest ?interest.
| |
| }
| |
| """)
| |
| sparql.setReturnFormat(JSON)
| |
| results = sparql.query().convert()
| |
|
| |
| for result in results["results"]["bindings"]:
| |
| print(result["interest"]["value"])
| |
| </syntaxhighlight>
| |
|
| |
| == Lab 4/6 - Updating data from Blazegraph via Python ==
| |
| <syntaxhighlight>
| |
| from SPARQLWrapper import SPARQLWrapper, POST, DIGEST
| |
|
| |
| namespace = "kb"
| |
| sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql")
| |
|
| |
| sparql.setMethod(POST)
| |
| sparql.setQuery("""
| |
| PREFIX ex: <http://example.org/>
| |
| INSERT DATA{
| |
| ex:Cade ex:interest ex:Mathematics.
| |
| }
| |
| """)
| |
|
| |
| results = sparql.query()
| |
| print(results.response.read())
| |
|
| |
|
| |
|
| |
|
| </syntaxhighlight>
| | g.bind("ex", ex) |
|
| |
|
| == Lecture 5: RDFS inference with RDFLib ==
| | # The Mueller Investigation was lead by Robert Mueller |
| | g.add((ex.MuellerInvestigation, ex.leadBy, ex.RobertMueller)) |
|
| |
|
| You can use the OWL-RL package to add inference capabilities to RDFLib. Download it [https://github.com/RDFLib/OWL-RL GitHub] and copy the ''owlrl'' subfolder into your project folder next to your Python files.
| | # 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)) |
|
| |
|
| [https://owl-rl.readthedocs.io/en/latest/owlrl.html OWL-RL documentation.]
| | # Paul Manafort was business partner of Rick Gates |
| | g.add((ex.PaulManafort, ex.businessPartner, ex.RickGates)) |
|
| |
|
| Example program to get started:
| | # He was campaign chairman for Donald Trump |
| <syntaxhighlight>
| | g.add((ex.PaulManafort, ex.campaignChairman, ex.DonaldTrump)) |
| import rdflib.plugins.sparql.update
| |
| import owlrl.RDFSClosure
| |
|
| |
|
| g = rdflib.Graph() | | # 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)) |
|
| |
|
| ex = rdflib.Namespace('http://example.org#') | | # He was convicted for bank and tax fraud. |
| g.bind('', ex) | | g.add((ex.PaulManafort, ex.convictedOf, ex.BankFraud)) |
| | g.add((ex.PaulManafort, ex.convictedOf, ex.TaxFraud)) |
|
| |
|
| g.update(""" | | # He pleaded guilty to conspiracy. |
| PREFIX ex: <http://example.org#>
| | g.add((ex.PaulManafort, ex.pleadGuiltyTo, ex.Conspiracy)) |
| PREFIX owl: <http://www.w3.org/2002/07/owl#>
| |
| INSERT DATA {
| |
| ex:Socrates rdf:type ex:Man .
| |
| ex:Man rdfs:subClassOf ex:Mortal .
| |
| }""")
| |
|
| |
|
| # The next three lines add inferred triples to g. | | # He was sentenced to prison. |
| rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
| | g.add((ex.PaulManafort, ex.sentencedTo, ex.Prison)) |
| rdfs.closure()
| |
| rdfs.flush_stored_triples()
| |
|
| |
|
| b = g.query("""
| | # He negotiated a plea agreement. |
| PREFIX ex: <http://example.org#>
| | g.add((ex.PaulManafort, ex.negotiated, ex.PleaAgreement)) |
| ASK {
| |
| ex:Socrates rdf:type ex:Mortal .
| |
| }
| |
| """)
| |
| print('Result: ' + bool(b))
| |
| </syntaxhighlight>
| |
| | |
| == Languaged tagged RDFS labels ==
| |
| <syntaxhighlight>
| |
| g.add((ex.France, RDFS.label, Literal("Frankrike", lang="no"))) | |
| g.add((ex.France, RDFS.label, Literal("France", lang="en")))
| |
| g.add((ex.France, RDFS.label, Literal("Francia", lang="es")))
| |
| </syntaxhighlight>
| |
|
| |
|
| == Lecture 6: RDFS Plus / OWL inference with RDFLib ==
| | # 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)) |
|
| |
|
| You can use the OWL-RL package again as for Lecture 5.
| | # 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)) |
|
| |
|
| Instead of:
| | # Use the serialize method of rdflib.Graph to write out the model in different formats (on screen or to file) |
| <syntaxhighlight>
| | print(g.serialize(format="ttl")) # To screen |
| # The next three lines add inferred triples to g.
| | #g.serialize("lab1.ttl", format="ttl") # To file |
| rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
| |
| rdfs.closure()
| |
| rdfs.flush_stored_triples()
| |
| </syntaxhighlight>
| |
| 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_OWL_RLSemantics(g, False, False, False)
| |
| owl.closure()
| |
| owl.flush_stored_triples()
| |
| </syntaxhighlight>
| |
|
| |
|
| Example updates and queries:
| | # Loop through the triples in the model to print out all triples that have pleading guilty as predicate |
| <syntaxhighlight>
| | for subject, object in g[ : ex.pleadGuiltyTo :]: |
| PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
| | print(subject, ex.pleadGuiltyTo, object) |
| PREFIX owl: <http://www.w3.org/2002/07/owl#>
| |
| PREFIX ex: <http://example.org#>
| |
|
| |
|
| INSERT DATA {
| | # --- IF you have more time tasks --- |
| ex:Socrates ex:hasWife ex:Xanthippe .
| |
| ex:hasHusband owl:inverseOf ex:hasWife .
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
|
| <syntaxhighlight>
| | # Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week |
| ASK {
| |
| ex:Xanthippe ex:hasHusband ex:Socrates .
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
|
| <syntaxhighlight>
| | #Write a method (function) that submits your model for rendering and saves the returned image to file. |
| ASK {
| | import requests |
| ex:Socrates ^ex:hasHusband ex:Xanthippe .
| | import shutil |
| }
| |
| </syntaxhighlight>
| |
|
| |
|
| <syntaxhighlight>
| | def graphToImage(graphInput): |
| INSERT DATA {
| | data = {"rdf":graphInput, "from":"ttl", "to":"png"} |
| ex:hasWife rdfs:subPropertyOf ex:hasSpouse .
| | link = "http://www.ldf.fi/service/rdf-grapher" |
| ex:hasSpouse rdf:type owl:SymmetricProperty . | | response = requests.get(link, params = data, stream=True) |
| }
| | # print(response.content) |
| </syntaxhighlight>
| | print(response.raw) |
| | with open("lab1.png", "wb") as file: |
| | shutil.copyfileobj(response.raw, file) |
|
| |
|
| <syntaxhighlight>
| | graph = g.serialize(format="ttl") |
| ASK {
| | graphToImage(graph) |
| ex:Socrates ex:hasSpouse ex:Xanthippe .
| |
| }
| |
| </syntaxhighlight>
| |
|
| |
|
| <syntaxhighlight>
| |
| ASK {
| |
| ex:Socrates ^ex:hasSpouse ex:Xanthippe .
| |
| }
| |
| </syntaxhighlight> | | </syntaxhighlight> |
|
| |
|
| |
|
| |
|
| |
|
| |
| <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>
| |