Lab Solutions: Difference between revisions

From info216
No edit summary
No edit summary
 
(55 intermediate revisions by 4 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''


=Example lab solutions=
<!--
=Getting started (Lab 1)=


==Getting started==
<syntaxhighlight>


<syntaxhighlight>
from rdflib import Graph, Namespace


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


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


g.add((EX.Cade, RDF.type, FOAF.Person))
# He was campaign chairman for Donald Trump
g.add((EX.Mary, RDF.type, FOAF.Person))
g.add((ex.PaulManafort, ex.campaignChairman, ex.DonaldTrump))
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 charged with money laundering, tax evasion, and foreign lobbying.
#for i in hobbies:
g.add((ex.PaulManafort, ex.chargedWith, ex.MoneyLaundering))
#    g.add((EX.Mary, FOAF.interest, EX[i]))
g.add((ex.PaulManafort, ex.chargedWith, ex.TaxEvasion))
g.add((ex.PaulManafort, ex.chargedWith, ex.ForeignLobbying))


print(g.serialize(format="turtle"))
# He was convicted for bank and tax fraud.
</syntaxhighlight>
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
import spotlight
from spotlight import SpotlightException


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


# Parameter given to spotlight to filter out results with confidence lower than this value
===For each investigation, list the number of indictments made===
CONFIDENCE = 0.5
<syntaxhighlight lang="SPARQL">
SERVER = "https://api.dbpedia-spotlight.org/en/annotate"
PREFIX ns1: <http://example.org#>


def annotate_entity(entity):
SELECT ?invs (COUNT(?invs) as ?count)
annotations = []
WHERE {
try:
  ?s ns1:investigation ?invs;
annotations = spotlight.annotate(address=SERVER,text=entity, confidence=CONFIDENCE)
      ns1:outcome ns1:indictment .
    # This catches errors thrown from Spotlight, including when no resource is found in DBpedia
}
except SpotlightException as e:
GROUP BY ?invs
print(e)
</syntaxhighlight>
return annotations


===For each investigation with multiple indictments, list the number of indictments made===
<syntaxhighlight lang="SPARQL">
PREFIX ns1: <http://example.org#>


ex = Namespace("http://example.org/")
SELECT ?invs (COUNT(?invs) as ?count)
dbr = Namespace("http://dbpedia.org/resource/")
WHERE {
dbp = Namespace("https://dbpedia.org/property/")
  ?s ns1:investigation ?invs;
dbpage = Namespace("https://dbpedia.org/page/")
      ns1:outcome ns1:indictment .
sem = Namespace("http://semanticweb.cs.vu.nl/2009/11/sem/")
}
tl = Namespace("http://purl.org/NET/c4dm/timeline.owl#")
GROUP BY ?invs
HAVING(?count > 1)
</syntaxhighlight>


g = Graph()
===For each investigation with multiple indictments, list the number of indictments made, sorted with the most indictments first===
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
HAVING(?count > 1)
ORDER BY DESC(?count)
</syntaxhighlight>


# iterrows creates an iterable object (list of rows)
===For each president, list the numbers of convictions and of pardons made===
for index, row in df.iterrows():
<syntaxhighlight lang="SPARQL">
investigation = URIRef(ex + row['investigation'])
PREFIX ns1: <http://example.org#>
investigation_spotlight = annotate_entity(row['investigation'])
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)
name_underscore = URIRef(dbpage + row['name'].replace(" ", "_"))
investigation_result = URIRef(
ex + row['investigation'] + "_investigation_" + row['name'].replace(" ", "_"))
indictment_days = Literal(row['indictment-days'], datatype=XSD.integer)
type = URIRef(dbr + row['type'].replace(" ", "_"))
cp_date = Literal(row['cp-date'], datatype=XSD.date)
cp_days = Literal(row['cp-days'], datatype=XSD.duration)
overturned = Literal(row['overturned'], datatype=XSD.boolean)
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(" ", "_"))
president_spotlight = annotate_entity(row['president'])


try:
SELECT ?president (COUNT(?outcome) as ?conviction) (COUNT(?pardon) as
g.add((( URIRef(investigation_spotlight[0]["URI"]), RDF.type, sem.Event)))
?pardons)
except:
WHERE {
g.add((investigation, RDF.type, sem.Event))
  ?s ns1:president ?president;
try:
      ns1:outcome ?outcome ;
g.add((( URIRef(investigation_spotlight[0]["URI"]), sem.hasBeginTimeStamp, investigation_start)))
      ns1:outcome ns1:conviction.
except:
      OPTIONAL{
g.add((investigation, sem.hasBeginTimeStamp, investigation_start))
        ?s ns1:pardoned ?pardon .
try:
        FILTER (?pardon = true)
g.add((( URIRef(investigation_spotlight[0]["URI"]), sem.hasEndTimeStamp, investigation_end)))
      }
except:
}
g.add((investigation, sem.hasEndTimeStamp, investigation_end))
GROUP BY ?president
try:
g.add((URIRef(investigation_spotlight[0]["URI"]), tl.duration, investigation_days))
except:
g.add((investigation, tl.duration, investigation_days))
try:
g.add((URIRef(investigation_spotlight[0]["URI"]), dbp.president, URIRef(president_spotlight[0]["URI"])))
except:
g.add((investigation, dbp.president, dbr.president_underscore))
try:
g.add((URIRef(investigation_spotlight[0]["URI"]), sem.hasSubEvent, investigation_result))
except:
g.add((investigation, sem.hasSubEvent, investigation_result))
g.add((investigation_result, ex.resultType, type))
g.add((investigation_result, ex.objectOfInvestigation, name_underscore))
g.add((investigation_result, ex.isAmerican, american))
g.add((investigation_result, ex.indictmentDuration, indictment_days))
g.add((investigation_result, ex.caseSolved, cp_date))
g.add((investigation_result, ex.daysBeforeCaseSolved, cp_days))
g.add((investigation_result, ex.overturned, overturned))
g.add((investigation_result, ex.pardoned, pardoned))
 
g.serialize("output.ttl", format="ttl")
</syntaxhighlight>
</syntaxhighlight>


==RDFS==
===Rename mullerkg:name to something like muellerkg:person===
<syntaxhighlight>
from rdflib.namespace import RDF, FOAF, XSD, RDFS
from rdflib import OWL, Graph, Namespace, URIRef, Literal, BNode
from rdflib.namespace import RDF, RDFS, XSD, OWL
import owlrl


ex = Namespace("http://example.org/")
<syntaxhighlight lang="SPARQL">
dbr = Namespace("http://dbpedia.org/resource/")
PREFIX ns1: <http://example.org#>
dbp = Namespace("https://dbpedia.org/property/")
dbpage = Namespace("https://dbpedia.org/page/")
sem = Namespace("http://semanticweb.cs.vu.nl/2009/11/sem/")
tl = Namespace("http://purl.org/NET/c4dm/timeline.owl#")


g = Graph()
DELETE{?s ns1:name ?o}
g.bind("ex", ex)
INSERT{?s ns1:person ?o}
g.bind("dbr", dbr)
WHERE {?s ns1:name ?o}
g.bind("dbp", dbp)
</syntaxhighlight>
g.bind("dbpage", dbpage)
g.bind("sem", sem)
g.bind("tl", tl)


g.parse(location="exampleTTL.ttl", format="turtle")
===Update the graph so all the investigated person and president nodes become the subjects in foaf:name triples with the corresponding strings===


# University of California and University of Valencia are both Universities.
<syntaxhighlight lang="SPARQL">
g.add((ex.University_of_California, RDF.type, ex.University))
PREFIX ns1: <http://example.org#>
g.add((ex.University_of_Valencia, RDF.type, ex.University))
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
# All universities are higher education institutions (HEIs).
g.add((ex.University, RDFS.subClassOf, ex.Higher_education))
# Only persons can have an expertise, and what they have expertise in is always a subject.
g.add((ex.expertise, RDFS.domain, FOAF.Person))
g.add((ex.expertise, RDFS.range, ex.subject))
# Only persons can graduate from a HEI.
g.add((ex.graduatedFromHEI, RDFS.domain, FOAF.Person))
g.add((ex.graduatedFromHEI, RDFS.range, ex.Higher_education))
# If you are a student, you are in fact a person as well.
g.add((ex.Student, RDFS.subClassOf, FOAF.Person))
# That a person is married to someone, means that they know them.
g.add((ex.married, RDFS.subPropertyOf, FOAF.knows))
# Finally, if a person has a name, that name is also the label of that entity."
g.add((FOAF.name, RDFS.subPropertyOf, RDFS.label))


# Having a degree from a HEI means that you have also graduated from that HEI.
#Persons
g.add((ex.graduatedFromHEI, RDFS.subPropertyOf, ex.degree))
INSERT {?person foaf:name ?name}
# That a city is a capital of a country means that this city is located in that country.
WHERE {
g.add((ex.capital, RDFS.domain, ex.Country))
      ?investigation ns1:person ?person .
g.add((ex.capital, RDFS.range, ex.City))
      BIND(REPLACE(STR(?person), STR(ns1:), "") AS ?name)
g.add((ex.capital, RDFS.subPropertyOf, ex.hasLocation))
}
# That someone was involved in a meeting, means that they have met the other participants.
    # This question was bad for the RDFS lab because we need complex OWL or easy sparql.
res = g.query("""
    CONSTRUCT {?person1 ex:haveMet ?person2}
    WHERE {
        ?person1 ex:meeting ?Meeting .
        ?Meeting ex:involved ?person2 .
        }
""")
for triplet in res:
    #we don't need to add that people have met themselves
    if (triplet[0] != triplet[2]):
        g.add((triplet))
# If someone partook in a meeting somewhere, means that they have visited that place"
    # This question was bad for the RDFS lab for the same reason.
res = g.query("""
    CONSTRUCT {?person ex:hasVisited ?place}
    WHERE {
        ?person1 ex:meeting ?Meeting .
        ?Meeting ex:location ?place .
        }
""")
for triplet in res:
        g.add((triplet))


rdfs = owlrl.OWLRL.OWLRL_Semantics(g, False, False, False)
#Presidents
rdfs.closure()
INSERT {?president foaf:name ?name}
rdfs.flush_stored_triples()
WHERE {
g.serialize("output.ttl",format="ttl")
      ?investigation ns1:president ?president .
      BIND(REPLACE(STR(?president), STR(ns1:), "") AS ?name)
}
</syntaxhighlight>
</syntaxhighlight>


==OWL 1==
===Use INSERT DATA updates to add these triples===
<syntaxhighlight>
import owlrl
from rdflib import Graph, Namespace, Literal, URIRef
from rdflib.namespace import RDF, RDFS, XSD, FOAF, OWL
from rdflib.collection import Collection


g = Graph()
<syntaxhighlight lang="SPARQL">
print()
PREFIX ns1: <http://example.org#>
# Namespaces
ex = Namespace("http://example.org/")
dbp = Namespace("http://dbpedia.org/resource/")
geo = Namespace("http://sws.geonames.org/")
schema = Namespace("https://schema.org/")
akt = Namespace("http://www.aktors.org/ontology/portal#")
vcard = Namespace("http://www.w3.org/2006/vcard/ns#")


g.bind("ex", ex)
INSERT DATA {
g.bind("owl", OWL)
    ns1:George_Papadopoulos ns1:adviserTo ns1:Donald_Trump;
        ns1:pleadGuiltyTo ns1:LyingToFBI;
        ns1:sentencedTo ns1:Prison.


g.parse(location="lab8turtle.txt", 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.
}


# Cade and Emma are two different persons.
#To test if added
g.add((ex.Cade, OWL.differentFrom, ex.Emma))
SELECT ?p ?o
# The country USA above is the same as the DBpedia resource http://dbpedia.org/resource/United_States (dbr:United_States) and the GeoNames resource http://sws.geonames.org/6252001/ (gn:6252001).
WHERE {ns1:Roger_Stone ?p ?o .}
g.add((ex.USA, OWL.sameAs, dbp.United_States))
</syntaxhighlight>
g.add((ex.USA, OWL.sameAs, geo["6252001"]))
# The person class (the RDF type the Cade and Emma resources) in your graph is the same as FOAF's, schema.org's and AKT's person classes
    # (they are http://xmlns.com/foaf/0.1/Person, http://schema.org/Person, and http://www.aktors.org/ontology/portal#Person, respectively.
g.add((FOAF.Person, OWL.sameAs, schema.Person))
g.add((FOAF.Person, OWL.sameAs, akt.Person))
# Nothing can be any two of a person, a university, or a city at the same time.
Collection(g, ex.DisjointClasses, [FOAF.Person, ex.University, ex.City])
g.add((OWL.AllDifferent, OWL.distinctMembers, ex.DisjointClasses))
# The property you have used in your RDF/RDFS graph to represent that 94709 is the US zip code of Berkeley, California in US
    # is a subproperty of VCard's postal code-property (http://www.w3.org/2006/vcard/ns#postal-code).
g.add((ex.postalCode, RDFS.subPropertyOf, vcard["postal-code"]))
# No two US cities can have the same postal code.
    # We have to add a relation from city to postal code first
res = g.query("""
    PREFIX RDF: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX ex: <http://example.org/>
    CONSTRUCT {?usa_city ex:us_city_postal_code ?postalcode}
    WHERE {
        ?address RDF:type ex:Address .
        ?address ex:country ex:USA .
        ?address ex:city ?usa_city .
        ?address ex:postalCode ?postalcode
        }
""")
for triplet in res:
        g.add((triplet))
    # Now we can make us cities have distinct postal codes
g.add((ex.us_city_postal_code, RDF.type, OWL.FunctionalProperty))
g.add((ex.us_city_postal_code, RDF.type, OWL.InverseFunctionalProperty))
g.add((ex.us_city_postal_code, RDFS.subPropertyOf, ex.postalcode))


# The property you have used for Emma living in Valencia is the same property as FOAF's based-near property
===Use DELETE DATA and then INSERT DATA updates to correct that Roger Stone was cleared of all charges===
    # (http://xmlns.com/foaf/0.1/based_near), and it is the inverse of DBpedia's hometown property (http://dbpedia.org/ontology/hometown, dbo:hometown).
g.add((ex.city, OWL.sameAs, FOAF.based_near))
g.add((ex.city, OWL.inverseOf, dbp.hometown))


g.add((ex.Cade, ex.married, ex.Mary))
<syntaxhighlight lang="SPARQL">
g.add((ex.Cade, ex.livesWith, ex.Mary))
PREFIX ns1: <http://example.org#>
g.add((ex.Cade, ex.sibling, ex.Andrew))
g.add((ex.Cade, ex.hasFather, ex.Bob))
g.add((ex.Bob, ex.fatherOf, ex.Cade))


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


#Look through the predicates(properties) above and add new triples for each one that describes them as any of the following:  
INSERT DATA {
    # a reflexive , irreflexive, symmetric, asymmetric, transitive, functional, or an Inverse Functional Property.
      ns1:Roger_Stone ns1:indictedFor ns1:ObstructionOfJustice,
g.add((ex.married, RDF.type, OWL.SymmetricProperty))
                                      ns1:WitnessTampering,
g.add((ex.married, RDF.type, OWL.FunctionalProperty))
                                      ns1:FalseStatements.
g.add((ex.married, RDF.type, OWL.InverseFunctionalProperty))
}
g.add((ex.married, RDF.type, OWL.IrreflexiveProperty))


g.add((ex.livesWith, RDF.type, OWL.SymmetricProperty))
#The task specifically requested DELETE DATA & INSERT DATA, put below is
g.add((ex.livesWith, RDF.type, OWL.ReflexiveProperty))
a more efficient solution
g.add((ex.livesWith, RDF.type, OWL.TransitiveProperty))


g.add((ex.sibling, RDF.type, OWL.SymmetricProperty))
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>


g.add((ex.hasFather, RDF.type, OWL.AsymmetricProperty))
===Use a DESCRIBE query to show the updated information about Roger Stone===
g.add((ex.hasFather, RDF.type, OWL.FunctionalProperty))
g.add((ex.hasFather, RDF.type, OWL.IrreflexiveProperty))


g.add((ex.fatherOf, RDF.type, OWL.AsymmetricProperty))
<syntaxhighlight lang="SPARQL">
g.add((ex.fatherOf, RDF.type, OWL.IrreflexiveProperty))
PREFIX ns1: <http://example.org#>
g.add((ex.fatherOf, RDF.type, OWL.InverseFunctionalProperty))
g.add((ex.fatherOf, RDF.type, OWL.IrreflexiveProperty))


# These three lines add inferred triples to the graph.
DESCRIBE ?o
owl = owlrl.CombinedClosure.RDFS_OWLRL_Semantics(g, False, False, False)
WHERE {ns1:Roger_Stone ns1:indictedFor ?o .}
owl.closure()
</syntaxhighlight>
owl.flush_stored_triples()


g.serialize("lab8output.xml",format="xml")
===Use a CONSTRUCT query to create a new RDF group with triples only about Roger Stone===
</syntaxhighlight>


==Semantic lifting - XML==
<syntaxhighlight lang="SPARQL">
<syntaxhighlight>
PREFIX ns1: <http://example.org#>
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF
import xml.etree.ElementTree as ET
import requests


g = Graph()
CONSTRUCT {
ex = Namespace("http://example.org/")
  ns1:Roger_Stone ?p ?o.
prov = Namespace("http://www.w3.org/ns/prov#")
  ?s ?p2 ns1:Roger_Stone.
g.bind("ex", ex)
}
g.bind("prov", prov)
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===


# URL of xml data
<syntaxhighlight lang="SPARQL">
url = 'http://feeds.bbci.co.uk/news/rss.xml'
PREFIX ns1: <http://example.org#>
# Retrieve the xml data from the web-url.
PREFIX dbp: <https://dbpedia.org/page/>
resp = requests.get(url)
# Creating an ElementTree from the response content
tree = ET.ElementTree(ET.fromstring(resp.content))
root = tree.getroot()


# I just realized this is cheating, but whatever, you should do it with xmltree
DELETE {?s ns1:person ?o1}
writerDict = {
INSERT {?s ns1:person ?o2}
    "Mon":"Thomas_Smith",
WHERE{
    "Tue":"Thomas_Smith",
  ?s ns1:person ?o1 .
    "Wed":"Thomas_Smith",
  BIND (IRI(replace(str(?o1), str(ns1:), str(dbp:)))  AS ?o2)
    "Thu":"Joseph_Olson",
    "Fri":"Joseph_Olson",
    "Sat":"Sophia_Cruise",
    "Sun":"Sophia_Cruise"
}
}
copyright = Literal(root.findall("./channel")[0].find("copyright").text)


for item in root.findall("./channel/item"):
#This update changes the object in triples with ns1:person as the
    copyright = Literal(root.findall("./channel")[0].find("copyright").text)
predicate. It changes it's prefix of ns1 (which is the
"shortcut/shorthand" for example.org) to the prefix dbp (dbpedia.org)
</syntaxhighlight>


    News_article_id = URIRef(item.find("guid").text)
===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. ===
    title = Literal(item.find("title").text)
    description = Literal(item.find("description").text)
    link = URIRef(item.find("link").text)
    pubDate = Literal(item.find("pubDate").text)
    writerName = ex[writerDict[pubDate[:3]]]


    g.add((News_article_id, ex.title, title))
<syntaxhighlight lang="SPARQL">
    g.add((News_article_id, ex.description, description))
#Whilst this solution is not exactly what the task asks for, I feel like
    g.add((News_article_id, ex.source_link, link))
this is more appropiate given the dataset. The following update
    g.add((News_article_id, ex.pubDate, pubDate))
changes the objects that uses the cp_date as predicate from a URI, to a
    g.add((News_article_id, ex.copyright, copyright))
literal with date as it's datatype
    g.add((News_article_id, RDF.type, ex.News_article))
    g.add((News_article_id, RDF.type, prov.Entity))


    g.add((News_article_id, ex.authoredBy, writerName))
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
    g.add((writerName, RDF.type, prov.Person))
PREFIX ns1: <http://example.org#>
    g.add((writerName, RDF.type, prov.Agent))
    g.add((ex.authoredBy, RDF.type, prov.Generation))


print(g.serialize(format="turtle"))
DELETE {?s ns1:cp_date ?o}
</syntaxhighlight>
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)
}


==OWL 2==
#To test:
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, BNode
from rdflib.namespace import RDF, OWL, RDFS
from rdflib.collection import Collection


g = Graph()
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
ex = Namespace("http://example.org/")
PREFIX ns1: <http://example.org#>
g.bind("ex", ex)
g.bind("owl", OWL)


# anyone who is a graduate has at least one degree
SELECT ?s ?o
br = BNode()
WHERE{
g.add((br, RDF.type, OWL.Restriction))
  ?s ns1:cp_date ?o.
g.add((br, OWL.onProperty, ex.degree))
  FILTER(datatype(?o) = xsd:date)
g.add((br, OWL.minCardinality, Literal(1)))
}
bi = BNode()
Collection(g, bi, [ex.Person, br])
g.add((ex.Graduate, OWL.intersectionOf, bi))


#anyone who is a university graduate has at least one degree from a university
#To change it to an integer, use the following code, and to change it
br = BNode()
back to date, swap "xsd:integer" to "xsd:date"
g.add((br, RDF.type, OWL.Restriction))
g.add((br, OWL.onProperty, ex.degree))
g.add((br, OWL.someValuesFrom, ex.University))
bi = BNode()
Collection(g, bi, [ex.Graduate, br])
                #[ex.Person, br] also someValueFrom implies a cardinality of at least one so they would be equivalent.
                #[ex.Person, ex.Graduate, br] would be redundant since intersection is associative.
g.add((ex.University_graduate, OWL.intersectionOf, bi))


#a grade is either an A, B, C, D, E or F
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX ns1: <http://example.org#>


bi = BNode()
DELETE {?s ns1:cp_date ?o}
Collection(g, bi, [Literal("A"), Literal("B"), Literal("C"), Literal("D"), Literal("E"), Literal("F")])
INSERT{?s ns1:cp_date ?o2}
b1 = BNode()
WHERE{
g.add((b1, RDF.type, RDFS.Datatype))
  ?s ns1:cp_date ?o .
g.add((b1, OWL.oneOf, bi))
  BIND (STRDT(STR(?o), xsd:integer) AS ?o2)
}


g.add((ex.grade, RDFS.range, b1))
</syntaxhighlight>


#a straight A student is a student that has only A grades
=SPARQL Programming (Lab 5)=
b1 = BNode()
g.add((b1, RDF.type, OWL.Restriction))
g.add((b1, OWL.onProperty, ex.grade))
g.add((b1, OWL.allValuesFrom, Literal("A")))


b2 = BNode()
<syntaxhighlight>
g.add((b2, RDF.type, OWL.Restriction))
g.add((b2, OWL.onProperty, ex.grade))
g.add((b2, OWL.someValuesFrom, Literal("A")))


bi = BNode()
from rdflib import Graph, Namespace, RDF, FOAF
Collection(g, bi, [ex.Student, b1, b2])
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE
g.add((ex.Straight_A_student, OWL.intersectionOf, bi))


#a graduate has no F grades
g = Graph()
b3 = BNode()
g.parse("Russia_investigation_kg.ttl")
Collection(g, b3, [Literal("A"), Literal("B"), Literal("C"), Literal("D"), Literal("E")])
b4 = BNode()
g.add((b4, RDF.type, RDFS.Datatype))
g.add((b4, OWL.oneOf, b3))
b5 = BNode()
g.add((b5, RDF.type, OWL.Restriction))
g.add((b5, OWL.onProperty, ex.grade))
g.add((b5, OWL.allValuesFrom, b4))


b6 = BNode()
# ----- RDFLIB -----
Collection(g, b6, [ex.Person, b1, b5])
ex = Namespace('http://example.org#')
g.add((ex.Graduate, OWL.intersectionOf, b6))


#a student has a unique student number
NS = {
g.add((ex.student_number, RDF.type, OWL.FunctionalProperty))
    '': ex,
g.add((ex.student_number, RDF.type, OWL.InverseFunctionalProperty))
    'rdf': RDF,
    'foaf': FOAF,
}


#each student has exactly one average grade
# Print out a list of all the predicates used in your graph.
b1 = BNode()
task1 = g.query("""
g.add((b1, RDF.type, OWL.Restriction))
SELECT DISTINCT ?p WHERE{
g.add((b1, OWL.onProperty, ex.average_grade))
    ?s ?p ?o .
g.add((b1, OWL.cardinality, Literal(1)))
}
""", initNs=NS)


b2 = BNode()
print(list(task1))
g.add((b2, RDF.type, OWL.Restriction))
g.add((b2, OWL.onProperty, ex.student_number))
g.add((b2, OWL.cardinality, Literal(1)))


Collection(g, b3, [ex.Person, b1, b2])
# Print out a sorted list of all the presidents represented in your graph.
g.add((ex.Student, OWL.intersectionOf, b3))
task2 = g.query("""
SELECT DISTINCT ?president WHERE{
    ?s :president ?president .
}
ORDER BY ?president
""", initNs=NS)


#a course is either a bachelor, a master or a Ph.D course
print(list(task2))
bi = BNode()
Collection(g, bi, [ex.Bachelor_course, ex.Master_course, ex["Ph.D_course"]])
b1 = BNode()
#g.add((b1, RDF.type, OWL.Class))
g.add((b1, OWL.oneOf, bi))


g.add((ex.Course, RDF.type, b1))
# 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 = {}


#a bachelor student takes only bachelor courses
task3 = g.query("""
g.add((ex.Bachelor_student, RDFS.subClassOf, ex.Student))
SELECT ?president ?person WHERE{
b1 = BNode()
    ?s :president ?president;
g.add((b1, RDF.type, OWL.Restriction))
      :name ?person;
g.add((b1, OWL.onProperty, ex.hasCourse))
      :outcome :indictment.
g.add((b1, OWL.allValuesFrom, ex.Bachelor_course))
}
""", initNs=NS)


b2 = BNode()
for president, person in task3:
Collection(g, b2, [ex.Student, b1])
    if president not in task3_dic:
g.add((ex.Bachelor_student, OWL.intersectionOf, b2))
        task3_dic[president] = [person]
    else:
        task3_dic[president].append(person)


#a masters student takes only master courses and at most one bachelor course
print(task3_dic)


b1 = BNode()
# Use an ASK query to investigate whether Donald Trump has pardoned more than 5 people.
g.add((b1, RDF.type, OWL.Restriction))
g.add((b1, OWL.onProperty, ex.hasCourse))
g.add((b1, OWL.maxQualifiedCardinality, Literal(1)))
g.add((b1, OWL.onClass, ex.Bachelor_course))


b2 = BNode()
# 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:
g.add((b2, RDF.type, OWL.Restriction))
task4 = g.query("""
g.add((b2, OWL.onProperty, ex.hasCourse))
ASK {
g.add((b2, OWL.someValuesFrom, ex.Master_course))
  SELECT (COUNT(?s) as ?count) WHERE{
    ?s :pardoned :true;
    :president :Bill_Clinton  .
    }
    HAVING (?count > 5)
}
""", initNs=NS)


b3 = BNode()
print(task4.askAnswer)
Collection(g, b3, [ex.Master_course, ex.Bachelor_course])


b5 = BNode()
# Which works fine in Blazegraph and is a valid SPARQL query will always provide false in RDFLib cause it uses HAVING.  
g.add((b5, RDF.type, OWL.Restriction))
# Instead you have to use a nested SELECT query like below, where you use FILTER instead of HAVING. Donald Trump has no pardons,
g.add((b5, OWL.onProperty, ex.hasCourse))
# so I have instead chosen Bill Clinton with 13 to check if the query works.  
g.add((b5, OWL.allValuesFrom, b3))


b6 = BNode()
task4 = g.query("""
Collection(g, b6, [ex.Student, b1, b2, b5])
    ASK{
g.add((ex.Master_student, OWL.intersectionOf, b6))
        SELECT ?count WHERE{{
          SELECT (COUNT(?s) as ?count) WHERE{
            ?s :pardoned :true;
                  :president :Bill_Clinton  .
                }}
        FILTER (?count > 5)
        }
    }
""", initNs=NS)


#a Ph.D student takes only Ph.D and at most two masters courses
print(task4.askAnswer)
b1 = BNode()
g.add((b1, RDF.type, OWL.Restriction))
g.add((b1, OWL.onProperty, ex.hasCourse))
g.add((b1, OWL.maxQualifiedCardinality, Literal(2)))
g.add((b1, OWL.onClass, ex.Master_course))


b2 = BNode()
# Use a DESCRIBE query to create a new graph with information about Donald Trump. Print out the graph in Turtle format.
g.add((b2, RDF.type, OWL.Restriction))
g.add((b2, OWL.onProperty, ex.hasCourse))
g.add((b2, OWL.someValuesFrom, ex["Ph.D_course"]))


b3 = BNode()
# By all accounts, it seems DESCRIBE querires are yet to be implemented in RDFLib, but they are attempting to implement it:
Collection(g, b3, [ex.Master_course, ex["Ph.D_course"]])
# 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


b5 = BNode()
# task5 = g.query("""
g.add((b5, RDF.type, OWL.Restriction))
# DESCRIBE :Donald_Trump
g.add((b5, OWL.onProperty, ex.hasCourse))
# """, initNs=NS)
g.add((b5, OWL.allValuesFrom, b3))


b6 = BNode()
# print(task5.serialize())
Collection(g, b6, [ex.Student, b1, b2, b5])
g.add((ex["Ph.D_student"], OWL.intersectionOf, b6))
#a Ph.D. student cannot take a bachelor course
    #NA, it's already true
</syntaxhighlight>


==Lab 11: Semantic Lifting - HTML==
# ----- SPARQLWrapper -----


<syntaxhighlight>
SERVER = 'http://localhost:7200' #Might need to replace this
from bs4 import BeautifulSoup as bs
REPOSITORY = 'Labs' #Replace with your repository name
from rdflib import Graph, Literal, URIRef, Namespace
from rdflib.namespace import RDF, SKOS, XSD
import requests


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


g = Graph()
# Ask whether there was an ongoing indictment on the date 1990-01-01.
ex = Namespace("http://example.org/")
sparql.setQuery("""
g.bind("ex", ex)
    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)  
    }
""")


# Download html from URL and parse it with BeautifulSoup.
sparql.setReturnFormat(JSON)
url = "https://www.semanticscholar.org/topic/Knowledge-Graph/159858"
results = sparql.query().convert()
page = requests.get(url)
html = bs(page.content, features="html.parser")
# print(html.prettify())


# Find the html that surrounds all the papers
print("The ongoing investigations on the 1990-01-01 are:")
papers = html.find_all('div', attrs={'class': 'flex-container'})
for result in results["results"]["bindings"]:
# Find the html that surrounds the info box
    print(result["s"]["value"])
topic = html.find_all(
    'div', attrs={'class': 'flex-item__left-column entity-header'})


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


# Iterate through each paper to make triples:
sparql.setReturnFormat(TURTLE)
for paper in papers:
results = sparql.query().convert()
    # e.g selecting title.
    title = paper.find('div', attrs={'class': 'timeline-paper-title'}).text
    author = paper.find('span', attrs={'class': 'author-list'}).text
    papper_year = paper.find(
        'li', attrs={'data-selenium-selector': "paper-year"}).text
    corpus_ID = paper.find(
        'li', attrs={'data-selenium-selector': "corpus-id"}).text
    corpus_ID = corpus_ID.replace(" ", "_")
    c_id = corpus_ID.replace("Corpus_ID:_", "")


    article = URIRef(ex + c_id)
print(results)


    # Adding tripels
# Print out a list of all the types used in your graph.
    g.add((article, RDF.type, ex.paper))
sparql.setQuery("""
    g.add((article, ex.HasID, Literal(c_id, datatype=XSD.int)))
     PREFIX ns1: <http://example.org#>
     g.add((article, ex.HasTitle, Literal(title, datatype=XSD.string)))
     PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
     g.add((article, ex.Publisher_year, Literal(papper_year, datatype=XSD.year)))


     author = author.split(", ")
     SELECT DISTINCT ?types
     for x in author:
     WHERE{
         name = x.replace(" ", "_")
         ?s rdf:type ?types .  
        name = URIRef(ex + name)
    }
""")


        g.add((article, ex.hasAuthor, name))
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


# Iterate through the info box to make triples:
rdf_Types = []
    for items in topic:
        main_topic = items.find('h1', attrs={'class': 'entity-name'}).text
        related_topic = items.find(
            'div', attrs={'class': 'entity-aliases'}).text
        related_topic = related_topic.replace("Known as: ", "")
        related_topic = related_topic.replace(f'\xa0Expand', "")
        related_topic = related_topic.replace(" ", "")
        main_topic = main_topic.replace(" ", "_")


        main_topic = URIRef(ex + main_topic)
for result in results["results"]["bindings"]:
    rdf_Types.append(result["types"]["value"])


        g.add((article, RDF.type, SKOS.Concept))
print(rdf_Types)
        g.add((article, SKOS.hasTopConcept, main_topic))


     related_topic = related_topic.split(',')
# 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#>


     for related_labels in related_topic:
     INSERT{
        related_topic = URIRef(ex + related_labels)
        ?invest rdf:type ns1:Investigation .
         g.add((article, SKOS.broader, related_topic))
    }
    WHERE{
         ?s ns1:investigation ?invest .
}"""


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


print(g.serialize(format='turtle'))
#To Test
</syntaxhighlight>
sparql.setQuery("""
    prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX ns1: <http://example.org#>


=More miscellaneous examples=
    ASK{
        ns1:watergate rdf:type ns1:Investigation.
    }
""")


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


===Printing the triples of the Graph in a readable way===
# Update the graph to that every resource that is an object in a muellerkg:person triple has the rdf:type muellerkg:IndictedPerson.
<syntaxhighlight>
update_str = """
# The turtle format has the purpose of being more readable for humans.  
    PREFIX ns1: <http://example.org#>
print(g.serialize(format="turtle"))
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
</syntaxhighlight>


===Coding Tasks Lab 1===
    INSERT{
<syntaxhighlight>
        ?person rdf:type ns1:IndictedPerson .
from rdflib import Graph, Namespace, URIRef, BNode, Literal
    }
from rdflib.namespace import RDF, FOAF, XSD
    WHERE{
        ?s ns1:name ?person .
}"""


g = Graph()
sparqlUpdate.setQuery(update_str)
ex = Namespace("http://example.org/")
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


g.add((ex.Cade, ex.married, ex.Mary))
#To test, run the query in the above task, replacing the ask query with e.g. ns1:Deborah_Gore_Dean rdf:type ns1:IndictedPerson
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))


# OR
# 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/>


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


ex = Namespace('http://example.org/')
sparqlUpdate.setQuery(update_str)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


g.add((ex.Cade, FOAF.name, Literal("Cade", datatype=XSD.string)))
#Same test as above, replace it with e.g. ns1:watergate dc:title "watergate"
g.add((ex.Mary, FOAF.name, Literal("Mary", datatype=XSD.string)))
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))


# 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/>


print(g.serialize(format="turtle"))
    SELECT ?name
    WHERE{
    ?s  ns1:name ?name;
            ns1:outcome ns1:indictment.
    }
    ORDER BY ?name
""")


</syntaxhighlight>
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


==Basic RDF programming==
names = []


===Different ways to create an address===
for result in results["results"]["bindings"]:
    names.append(result["name"]["value"])


<syntaxhighlight>
print(names)


from rdflib import Graph, Namespace, URIRef, BNode, Literal
# Print out the minimum, average and maximum indictment days for all the indictments in the graph.
from rdflib.namespace import RDF, FOAF, XSD


g = Graph()
sparql.setQuery("""
ex = Namespace("http://example.org/")
    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)
}
""")


# How to represent the address of Cade Tracey. From probably the worst solution to the best.
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


# Solution 1 -
for result in results["results"]["bindings"]:
# 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.
    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"]}')


g.add((ex.Cade_Tracey, ex.livesIn, Literal("1516_Henry_Street, Berkeley, California 94709, USA")))
# 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#>


# Solution 2 -
    SELECT ?investigation (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
# Seperate the different pieces information into their own triples
    ?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
""")


g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
sparql.setReturnFormat(JSON)
g.add((ex.Cade_tracey, ex.city, Literal("Berkeley")))
results = sparql.query().convert()
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")))


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


# Solution 3 - Some parts of the addresses can make more sense to be resources than Literals.
</syntaxhighlight>
# 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")))
=Wikidata SPARQL (Lab 6)=
g.add((ex.Cade_tracey, ex.city, ex.Berkeley))
===Use a DESCRIBE query to retrieve some triples about your entity===
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))


<syntaxhighlight lang="SPARQL">
DESCRIBE wd:Q42 LIMIT 100
</syntaxhighlight>


# Solution 4
===Use a SELECT query to retrieve the first 100 triples about your entity===
# 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">
SELECT * WHERE {
  wd:Q42 ?p ?o .
} LIMIT 100
</syntaxhighlight>


g.add((ex.Cade_Tracey, ex.address, ex.CadeAddress))
===Write a local SELECT query that embeds a SERVICE query to retrieve the first 100 triples about your entity to your local machine===
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
<syntaxhighlight lang="SPARQL">
PREFIX wd: <http://www.wikidata.org/entity/>


# Blank node for Address. 
SELECT * WHERE {
address = BNode()
    SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
g.add((ex.Cade_Tracey, ex.address, address))
        SELECT * WHERE {
g.add((address, RDF.type, ex.Address))
            wd:Q42 ?p ?o .
g.add((address, ex.street, Literal("1516 Henry Street", datatype=XSD.string)))
        } LIMIT 100
g.add((address, ex.city, ex.Berkeley))
    }
g.add((address, ex.state, ex.California))
}
g.add((address, ex.postalCode, Literal("94709", datatype=XSD.string)))
</syntaxhighlight>
g.add((address, ex.country, ex.USA))


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


# Solution 5 using existing vocabularies for address
<syntaxhighlight lang="SPARQL">
PREFIX wd: <http://www.wikidata.org/entity/>


# (in this case https://schema.org/PostalAddress from schema.org).
INSERT {
# Also using existing ontology for places like California. (like http://dbpedia.org/resource/California from dbpedia.org)
    wd:Q42 ?p ?o .
} WHERE {
    SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
        SELECT * WHERE {
            wd:Q42 ?p ?o .
        } LIMIT 100
    }
}
</syntaxhighlight>


schema = Namespace("https://schema.org/")
===Use a FILTER statement to only SELECT primary triples in this sense.===
dbp = Namespace("https://dpbedia.org/resource/")


g.add((ex.Cade_Tracey, schema.address, ex.CadeAddress))
<syntaxhighlight lang="SPARQL">
g.add((ex.CadeAddress, RDF.type, schema.PostalAddress))
PREFIX wd: <http://www.wikidata.org/entity/>
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))


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


===Typed Literals===
===Use Wikidata's in-built SERVICE wikibase:label to get labels for all the object resources===
<syntaxhighlight>
 
from rdflib import Graph, Literal, Namespace
<syntaxhighlight lang="SPARQL">
from rdflib.namespace import XSD
PREFIX wd: <http://www.wikidata.org/entity/>
g = Graph()
ex = Namespace("http://example.org/")


g.add((ex.Cade, ex.age, Literal(27, datatype=XSD.integer)))
SELECT ?p ?oLabel WHERE {
g.add((ex.Cade, ex.gpa, Literal(3.3, datatype=XSD.float)))
    wd:Q42 ?p ?o .
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)))
    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>


===Edit your query (by relaxing the FILTER expression) so it also returns triples where the object has DATATYPE xsd:string.===
<syntaxhighlight lang="SPARQL">
PREFIX wd: <http://www.wikidata.org/entity/>


===Writing and reading graphs/files===
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>


<syntaxhighlight>
===Relax the FILTER expression again so it also returns triples with these three predicates (rdfs:label, skos:altLabel and schema:description) ===
  # Writing the graph to a file on your system. Possible formats = turtle, n3, xml, nt.
g.serialize(destination="triples.txt", format="turtle")


  # Parsing a local file
<syntaxhighlight lang="SPARQL">
parsed_graph = g.parse(location="triples.txt", format="turtle")
PREFIX wd: <http://www.wikidata.org/entity/>


  # Parsing a remote endpoint like Dbpedia
SELECT ?p ?oLabel ?o WHERE {
dbpedia_graph = g.parse("http://dbpedia.org/resource/Pluto")
    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>


===Graph Binding===
===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>
#Graph Binding is useful for at least two reasons:
#(1) We no longer need to specify prefixes with SPARQL queries if they are already binded to the graph.
#(2) When serializing the graph, the serialization will show the correct expected prefix
# instead of default namespace names ns1, ns2 etc.


g = Graph()
<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/>


ex = Namespace("http://example.org/")
SELECT * WHERE {
dbp = Namespace("http://dbpedia.org/resource/")
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
schema = Namespace("https://schema.org/")
    SELECT ?p ?oLabel ?o WHERE {
        wd:Q42 ?p ?o .


g.bind("ex", ex)
        FILTER (
g.bind("dbp", dbp)
          (STRSTARTS(STR(?p), STR(wdt:)) &&
g.bind("schema", schema)
          STRSTARTS(STR(?o), STR(wd:)) || DATATYPE(?o) = xsd:string)
</syntaxhighlight>
          ||
          (?p IN (rdfs:label, skos:altLabel, schema:description) &&
          DATATYPE(?o) = rdf:langString && LANG(?o) = "en")
        )


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


<syntaxhighlight>
    } LIMIT 100
from rdflib import Graph, Namespace
  }
from rdflib.collection import Collection
}
</syntaxhighlight>


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


# Sometimes we want to add many objects or subjects for the same predicate at once.  
<syntaxhighlight lang="SPARQL">
# In these cases we can use Collection() to save some time.
PREFIX wikibase: <http://wikiba.se/ontology#>
# In this case I want to add all countries that Emma has visited at once.
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/>


b = BNode()
INSERT {
g.add((ex.Emma, ex.visit, b))
  wd:Q42 ?p ?o .
Collection(g, b,
  ?o rdfs:label ?oLabel .
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])
} WHERE {
  SERVICE <https://query.wikidata.org/bigdata/namespace/wdq/sparql> {
    SELECT ?p ?oLabel ?o WHERE {
        wd:Q42 ?p ?o .


# OR
        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.add((ex.Emma, ex.visit, ex.EmmaVisits))
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
Collection(g, ex.EmmaVisits,
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])


    } LIMIT 500
  }
}
</syntaxhighlight>
</syntaxhighlight>


==SPARQL==
==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. ===


Also see the [[SPARQL Examples]] page!
<syntaxhighlight lang="SPARQL">
PREFIX wd: <http://www.wikidata.org/entity/>


===Querying a local ("in memory") graph===
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)


Example contents of the file family.ttl:
    SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
@prefix rex: <http://example.org/royal#> .
@prefix fam: <http://example.org/family#> .
   
   
rex:IngridAlexandra fam:hasParent rex:HaakonMagnus .
} LIMIT 100
rex:SverreMagnus fam:hasParent rex:HaakonMagnus .
</syntaxhighlight>
rex:HaakonMagnus fam:hasParent rex:Harald .
rex:MarthaLouise fam:hasParent rex:Harald .
rex:HaakonMagnus fam:hasSister rex:MarthaLouise .


import rdflib
===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. ===
g = rdflib.Graph()
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:
<syntaxhighlight lang="SPARQL">
import rdflib
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX bd: <http://www.bigdata.com/rdf#>
g = rdflib.Graph()
PREFIX wd: <http://www.wikidata.org/entity/>
g.parse("family.ttl", format='ttl')
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
q = rdflib.plugins.sparql.prepareQuery(
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
        """SELECT ?child ?sister WHERE {
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
                  ?child fam:hasParent ?parent .
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
                  ?parent fam:hasSister ?sister .
PREFIX schema: <http://schema.org/>
        }""",
        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)===
INSERT {
<syntaxhighlight>
  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 .


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


PREFIX ex:   <http://example.org/>
        SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


SELECT ?visit
    } LIMIT 500
WHERE {
   }
   ex:Emma ex:visit/rdf:rest*/rdf:first ?visit
}
}
</syntaxhighlight>
</syntaxhighlight>


=CSV to RDF (Lab 7)=
<syntaxhighlight lang="Python">
#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


===Using parameters/variables in rdflib queries===
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


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


g = Graph()
g = Graph()
Line 1,275: Line 1,098:
g.bind("ex", ex)
g.bind("ex", ex)


g.add((ex.Cade, ex.livesIn, ex.France))
#Pandas' read_csv function to load russia-investigation.csv
g.add((ex.Anne, ex.livesIn, ex.Norway))
df = read_csv("russia-investigation.csv")
g.add((ex.Sofie, ex.livesIn, ex.Sweden))
#Replaces all instances of nan to None type with numpy's nan
g.add((ex.Per, ex.livesIn, ex.Norway))
df = df.replace(nan, None)
g.add((ex.John, ex.livesIn, ex.USA))


#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)


def find_people_from_country(country):
return value
        country = URIRef(ex + country)
        q = prepareQuery(
        """
        PREFIX ex: <http://example.org/>
        SELECT ?person WHERE {
        ?person ex:livesIn ?country.
        }
        """)


        capital_result = g.query(q, initBindings={'country': country})
#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"])


        for row in capital_result:
#Spotlight Search
            print(row)
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")


find_people_from_country("Norway")
</syntaxhighlight>
</syntaxhighlight>


===SELECTING data from Blazegraph via Python===
=JSON-LD (Lab 8)=
<syntaxhighlight>
== Task 1) Basic JSON-LD ==
 
<syntaxhighlight lang="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"
        }
        ]}
    ]
}


from SPARQLWrapper import SPARQLWrapper, JSON


# This creates a server connection to the same URL that contains the graphic interface for Blazegraph.
</syntaxhighlight>
# You also need to add "sparql" to end of the URL like below.


sparql = SPARQLWrapper("http://localhost:9999/blazegraph/sparql")
== Task 2 & 3) Retrieving JSON-LD from ConceptNet / Programming JSON-LD in Python ==


# SELECT all triples in the database.
<syntaxhighlight lang="Python">


sparql.setQuery("""
import rdflib
    SELECT DISTINCT ?p WHERE {
    ?s ?p ?o.
    }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


for result in results["results"]["bindings"]:
CN_BASE = 'http://api.conceptnet.io/c/en/'
    print(result["p"]["value"])


# SELECT all interests of Cade
g = rdflib.Graph()
g.parse(CN_BASE+'indictment', format='json-ld')


sparql.setQuery("""
# To download JSON object:
    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"]:
import json
    print(result["interest"]["value"])
import requests
</syntaxhighlight>


===Updating data from Blazegraph via Python===
json_obj = requests.get(CN_BASE+'indictment').json()
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, POST, DIGEST


namespace = "kb"
# To change the @context:
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql")


sparql.setMethod(POST)
context = {
sparql.setQuery("""
    "@base": "http://ex.org/",
    PREFIX ex: <http://example.org/>
    "edges": "http://ex.org/triple/",
    INSERT DATA{
    "start": "http://ex.org/s/",
    ex:Cade ex:interest ex:Mathematics.
    "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)


results = sparql.query()
g = rdflib.Graph()
print(results.response.read())
g.parse(data=json_str, format='json-ld')


# To extract triples (here with labels):


</syntaxhighlight>
r = g.query("""
===Retrieving data from Wikidata with SparqlWrapper===
        SELECT ?s ?sLabel ?p ?o ?oLabel WHERE {
<syntaxhighlight>
            ?edge
from SPARQLWrapper import SPARQLWrapper, JSON
                <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())


sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
# Construct a new graph:
# In the query I want to select all the Vitamins in wikidata.


sparql.setQuery("""
r = g.query("""
    SELECT ?nutrient ?nutrientLabel WHERE
        CONSTRUCT {
{
            ?s ?p ?o .
  ?nutrient wdt:P279 wd:Q34956.
            ?s <http://ex.org/label> ?sLabel .
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
            ?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})


sparql.setReturnFormat(JSON)
print(r.graph.serialize(format='ttl'))
results = sparql.query().convert()


for result in results["results"]["bindings"]:
    print(result["nutrient"]["value"], "  ", result["nutrientLabel"]["value"])
</syntaxhighlight>
</syntaxhighlight>


=SHACL (Lab 9)=
<syntaxhighlight lang="Python">


More examples can be found in the example section on the official query service here: https://query.wikidata.org/.
from pyshacl import validate
from rdflib import Graph


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


<syntaxhighlight>
prefixes = """
"""
@prefix ex: <http://example.org/> .
Dumps a database to a local RDF file.
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
You need to install the SPARQLWrapper package first...
@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#> .
"""
"""


import datetime
shape_graph = """
from SPARQLWrapper import SPARQLWrapper, RDFXML
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.
    ] .


# your namespace, the default is 'kb'
# --- If you have more time tasks ---
ns = 'kb'
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 SPARQL endpoint
    # The value of a property that indicates an end date must be xsd:date or unknown (tip: you can use sh:or (...) ).
endpoint = 'http://info216.i2s.uib.no/bigdata/namespace/' + ns + '/sparql'
    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 ;
    ] ;


# - the endpoint just moved, the old one was:
    # No URI-s can contain hyphens ('-').
# endpoint = 'http://i2s.uib.no:8888/bigdata/namespace/' + ns + '/sparql'
    sh:property [
        sh:path ex:outcome ;
        sh:nodeKind sh:IRI ;
        sh:pattern "^[^-]*$" ;
    ] ;


# create wrapper
    # Presidents must be identified with URIs.
wrapper = SPARQLWrapper(endpoint)
    sh:property [
        sh:path ex:president ;
        sh:minCount 1 ;
        sh:class ex:President ;
        sh:nodeKind sh:IRI ;
    ] .
"""


# prepare the SPARQL update
shacl_graph = Graph()
wrapper.setQuery('CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }')
# parses the contents of a shape_graph you made in the previous task
wrapper.setReturnFormat(RDFXML)
shacl_graph.parse(data=prefixes+shape_graph)


# execute the SPARQL update and convert the result to an rdflib.Graph
# uses pySHACL's validate method to apply the shape_graph constraints to the data_graph
graph = wrapper.query().convert()
results = validate(
    data_graph,
    shacl_graph=shacl_graph,
    inference='both'
)


# the destination file, with code to make it timestamped
# prints out the validation result
destfile = 'rdf_dumps/slr-kg4news-' + datetime.datetime.now().strftime('%Y%m%d-%H%M') + '.rdf'
boolean_value, results_graph, results_text = results


# serialize the result to file
# print(boolean_value)
graph.serialize(destination=destfile, format='ttl')
print(results_graph.serialize(format='ttl'))
# print(results_text)


# report and quit
#Write a SPARQL query to print out each distinct sh:resultMessage in the results_graph
print('Wrote %u triples to file %s .' %
distinct_messages = """
      (len(res), destfile))
PREFIX sh: <http://www.w3.org/ns/shacl#>  
</syntaxhighlight>


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


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


sparql = SPARQLWrapper("http://dbpedia.org/sparql")
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
"""


sparql.setQuery("""
messages = results_graph.query(count_messages)
    PREFIX dbr: <http://dbpedia.org/resource/>
for row in messages:
    PREFIX dbo: <http://dbpedia.org/ontology/>
     print("COUNT    MESSAGE")
    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
     print(row.num_messages, "     ", row.message)
     SELECT ?comment
    WHERE {
    dbr:Barack_Obama rdfs:comment ?comment.
    FILTER (langMatches(lang(?comment),"en"))
     }
""")


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


for result in results["results"]["bindings"]:
    print(result["comment"]["value"])
</syntaxhighlight>
</syntaxhighlight>


==Lifting CSV to RDF==
=RDFS (Lab 10)=
 
<syntaxhighlight lang="Python">


<syntaxhighlight>
import owlrl
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib import Graph, RDF, Namespace, Literal, XSD, FOAF, RDFS
from rdflib.namespace import RDF, FOAF, RDFS, OWL
from rdflib.collection import Collection
import pandas as pd


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


# Load the CSV data as a pandas Dataframe.
csv_data = pd.read_csv("task1.csv")


# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
NS = {
csv_data = csv_data.replace(to_replace=" ", value="_", regex=True)
    'ex': ex,
    'rdf': RDF,
    'rdfs': RDFS,
    'foaf': FOAF,
}


# Here I mark all missing/empty data as "unknown". This makes it easy to delete triples containing this later.
#Write a small function that computes the RDFS closure on your graph.
csv_data = csv_data.fillna("unknown")
def flush():
    engine = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
    engine.closure()
    engine.flush_stored_triples()


# Loop through the CSV data, and then make RDF triples.
#Rick Gates was charged with money laundering and tax evasion.
for index, row in csv_data.iterrows():
g.add((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
    # The names of the people act as subjects.
g.add((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
    subject = row['Name']
    # Create triples: e.g. "Cade_Tracey - age - 27"
    g.add((URIRef(ex + subject), URIRef(ex + "age"), Literal(row["Age"])))
    g.add((URIRef(ex + subject), URIRef(ex + "married"), URIRef(ex + row["Spouse"])))
    g.add((URIRef(ex + subject), URIRef(ex + "country"), URIRef(ex + row["Country"])))


    # If We want can add additional RDF/RDFS/OWL information e.g
#When one thing that is charged with another thing,
    g.add((URIRef(ex + subject), RDF.type, FOAF.Person))
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.


# I remove triples that I marked as unknown earlier.
#Write a SPARQL query that checks the RDF type(s) of Rick Gates and money laundering in your RDF graph.
g.remove((None, None, URIRef("http://example.org/unknown")))
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)


# Clean printing of the graph.
#A person under investigation is a FOAF person
print(g.serialize(format="turtle").decode())
g.add((ex.PersonUnderInvestigation, RDFS.subClassOf, FOAF.Person))
</syntaxhighlight>
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)


===CSV file for above example===
print(g.serialize())


<syntaxhighlight>
"Name","Age","Spouse","Country"
"Cade Tracey","26","Mary Jackson","US"
"Bob Johnson","21","","Canada"
"Mary Jackson","25","","France"
"Phil Philips","32","Catherine Smith","Japan"
</syntaxhighlight>
</syntaxhighlight>


=OWL 1 (Lab 11)=
<syntaxhighlight lang="Python">


=Coding Tasks Lab 6=
from rdflib import Graph, RDFS, Namespace, RDF, FOAF, BNode, OWL, URIRef, Literal, XSD
<syntaxhighlight>
from rdflib.collection import Collection
import pandas as pd
import owlrl


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


from rdflib import Graph, Namespace, URIRef, Literal, BNode
from rdflib.namespace import RDF, XSD
ex = Namespace("http://example.org/")
sem = Namespace("http://semanticweb.cs.vu.nl/2009/11/sem/")
g = Graph()
g.bind("ex", ex)
g.bind("ex", ex)
g.bind("sem", sem)
# 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))


# Removing unwanted characters
# Actually, all the names mentioned in connection with the Mueller investigation refer to different people.
df = pd.read_csv('russia-investigation.csv')
b1 = BNode()
# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
b2 = BNode()
df = df.replace(to_replace=" ", value="_", regex=True)
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])
# This may seem odd, but in the data set we have a name like this:("Scooter"). So we have to remove quotation marks
g.add((b1, RDF.type, OWL.AllDifferent))
df = df.replace(to_replace=f'"', value="", regex=True)
g.add((b1, OWL.distinctMembers, b2))
# # 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.
# All these people are foaf:Persons as well as schema:Persons
for index, row in df.iterrows():
g.add((FOAF.Person, OWL.equivalentClass, schema.Person))
    name = row['investigation']
    investigation = URIRef(ex + name)
    g.add((investigation, RDF.type, sem.Event))
    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")
# Tax evation is a kind of bank and tax fraud.
print(g.serialize(format="turtle"))
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.")))


</syntaxhighlight>
# 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))


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


===RDFS-plus (OWL) Properties===
# Leading an organization is a way of being involved in an organization.
<syntaxhighlight>
g.add((ex.leading, RDFS.subPropertyOf, ex.involved))
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
# 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.
# which means that: (mother livesWith child % child livesWith father) != mother livesWith father. Which makes it non-transitive.
</syntaxhighlight>


<!--
# Being a campaign manager or an advisor for is a way of supporting someone.
==Lifting XML to RDF==
g.add((ex.campaignManagerTo, RDFS.subPropertyOf, ex.supports))
<syntaxhighlight>
g.add((ex.advisorTo, RDFS.subPropertyOf, ex.supports))
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF, XSD, RDFS
import xml.etree.ElementTree as ET


g = Graph()
# Donald Trump is a politician and a Republican.
ex = Namespace("http://example.org/TV/")
g.add((ex.Donald_Trump, RDF.type, ex.Politician))
prov = Namespace("http://www.w3.org/ns/prov#")
g.add((ex.Donald_Trump, RDF.type, ex.Republican))
g.bind("ex", ex)
g.bind("prov", prov)


tree = ET.parse("tv_shows.xml")
# A Republican politician is both a politician and a Republican.
root = tree.getroot()
g.add((ex.RepublicanPolitician, RDFS.subClassOf, ex.Politician))
g.add((ex.RepublicanPolitician, RDFS.subClassOf, ex.Republican))


for tv_show in root.findall('tv_show'):
#hasBusinessPartner
    show_id = tv_show.attrib["id"]
g.add((ex.Paul_Manafort, ex.hasBusinessPartner, ex.Rick_Gates))
    title = tv_show.find("title").text
g.add((ex.hasBusinessPartner, RDF.type, OWL.SymmetricProperty))
g.add((ex.hasBusinessPartner, RDF.type, OWL.IrreflexiveProperty))


    g.add((URIRef(ex + show_id), ex.title, Literal(title, datatype=XSD.string)))
#adviserTo
    g.add((URIRef(ex + show_id), RDF.type, ex.TV_Show))
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 


    for actor in tv_show.findall("actor"):
#wasLyingTo
        first_name = actor.find("firstname").text
g.add((ex.Rick_Gates_Lying, ex.wasLyingTo, ex.FBI))
        last_name = actor.find("lastname").text
g.add((ex.wasLyingTo, RDF.type, OWL.IrreflexiveProperty))
        full_name = first_name + "_" + last_name
# Not asymmetric as the subject and object could lie to each other; also in this context, the FBI can lie to you
       
        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())
#presidentOf
</syntaxhighlight>
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


===RDFS inference with RDFLib===
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>
</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.]
=OWL 2 (Lab 12)=
<syntaxhighlight lang="Python">


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.
@prefix : <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
<syntaxhighlight>
@prefix dc: <http://purl.org/dc/terms#> .
import rdflib.plugins.sparql.update
@prefix io: <http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#> .
import owlrl.RDFSClosure
@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#> .


g = rdflib.Graph()
<http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology> rdf:type owl:Ontology .


ex = rdflib.Namespace('http://example.org#')
#################################################################
g.bind('', ex)
#    Object Properties
#################################################################


g.update("""
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#indictedIn
PREFIX ex: <http://example.org#>
io:indictedIn rdf:type owl:ObjectProperty ;
PREFIX owl: <http://www.w3.org/2002/07/owl#>
              rdfs:subPropertyOf io:involvedIn ;
INSERT DATA {
              rdfs:domain io:InvestigatedPerson ;
    ex:Socrates rdf:type ex:Man .
              rdfs:range io:Investigation .
    ex:Man rdfs:subClassOf ex:Mortal .
}""")


rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
# RDF_Semantics parameters:
# - graph (rdflib.Graph) – The RDF graph to be extended.
# - axioms (bool) – Whether (non-datatype) axiomatic triples should be added or not.
# - daxioms (bool) – Whether datatype axiomatic triples should be added or not.
# - rdfs (bool) – Whether RDFS inference is also done (used in subclassed only).
# For now, you will in most cases use all False in RDFS_Semtantics.


# Generates the closure of the graph - generates the new entailed triples, but does not add them to the graph.
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#investigating
rdfs.closure()
io:investigating rdf:type owl:ObjectProperty ;
# Adds the new triples to the graph and empties the RDFS triple-container.
                rdfs:subPropertyOf io:involvedIn ;
rdfs.flush_stored_triples()
                rdfs:domain io:Investigator ;
                rdfs:range io:Investigation .


# 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>


===Language tagged RDFS labels===
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#involvedIn
<syntaxhighlight>
io:involvedIn rdf:type owl:ObjectProperty ;
from rdflib import Graph, Namespace, Literal
              rdfs:domain foaf:Person ;
from rdflib.namespace import RDFS
              rdfs:range io:Investigation .


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


g.add((ex.France, RDFS.label, Literal("Frankrike", lang="no")))
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#leading
g.add((ex.France, RDFS.label, Literal("France", lang="en")))
io:leading rdf:type owl:ObjectProperty ;
g.add((ex.France, RDFS.label, Literal("Francia", lang="es")))
          rdfs:subPropertyOf io:investigating ;
          rdfs:domain io:InvestigationLeader ;
          rdfs:range io:Investigation .




</syntaxhighlight>
#################################################################
#    Data properties
#################################################################


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


You can use the OWL-RL package again as for Lecture 5.


Instead of:  
###  http://www.w3.org/ns/prov#endedAtTime
<syntaxhighlight>
prov:endedAtTime rdf:type owl:DatatypeProperty ,
# The next three lines add inferred triples to g.
                          owl:FunctionalProperty ;
rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
                rdfs:domain io:Investigation ;
rdfs.closure()
                rdfs:range xsd:dateTime .
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_OWLRL_Semantics(g, False, False, False)
owl.closure()
owl.flush_stored_triples()
</syntaxhighlight>


Example updates and queries:
<syntaxhighlight>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX ex: <http://example.org#>


INSERT DATA {
###  http://www.w3.org/ns/prov#startedAtTime
    ex:Socrates ex:hasWife ex:Xanthippe .
prov:startedAtTime rdf:type owl:DatatypeProperty ,
    ex:hasHusband owl:inverseOf ex:hasWife .
                            owl:FunctionalProperty ;
}
                  rdfs:domain io:Investigation ;
</syntaxhighlight>
                  rdfs:range xsd:dateTime .


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


<syntaxhighlight>
###  http://xmlns.com/foaf/0.1/name
ASK {
foaf:name rdf:type owl:DatatypeProperty ;
  ex:Socrates ^ex:hasHusband ex:Xanthippe .
          rdfs:domain foaf:Person ;
}
          rdfs:range xsd:string .
</syntaxhighlight>
 
<syntaxhighlight>
INSERT DATA {
    ex:hasWife rdfs:subPropertyOf ex:hasSpouse .
    ex:hasSpouse rdf:type owl:SymmetricProperty .
}
</syntaxhighlight>
 
<syntaxhighlight>
ASK {
  ex:Socrates ex:hasSpouse ex:Xanthippe .
}
</syntaxhighlight>
 
<syntaxhighlight>
ASK {
  ex:Socrates ^ex:hasSpouse ex:Xanthippe .
}
</syntaxhighlight>




###  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 .


===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>


==Lifting HTML to RDF==
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Investigation
<syntaxhighlight>
io:Investigation rdf:type owl:Class .
from bs4 import BeautifulSoup as bs, NavigableString
from rdflib import Graph, URIRef, Namespace
from rdflib.namespace import RDF


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


html = open("tv_shows.html").read()
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#InvestigationLeader
html = bs(html, features="html.parser")
io:InvestigationLeader rdf:type owl:Class ;
                      rdfs:subClassOf io:Investigator .


shows = html.find_all('li', attrs={'class': 'show'})
for show in shows:
    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))
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Investigator
io:Investigator rdf:type owl:Class ;
                rdfs:subClassOf io:Person .




print(g.serialize(format="turtle").decode())
###  http://www.semanticweb.org/bruker/ontologies/2023/2/InvestigationOntology#Person
</syntaxhighlight>
io:Person rdf:type owl:Class ;
          rdfs:subClassOf foaf:Person .


===HTML code for the example above===
<syntaxhighlight>
<!DOCTYPE html>
<html>
<head>
    <meta charset="utf-8">
    <title></title>
</head>
<body>
    <div class="tv_shows">
        <ul>
            <li class="show">
                <h3>The_Sopranos</h3>
                <div class="irrelevant_data"></div>
                <ul class="actor_list">
                    <li>James Gandolfini</li>
                </ul>
            </li>
            <li class="show">
                <h3>Seinfeld</h3>
                <div class="irrelevant_data"></div>
                <ul class="actor_list">
                    <li >Jerry Seinfeld</li>
                    <li>Jason Alexander</li>
                    <li>Julia Louis-Dreyfus</li>
                </ul>
            </li>
        </ul>
    </div>
</body>
</html>
</syntaxhighlight>


==Web APIs with JSON==
###  http://xmlns.com/foaf/0.1/Person
<syntaxhighlight>
foaf:Person rdf:type owl:Class .
import requests
import json
import pprint


# Retrieve JSON data from API service URL. Then load it with the json library as a json object.
url = "http://api.geonames.org/postalCodeLookupJSON?postalcode=46020&#country=ES&username=demo"
data = requests.get(url).content.decode("utf-8")
data = json.loads(data)
pprint.pprint(data)
</syntaxhighlight>


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


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


<syntaxhighlight>
import rdflib


g = rdflib.Graph()
###  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" .


example = """
{
  "@context": {
    "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
###  http://dbpedia.org/resource/Michael_Flynn
g.parse(data=example, format='json-ld')
dbr:Michael_Flynn rdf:type owl:NamedIndividual ;
                  foaf:name "Michael Flynn" .


# serialisation does expansion by default
for line in g.serialize(format='json-ld').decode().splitlines():
    print(line)


# by supplying a context object, serialisation can do compaction
###  http://dbpedia.org/resource/Paul_Manafort
context = {
dbr:Paul_Manafort rdf:type owl:NamedIndividual ;
    "foaf": "http://xmlns.com/foaf/0.1/"
                  io:indictedIn <http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> ;
}
                  foaf:name "Paul Manafort" .
for line in g.serialize(format='json-ld', context=context).decode().splitlines():
    print(line)
</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>
###  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" .


==OWL - Complex Classes and Restrictions==
<syntaxhighlight>
import owlrl
from rdflib import Graph, Literal, Namespace, BNode
from rdflib.namespace import RDF, OWL, RDFS
from rdflib.collection import Collection


g = Graph()
###  http://dbpedia.org/resource/Roger_Stone
ex = Namespace("http://example.org/")
dbr:Roger_Stone rdf:type owl:NamedIndividual ;
g.bind("ex", ex)
                foaf:name "Roger Stone" .
g.bind("owl", OWL)


# a Season is either Autumn, Winter, Spring, Summer
seasons = BNode()
Collection(g, seasons, [ex.Winter, ex.Autumn, ex.Spring, ex.Summer])
g.add((ex.Season, OWL.oneOf, seasons))


# A Parent is a Father or Mother
###  http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)
b = BNode()
<http://dbpedia.org/resource/Special_Counsel_investigation_(2017–2019)> rdf:type owl:NamedIndividual ;
Collection(g, b, [ex.Father, ex.Mother])
                                                                        foaf:title "Mueller Investigation" .
g.add((ex.Parent, OWL.unionOf, b))


# A Woman is a person who has the "female" gender
br = BNode()
g.add((br, RDF.type, OWL.Restriction))
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()
#    General axioms
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.
[ rdf:type owl:AllDifferent ;
br = BNode()
  owl:distinctMembers ( dbr:Donald_Trump
g.add((br, RDF.type, OWL.Restriction))
                        dbr:Elizabeth_Prelogar
g.add((br, OWL.onProperty, ex.eats))
                        dbr:Michael_Flynn
g.add((br, OWL.QualifiedCardinality, Literal(0)))
                        dbr:Paul_Manafort
g.add((br, OWL.onClass, ex.Meat))
                        dbr:Robert_Mueller
bi = BNode()
                        dbr:Roger_Stone
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...:  
###  Generated by the OWL API (version 4.5.25.2023-02-15T19:15:49Z) https://github.com/owlcs/owlapi
g.add((ex.Bob, RDF.type, ex.Parent))
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>
</syntaxhighlight>


==Protege-OWL reasoning with HermiT==
=Using Graph Embeddings (Lab 13)=
 
https://colab.research.google.com/drive/1WkRJUeUBVF5yVv7o0pOKfsd4pqG6369k


[[:File:DL-reasoning-RoyalFamily-final.owl.txt | Example file]] from Lecture 13 about OWL-DL, rules and reasoning.
=Training Graph Embeddings (Lab 14)=


https://colab.research.google.com/drive/1jKpzlQ7gYTVzgphJsrK5iuMpFhkrY96q
-->
-->

Latest revision as of 10:56, 20 January 2025

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


Retrieved from "http://info216.wiki.uib.no/index.php?title=Lab_Solutions&oldid=2590"