Lab Solutions: Difference between revisions

From info216
No edit summary
(Proposed solution for Lab 7 RDFS)
(19 intermediate revisions by 3 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.
This page will be updated with Python examples related to the labs as the course progresses.


=Example lab solutions=
=Examples from the lectures=
 
==Getting started==


==Lecture 1: Introduction to KGs==
Turtle example:
<syntaxhighlight>
<syntaxhighlight>
 
@prefix ex: <http://example.org/> .
from rdflib.collection import Collection
ex:Roger_Stone
from rdflib import Graph, Namespace, Literal, URIRef
    ex:name "Roger Stone" ;
from rdflib.namespace import RDF, FOAF, XSD
    ex:occupation ex:lobbyist ;
 
    ex:significant_person ex:Donald_Trump .
g = Graph()
ex:Donald_Trump
EX = Namespace('http://EXample.org/')
    ex:name "Donald Trump" .
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.namespace_manager.bind('relationship', RL)
g.namespace_manager.bind('dbpediaOntology', DBO)
g.namespace_manager.bind('dbpediaPage', DBR)
 
g.add((EX.Cade, RDF.type, FOAF.Person))
g.add((EX.Mary, RDF.type, FOAF.Person))
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']
#for i in hobbies:
#    g.add((EX.Mary, FOAF.interest, EX[i]))
 
print(g.serialize(format="turtle"))
</syntaxhighlight>
</syntaxhighlight>


==RDFlib==
==Lecture 2: RDF==
<syntaxhighlight>
Blank nodes for anonymity, or when we have not decided on a URI:
 
<syntaxhighlight lang="Python">
from rdflib.namespace import RDF, XSD, FOAF
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
from rdflib import Graph, Namespace, Literal, BNode
from rdflib.collection import Collection


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


g = Graph()
g = Graph()
ex = Namespace('http://example.org/')
g.bind('ex', EX)  # this is why the line '@prefix ex: <http://example.org/> .'
schema = Namespace("https://schema.org/")
                  # and the 'ex.' prefix are used when we print out Turtle later
dbp = Namespace("https://dbpedia.org/resource/")
 
g.bind("ex", ex)
g.bind("dbp", dbp)
g.bind("schema", schema)


address = BNode()
robertMueller = BNode()
degree = BNode()
g.add((robertMueller, RDF.type, EX.Human))
 
g.add((robertMueller, FOAF.name, Literal('Robert Mueller', lang='en')))
# from lab 1
g.add((robertMueller, EX.position_held, Literal('Director of the Federal Bureau of Investigation', lang='en')))
g.add((ex.Cade, FOAF.name, Literal("Cade Tracey", datatype=XSD.string)))
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.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
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
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
emma_degree = BNode()
g.add((ex.Emma, FOAF.name, Literal("Emma Dominguez", datatype=XSD.string)))
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
emma_address = BNode()
g.add((ex.Emma, schema.address, emma_address))
g.add((emma_address, RDF.type, schema.PostalAdress))
g.add((emma_address, schema.streetAddress,
      Literal('Carrer de la Guardia Civil 20')))
g.add((emma_address, schema.addressRegion, dbp.Valencia))
g.add((emma_address, schema.postalCode, Literal('46020')))
g.add((emma_address, schema.addressCountry, dbp.Spain))
 
b = BNode()
g.add((ex.Emma, ex.visit, b))
Collection(g, b,
          [dbp.Portugal, dbp.Italy, dbp.France, dbp.Germany, dbp.Denmark, dbp.Sweden])


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


==SPARQL - Blazegraph==
Blank nodes used to group related properties:
<syntaxhighlight>
<syntaxhighlight>
PREFIX ex: <http://example.org/>
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX xml: <http://www.w3.org/XML/1998/namespace>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>


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


#select all triplets in graph
g = Graph()
SELECT ?s ?p ?o
g.bind('ex', EX)
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
# This is a task in Exercise 2
DELETE { ?s ?p ex:University_of_Valencia }
INSERT { ?s ?p ex:Universidad_de_Valencia }
WHERE  { ?s ?p ex:University_of_Valencia }


#check if the deletion worked
print(g.serialize(format='turtle'))
SELECT ?s ?o2
WHERE  {
  ?s ex:degree ?o .
  ?o ex:degreeSource ?o2 .
      }
#describe sergio
DESCRIBE ex:Sergio ?o
WHERE {
  ex:Sergio ?p ?o .
  ?o ?p2 ?o2 .
  }
</syntaxhighlight>
</syntaxhighlight>


==SPARQL - RDFlib==
Literals:
<syntaxhighlight>
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
 
namespace = "lab4"
sparql = SPARQLWrapper("http://10.111.21.183:9999/blazegraph/namespace/"+ namespace + "/sparql")
 
# Print out Cades interests
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT * WHERE {
    ex:Cade ex:interest ?interest.
    }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print(result["interest"]["value"])
 
# Print Emmas city and country
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT ?emmaCity ?emmaCountry
    WHERE {
        ex:Emma ex:address ?address .
        ?address ex:city ?emmaCity .
        ?address ex:country ?emmaCountry .
        }
""")
sparql.setReturnFormat(JSON)
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
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT ?person ?age
    WHERE {
        ?person ex:age ?age .
        FILTER(?age > 26) . 
        }
        """)
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
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
sparql.setQuery("""
    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
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT * WHERE {
    ex:Cade ex:interest ?interest.
    }
""")
sparql.setReturnFormat(JSON)
sparql.setMethod(GET)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print(result["interest"]["value"])
 
# Check university names
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT ?s ?o2
    WHERE  {
        ?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"])
 
 
#Delete and insert university of valencia
sparql.setQuery("""
    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
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    SELECT ?s ?o2
    WHERE  {
        ?s ex:degree ?o .
        ?o ex:degreeSource ?o2 .
      }
    """)
sparql.setReturnFormat(JSON)
sparql.setMethod(GET)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
    print(result["o2"]["value"])
 
#Insert Sergio
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    PREFIX foaf: <http://xmlns.com/foaf/0.1/>
    INSERT DATA {
        ex:Sergio a foaf:Person ;
        ex:address [ a ex:Address ;
                ex:city ex:Valenciay ;
                ex:country ex:Spain ;
                ex:postalCode "46021"^^xsd:string ;
                ex:state ex:California ;
                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.setReturnFormat(TURTLE)
sparql.setQuery("""
    PREFIX ex: <http://example.org/>
    DESCRIBE ex:Sergio ?o
    WHERE {
        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
EX = Namespace('http://example.org/')
sparql.setQuery("""
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX ex: <http://example.org/>
    CONSTRUCT {?city ex:locatedIn ?country}
    Where {
        ?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'))


</syntaxhighlight>
==Web APIs and JSON-LD==
<syntaxhighlight>
import requests
from rdflib import FOAF, Namespace, Literal, RDF, Graph, TURTLE
r = requests.get('http://api.open-notify.org/astros.json').json()
g = Graph()
g = Graph()
EX = Namespace('http://EXample.org/')
g.bind('ex', EX)
g.bind("ex", EX)


for item in r['people']:
g.add((EX.Robert_Mueller, RDF.type, EX.Human))
    craft = item['craft'].replace(" ","_")
g.add((EX.Robert_Mueller, FOAF.name, Literal('Robert Mueller', lang='en')))
    person = item['name'].replace(" ","_")
g.add((EX.Robert_Mueller, FOAF.name, Literal('رابرت مولر', lang='fa')))
    g.add((EX[person], EX.onCraft, EX[craft]))
g.add((EX.Robert_Mueller, DC.description, Literal('sixth director of the FBI', datatype=XSD.string)))
    g.add((EX[person], RDF.type, FOAF.Person))
g.add((EX.Robert_Mueller, EX.start_time, Literal(2001, datatype=XSD.integer)))
    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:
print(g.serialize(format='turtle'))
    # (we don't need to add that they know themselves)
    if (triplet[0] != triplet[2]):
        g.add((triplet))
       
print(g.serialize(format="turtle"))
</syntaxhighlight>
</syntaxhighlight>


==Semantic lifting - CSV==
Alternative container (open):
<syntaxhighlight>
<syntaxhighlight>
import pandas as pd
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
from rdflib import Graph, Namespace, URIRef, Literal
from rdflib.namespace import RDF, XSD
import spotlight
from spotlight import SpotlightException


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


# Parameter given to spotlight to filter out results with confidence lower than this value
g = Graph()
CONFIDENCE = 0.5
g.bind('ex', EX)
SERVER = "https://api.dbpedia-spotlight.org/en/annotate"
 
def annotate_entity(entity):
annotations = []
try:
annotations = spotlight.annotate(address=SERVER,text=entity, confidence=CONFIDENCE)
    # This catches errors thrown from Spotlight, including when no resource is found in DBpedia
except SpotlightException as e:
print(e)
return annotations


muellerReportArchives = BNode()
g.add((muellerReportArchives, RDF.type, RDF.Alt))


ex = Namespace("http://example.org/")
archive1 = 'https://archive.org/details/MuellerReportVolume1Searchable/' \
dbr = Namespace("http://dbpedia.org/resource/")
                    'Mueller%20Report%20Volume%201%20Searchable/'
dbp = Namespace("https://dbpedia.org/property/")
archive2 = 'https://edition.cnn.com/2019/04/18/politics/full-mueller-report-pdf/index.html'
dbpage = Namespace("https://dbpedia.org/page/")
archive3 = 'https://www.politico.com/story/2019/04/18/mueller-report-pdf-download-text-file-1280891'
sem = Namespace("http://semanticweb.cs.vu.nl/2009/11/sem/")
tl = Namespace("http://purl.org/NET/c4dm/timeline.owl#")


g = Graph()
g.add((muellerReportArchives, RDFS.member, Literal(archive1, datatype=XSD.anyURI)))
g.bind("ex", ex)
g.add((muellerReportArchives, RDFS.member, Literal(archive2, datatype=XSD.anyURI)))
g.bind("dbr", dbr)
g.add((muellerReportArchives, RDFS.member, Literal(archive3, datatype=XSD.anyURI)))
g.bind("dbp", dbp)
g.bind("dbpage", dbpage)
g.bind("sem", sem)
g.bind("tl", tl)


df = pd.read_csv("russia-investigations.csv")
g.add((EX.Mueller_Report, RDF.type, FOAF.Document))
# 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.
g.add((EX.Mueller_Report, DC.contributor, EX.Robert_Mueller))
df["name"] = df["name"].astype("str")
g.add((EX.Mueller_Report, SCHEMA.archivedAt, muellerReportArchives))
df["type"] = df["type"].astype("str")


# iterrows creates an iterable object (list of rows)
print(g.serialize(format='turtle'))
for index, row in df.iterrows():
investigation = URIRef(ex + row['investigation'])
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:
g.add((( URIRef(investigation_spotlight[0]["URI"]), RDF.type, sem.Event)))
except:
g.add((investigation, RDF.type, sem.Event))
try:
g.add((( URIRef(investigation_spotlight[0]["URI"]), sem.hasBeginTimeStamp, investigation_start)))
except:
g.add((investigation, sem.hasBeginTimeStamp, investigation_start))
try:
g.add((( URIRef(investigation_spotlight[0]["URI"]), sem.hasEndTimeStamp, investigation_end)))
except:
g.add((investigation, sem.hasEndTimeStamp, investigation_end))
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==
Sequence container (open):
<syntaxhighlight>
<syntaxhighlight>
from rdflib.namespace import RDF, FOAF, XSD, RDFS
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
from rdflib import OWL, Graph, Namespace, URIRef, Literal, BNode
from rdflib.namespace import RDF, RDFS, XSD, OWL
import owlrl


ex = Namespace("http://example.org/")
EX = Namespace('http://example.org/')
dbr = Namespace("http://dbpedia.org/resource/")
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()
g = Graph()
g.bind("ex", ex)
g.bind('ex', EX)
g.bind("dbr", dbr)
g.bind("dbp", dbp)
g.bind("dbpage", dbpage)
g.bind("sem", sem)
g.bind("tl", tl)


g.parse(location="exampleTTL.ttl", format="turtle")
donaldTrumpSpouses = BNode()
g.add((donaldTrumpSpouses, RDF.type, RDF.Seq))
g.add((donaldTrumpSpouses, RDF._1, EX.IvanaTrump))
g.add((donaldTrumpSpouses, RDF._2, EX.MarlaMaples))
g.add((donaldTrumpSpouses, RDF._3, EX.MelaniaTrump))


# University of California and University of Valencia are both Universities.
g.add((EX.Donald_Trump, SCHEMA.spouse, donaldTrumpSpouses))
g.add((ex.University_of_California, RDF.type, ex.University))
g.add((ex.University_of_Valencia, RDF.type, ex.University))
# 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.
print(g.serialize(format='turtle'))
g.add((ex.graduatedFromHEI, RDFS.subPropertyOf, ex.degree))
# That a city is a capital of a country means that this city is located in that country.
g.add((ex.capital, RDFS.domain, ex.Country))
g.add((ex.capital, RDFS.range, ex.City))
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)
rdfs.closure()
rdfs.flush_stored_triples()
g.serialize("output.ttl",format="ttl")
</syntaxhighlight>
</syntaxhighlight>


==OWL 1==
Collection (closed list):
<syntaxhighlight>
<syntaxhighlight>
import owlrl
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
from rdflib import Graph, Namespace, Literal, URIRef
from rdflib.namespace import RDF, RDFS, XSD, FOAF, OWL
from rdflib.collection import Collection
 
g = Graph()
print()
# 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)
g.bind("owl", OWL)


g.parse(location="lab8turtle.txt", format="turtle")
EX = Namespace('http://example.org/')
 
# Cade and Emma are two different persons.
g.add((ex.Cade, OWL.differentFrom, ex.Emma))
# 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).
g.add((ex.USA, OWL.sameAs, dbp.United_States))
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
    # (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))
g.add((ex.Cade, ex.livesWith, ex.Mary))
g.add((ex.Cade, ex.sibling, ex.Andrew))
g.add((ex.Cade, ex.hasFather, ex.Bob))
g.add((ex.Bob, ex.fatherOf, ex.Cade))
 
 
#Look through the predicates(properties) above and add new triples for each one that describes them as any of the following:
    # a reflexive , irreflexive, symmetric, asymmetric, transitive, functional, or an Inverse Functional Property.
g.add((ex.married, RDF.type, OWL.SymmetricProperty))
g.add((ex.married, RDF.type, OWL.FunctionalProperty))
g.add((ex.married, RDF.type, OWL.InverseFunctionalProperty))
g.add((ex.married, RDF.type, OWL.IrreflexiveProperty))
 
g.add((ex.livesWith, RDF.type, OWL.SymmetricProperty))
g.add((ex.livesWith, RDF.type, OWL.ReflexiveProperty))
g.add((ex.livesWith, RDF.type, OWL.TransitiveProperty))
 
g.add((ex.sibling, RDF.type, OWL.SymmetricProperty))
 
g.add((ex.hasFather, RDF.type, OWL.AsymmetricProperty))
g.add((ex.hasFather, RDF.type, OWL.FunctionalProperty))
g.add((ex.hasFather, RDF.type, OWL.IrreflexiveProperty))
 
g.add((ex.fatherOf, RDF.type, OWL.AsymmetricProperty))
g.add((ex.fatherOf, RDF.type, OWL.IrreflexiveProperty))
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.
owl = owlrl.CombinedClosure.RDFS_OWLRL_Semantics(g, False, False, False)
owl.closure()
owl.flush_stored_triples()
 
g.serialize("lab8output.xml",format="xml")
</syntaxhighlight>
 
==Semantic lifting - XML==
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF
import xml.etree.ElementTree as ET
import requests


g = Graph()
g = Graph()
ex = Namespace("http://example.org/")
g.bind('ex', EX)
prov = Namespace("http://www.w3.org/ns/prov#")
g.bind("ex", ex)
g.bind("prov", prov)


# URL of xml data
url = 'http://feeds.bbci.co.uk/news/rss.xml'
# Retrieve the xml data from the web-url.
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
writerDict = {
    "Mon":"Thomas_Smith",
    "Tue":"Thomas_Smith",
    "Wed":"Thomas_Smith",
    "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"):
    copyright = Literal(root.findall("./channel")[0].find("copyright").text)
    News_article_id = URIRef(item.find("guid").text)
    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))
    g.add((News_article_id, ex.description, description))
    g.add((News_article_id, ex.source_link, link))
    g.add((News_article_id, ex.pubDate, pubDate))
    g.add((News_article_id, ex.copyright, copyright))
    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))
    g.add((writerName, RDF.type, prov.Person))
    g.add((writerName, RDF.type, prov.Agent))
    g.add((ex.authoredBy, RDF.type, prov.Generation))
print(g.serialize(format="turtle"))
</syntaxhighlight>
==OWL 2==
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, BNode
from rdflib.namespace import RDF, OWL, RDFS
from rdflib.collection import Collection
from rdflib.collection import Collection


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


# anyone who is a graduate has at least one degree
donaldTrumpSpouses = BNode()
br = BNode()
Collection(g, donaldTrumpSpouses, [
g.add((br, RDF.type, OWL.Restriction))
    EX.IvanaTrump, EX.MarlaMaples, EX.MelaniaTrump
g.add((br, OWL.onProperty, ex.degree))
])
g.add((br, OWL.minCardinality, Literal(1)))
g.add((EX.Donald_Trump, SCHEMA.spouse, donaldTrumpSpouses))
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
print(g.serialize(format='turtle'))
br = BNode()
g.serialize(destination='s02_Donald_Trump_spouses_list.ttl', format='turtle')
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
print(g.serialize(format='turtle'))
 
bi = BNode()
Collection(g, bi, [Literal("A"), Literal("B"), Literal("C"), Literal("D"), Literal("E"), Literal("F")])
b1 = BNode()
g.add((b1, RDF.type, RDFS.Datatype))
g.add((b1, OWL.oneOf, bi))
 
g.add((ex.grade, RDFS.range, b1))
 
#a straight A student is a student that has only A grades
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()
g.add((b2, RDF.type, OWL.Restriction))
g.add((b2, OWL.onProperty, ex.grade))
g.add((b2, OWL.someValuesFrom, Literal("A")))
 
bi = BNode()
Collection(g, bi, [ex.Student, b1, b2])
g.add((ex.Straight_A_student, OWL.intersectionOf, bi))
 
#a graduate has no F grades
b3 = BNode()
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()
Collection(g, b6, [ex.Person, b1, b5])
g.add((ex.Graduate, OWL.intersectionOf, b6))
 
#a student has a unique student number
g.add((ex.student_number, RDF.type, OWL.FunctionalProperty))
g.add((ex.student_number, RDF.type, OWL.InverseFunctionalProperty))
 
#each student has exactly one average grade
b1 = BNode()
g.add((b1, RDF.type, OWL.Restriction))
g.add((b1, OWL.onProperty, ex.average_grade))
g.add((b1, OWL.cardinality, Literal(1)))
 
b2 = BNode()
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])
g.add((ex.Student, OWL.intersectionOf, b3))
 
#a course is either a bachelor, a master or a Ph.D course
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))
 
#a bachelor student takes only bachelor courses
g.add((ex.Bachelor_student, RDFS.subClassOf, ex.Student))
b1 = BNode()
g.add((b1, RDF.type, OWL.Restriction))
g.add((b1, OWL.onProperty, ex.hasCourse))
g.add((b1, OWL.allValuesFrom, ex.Bachelor_course))
 
b2 = BNode()
Collection(g, b2, [ex.Student, b1])
g.add((ex.Bachelor_student, OWL.intersectionOf, b2))
 
#a masters student takes only master courses and at most one bachelor course
 
b1 = BNode()
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()
g.add((b2, RDF.type, OWL.Restriction))
g.add((b2, OWL.onProperty, ex.hasCourse))
g.add((b2, OWL.someValuesFrom, ex.Master_course))
 
b3 = BNode()
Collection(g, b3, [ex.Master_course, ex.Bachelor_course])
 
b5 = BNode()
g.add((b5, RDF.type, OWL.Restriction))
g.add((b5, OWL.onProperty, ex.hasCourse))
g.add((b5, OWL.allValuesFrom, b3))
 
b6 = BNode()
Collection(g, b6, [ex.Student, b1, b2, b5])
g.add((ex.Master_student, OWL.intersectionOf, b6))
 
#a Ph.D student takes only Ph.D and at most two masters courses
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()
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()
Collection(g, b3, [ex.Master_course, ex["Ph.D_course"]])
 
b5 = BNode()
g.add((b5, RDF.type, OWL.Restriction))
g.add((b5, OWL.onProperty, ex.hasCourse))
g.add((b5, OWL.allValuesFrom, b3))
 
b6 = BNode()
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>
</syntaxhighlight>


==Lab 11: Semantic Lifting - HTML==
=Example lab solutions=


<syntaxhighlight>
==Getting started (Lab 1)==
from bs4 import BeautifulSoup as bs
from rdflib import Graph, Literal, URIRef, Namespace
from rdflib.namespace import RDF, SKOS, XSD
import requests
 
 
g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)


# Download html from URL and parse it with BeautifulSoup.
url = "https://www.semanticscholar.org/topic/Knowledge-Graph/159858"
page = requests.get(url)
html = bs(page.content, features="html.parser")
# print(html.prettify())
# Find the html that surrounds all the papers
papers = html.find_all('div', attrs={'class': 'flex-container'})
# Find the html that surrounds the info box
topic = html.find_all(
    'div', attrs={'class': 'flex-item__left-column entity-header'})
# Iterate through each paper to make triples:
for paper in papers:
    # 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)
    # Adding tripels
    g.add((article, RDF.type, ex.paper))
    g.add((article, ex.HasID, Literal(c_id, datatype=XSD.int)))
    g.add((article, ex.HasTitle, Literal(title, datatype=XSD.string)))
    g.add((article, ex.Publisher_year, Literal(papper_year, datatype=XSD.year)))
    author = author.split(", ")
    for x in author:
        name = x.replace(" ", "_")
        name = URIRef(ex + name)
        g.add((article, ex.hasAuthor, name))
# Iterate through the info box to make triples:
    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)
        g.add((article, RDF.type, SKOS.Concept))
        g.add((article, SKOS.hasTopConcept, main_topic))
    related_topic = related_topic.split(',')
    for related_labels in related_topic:
        related_topic = URIRef(ex + related_labels)
        g.add((article, SKOS.broader, related_topic))
print(g.serialize(format='turtle'))
</syntaxhighlight>
==Owlready2==
Martin's solution. NOTE: intead of using "is_a" to define classes like I have done, use "equivalent_to" to make the resoner work. 
<syntaxhighlight>
<syntaxhighlight>
from owlready2 import *
from rdflib import Graph, Namespace
BASE = 'http://info216.uib.no/owlready2-lab/'
onto = get_ontology(BASE)


def clean_onto(onto):
    with onto:
        for ind in onto.individuals():
            destroy_entity(ind)
        for prop in onto.properties():
            destroy_entity(prop)
        for cls in onto.classes():
            destroy_entity(cls)
def onto2graph(onto):
    graph = Graph()
    onto.save('temp_owlready2.nt', format='ntriples')
    graph.parse('temp_owlready2.nt', format='ntriples')
    return graph
def print_onto(onto):
    g = onto2graph(onto)
    g.bind('', Namespace(BASE))
    print(g.serialize(format='ttl'))
clean_onto(onto)
# anyone who is a graduate has at least one degree
with onto:
    class Student(Thing): pass
    class Degree(Thing): pass
    class hasDegree(Student >> Degree): pass
    class Graduate(Student):
        is_a = [hasDegree.some(Degree)]
#anyone who is a university graduate has at least one degree from a university
with onto:
    class UniversityDegree(Degree): pass
    class UniversityGraduate(Graduate):
        is_a = [hasDegree.some(UniversityDegree)]
#a grade is either an A, B, C, D, E or F
with onto:
    class Grade(Thing): pass
    class A(Grade): pass
    class B(Grade): pass
    class C(Grade): pass
    class D(Grade): pass
    class E(Grade): pass
    class F(Grade): pass
Grade.is_a.append(OneOf([A, B, C, D, E, F]))
#a straight A student is a student that has only A grades
with onto:
    class hasGrade(Student >> Grade): pass
    class StraightAStudent(Student):
        is_a = [hasGrade.only(A)]
#a graduate has no F grades
#Graduate.is_a.append(hasGrade.only(OneOf[A,B,C,D,E]))
#a student has a unique student number
with onto:
    class StudentNumber(Thing):pass
    class hasStudentNumber(Student >> StudentNumber, FunctionalProperty, InverseFunctionalProperty):pass
#each student has exactly one average grade
with onto:
    class AverageGrade(Grade):pass
    class hasAverageGrade(Student >> AverageGrade):pass
Student.is_a.append(hasAverageGrade.exactly(1,AverageGrade))
Student.is_a.append(hasStudentNumber.exactly(1,StudentNumber))
   
#a course is either a bachelor, a master or a Ph.D course
with onto:
    class Course(Thing):pass
    class BachelorCourse(Course):pass
    class MasterCourse(Course):pass
    class PhDCourse(Course):pass
   
Course.is_a.append(OneOf([BachelorCourse, MasterCourse, PhDCourse]))
#a bachelor student takes only bachelor courses
with onto:
    class takesCourse(Student>>Course):pass
    class BachelorStudent(Student):
        is_a = [
            takesCourse.only(BachelorCourse) &
            takesCourse.some(Course)
        ]
       
#a masters student takes only master courses and at most one bachelor course
with onto:
    class MasterOrBachelorCourse(Course):pass
    class MasterStudent(Student):
        is_a = [
            takesCourse.only(Not(PhDCourse)) &
            takesCourse.max(1,BachelorCourse) &
            takesCourse.some(MasterCourse)
            ]
#a Ph.D student takes only Ph.D and at most two masters courses
with onto:
    class PhDStudent(Student):
        is_a = [
            takesCourse.only(Not(BachelorCourse))&
            takesCourse.max(2,MasterCourse)&
            takesCourse.some(PhDCourse)
            ]
# In comparison to lab 10..
"""
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()
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()
Collection(g, b3, [ex.Master_course, ex["Ph.D_course"]])
b5 = BNode()
g.add((b5, RDF.type, OWL.Restriction))
g.add((b5, OWL.onProperty, ex.hasCourse))
g.add((b5, OWL.allValuesFrom, b3))
b6 = BNode()
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
#print(onto2graph(onto).serialize(format="turtle"))
clean_onto(onto)
# anyone who is a graduate has at least one degree
# a graduate is a student with at least one degree
with onto:
    class Student(Thing): pass
    class Degree(Thing): pass
    class hasDegree(Student >> Degree): pass
    class Graduate(Student):
        equivalent_to = [hasDegree.some(Degree)]
# test with individual
with onto:
    cade = Student()
    infosci = Degree()
    cade.hasDegree.append(infosci)
from owlready2 import sync_reasoner
print(onto.Graduate in cade.is_a)
sync_reasoner()
print(onto.Graduate in cade.is_a)
print("graduate is: ", Graduate.is_a)
print("cade is: ", cade.is_a)
</syntaxhighlight>
Alternative solution. More pro from Andreas, but only a quick draft he stresses (but I still think it's valuable to share), so you might need to make some changes (like the one recommended above: equivalent_to instead of is_a).
<syntaxhighlight>
from owlready2 import get_ontology, Thing, ObjectProperty
from rdflib import Graph, Namespace
from rdflib import Graph, Namespace


BASE = 'http://info216.uib.no/owlready2-lab/'
g = Graph()
onto = get_ontology(BASE)


def onto2graph(onto):
ex = Namespace('http://example.org/')
    graph = Graph()
    onto.save('temp.nt', format='ntriples')
    graph.parse('temp.nt', format='ntriples')
    return graph


def print_onto(onto):
g.bind("ex", ex)
    g = onto2graph(onto)
    g.bind('', Namespace(BASE))
    print(g.serialize(format='ttl'))


from owlready2 import destroy_entity
#The Mueller Investigation was lead by Robert Mueller.
def clean_onto(onto):
g.add((ex.Mueller_Investigation, ex.leadBy, ex.Robert_Muller))
    with onto:
        for ind in onto.individuals():
            destroy_entity(ind)
        for prop in onto.properties():
            destroy_entity(prop)
        for cls in onto.classes():
            destroy_entity(cls)


# anyone who is a graduate has at least one degree
#It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, and Roger Stone.
with onto:
g.add((ex.Mueller_Investigation, ex.involved, ex.Paul_Manafort))
    class Student(Thing): pass
g.add((ex.Mueller_Investigation, ex.involved, ex.Rick_Gates))
    class Degree(Thing): pass
g.add((ex.Mueller_Investigation, ex.involved, ex.George_Papadopoulos))
    class hasDegree(Student >> Degree): pass
g.add((ex.Mueller_Investigation, ex.involved, ex.Michael_Flynn))
    class Graduate(Student):
g.add((ex.Mueller_Investigation, ex.involved, ex.Michael_Cohen))
        is_a = [hasDegree.some(Degree)]
g.add((ex.Mueller_Investigation, ex.involved, ex.Roger_Stone))


# anyone who is a university graduate has at least one degree from a university
# --- Paul Manafort ---
with onto:
#Paul Manafort was business partner of Rick Gates.
    class hasDegree(ObjectProperty): pass
g.add((ex.Paul_Manafort, ex.businessManager, ex.Rick_Gates))
    class degreeFrom(ObjectProperty): pass
# He was campaign chairman for Trump
    class Degree(Thing): pass
g.add((ex.Paul_Manafort, ex.campaignChairman, ex.Donald_Trump))
    class University(Thing): pass
    class UniversityGraduate(Thing):
        hasDegree: Degree
        is_a = [hasDegree.some(Degree & degreeFrom.some(University))]
print_onto(onto)


from owlready2 import declare_datatype
# He was charged with money laundering, tax evasion, and foreign lobbying.
class XSDString(object):
g.add((ex.Paul_Manafort, ex.chargedWith, ex.MoneyLaundering))
    def __init__(self, value): self.value = value
g.add((ex.Paul_Manafort, ex.chargedWith, ex.TaxEvasion))
def str_parser(s): return s
g.add((ex.Paul_Manafort, ex.chargedWith, ex.ForeignLobbying))
def str_unparser(s): return s
declare_datatype(XSDString, 'http://www.w3.org/2001/XMLSchema#string', str_parser, str_unparser)


# a grade is either an A, B, C, D, E or F
# He was convicted for bank and tax fraud.
from owlready2 import OneOf
g.add((ex.Paul_Manafort, ex.convictedFor, ex.BankFraud))
with onto:
g.add((ex.Paul_Manafort, ex.convictedFor, ex.TaxFraud))
    class Grade(Thing): pass
    class charGrade(Grade >> XSDString): pass
    grade_A = Grade()
    grade_A.charGrade = ['A']
    grade_B = Grade()
    grade_B.charGrade = ['B']
    grade_C = Grade()
    grade_C.charGrade = ['C']
    grade_D = Grade()
    grade_D.charGrade = ['D']
    grade_E = Grade()
    grade_E.charGrade = ['E']
    grade_F = Grade()
    grade_F.charGrade = ['F']
    Grade.equivalent_to.append(OneOf([
        grade_A, grade_B, grade_C, grade_D, grade_E, grade_F
    ]))  
print_onto(onto)


# a straight A student is a student that has only A grades
# He pleaded guilty to conspiracy.
with onto:
g.add((ex.Paul_Manafort, ex.pleadGuiltyTo, ex.Conspiracy))
    class Grade(Thing): pass
# He was sentenced to prison.
    class charGrade(Grade >> XSDString): pass
g.add((ex.Paul_Manafort, ex.sentencedTo, ex.Prison))
    grade_A = Grade()
# He negotiated a plea agreement.
    grade_A.charGrade = ['A']
g.add((ex.Paul_Manafort, ex.negoiated, ex.PleaBargain))
    grade_B = Grade()
    grade_B.charGrade = ['B']
    # ...
    Grade.equivalent_to.append(OneOf([
        grade_A, grade_B, # ...
    ]))  


    class Student(Thing): pass
# --- Rick Gates ---
    class hasGrade(Student >> Grade): pass
#Rick Gates was charged with money laundering, tax evasion and foreign lobbying.
    class GradeA(Grade):
g.add((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
        equivalent_to = [OneOf([grade_A])]
g.add((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
    class StraightAStudent(Student):
g.add((ex.Rick_Gates, ex.chargedWith, ex.ForeignLobbying))
        equivalent_to = [
            hasGrade.some(GradeA) & hasGrade.only(GradeA)
        ]
print_onto(onto)


# a graduate has no F grades
#He pleaded guilty to conspiracy and lying to FBI.
with onto:
g.add((ex.Rick_Gates, ex.pleadGuiltyTo, ex.Conspiracy))
    class Grade(Thing): pass
g.add((ex.Rick_Gates, ex.pleadGuiltyTo, ex.LyingToFBI))
    class charGrade(Grade >> XSDString): pass
    grade_A = Grade()
    grade_A.charGrade = ['A']
    # ...
    grade_F.charGrade = ['F']
    Grade.equivalent_to.append(OneOf([
        grade_A, # ...
        grade_F
    ]))  


    class Student(Thing): pass
#Use the serialize method to write out the model in different formats on screen
    class hasGrade(Student >> Grade): pass
print(g.serialize(format="ttl"))
    class GradeF(Grade):
# g.serialize("lab1.ttl", format="ttl") #or to file
        equivalent_to = [OneOf([grade_F])]
    class Graduate(Student):
        equivalent_to = [Student & ~ hasGrade.some(GradeF)]
print_onto(onto)


# a student has a single unique student number
#Loop through the triples in the model to print out all triples that have pleading guilty as predicate
class XSDInt(object):
for subject, object in g[ : ex.pleadGuiltyTo : ]:
    def __init__(self, value): self.value = value
    print(subject, ex.pleadGuiltyTo, object)
def int_parser(s): return int(s)
def int_unparser(i): return str(i)
declare_datatype(XSDInt, 'http://www.w3.org/2001/XMLSchema#int', int_parser, int_unparser)


from owlready2 import FunctionalProperty, InverseFunctionalProperty
# Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week
with onto:
    class Student(Thing): pass
    class hasStudentNumber(Student >> XSDInt):
        is_a = [FunctionalProperty, InverseFunctionalProperty]
print_onto(onto)


# each student has exactly one average grade
#Write a method (function) that submits your model for rendering and saves the returned image to file.
class XSDFloat(object):
import requests
    def __init__(self, value): self.value = value
import shutil
def int_parser(s): return float(s)
def int_unparser(f): return str(f)
declare_datatype(XSDFloat, 'http://www.w3.org/2001/XMLSchema#float', int_parser, int_unparser)
 
with onto:
    class Student(Thing): pass
    class hasAverageGrade(Grade >> XSDFloat): pass
    Student.is_a.append(hasAverageGrade.exactly(1, XSDFloat))
print_onto(onto)
 
# a course is either a bachelor, a master or a Ph.D course
from owlready2 import AllDisjoint
with onto:
    class Course(Thing): pass
    class BachelorCourse(Course): pass
    class MasterCourse(Course): pass
    class PhDCourse(Course): pass
    AllDisjoint([BachelorCourse, MasterCourse, PhDCourse])
print_onto(onto)
 
# a bachelor student takes only bachelor courses
from owlready2 import AllDisjoint
with onto:
    class Course(Thing): pass
    class BachelorCourse(Course): pass
    class MasterCourse(Course): pass
    class PhDCourse(Course): pass
    AllDisjoint([BachelorCourse, MasterCourse, PhDCourse])
print_onto(onto)
 
# a masters student takes only master courses, except for at most one bachelor course
with onto:
    class Student(Thing): pass
    class Course(Thing): pass
    class takesCourse(Student >> Course): pass
    class BachelorCourse(Course): pass
    class MasterCourse(Course): pass
    class MasterStudent(Student):
        is_a = [
            takesCourse.some(MasterCourse) &
            takesCourse.only(MasterCourse | BachelorCourse) &
            takesCourse.max(1, BachelorCourse)
        ]
print_onto(onto)
 
# a Ph.D student takes only Ph.D courses, except for at most two masters courses
with onto:
    class Student(Thing): pass
    class Course(Thing): pass
    class takesCourse(Student >> Course): pass
    class MasterCourse(Course): pass
    class PhDCourse(Course): pass
    class PhDStudent(Student):
        is_a = [
            takesCourse.some(PhDCourse) &
            takesCourse.only(PhDCourse | MasterCourse) &
            takesCourse.max(2, MasterCourse)
        ]
print_onto(onto)
 
# a Ph.D. student cannot take a bachelor course
with onto:
    class Student(Thing): pass
    class Course(Thing): pass
    class takesCourse(Student >> Course): pass
    class BachelorCourse(Course): pass
    class PhDStudent(Student):
        is_a = [
            takesCourse.max(0, BachelorCourse)
        ]
print_onto(onto)
 
# ...alternative solution
clean_onto(onto)
with onto:
    class Student(Thing): pass
    class Course(Thing): pass
    class takesCourse(Student >> Course): pass
    class BachelorCourse(Course): pass
    class PhDStudent(Student):
        is_a = [Student & ~ takesCourse.some(BachelorCourse)]
print_onto(onto)


# a graduate is a student with at least one degree
def graphToImage(graph):
with onto:
    data = {"rdf":graph, "from":"ttl", "to":"png"}
     class Student(Thing): pass
    link = "http://www.ldf.fi/service/rdf-grapher"
     class Degree(Thing): pass
     response = requests.get(link, params = data, stream=True)
     class hasDegree(Student >> Degree): pass
     # print(response.content)
     class Graduate(Student):  
     print(response.raw)
         equivalent_to = [Student & hasDegree.some(Degree)]
     with open("lab1.png", "wb") as fil:
         shutil.copyfileobj(response.raw, fil)


# test with individual
graph = g.serialize(format="ttl")
with onto:
graphToImage(graph)
    cade = Student()
    infosci = Degree()
    cade.hasDegree.append(infosci)
 
from owlready2 import sync_reasoner
 
print(onto.Graduate in cade.is_a)
sync_reasoner()
print(onto.Graduate in cade.is_a)
 
# if you have more time:
# populate the ontology with individuals
# a straight A student is a student that has only A grades
clean_onto(onto)
with onto:
    class Grade(Thing): pass
    class charGrade(Grade >> XSDString): pass
    grade_A = Grade()
    grade_A.charGrade = ['A']
    grade_B = Grade()
    grade_B.charGrade = ['B']
    # ...
    Grade.equivalent_to.append(OneOf([
        grade_A, grade_B,  # ...
    ]))
 
    class Student(Thing): pass
    class hasGrade(Student >> Grade): pass
    class GradeA(Grade):
        equivalent_to = [OneOf([grade_A])]
    class StraightAStudent(Student):
        equivalent_to = [
            Student &
            hasGrade.some(GradeA) & hasGrade.only(GradeA)
        ]
    # add individual
    cade = Student()
    cade.hasGrade.append(grade_A)
print_onto(onto)
 
from owlready2 import sync_reasoner
print(onto.StraightAStudent in cade.is_a)
sync_reasoner()
print(onto.StraightAStudent in cade.is_a)
 
from owlready2 import close_world
close_world(onto)  # because of the "only"-restriction
sync_reasoner()
print(onto.StraightAStudent in cade.is_a)
</syntaxhighlight>
</syntaxhighlight>


=More miscellaneous examples=
==RDF programming with RDFlib (Lab 2)==
 


===Printing the triples of the Graph in a readable way===
<syntaxhighlight>
<syntaxhighlight>
# The turtle format has the purpose of being more readable for humans.
print(g.serialize(format="turtle"))
</syntaxhighlight>


===Coding Tasks Lab 1===
from rdflib import Graph, URIRef, Namespace, Literal, XSD, BNode
<syntaxhighlight>
from rdflib.collection import Collection
from rdflib import Graph, Namespace, URIRef, BNode, Literal
from rdflib.namespace import RDF, FOAF, XSD
 
g = Graph()
ex = Namespace("http://example.org/")
 
g.add((ex.Cade, ex.married, ex.Mary))
g.add((ex.France, ex.capital, ex.Paris))
g.add((ex.Cade, ex.age, Literal("27", datatype=XSD.integer)))
g.add((ex.Mary, ex.age, Literal("26", datatype=XSD.integer)))
g.add((ex.Mary, ex.interest, ex.Hiking))
g.add((ex.Mary, ex.interest, ex.Chocolate))
g.add((ex.Mary, ex.interest, ex.Biology))
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Paris, RDF.type, ex.City))
g.add((ex.Paris, ex.locatedIn, ex.France))
g.add((ex.Cade, ex.characteristic, ex.Kind))
g.add((ex.Mary, ex.characteristic, ex.Kind))
g.add((ex.Mary, RDF.type, FOAF.Person))
g.add((ex.Cade, RDF.type, FOAF.Person))
 
# OR


g = Graph()
g = Graph()
g.parse("lab1.ttl", format="ttl") #Retrives the triples from lab 1


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


g.add((ex.Cade, FOAF.name, Literal("Cade", datatype=XSD.string)))
# --- Michael Cohen ---
g.add((ex.Mary, FOAF.name, Literal("Mary", datatype=XSD.string)))
#Michael Cohen was Donald Trump's attorney.
g.add((ex.Cade, RDF.type, FOAF.Person))
g.add((ex.Michael_Cohen, ex.attorneyTo, ex.Donald_Trump))
g.add((ex.Mary, RDF.type, FOAF.Person))
#He pleaded guilty to lying to the FBI.
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Michael_Cohen, ex.pleadGuiltyTo, ex.LyingToCongress))
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(g.serialize(format="turtle"))
# --- Michael Flynn ---
#Michael Flynn was adviser to Trump.
g.add((ex.Michael_Flynn, ex.adviserTo, ex.Donald_Trump))
#He pleaded guilty to lying to the FBI.
g.add((ex.Michael_Flynn, ex.pleadGuiltyTo, ex.LyingToFBI))
# He negotiated a plea agreement.
g.add((ex.Michael_Flynn, ex.negoiated, ex.PleaBargain))  


</syntaxhighlight>
#How can you modify your knowledge graph to account for the different lying?
#Remove these to not have duplicates
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))


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


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


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


from rdflib import Graph, Namespace, URIRef, BNode, Literal
print(g.serialize(format="ttl"))
from rdflib.namespace import RDF, FOAF, XSD


g = Graph()
#Save (serialize) your graph to a Turtle file.
ex = Namespace("http://example.org/")
# g.serialize("lab2.ttl", format="ttl")


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


# How to represent the address of Cade Tracey. From probably the worst solution to the best.
#Read (parse) the Turtle file back into a Python program, and check that the new triples are there
def serialize_Graph():
    newGraph = Graph()
    newGraph.parse("lab2.ttl")
    print(newGraph.serialize())


# Solution 1 -
# serialize_Graph() #Don't need this to run until after adding the triples above to the ttl file
# 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.


g.add((ex.Cade_Tracey, ex.livesIn, Literal("1516_Henry_Street, Berkeley, California 94709, USA")))
#Write a method (function) that starts with Donald Trump prints out a graph depth-first to show how the other graph nodes are connected to him
visited_nodes = set()


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


# Solution 2 -
def print_Tree(tree, root, indent=0):
# Seperate the different pieces information into their own triples
    #Print the tree depth-first.
 
    print(str(root))
g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
    for s, p, o in tree:
g.add((ex.Cade_tracey, ex.city, Literal("Berkeley")))
        if s==root:
g.add((ex.Cade_tracey, ex.state, Literal("California")))
            print('    '*indent + '  ' + str(p), end=' ')
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
            print_Tree(tree, o, indent+1)
g.add((ex.Cade_tracey, ex.country, Literal("USA")))
   
 
tree = create_Tree(g, [ex.Donald_Trump])
 
print_Tree(tree, ex.Donald_Trump)
# Solution 3 - Some parts of the addresses can make more sense to be resources than Literals.
# Larger concepts like a city or state are typically represented as resources rather than Literals, but this is not necesarilly a requirement in the case that you don't intend to say more about them.
 
g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
g.add((ex.Cade_tracey, ex.city, ex.Berkeley))
g.add((ex.Cade_tracey, ex.state, ex.California))
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
g.add((ex.Cade_tracey, ex.country, ex.USA))
 
 
# Solution 4
# Grouping of the information into an Address. We can Represent the address concept with its own URI OR with a Blank Node.
# One advantage of this is that we can easily remove the entire address, instead of removing each individual part of the address.
# Solution 4 or 5 is how I would recommend to make addresses. Here, ex.CadeAddress could also be called something like ex.address1 or so on, if you want to give each address a unique ID.
 
# Address URI - CadeAdress
 
g.add((ex.Cade_Tracey, ex.address, ex.CadeAddress))
g.add((ex.CadeAddress, RDF.type, ex.Address))
g.add((ex.CadeAddress, ex.street, Literal("1516 Henry Street")))
g.add((ex.CadeAddress, ex.city, ex.Berkeley))
g.add((ex.CadeAddress, ex.state, ex.California))
g.add((ex.CadeAddress, ex.postalCode, Literal("94709")))
g.add((ex.CadeAddress, ex.country, ex.USA))
 
# OR
 
# Blank node for Address. 
address = BNode()
g.add((ex.Cade_Tracey, ex.address, address))
g.add((address, RDF.type, ex.Address))
g.add((address, ex.street, Literal("1516 Henry Street", datatype=XSD.string)))
g.add((address, ex.city, ex.Berkeley))
g.add((address, ex.state, ex.California))
g.add((address, ex.postalCode, Literal("94709", datatype=XSD.string)))
g.add((address, ex.country, ex.USA))
 
 
# Solution 5 using existing vocabularies for address
 
# (in this case https://schema.org/PostalAddress from schema.org).
# Also using existing ontology for places like California. (like http://dbpedia.org/resource/California from dbpedia.org)
 
schema = Namespace("https://schema.org/")
dbp = Namespace("https://dpbedia.org/resource/")
 
g.add((ex.Cade_Tracey, schema.address, ex.CadeAddress))
g.add((ex.CadeAddress, RDF.type, schema.PostalAddress))
g.add((ex.CadeAddress, schema.streetAddress, Literal("1516 Henry Street")))
g.add((ex.CadeAddress, schema.addresCity, dbp.Berkeley))
g.add((ex.CadeAddress, schema.addressRegion, dbp.California))
g.add((ex.CadeAddress, schema.postalCode, Literal("94709")))
g.add((ex.CadeAddress, schema.addressCountry, dbp.United_States))


</syntaxhighlight>
</syntaxhighlight>


===Typed Literals===
==SPARQL Programming (Lab 4)==
'''NOTE: These tasks were performed on the old dataset, with the new dataset, some of these answers would be different.'''
<syntaxhighlight>
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace
from rdflib.namespace import XSD
g = Graph()
ex = Namespace("http://example.org/")
g.add((ex.Cade, ex.age, Literal(27, datatype=XSD.integer)))
g.add((ex.Cade, ex.gpa, Literal(3.3, datatype=XSD.float)))
g.add((ex.Cade, FOAF.name, Literal("Cade Tracey", datatype=XSD.string)))
g.add((ex.Cade, ex.birthday, Literal("2006-01-01", datatype=XSD.date)))
</syntaxhighlight>


 
from rdflib import Graph, Namespace, RDF, FOAF
===Writing and reading graphs/files===
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE
 
<syntaxhighlight>
  # 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
parsed_graph = g.parse(location="triples.txt", format="turtle")
 
  # Parsing a remote endpoint like Dbpedia
dbpedia_graph = g.parse("http://dbpedia.org/resource/Pluto")
</syntaxhighlight>
 
===Graph Binding===
<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()
g = Graph()
g.parse("Russia_investigation_kg.ttl")


ex = Namespace("http://example.org/")
# ----- RDFLIB -----
dbp = Namespace("http://dbpedia.org/resource/")
ex = Namespace('http://example.org#')
schema = Namespace("https://schema.org/")
 
g.bind("ex", ex)
g.bind("dbp", dbp)
g.bind("schema", schema)
</syntaxhighlight>


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


<syntaxhighlight>
# Print out a list of all the predicates used in your graph.
from rdflib import Graph, Namespace
task1 = g.query("""
from rdflib.collection import Collection
SELECT DISTINCT ?p WHERE{
    ?s ?p ?o .
}
""", initNs=NS)


print(list(task1))


# Sometimes we want to add many objects or subjects for the same predicate at once.  
# Print out a sorted list of all the presidents represented in your graph.
# In these cases we can use Collection() to save some time.
task2 = g.query("""
# In this case I want to add all countries that Emma has visited at once.
SELECT DISTINCT ?president WHERE{
    ?s :president ?president .
}
ORDER BY ?president
""", initNs=NS)


b = BNode()
print(list(task2))
g.add((ex.Emma, ex.visit, b))
Collection(g, b,
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])


# OR
# 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 = {}


g.add((ex.Emma, ex.visit, ex.EmmaVisits))
task3 = g.query("""
Collection(g, ex.EmmaVisits,
SELECT ?president ?person WHERE{
     [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])
     ?s :president ?president;
      :name ?person;
      :outcome :indictment.
}
""", initNs=NS)


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


==SPARQL==
print(task3_dic)


Also see the [[SPARQL Examples]] page!
# Use an ASK query to investigate whether Donald Trump has pardoned more than 5 people.


===Querying a local ("in memory") graph===
# This task is a lot trickier than it needs to be. As far as I'm aware RDFLib has no HAVING support, so a query like this:
 
task4 = g.query("""
Example contents of the file family.ttl:
ASK {
@prefix rex: <http://example.org/royal#> .
  SELECT (COUNT(?s) as ?count) WHERE{
@prefix fam: <http://example.org/family#> .
    ?s :pardoned :true;
    :president :Bill_Clinton .
rex:IngridAlexandra fam:hasParent rex:HaakonMagnus .
    }
rex:SverreMagnus fam:hasParent rex:HaakonMagnus .
    HAVING (?count > 5)
rex:HaakonMagnus fam:hasParent rex:Harald .
rex:MarthaLouise fam:hasParent rex:Harald .
rex:HaakonMagnus fam:hasSister rex:MarthaLouise .
 
import rdflib
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:
import rdflib
g = rdflib.Graph()
g.parse("family.ttl", format='ttl')
q = rdflib.plugins.sparql.prepareQuery(
        """SELECT ?child ?sister WHERE {
                  ?child fam:hasParent ?parent .
                  ?parent fam:hasSister ?sister .
        }""",
        initNs = { "fam": "http://example.org/family#"})
  sm = rdflib.URIRef("http://example.org/royal#SverreMagnus")
for row in g.query(q, initBindings={'child': sm}):
        print(row)
 
===Select all contents of lists (rdfllib.Collection)===
<syntaxhighlight>
 
# rdflib.Collection has a different interntal structure so it requires a slightly more advance query. Here I am selecting all places that Emma has visited.
 
PREFIX ex:  <http://example.org/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
 
SELECT ?visit
WHERE {
  ex:Emma ex:visit/rdf:rest*/rdf:first ?visit
}
}
</syntaxhighlight>
""", initNs=NS)


print(task4.askAnswer)


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


<syntaxhighlight>
task4 = g.query("""
from rdflib import Graph, Namespace, URIRef
    ASK{
from rdflib.plugins.sparql import prepareQuery
        SELECT ?count WHERE{{
          SELECT (COUNT(?s) as ?count) WHERE{
            ?s :pardoned :true;
                  :president :Bill_Clinton  .
                }}
        FILTER (?count > 5)
        }
    }
""", initNs=NS)


g = Graph()
print(task4.askAnswer)
ex = Namespace("http://example.org/")
g.bind("ex", ex)


g.add((ex.Cade, ex.livesIn, ex.France))
# Use a DESCRIBE query to create a new graph with information about Donald Trump. Print out the graph in Turtle format.
g.add((ex.Anne, ex.livesIn, ex.Norway))
g.add((ex.Sofie, ex.livesIn, ex.Sweden))
g.add((ex.Per, ex.livesIn, ex.Norway))
g.add((ex.John, ex.livesIn, ex.USA))


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


def find_people_from_country(country):
# task5 = g.query("""  
        country = URIRef(ex + country)
# DESCRIBE :Donald_Trump
        q = prepareQuery(
# """, initNs=NS)
        """
        PREFIX ex: <http://example.org/>
        SELECT ?person WHERE {
        ?person ex:livesIn ?country.
        }
        """)


        capital_result = g.query(q, initBindings={'country': country})
# print(task5.serialize())


        for row in capital_result:
# ----- SPARQLWrapper -----
            print(row)


find_people_from_country("Norway")
namespace = "kb" #Default namespace
</syntaxhighlight>
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql") #Replace localhost:9999 with your URL


===SELECTING data from Blazegraph via Python===
# The current dates are URIs, we would want to change them to Literals with datatype "date" for task 1 & 2
<syntaxhighlight>
update_str = """
    PREFIX ns1: <http://example.org#>


from SPARQLWrapper import SPARQLWrapper, JSON
    DELETE {
        ?s ns1:cp_date ?cp;
            ns1:investigation_end ?end;
            ns1:investigation_start ?start.
    }
    INSERT{
        ?s ns1:cp_date ?cpDate;
            ns1:investigation_end ?endDate;
            ns1:investigation_start ?startDate.
    }
    WHERE{
        ?s ns1:cp_date ?cp . #Date conviction was recieved
        BIND (replace(str(?cp), str(ns1:), "")  AS ?cpRemoved)
        BIND (STRDT(STR(?cpRemoved), xsd:date) AS ?cpDate)
       
        ?s ns1:investigation_end ?end . #Investigation End
        BIND (replace(str(?end), str(ns1:), "")  AS ?endRemoved)
        BIND (STRDT(STR(?endRemoved), xsd:date) AS ?endDate)
       
        ?s ns1:investigation_start ?start . #Investigation Start
        BIND (replace(str(?start), str(ns1:), "")  AS ?startRemoved)
        BIND (STRDT(STR(?startRemoved), xsd:date) AS ?startDate)
}"""


# This creates a server connection to the same URL that contains the graphic interface for Blazegraph.  
sparql.setQuery(update_str)
# You also need to add "sparql" to end of the URL like below.
sparql.setMethod(POST)
 
sparql.query()
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/sparql")
 
# SELECT all triples in the database.


# Ask whether there was an ongoing indictment on the date 1990-01-01.
sparql.setQuery("""
sparql.setQuery("""
     SELECT DISTINCT ?p WHERE {
     PREFIX ns1: <http://example.org#>
    ?s ?p ?o.
    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)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()
print(f"Are there any investigation on the 1990-01-01: {results['boolean']}")


for result in results["results"]["bindings"]:
# List ongoing indictments on that date 1990-01-01.
    print(result["p"]["value"])
 
# SELECT all interests of Cade
 
sparql.setQuery("""
sparql.setQuery("""
     PREFIX ex: <http://example.org/>
     PREFIX ns1: <http://example.org#>
     SELECT DISTINCT ?interest WHERE {
     SELECT ?s
    ex:Cade ex:interest ?interest.
    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)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()


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


===Updating data from Blazegraph via Python===
# Describe investigation number 100 (muellerkg:investigation_100).
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, POST, DIGEST
 
namespace = "kb"
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql")
 
sparql.setMethod(POST)
sparql.setQuery("""
sparql.setQuery("""
     PREFIX ex: <http://example.org/>
     PREFIX ns1: <http://example.org#>
     INSERT DATA{
     DESCRIBE ns1:investigation_100
    ex:Cade ex:interest ex:Mathematics.
    }
""")
""")


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


print(results.serialize())


</syntaxhighlight>
# Print out a list of all the types used in your graph.
===Retrieving data from Wikidata with SparqlWrapper===
sparql.setQuery("""
<syntaxhighlight>
    PREFIX ns1: <http://example.org#>
from SPARQLWrapper import SPARQLWrapper, JSON
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
     SELECT DISTINCT ?types
# In the query I want to select all the Vitamins in wikidata.
    WHERE{
 
        ?s rdf:type ?types .  
sparql.setQuery("""
    }
     SELECT ?nutrient ?nutrientLabel WHERE
{
  ?nutrient wdt:P279 wd:Q34956.
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
}
""")
""")


sparql.setReturnFormat(JSON)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()
rdf_Types = []


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


print(rdf_Types)


More examples can be found in the example section on the official query service here: https://query.wikidata.org/.
# 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#>


===Download from BlazeGraph===
    INSERT{
        ?invest rdf:type ns1:Investigation .
    }
    WHERE{
        ?s ns1:investigation ?invest .
}"""


<syntaxhighlight>
sparql.setQuery(update_str)
"""
sparql.setMethod(POST)
Dumps a database to a local RDF file.
sparql.query()
You need to install the SPARQLWrapper package first...
"""


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


# your namespace, the default is 'kb'
    ASK{
ns = 'kb'
        ns1:watergate rdf:type ns1:Investigation.
    }
""")


# the SPARQL endpoint
sparql.setReturnFormat(JSON)
endpoint = 'http://info216.i2s.uib.no/bigdata/namespace/' + ns + '/sparql'
results = sparql.query().convert()
print(results['boolean'])


# - the endpoint just moved, the old one was:
# Update the graph to that every resource that is an object in a muellerkg:person triple has the rdf:type muellerkg:IndictedPerson.
# endpoint = 'http://i2s.uib.no:8888/bigdata/namespace/' + ns + '/sparql'
update_str = """
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


# create wrapper
    INSERT{
wrapper = SPARQLWrapper(endpoint)
        ?person rdf:type ns1:IndictedPerson .
    }
    WHERE{
        ?s ns1:person ?person .
}"""


# prepare the SPARQL update
sparql.setQuery(update_str)
wrapper.setQuery('CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }')
sparql.setMethod(POST)
wrapper.setReturnFormat(RDFXML)
sparql.query()


# execute the SPARQL update and convert the result to an rdflib.Graph
#To test, run the query in the above task, replacing the ask query with e.g. ns1:Deborah_Gore_Dean rdf:type ns1:IndictedPerson
graph = wrapper.query().convert()


# the destination file, with code to make it timestamped
# 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.
destfile = 'rdf_dumps/slr-kg4news-' + datetime.datetime.now().strftime('%Y%m%d-%H%M') + '.rdf'
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/>


# serialize the result to file
    INSERT{
graph.serialize(destination=destfile, format='ttl')
        ?invest dc:title ?investString.
    }
    WHERE{
        ?s ns1:investigation ?invest .
        BIND (replace(str(?invest), str(ns1:), "") AS ?investString)
}"""


# report and quit
sparql.setQuery(update_str)
print('Wrote %u triples to file %s .' %
sparql.setMethod(POST)
      (len(res), destfile))
sparql.query()
</syntaxhighlight>


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


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


sparql = SPARQLWrapper("http://dbpedia.org/sparql")
     SELECT ?name
 
     WHERE{
sparql.setQuery("""
     ?s  ns1:person ?name;
    PREFIX dbr: <http://dbpedia.org/resource/>
        ns1:outcome ns1:indictment.
    PREFIX dbo: <http://dbpedia.org/ontology/>
    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
     SELECT ?comment
     WHERE {
     dbr:Barack_Obama rdfs:comment ?comment.
    FILTER (langMatches(lang(?comment),"en"))
     }
     }
    ORDER BY ?name
""")
""")


sparql.setReturnFormat(JSON)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()
names = []


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


==Lifting CSV to RDF==
print(names)


<syntaxhighlight>
# Print out the minimum, average and maximum indictment days for all the indictments in the graph.
from rdflib import Graph, Literal, Namespace, URIRef
sparql.setQuery("""
from rdflib.namespace import RDF, FOAF, RDFS, OWL
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
import pandas as pd
    PREFIX ns1: <http://example.org#>


g = Graph()
    SELECT (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min) WHERE{
ex = Namespace("http://example.org/")
        ?s  ns1:indictment_days ?days;
g.bind("ex", ex)
            ns1:outcome ns1:indictment.
   
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
    BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
}
""")


# Load the CSV data as a pandas Dataframe.
sparql.setReturnFormat(JSON)
csv_data = pd.read_csv("task1.csv")
results = sparql.query().convert()


# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
for result in results["results"]["bindings"]:
csv_data = csv_data.replace(to_replace=" ", value="_", regex=True)
    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"]}')


# Here I mark all missing/empty data as "unknown". This makes it easy to delete triples containing this later.
# Print out the minimum, average and maximum indictment days for all the indictments in the graph per investigation.
csv_data = csv_data.fillna("unknown")
sparql.setQuery("""
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    PREFIX ns1: <http://example.org#>


# Loop through the CSV data, and then make RDF triples.
    SELECT ?investigation (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
for index, row in csv_data.iterrows():
     ?s  ns1:indictment_days ?days;
     # The names of the people act as subjects.
        ns1:outcome ns1:indictment;
    subject = row['Name']
        ns1:investigation ?investigation.
    # Create triples: e.g. "Cade_Tracey - age - 27"
      
     g.add((URIRef(ex + subject), URIRef(ex + "age"), Literal(row["Age"])))
    BIND (replace(str(?days), str(ns1:), "") AS ?daysR)
     g.add((URIRef(ex + subject), URIRef(ex + "married"), URIRef(ex + row["Spouse"])))
     BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
     g.add((URIRef(ex + subject), URIRef(ex + "country"), URIRef(ex + row["Country"])))
     }
    GROUP BY ?investigation
""")


    # If We want can add additional RDF/RDFS/OWL information e.g
sparql.setReturnFormat(JSON)
    g.add((URIRef(ex + subject), RDF.type, FOAF.Person))
results = sparql.query().convert()


# I remove triples that I marked as unknown earlier.
for result in results["results"]["bindings"]:
g.remove((None, None, URIRef("http://example.org/unknown")))
    print(f'{result["investigation"]["value"]} - min: {result["min"]["value"]}, max: {result["max"]["value"]}, avg: {result["avg"]["value"]}')


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


===CSV file for above example===
==CSV To RDF (Lab 5)==
 
<syntaxhighlight>
<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>


#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


=Coding Tasks Lab 6=
SERVER = "https://api.dbpedia-spotlight.org/en/annotate"
<syntaxhighlight>
# 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
import pandas as pd
CONFIDENCE = 0.83
 
 
from rdflib import Graph, Namespace, URIRef, Literal, BNode
from rdflib.namespace import RDF, XSD


def annotate_entity(entity, filters={'types': 'DBpedia:Person'}):
annotations = []
try:
annotations = annotate(address=SERVER, text=entity, confidence=CONFIDENCE, filters=filters)
except SpotlightException as e:
print(e)
return annotations


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


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


# Removing unwanted characters
#Function that prepares the values to be added to the graph as a URI or Literal
df = pd.read_csv('russia-investigation.csv')
def prepareValue(row):
# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
if row == None: #none type
df = df.replace(to_replace=" ", value="_", regex=True)
value = Literal(row)
# This may seem odd, but in the data set we have a name like this:("Scooter"). So we have to remove quotation marks
elif isinstance(row, str) and re.match(r'\d{4}-\d{2}-\d{2}', row): #date
df = df.replace(to_replace=f'"', value="", regex=True)
value = Literal(row, datatype=XSD.date)
# # Here I mark all missing/empty data as "unknown". This makes it easy to delete triples containing this later.
elif isinstance(row, bool): #boolean value (true / false)
df = df.fillna("unknown")
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)


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


#Spotlight Search
name = annotate_entity(str(row['name']))
                # Removing the period as some presidents won't be found with it
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))


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


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


===RDFS-plus (OWL) Properties===
csv_to_rdf(df)
<syntaxhighlight>
print(g.serialize())
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>
</syntaxhighlight>


<!--
==SHACL (Lab 6)==
==Lifting XML to RDF==
<syntaxhighlight>
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF, XSD, RDFS
import xml.etree.ElementTree as ET


g = Graph()
from pyshacl import validate
ex = Namespace("http://example.org/TV/")
from rdflib import Graph
prov = Namespace("http://www.w3.org/ns/prov#")
g.bind("ex", ex)
g.bind("prov", prov)


tree = ET.parse("tv_shows.xml")
data_graph = Graph()
root = tree.getroot()
# parses the Turtle examples from the lab
data_graph.parse("data_graph.ttl")


for tv_show in root.findall('tv_show'):
# Remember to test you need to change the rules so they conflict with the data graph (or vice versa). For example, change "exactly one name" to have exactly two, and see the output
    show_id = tv_show.attrib["id"]
shape_graph = """
    title = tv_show.find("title").text
@prefix ex: <http://example.org/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix sh: <http://www.w3.org/ns/shacl#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .


     g.add((URIRef(ex + show_id), ex.title, Literal(title, datatype=XSD.string)))
ex:LabTasks_Shape
     g.add((URIRef(ex + show_id), RDF.type, ex.TV_Show))
    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.
    ] .


     for actor in tv_show.findall("actor"):
# --- If you have more time tasks ---
         first_name = actor.find("firstname").text
ex:MoreTime_Shape rdf:type sh:NodeShape;
         last_name = actor.find("lastname").text
    sh:targetClass ex:Indictment;
         full_name = first_name + "_" + last_name
   
          
     # The only allowed values for ex:american are true, false or unknown.
         g.add((URIRef(ex + show_id), ex.stars, URIRef(ex + full_name)))
    sh:property [
         g.add((URIRef(ex + full_name), ex.starsIn, URIRef(title)))
         sh:path ex:american;
         g.add((URIRef(ex + full_name), RDF.type, ex.Actor))
         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;
    ] ;


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


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


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


shacl_graph = Graph()
# parses the contents of a shape_graph made in the tasks
shacl_graph.parse(data=shape_graph)


===RDFS inference with RDFLib===
# uses pySHACL's validate method to apply the shape_graph constraints to the data_graph
You can use the OWL-RL package to add inference capabilities to RDFLib. It can be installed using the pip install command:
results = validate(
<syntaxhighlight>
    data_graph,
pip install owlrl
     shacl_graph=shacl_graph,
</syntaxhighlight>
    inference='both'
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.]
 
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.
<syntaxhighlight>
import rdflib.plugins.sparql.update
import owlrl.RDFSClosure
 
g = rdflib.Graph()
 
ex = rdflib.Namespace('http://example.org#')
g.bind('', ex)
 
g.update("""
PREFIX ex: <http://example.org#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
INSERT DATA {
    ex:Socrates rdf:type ex:Man .
     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.
rdfs.closure()
# Adds the new triples to the graph and empties the RDFS triple-container.
rdfs.flush_stored_triples()
 
# Ask-query to check whether a new triple has been generated from the entailment.
b = g.query("""
PREFIX ex: <http://example.org#>
ASK {
    ex:Socrates rdf:type ex:Mortal .
}
""")
print('Result: ' + bool(b))
</syntaxhighlight>


===Language tagged RDFS labels===
# prints out the validation result
<syntaxhighlight>
boolean_value, results_graph, results_text = results
from rdflib import Graph, Namespace, Literal
from rdflib.namespace import RDFS
 
g = Graph()
ex = Namespace("http://example.org/")
 
g.add((ex.France, RDFS.label, Literal("Frankrike", lang="no")))
g.add((ex.France, RDFS.label, Literal("France", lang="en")))
g.add((ex.France, RDFS.label, Literal("Francia", lang="es")))


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


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


==OWL==
SELECT DISTINCT ?message WHERE {
===Basic inference with RDFLib===
    [] sh:result ?errorBlankNode.
    ?errorBlankNode sh:resultMessage ?message.   


You can use the OWL-RL package again as for Lecture 5.
    # Alternativ and cleaner solution, look at https://www.w3.org/TR/sparql11-query/#pp-language (9.1 Property Path Syntax)
 
     # [] sh:result / sh:resultMessage ?message .
Instead of:
<syntaxhighlight>
# The next three lines add inferred triples to g.
rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
rdfs.closure()
rdfs.flush_stored_triples()
</syntaxhighlight>
you can write this to get both RDFS and basic RDFS Plus / OWL inference:
<syntaxhighlight>
# The next three lines add inferred triples to g.
owl = owlrl.CombinedClosure.RDFS_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 {
     ex:Socrates ex:hasWife ex:Xanthippe .
    ex:hasHusband owl:inverseOf ex:hasWife .
}
}
</syntaxhighlight>
"""
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
ASK {
count_messages = """
  ex:Xanthippe ex:hasHusband ex:Socrates .
PREFIX sh: <http://www.w3.org/ns/shacl#>  
}
</syntaxhighlight>


<syntaxhighlight>
SELECT ?message (COUNT(?node) AS ?num_messages) WHERE {
ASK {
    [] sh:result ?errorBlankNode .
  ex:Socrates ^ex:hasHusband ex:Xanthippe .
     ?errorBlankNode sh:resultMessage ?message ;
}
                    sh:focusNode ?node .
</syntaxhighlight>
 
<syntaxhighlight>
INSERT DATA {
     ex:hasWife rdfs:subPropertyOf ex:hasSpouse .
    ex:hasSpouse rdf:type owl:SymmetricProperty .  
}
}
</syntaxhighlight>
GROUP BY ?message
ORDER BY DESC(?count) ?message
"""


<syntaxhighlight>
messages = results_graph.query(count_messages)
ASK {
for row in messages:
  ex:Socrates ex:hasSpouse ex:Xanthippe .
    print(f"COUNT: {row.num_messages} | MESSAGE: {row.message}")
}
</syntaxhighlight>


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


 
==RDFS (Lab 7)==
 
 
 
 
===XML Data for above example===
<syntaxhighlight>
<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==
import owlrl
<syntaxhighlight>
from rdflib import Graph, RDF, Namespace, FOAF, RDFS
from bs4 import BeautifulSoup as bs, NavigableString
from rdflib import Graph, URIRef, Namespace
from rdflib.namespace import RDF


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)


html = open("tv_shows.html").read()
NS = {
html = bs(html, features="html.parser")
     'ex': ex,
 
     'rdf': RDF,
shows = html.find_all('li', attrs={'class': 'show'})
     'rdfs': RDFS,
for show in shows:
     'foaf': FOAF,
    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))
 
 
print(g.serialize(format="turtle").decode())
</syntaxhighlight>
 
===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==
<syntaxhighlight>
import requests
import json
import pprint
 
# Retrieve JSON data from API service URL. Then load it with the json library as a json object.
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>
 
 
==JSON-LD==
 
<syntaxhighlight>
import rdflib
 
g = rdflib.Graph()
 
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
#Write a small function that computes the RDFS closure on your graph.
g.parse(data=example, format='json-ld')
def flush():
    owlrl.DeductiveClosure(owlrl.RDFS_Semantics).expand(g)


# serialisation does expansion by default
#Rick Gates was charged with money laundering and tax evasion.
for line in g.serialize(format='json-ld').decode().splitlines():
g.add((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
    print(line)
g.add((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))


# by supplying a context object, serialisation can do compaction
#When one thing that is charged with another thing,
context = {
g.add((ex.chargedWith, RDFS.domain, ex.PersonUnderInvestigation))  #the first thing is a person under investigation and
    "foaf": "http://xmlns.com/foaf/0.1/"
g.add((ex.chargedWith, RDFS.range, ex.Offense)) #the second thing is an offense.
}
for line in g.serialize(format='json-ld', context=context).decode().splitlines():
    print(line)
</syntaxhighlight>


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


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


==OWL - Complex Classes and Restrictions==
#Paul Manafort was convicted for tax evasion.
<syntaxhighlight>
g.add((ex.Paul_Manafort, ex.convictedFor, ex.TaxEvasion))
import owlrl
#the first thing is also charged with the second thing
from rdflib import Graph, Literal, Namespace, BNode
g.add((ex.convictedFor, RDFS.subPropertyOf, ex.chargedWith))  
from rdflib.namespace import RDF, OWL, RDFS
print('Is Paul Manafort charged with Tax Evasion:', g.query('ASK {ex:Paul_Manafort ex:chargedWith ex:TaxEvasion}', initNs=NS).askAnswer)
from rdflib.collection import Collection
flush()
 
print('Is Paul Manafort charged with Tax Evasion:', g.query('ASK {ex:Paul_Manafort ex:chargedWith ex:TaxEvasion}', initNs=NS).askAnswer)
g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)
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
b = BNode()
Collection(g, b, [ex.Father, ex.Mother])
g.add((ex.Parent, OWL.unionOf, b))
 
# A Woman is a person who has the "female" gender
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()
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.
br = BNode()
g.add((br, RDF.type, OWL.Restriction))
g.add((br, OWL.onProperty, ex.eats))
g.add((br, OWL.QualifiedCardinality, Literal(0)))
g.add((br, OWL.onClass, ex.Meat))
bi = BNode()
Collection(g, bi, [ex.Person, br])
g.add((ex.Vegetarian, OWL.intersectionOf, bi))
 
# A Worried Parent is a parent who has at least one sick child
br = BNode()
g.add((br, RDF.type, OWL.Restriction))
g.add((br, OWL.onProperty, ex.hasChild))
g.add((br, OWL.QualifiedMinCardinality, Literal(1)))
g.add((br, OWL.onClass, ex.Sick))
bi = BNode()
Collection(g, bi, [ex.Parent, br])
g.add((ex.WorriedParent, OWL.intersectionOf, bi))


# using the restriction above, If we now write...:
print(g.serialize())
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==
[[:File:DL-reasoning-RoyalFamily-final.owl.txt | Example file]] from Lecture 13 about OWL-DL, rules and reasoning.
-->

Revision as of 14:00, 21 March 2023

This page will be updated with Python examples related to the labs as the course progresses.

Examples from the lectures

Lecture 1: Introduction to KGs

Turtle example:

@prefix ex: <http://example.org/> .
ex:Roger_Stone
    ex:name "Roger Stone" ;
    ex:occupation ex:lobbyist ;
    ex:significant_person ex:Donald_Trump .
ex:Donald_Trump
    ex:name "Donald Trump" .

Lecture 2: RDF

Blank nodes for anonymity, or when we have not decided on a URI:

from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD

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

g = Graph()
g.bind('ex', EX)  # this is why the line '@prefix ex: <http://example.org/> .'
                  # and the 'ex.' prefix are used when we print out Turtle later

robertMueller = BNode()
g.add((robertMueller, RDF.type, EX.Human))
g.add((robertMueller, FOAF.name, Literal('Robert Mueller', lang='en')))
g.add((robertMueller, EX.position_held, Literal('Director of the Federal Bureau of Investigation', lang='en')))

print(g.serialize(format='turtle'))

Blank nodes used to group related properties:

from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD

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

g = Graph()
g.bind('ex', EX)

# This is a task in Exercise 2

print(g.serialize(format='turtle'))

Literals:

from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD

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

g = Graph()
g.bind('ex', EX)

g.add((EX.Robert_Mueller, RDF.type, EX.Human))
g.add((EX.Robert_Mueller, FOAF.name, Literal('Robert Mueller', lang='en')))
g.add((EX.Robert_Mueller, FOAF.name, Literal('رابرت مولر', lang='fa')))
g.add((EX.Robert_Mueller, DC.description, Literal('sixth director of the FBI', datatype=XSD.string)))
g.add((EX.Robert_Mueller, EX.start_time, Literal(2001, datatype=XSD.integer)))

print(g.serialize(format='turtle'))

Alternative container (open):

from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD

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

g = Graph()
g.bind('ex', EX)

muellerReportArchives = BNode()
g.add((muellerReportArchives, RDF.type, RDF.Alt))

archive1 = 'https://archive.org/details/MuellerReportVolume1Searchable/' \
                    'Mueller%20Report%20Volume%201%20Searchable/'
archive2 = 'https://edition.cnn.com/2019/04/18/politics/full-mueller-report-pdf/index.html'
archive3 = 'https://www.politico.com/story/2019/04/18/mueller-report-pdf-download-text-file-1280891'

g.add((muellerReportArchives, RDFS.member, Literal(archive1, datatype=XSD.anyURI)))
g.add((muellerReportArchives, RDFS.member, Literal(archive2, datatype=XSD.anyURI)))
g.add((muellerReportArchives, RDFS.member, Literal(archive3, datatype=XSD.anyURI)))

g.add((EX.Mueller_Report, RDF.type, FOAF.Document))
g.add((EX.Mueller_Report, DC.contributor, EX.Robert_Mueller))
g.add((EX.Mueller_Report, SCHEMA.archivedAt, muellerReportArchives))

print(g.serialize(format='turtle'))

Sequence container (open):

from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD

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

g = Graph()
g.bind('ex', EX)

donaldTrumpSpouses = BNode()
g.add((donaldTrumpSpouses, RDF.type, RDF.Seq))
g.add((donaldTrumpSpouses, RDF._1, EX.IvanaTrump))
g.add((donaldTrumpSpouses, RDF._2, EX.MarlaMaples))
g.add((donaldTrumpSpouses, RDF._3, EX.MelaniaTrump))

g.add((EX.Donald_Trump, SCHEMA.spouse, donaldTrumpSpouses))

print(g.serialize(format='turtle'))

Collection (closed list):

from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD

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

g = Graph()
g.bind('ex', EX)

from rdflib.collection import Collection

g = Graph()
g.bind('ex', EX)

donaldTrumpSpouses = BNode()
Collection(g, donaldTrumpSpouses, [
    EX.IvanaTrump, EX.MarlaMaples, EX.MelaniaTrump
])
g.add((EX.Donald_Trump, SCHEMA.spouse, donaldTrumpSpouses))

print(g.serialize(format='turtle'))
g.serialize(destination='s02_Donald_Trump_spouses_list.ttl', format='turtle')

print(g.serialize(format='turtle'))

Example lab solutions

Getting started (Lab 1)

from rdflib import Graph, Namespace

g = Graph()

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

g.bind("ex", ex)

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

#It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, and Roger Stone.
g.add((ex.Mueller_Investigation, ex.involved, ex.Paul_Manafort))
g.add((ex.Mueller_Investigation, ex.involved, ex.Rick_Gates))
g.add((ex.Mueller_Investigation, ex.involved, ex.George_Papadopoulos))
g.add((ex.Mueller_Investigation, ex.involved, ex.Michael_Flynn))
g.add((ex.Mueller_Investigation, ex.involved, ex.Michael_Cohen))
g.add((ex.Mueller_Investigation, ex.involved, ex.Roger_Stone))

# --- Paul Manafort ---
#Paul Manafort was business partner of Rick Gates.
g.add((ex.Paul_Manafort, ex.businessManager, ex.Rick_Gates))
# He was campaign chairman for Trump
g.add((ex.Paul_Manafort, ex.campaignChairman, ex.Donald_Trump))

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

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

# He pleaded guilty to conspiracy.
g.add((ex.Paul_Manafort, ex.pleadGuiltyTo, ex.Conspiracy))
# He was sentenced to prison.
g.add((ex.Paul_Manafort, ex.sentencedTo, ex.Prison))
# He negotiated a plea agreement.
g.add((ex.Paul_Manafort, ex.negoiated, ex.PleaBargain))

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

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

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

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

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

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

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

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

RDF programming with RDFlib (Lab 2)

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

g = Graph()
g.parse("lab1.ttl", format="ttl") #Retrives the triples from lab 1

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

# --- Michael Cohen ---
#Michael Cohen was Donald Trump's attorney.
g.add((ex.Michael_Cohen, ex.attorneyTo, ex.Donald_Trump))
#He pleaded guilty to lying to the FBI.
g.add((ex.Michael_Cohen, ex.pleadGuiltyTo, ex.LyingToCongress))

# --- Michael Flynn ---
#Michael Flynn was adviser to Trump.
g.add((ex.Michael_Flynn, ex.adviserTo, ex.Donald_Trump))
#He pleaded guilty to lying to the FBI.
g.add((ex.Michael_Flynn, ex.pleadGuiltyTo, ex.LyingToFBI))
# He negotiated a plea agreement.
g.add((ex.Michael_Flynn, ex.negoiated, ex.PleaBargain)) 

#How can you modify your knowledge graph to account for the different lying?
#Remove these to not have duplicates
g.remove((ex.Michael_Flynn, ex.pleadGuiltyTo, ex.LyingToFBI)) 
g.remove((ex.Michael_Flynn, ex.negoiated, ex.PleaBargain))
g.remove((ex.Rick_Gates, ex.pleadGuiltyTo, ex.LyingToFBI))
g.remove((ex.Rick_Gates, ex.pleadGuiltyTo, ex.Conspiracy))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.ForeignLobbying))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
g.remove((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
g.remove((ex.Michael_Cohen, ex.pleadGuiltyTo, ex.LyingToCongress))

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

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

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

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

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

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

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

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

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

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

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

SPARQL Programming (Lab 4)

NOTE: These tasks were performed on the old dataset, with the new dataset, some of these answers would be different.

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

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

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

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

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

print(list(task1))

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

print(list(task2))

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

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

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

print(task3_dic)

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

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

print(task4.askAnswer)

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

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

print(task4.askAnswer)

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

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

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

# print(task5.serialize())

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

namespace = "kb" #Default namespace
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql") #Replace localhost:9999 with your URL

# The current dates are URIs, we would want to change them to Literals with datatype "date" for task 1 & 2
update_str = """
    PREFIX ns1: <http://example.org#>

    DELETE {
        ?s ns1:cp_date ?cp;
            ns1:investigation_end ?end;
            ns1:investigation_start ?start.
    }
    INSERT{
        ?s ns1:cp_date ?cpDate;
            ns1:investigation_end ?endDate;
            ns1:investigation_start ?startDate.
    }
    WHERE{
        ?s ns1:cp_date ?cp . #Date conviction was recieved
        BIND (replace(str(?cp), str(ns1:), "")  AS ?cpRemoved)
        BIND (STRDT(STR(?cpRemoved), xsd:date) AS ?cpDate)
        
        ?s ns1:investigation_end ?end . #Investigation End
        BIND (replace(str(?end), str(ns1:), "")  AS ?endRemoved)
        BIND (STRDT(STR(?endRemoved), xsd:date) AS ?endDate)
        
        ?s ns1:investigation_start ?start . #Investigation Start
        BIND (replace(str(?start), str(ns1:), "")  AS ?startRemoved)
        BIND (STRDT(STR(?startRemoved), xsd:date) AS ?startDate)
}"""

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

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

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

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

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

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

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

print(results.serialize())

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

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

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

rdf_Types = []

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

print(rdf_Types)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

names = []

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

print(names)

# Print out the minimum, average and maximum indictment days for all the indictments in the graph.
sparql.setQuery("""
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    PREFIX ns1: <http://example.org#>

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

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

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

# Print out the minimum, average and maximum indictment days for all the indictments in the graph per investigation.
sparql.setQuery("""
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    PREFIX ns1: <http://example.org#>

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

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

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

CSV To RDF (Lab 5)

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

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

def annotate_entity(entity, filters={'types': 'DBpedia:Person'}):
	annotations = []
	try:
		annotations = annotate(address=SERVER, text=entity, confidence=CONFIDENCE, filters=filters)
	except SpotlightException as e:
		print(e)
	return annotations

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

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

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

	return value

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

		#Spotlight Search
		name = annotate_entity(str(row['name']))
                # Removing the period as some presidents won't be found with it
		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())

SHACL (Lab 6)

from pyshacl import validate
from rdflib import Graph

data_graph = Graph()
# parses the Turtle examples from the lab
data_graph.parse("data_graph.ttl")

# Remember to test you need to change the rules so they conflict with the data graph (or vice versa). For example, change "exactly one name" to have exactly two, and see the output 
shape_graph = """
@prefix ex: <http://example.org/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix sh: <http://www.w3.org/ns/shacl#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .

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

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

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

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

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

shacl_graph = Graph()
# parses the contents of a shape_graph made in the tasks
shacl_graph.parse(data=shape_graph)

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

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

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

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

SELECT DISTINCT ?message WHERE {
    [] sh:result ?errorBlankNode.
    ?errorBlankNode sh:resultMessage ?message.    

    # Alternativ and cleaner solution, look at https://www.w3.org/TR/sparql11-query/#pp-language (9.1 Property Path Syntax)
    # [] sh:result / sh:resultMessage ?message .
}
"""
messages = results_graph.query(distinct_messages)
for row in messages:
    print(row.message)

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

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

messages = results_graph.query(count_messages)
for row in messages:
    print(f"COUNT: {row.num_messages} | MESSAGE: {row.message}")

RDFS (Lab 7)

import owlrl
from rdflib import Graph, RDF, Namespace, FOAF, RDFS

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

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

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

#Write a small function that computes the RDFS closure on your graph.
def flush():
    owlrl.DeductiveClosure(owlrl.RDFS_Semantics).expand(g)

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

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

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

#A person under investigation is a FOAF person
g.add((ex.PersonUnderInvestigation, RDFS.subClassOf, FOAF.Person))
print('Is Rick Gates a foaf:Person:', g.query('ASK {ex:Rick_Gates rdf:type foaf:Person}', initNs=NS).askAnswer)
flush()
print('Is Rick Gates a foaf:Person:', 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)) 
print('Is Paul Manafort charged with Tax Evasion:', g.query('ASK {ex:Paul_Manafort ex:chargedWith ex:TaxEvasion}', initNs=NS).askAnswer)
flush()
print('Is Paul Manafort charged with Tax Evasion:', g.query('ASK {ex:Paul_Manafort ex:chargedWith ex:TaxEvasion}', initNs=NS).askAnswer)

print(g.serialize())