Lab Solutions: Difference between revisions

From info216
No edit summary
No edit summary
 
(51 intermediate revisions by 4 users not shown)
Line 1: Line 1:
This page will be updated with Python examples related to the labs as the course progresses.
Here we will present suggested solutions after each lab. ''The page will be updated as the course progresses''
=[[/info216.wiki.uib.no/Lab: Getting started with VSCode, Python and RDFlib|1 Lab: Getting started with VSCode, Python and RDFlib]] =
<syntaxhighlight>
 
from rdflib import Graph, Namespace
 
ex = Namespace('http://example.org/')
 
g = Graph()


=Examples from the lectures=
g.bind("ex", ex)


==Lecture 1: Introduction to KGs==
# The Mueller Investigation was lead by Robert Mueller
Turtle example:
g.add((ex.MuellerInvestigation, ex.leadBy, ex.RobertMueller))
<syntaxhighlight>
 
@prefix ex: <http://example.org/> .
# It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, Michael Cohen, and Roger Stone.
ex:Roger_Stone
g.add((ex.MuellerInvestigation, ex.involved, ex.PaulManafort))
    ex:name "Roger Stone" ;
g.add((ex.MuellerInvestigation, ex.involved, ex.RickGates))
    ex:occupation ex:lobbyist ;
g.add((ex.MuellerInvestigation, ex.involved, ex.GeorgePapadopoulos))
    ex:significant_person ex:Donald_Trump .
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelFlynn))
ex:Donald_Trump
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelCohen))
    ex:name "Donald Trump" .
g.add((ex.MuellerInvestigation, ex.involved, ex.RogerStone))
</syntaxhighlight>
 
# Paul Manafort was business partner of Rick Gates
g.add((ex.PaulManafort, ex.businessPartner, ex.RickGates))
 
# He was campaign chairman for Donald Trump
g.add((ex.PaulManafort, ex.campaignChairman, ex.DonaldTrump))
 
# He was charged with money laundering, tax evasion, and foreign lobbying.
g.add((ex.PaulManafort, ex.chargedWith, ex.MoneyLaundering))
g.add((ex.PaulManafort, ex.chargedWith, ex.TaxEvasion))
g.add((ex.PaulManafort, ex.chargedWith, ex.ForeignLobbying))
 
# He was convicted for bank and tax fraud.
g.add((ex.PaulManafort, ex.convictedOf, ex.BankFraud))
g.add((ex.PaulManafort, ex.convictedOf, ex.TaxFraud))
 
# He pleaded guilty to conspiracy.
g.add((ex.PaulManafort, ex.pleadGuiltyTo, ex.Conspiracy))
 
# He was sentenced to prison.
g.add((ex.PaulManafort, ex.sentencedTo, ex.Prison))
 
# He negotiated a plea agreement.
g.add((ex.PaulManafort, ex.negotiated, ex.PleaAgreement))
 
# Rick Gates was charged with money laundering, tax evasion and foreign lobbying.
g.add((ex.RickGates, ex.chargedWith, ex.MoneyLaundering))
g.add((ex.RickGates, ex.chargedWith, ex.TaxEvasion))
g.add((ex.RickGates, ex.chargedWith, ex.ForeignLobbying))
 
# He pleaded guilty to conspiracy and lying to FBI.
g.add((ex.RickGates, ex.pleadGuiltyTo, ex.Conspiracy))
g.add((ex.RickGates, ex.pleadGuiltyTo, ex.LyingToFBI))
 
# Use the serialize method of rdflib.Graph to write out the model in different formats (on screen or to file)
print(g.serialize(format="ttl")) # To screen
#g.serialize("lab1.ttl", format="ttl") # To file
 
# Loop through the triples in the model to print out all triples that have pleading guilty as predicate
for subject, object in g[ : ex.pleadGuiltyTo :]:
    print(subject, ex.pleadGuiltyTo, object)


==Lecture 2: RDF==
# --- IF you have more time tasks ---
Blank nodes for anonymity, or when we have not decided on a URI:
<syntaxhighlight lang="Python">
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD


EX = Namespace('http://example.org/')
# Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week


g = Graph()
#Write a method (function) that submits your model for rendering and saves the returned image to file.
g.bind('ex', EX)  # this is why the line '@prefix ex: <http://example.org/> .'
import requests
                  # and the 'ex.' prefix are used when we print out Turtle later
import shutil
 
def graphToImage(graphInput):
    data = {"rdf":graphInput, "from":"ttl", "to":"png"}
    link = "http://www.ldf.fi/service/rdf-grapher"
    response = requests.get(link, params = data, stream=True)
    # print(response.content)
    print(response.raw)
    with open("lab1.png", "wb") as file:
        shutil.copyfileobj(response.raw, file)


robertMueller = BNode()
graph = g.serialize(format="ttl")
g.add((robertMueller, RDF.type, EX.Human))
graphToImage(graph)
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'))
</syntaxhighlight>
</syntaxhighlight>


Blank nodes used to group related properties:
=2 [[/info216.wiki.uib.no/Lab: SPARQL|Lab: SPARQL queries]] =
<syntaxhighlight>
<syntaxhighlight>
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD
List all triples in your graph.
 
select * where {
?s ?p ?o .
}
 
List the first 100 triples in your graph.
 
select * where {
?s ?p ?o .
} limit 100
 
Count the number of triples in your graph.
 
select (count(?s)as ?tripleCount) where {
?s ?p ?o .
}
 
Count the number of indictments in your graph.
 
PREFIX muellerkg: <http://example.org#>
select (Count(?s)as ?numIndictment) where {
?s ?p muellerkg:Indictment .
}
 
List everyone who pleaded guilty, along with the name of the investigation.
 
PREFIX m: <http://example.org#>
select ?name ?s where {
?s ?p m:guilty-plea;
    m:name ?name.
} 
 
List everyone who were convicted, but who had their conviction overturned by which president.
 
PREFIX muellerkg: <http://example.org#>
#List everyone who were convicted, but who had their conviction overturned by which president.
 
select ?name ?president  where {
?s ?p muellerkg:conviction;
muellerkg:name ?name;
    muellerkg:overturned true;
    muellerkg:president ?president. 
} limit 100


EX = Namespace('http://example.org/')
For each investigation, list the number of indictments made.


g = Graph()
PREFIX muellerkg: <http://example.org#>
g.bind('ex', EX)
select ?investigation (count(?investigation) as ?numIndictments) where {
?s muellerkg:investigation ?investigation .
} group by (?investigation)


# This is a task in Exercise 2
For each investigation with multiple indictments, list the number of indictments made.


print(g.serialize(format='turtle'))
PREFIX muellerkg: <http://example.org#>
</syntaxhighlight>
select ?investigation (count(?investigation) as ?numIndictments) where {
?s muellerkg:investigation ?investigation.
} group by (?investigation)
having (?numIndictments > 1)


Literals:
For each investigation with multiple indictments, list the number of indictments made, sorted with the most indictments first.
<syntaxhighlight>
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD


EX = Namespace('http://example.org/')
PREFIX muellerkg: <http://example.org#>
select ?investigation (count(?investigation) as ?numIndictments) where {
?s muellerkg:investigation ?investigation.
} group by (?investigation)
having (?numIndictments > 1)
order by desc(?numIndictments)


g = Graph()
For each president, list the numbers of convictions and of pardons made after conviction.
g.bind('ex', EX)


g.add((EX.Robert_Mueller, RDF.type, EX.Human))
PREFIX muellerkg: <http://example.org#>
g.add((EX.Robert_Mueller, FOAF.name, Literal('Robert Mueller', lang='en')))
SELECT ?president (COUNT(?conviction) AS ?numConvictions) (COUNT(?pardon) AS ?numPardoned)  
g.add((EX.Robert_Mueller, FOAF.name, Literal('رابرت مولر', lang='fa')))
WHERE {
g.add((EX.Robert_Mueller, DC.description, Literal('sixth director of the FBI', datatype=XSD.string)))
    ?indictment muellerkg:president ?president ;
g.add((EX.Robert_Mueller, EX.start_time, Literal(2001, datatype=XSD.integer)))
                muellerkg:outcome muellerkg:conviction .
    BIND(?indictment AS ?conviction)
    OPTIONAL {
        ?indictment muellerkg:pardoned true .
        BIND(?indictment AS ?pardon)
    }
}
GROUP BY ?president


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


Alternative container (open):
== 3 [[/info216.wiki.uib.no/Lab: SPARQL Programming|Lab: SPARQL programming]] ==
<syntaxhighlight>
<syntaxhighlight>
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD


EX = Namespace('http://example.org/')
from rdflib import Graph, Namespace, RDF, FOAF
from SPARQLWrapper import SPARQLWrapper, JSON, POST, GET, TURTLE


g = Graph()
g = Graph()
g.bind('ex', EX)
g.parse("Russia_investigation_kg.ttl")


muellerReportArchives = BNode()
# ----- RDFLIB -----
g.add((muellerReportArchives, RDF.type, RDF.Alt))
ex = Namespace('http://example.org#')


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


g.add((muellerReportArchives, RDFS.member, Literal(archive1, datatype=XSD.anyURI)))
# Print out a list of all the predicates used in your graph.
g.add((muellerReportArchives, RDFS.member, Literal(archive2, datatype=XSD.anyURI)))
task1 = g.query("""
g.add((muellerReportArchives, RDFS.member, Literal(archive3, datatype=XSD.anyURI)))
SELECT DISTINCT ?p WHERE{
    ?s ?p ?o .
}
""", initNs=NS)


g.add((EX.Mueller_Report, RDF.type, FOAF.Document))
print(list(task1))
g.add((EX.Mueller_Report, DC.contributor, EX.Robert_Mueller))
g.add((EX.Mueller_Report, SCHEMA.archivedAt, muellerReportArchives))


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


Sequence container (open):
# 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.
<syntaxhighlight>
task3_dic = {}
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD


EX = Namespace('http://example.org/')
task3 = g.query("""
SELECT ?president ?person WHERE{
    ?s :president ?president;
      :name ?person;
      :outcome :indictment.
}
""", initNs=NS)


g = Graph()
for president, person in task3:
g.bind('ex', EX)
    if president not in task3_dic:
        task3_dic[president] = [person]
    else:
        task3_dic[president].append(person)


donaldTrumpSpouses = BNode()
print(task3_dic)
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))
# Use an ASK query to investigate whether Donald Trump has pardoned more than 5 people.


print(g.serialize(format='turtle'))
task4 = g.query("""
</syntaxhighlight>
    ASK{
        SELECT ?count WHERE{{
          SELECT (COUNT(?s) as ?count) WHERE{
            ?s :pardoned :true;
                  :president :Bill_Clinton  .
                }}
        FILTER (?count > 5)
        }
    }
""", initNs=NS)


Collection (closed list):
print(task4.askAnswer)
<syntaxhighlight>
from rdflib import Graph, Namespace, Literal, BNode, RDF, RDFS, DC, FOAF, XSD


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


g = Graph()
# task5 = g.query("""
g.bind('ex', EX)
# DESCRIBE :Donald_Trump
# """, initNs=NS)


from rdflib.collection import Collection
# print(task5.serialize())


g = Graph()
# ----- SPARQLWrapper -----
g.bind('ex', EX)


donaldTrumpSpouses = BNode()
SERVER = 'http://localhost:7200' #Might need to replace this
Collection(g, donaldTrumpSpouses, [
REPOSITORY = 'Labs' #Replace with your repository name
    EX.IvanaTrump, EX.MarlaMaples, EX.MelaniaTrump
])
g.add((EX.Donald_Trump, SCHEMA.spouse, donaldTrumpSpouses))


print(g.serialize(format='turtle'))
# Query Endpoint
g.serialize(destination='s02_Donald_Trump_spouses_list.ttl', format='turtle')
sparql = SPARQLWrapper(f'{SERVER}/repositories/{REPOSITORY}')  
# Update Endpoint
sparqlUpdate = SPARQLWrapper(f'{SERVER}/repositories/{REPOSITORY}/statements')


print(g.serialize(format='turtle'))
# Ask whether there was an ongoing indictment on the date 1990-01-01.
</syntaxhighlight>
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']}")


=Example lab solutions=
# 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)
    }
""")


==Getting started (Lab 1)==
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


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


from rdflib import Graph, Namespace
# Describe investigation number 100 (muellerkg:investigation_100).
sparql.setQuery("""
    PREFIX ns1: <http://example.org#>
    DESCRIBE ns1:investigation_100
""")


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


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


g.bind("ex", ex)
# 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#>


#The Mueller Investigation was lead by Robert Mueller.
    SELECT DISTINCT ?types
g.add((ex.Mueller_Investigation, ex.leadBy, ex.Robert_Muller))
    WHERE{
        ?s rdf:type ?types .  
    }
""")


#It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, and Roger Stone.
sparql.setReturnFormat(JSON)
g.add((ex.Mueller_Investigation, ex.involved, ex.Paul_Manafort))
results = sparql.query().convert()
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 ---
rdf_Types = []
#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.
for result in results["results"]["bindings"]:
g.add((ex.Paul_Manafort, ex.chargedWith, ex.MoneyLaundering))
    rdf_Types.append(result["types"]["value"])
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.
print(rdf_Types)
g.add((ex.Paul_Manafort, ex.convictedFor, ex.BankFraud))
g.add((ex.Paul_Manafort, ex.convictedFor, ex.TaxFraud))


# He pleaded guilty to conspiracy.
# Update the graph to that every resource that is an object in a muellerkg:investigation triple has the rdf:type muellerkg:Investigation.
g.add((ex.Paul_Manafort, ex.pleadGuiltyTo, ex.Conspiracy))
update_str = """
# He was sentenced to prison.
    PREFIX ns1: <http://example.org#>
g.add((ex.Paul_Manafort, ex.sentencedTo, ex.Prison))
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
# He negotiated a plea agreement.
g.add((ex.Paul_Manafort, ex.negoiated, ex.PleaBargain))


# --- Rick Gates ---
    INSERT{
#Rick Gates was charged with money laundering, tax evasion and foreign lobbying.
        ?invest rdf:type ns1:Investigation .
g.add((ex.Rick_Gates, ex.chargedWith, ex.MoneyLaundering))
    }
g.add((ex.Rick_Gates, ex.chargedWith, ex.TaxEvasion))
    WHERE{
g.add((ex.Rick_Gates, ex.chargedWith, ex.ForeignLobbying))
        ?s ns1:investigation ?invest .
}"""


#He pleaded guilty to conspiracy and lying to FBI.
sparqlUpdate.setQuery(update_str)
g.add((ex.Rick_Gates, ex.pleadGuiltyTo, ex.Conspiracy))
sparqlUpdate.setMethod(POST)
g.add((ex.Rick_Gates, ex.pleadGuiltyTo, ex.LyingToFBI))
sparqlUpdate.query()


#Use the serialize method to write out the model in different formats on screen
#To Test
print(g.serialize(format="ttl"))
sparql.setQuery("""
# g.serialize("lab1.ttl", format="ttl") #or to file
    prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX ns1: <http://example.org#>


#Loop through the triples in the model to print out all triples that have pleading guilty as predicate
    ASK{
for subject, object in g[ : ex.pleadGuiltyTo : ]:
        ns1:watergate rdf:type ns1:Investigation.
     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
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
print(results['boolean'])


#Write a method (function) that submits your model for rendering and saves the returned image to file.
# Update the graph to that every resource that is an object in a muellerkg:person triple has the rdf:type muellerkg:IndictedPerson.
import requests
update_str = """
import shutil
    PREFIX ns1: <http://example.org#>
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


def graphToImage(graph):
     INSERT{
     data = {"rdf":graph, "from":"ttl", "to":"png"}
        ?person rdf:type ns1:IndictedPerson .
    link = "http://www.ldf.fi/service/rdf-grapher"
     }
     response = requests.get(link, params = data, stream=True)
     WHERE{
     # print(response.content)
        ?s ns1:name ?person .
    print(response.raw)
}"""
    with open("lab1.png", "wb") as fil:
        shutil.copyfileobj(response.raw, fil)


graph = g.serialize(format="ttl")
sparqlUpdate.setQuery(update_str)
graphToImage(graph)
sparqlUpdate.setMethod(POST)
</syntaxhighlight>
sparqlUpdate.query()


==RDF programming with RDFlib (Lab 2)==
#To test, run the query in the above task, replacing the ask query with e.g. ns1:Deborah_Gore_Dean rdf:type ns1:IndictedPerson


<syntaxhighlight>
# 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/>


from rdflib import Graph, URIRef, Namespace, Literal, XSD, BNode, URIRef
    INSERT{
from rdflib.collection import Collection
        ?invest dc:title ?investString.
    }
    WHERE{
        ?s ns1:investigation ?invest .
        BIND (replace(str(?invest), str(ns1:), "")  AS ?investString)
}"""


g = Graph()
sparqlUpdate.setQuery(update_str)
g.parse("lab1.ttl", format="ttl") #Retrives the triples from lab 1
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


ex = Namespace('http://example.org/')
#Same test as above, replace it with e.g. ns1:watergate dc:title "watergate"


# --- Michael Cohen ---
# Print out a sorted list of all the indicted persons represented in your graph.
#Michael Cohen was Donald Trump's attorney.
sparql.setQuery("""
g.add((ex.Michael_Cohen, ex.attorneyTo, ex.Donald_Trump))
    PREFIX ns1: <http://example.org#>
#He pleaded guilty to lying to the FBI.
    PREFIX foaf: <http://xmlns.com/foaf/0.1/>
g.add((ex.Michael_Cohen, ex.pleadGuiltyTo, ex.LyingToCongress))


# --- Michael Flynn ---
    SELECT ?name
#Michael Flynn was adviser to Trump.
    WHERE{
g.add((ex.Michael_Flynn, ex.adviserTo, ex.Donald_Trump))
    ?s  ns1:name ?name;
#He pleaded guilty to lying to the FBI.
            ns1:outcome ns1:indictment.
g.add((ex.Michael_Flynn, ex.pleadGuiltyTo, ex.LyingToFBI))
    }
# He negotiated a plea agreement.
    ORDER BY ?name
g.add((ex.Michael_Flynn, ex.negoiated, ex.PleaBargain))  
""")


#How can you modify your knowledge graph to account for the different lying?
sparql.setReturnFormat(JSON)
#Remove these to not have duplicates
results = sparql.query().convert()
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 ---
names = []
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 ---
for result in results["results"]["bindings"]:
GatesLying = BNode()
    names.append(result["name"]["value"])
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 ---
print(names)
CohenLying = BNode()
g.add((CohenLying, ex.crime, ex.LyingToCongress))
g.add((CohenLying, ex.liedAbout, Literal("Trump real estate deal", datatype=XSD.string)))
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"))
# Print out the minimum, average and maximum indictment days for all the indictments in the graph.


#Save (serialize) your graph to a Turtle file.
sparql.setQuery("""
# g.serialize("lab2.ttl", format="ttl")
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    PREFIX ns1: <http://example.org#>


#Add a few triples to the Turtle file with more information about Donald Trump.
    SELECT (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
'''
        ?s  ns1:indictment_days ?days;
ex:Donald_Trump ex:address [ ex:city ex:Palm_Beach ;
             ns1:outcome ns1:indictment.
             ex:country ex:United_States ;
   
            ex:postalCode 33480 ;
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
            ex:residence ex:Mar_a_Lago ;
     BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
            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
sparql.setReturnFormat(JSON)
def serialize_Graph():
results = sparql.query().convert()
    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
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"]}')


#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
# Print out the minimum, average and maximum indictment days for all the indictments in the graph per investigation.
visited_nodes = set()


def create_Tree(model, nodes):
sparql.setQuery("""
    #Traverse the model breadth-first to create the tree.
     prefix xsd: <http://www.w3.org/2001/XMLSchema#>
    global visited_nodes
     PREFIX ns1: <http://example.org#>
    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):
    SELECT ?investigation (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min) WHERE{
    #Print the tree depth-first.
     ?s ns1:indictment_days ?days;
    print(str(root))
         ns1:outcome ns1:indictment;
     for s, p, o in tree:
        ns1:investigation ?investigation.
         if s==root:
            print('    '*indent + '  ' + str(p), end=' ')
            print_Tree(tree, o, indent+1)
      
      
tree = create_Tree(g, [ex.Donald_Trump])
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
print_Tree(tree, ex.Donald_Trump)
    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"]}')
 
</syntaxhighlight>
 
== Lab 4 JSON-LD==
Part 1<syntaxhighlight lang="json-ld">
{
  "@context": {
      "@base": "http://example.org/",
      "edges": "http://example.org/triple",
      "start": "http://example.org/source",
      "rel": "http://exaxmple.org/predicate",
      "end": "http://example.org/object",
      "Person" : "http://example.org/Person",
      "birthday" : {
          "@id" : "http://example.org/birthday",
          "@type" : "xsd:date"
      },
      "nameEng" : {
          "@id" : "http://example.org/en/name",
          "@language" : "en"
      },
      "nameFr" : {
          "@id" : "http://example.org/fr/name",
          "@language" : "fr"
      },
      "nameCh" : {
          "@id" : "http://example.org/ch/name",
          "@language" : "ch"
      },
      "age" : {
          "@id" : "http://example.org/age",
          "@type" : "xsd:int"
      },
      "likes" : "http://example.org/games/likes",
      "haircolor" : "http://example.org/games/haircolor"
  },
  "@graph": [
      {
          "@id": "people/Jeremy",
          "@type": "Person",
          "birthday" : "1987.1.1",
          "nameEng" : "Jeremy",
          "age" : 26
      },
      {
          "@id": "people/Tom",
          "@type": "Person"
      },
      {
          "@id": "people/Ju",
          "@type": "Person",
          "birthday" : "2001.1.1",
          "nameCh" : "Ju",
          "age" : 22,
          "likes" : "bastketball"
      },
      {
          "@id": "people/Louis",
          "@type": "Person",
          "birthday" : "1978.1.1",
          "haircolor" : "Black",
          "nameFr" : "Louis",
          "age" : 45
      },
      {"edges" : [
      {
          "start" : "people/Jeremy",
          "rel" : "knows",
          "end" : "people/Tom"
      },
      {
          "start" : "people/Tom",
          "rel" : "knows",
          "end" : "people/Louis"
      },
      {
          "start" : "people/Louis",
          "rel" : "teaches",
          "end" : "people/Ju"
      },
      {
          "start" : "people/Ju",
          "rel" : "plays",
          "end" : "people/Jeremy"
      },
      {
          "start" : "people/Ju",
          "rel" : "plays",
          "end" : "people/Tom"
      }
      ]}
  ]
}
</syntaxhighlight>Part 2-3<syntaxhighlight lang="python">
import rdflib
 
CN_BASE = 'http://api.conceptnet.io/c/en/'
 
g = rdflib.Graph()
g.parse(CN_BASE+'indictment', format='json-ld')
 
# To download JSON object:
 
import json
import requests
 
json_obj = requests.get(CN_BASE+'indictment').json()
 
# To change the @context:
 
context = {
    "@base": "http://ex.org/",
    "edges": "http://ex.org/triple/",
    "start": "http://ex.org/s/",
    "rel": "http://ex.org/p/",
    "end": "http://ex.org/o/",
    "label": "http://ex.org/label"
}
json_obj['@context'] = context
json_str = json.dumps(json_obj)
 
g = rdflib.Graph()
g.parse(data=json_str, format='json-ld')
 
# To extract triples (here with labels):
 
r = g.query("""
        SELECT ?s ?sLabel ?p ?o ?oLabel WHERE {
            ?edge
                <http://ex.org/s/> ?s ;
                <http://ex.org/p/> ?p ;
                <http://ex.org/o/> ?o .
            ?s <http://ex.org/label> ?sLabel .
            ?o <http://ex.org/label> ?oLabel .
}
        """, initNs={'cn': CN_BASE})
print(r.serialize(format='txt').decode())
 
# Construct a new graph:
 
r = g.query("""
        CONSTRUCT {
            ?s ?p ?o .
            ?s <http://ex.org/label> ?sLabel .
            ?o <http://ex.org/label> ?oLabel .
        } WHERE {
            ?edge <http://ex.org/s/> ?s ;
                  <http://ex.org/p/> ?p ;
                  <http://ex.org/o/> ?o .
            ?s <http://ex.org/label> ?sLabel .
            ?o <http://ex.org/label> ?oLabel .
}
        """, initNs={'cn': CN_BASE})
 
print(r.graph.serialize(format='ttl'))
</syntaxhighlight>
 
== Lab 6 SHACL ==
<syntaxhighlight lang="turtle">
Every person under investigation has exactly one name.
ex:PersonShape
  a sh:NodeShape;
  sh:targetClass ex:PersonUnderInvestigation;
  sh:property [
  sh:path foaf:name;
  sh:maxCount 1;
  sh:minCount 1
].


The object of a charged with property must be a URI.
ex:PersonShape
  a sh:NodeShape;
  sh:targetClass ex:PersonUnderInvestigation;
  sh:property [
    sh:path ex:chargedWith;
    sh:nodeKind sh:URI
  ].
The object of a charged with property must be an offense.
ex:PersonShape
  a sh:NodeShape;
  sh:targetClass ex:PersonUnderInvestigation;
  sh:property [
    sh:path ex:chargedWith;
    sh:class ex:Offense
  ].
 
All person names must be language-tagged (hint: rdf:langString is a datatype!).
ex:PersonShape
  a sh:NodeShape;
  sh:targetClass ex:PersonUnderInvestigation;
  sh:property [
    sh:path foaf:name;
    sh:datatype rdf:langString
  ].
</syntaxhighlight>
</syntaxhighlight>

Latest revision as of 09:09, 17 March 2025

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

1 Lab: Getting started with VSCode, Python and RDFlib

from rdflib import Graph, Namespace

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

g = Graph()

g.bind("ex", ex)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

2 Lab: SPARQL queries

List all triples in your graph.

select * where { 
	?s ?p ?o .
} 

List the first 100 triples in your graph.

select * where { 
	?s ?p ?o .
} limit 100 

Count the number of triples in your graph.

select (count(?s)as ?tripleCount) where { 
	?s ?p ?o .
} 

Count the number of indictments in your graph.

PREFIX muellerkg: <http://example.org#>
select (Count(?s)as ?numIndictment) where { 
	?s ?p muellerkg:Indictment .
} 

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

PREFIX m: <http://example.org#>
select ?name ?s where { 
	?s ?p m:guilty-plea;
    	m:name ?name.
}  

List everyone who were convicted, but who had their conviction overturned by which president.

PREFIX muellerkg: <http://example.org#>
#List everyone who were convicted, but who had their conviction overturned by which president.

select ?name ?president   where { 
	?s ?p muellerkg:conviction;
		muellerkg:name ?name;
    	muellerkg:overturned true;
     	muellerkg:president ?president.  	
} limit 100 

For each investigation, list the number of indictments made.

PREFIX muellerkg: <http://example.org#>
select ?investigation (count(?investigation) as ?numIndictments) where { 
	?s muellerkg:investigation ?investigation .
} group by (?investigation)

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

PREFIX muellerkg: <http://example.org#>
select ?investigation (count(?investigation) as ?numIndictments) where { 
	?s muellerkg:investigation ?investigation.
} group by (?investigation)
having (?numIndictments > 1)

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

PREFIX muellerkg: <http://example.org#>
select ?investigation (count(?investigation) as ?numIndictments) where { 
	?s muellerkg:investigation ?investigation.
} group by (?investigation)
having (?numIndictments > 1)
order by desc(?numIndictments)

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

PREFIX muellerkg: <http://example.org#>
SELECT ?president (COUNT(?conviction) AS ?numConvictions) (COUNT(?pardon) AS ?numPardoned) 
WHERE { 
    ?indictment muellerkg:president ?president ;
                muellerkg:outcome muellerkg:conviction .
    BIND(?indictment AS ?conviction)
    OPTIONAL {
        ?indictment muellerkg:pardoned true .
        BIND(?indictment AS ?pardon)
    }
} 
GROUP BY ?president

3 Lab: SPARQL programming

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.

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)


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

# print(task5.serialize())

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

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

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

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

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

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

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

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

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

print(results)

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

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

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

rdf_Types = []

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

print(rdf_Types)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

names = []

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

print(names)

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

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

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

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

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

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

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

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

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

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

Lab 4 JSON-LD

Part 1

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

Part 2-3

import rdflib

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

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

# To download JSON object:

import json
import requests

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

# To change the @context:

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

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

# To extract triples (here with labels):

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

# Construct a new graph:

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

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

Lab 6 SHACL

Every person under investigation has exactly one name.
ex:PersonShape 
   a sh:NodeShape;
   sh:targetClass ex:PersonUnderInvestigation;
   sh:property [
   sh:path foaf:name;
   sh:maxCount 1;
   sh:minCount 1
].

The object of a charged with property must be a URI.
ex:PersonShape 
   a sh:NodeShape;
   sh:targetClass ex:PersonUnderInvestigation;
   sh:property [
     sh:path ex:chargedWith;
     sh:nodeKind sh:URI
   ].
 
 The object of a charged with property must be an offense.
 ex:PersonShape 
   a sh:NodeShape;
   sh:targetClass ex:PersonUnderInvestigation;
   sh:property [
     sh:path ex:chargedWith;
     sh:class ex:Offense
   ].
   
 All person names must be language-tagged (hint: rdf:langString is a datatype!).
 ex:PersonShape 
   a sh:NodeShape;
   sh:targetClass ex:PersonUnderInvestigation;
   sh:property [
     sh:path foaf:name;
     sh:datatype rdf:langString
   ].
Retrieved from "http://info216.wiki.uib.no/index.php?title=Lab_Solutions&oldid=2687"