Lab Solutions: Difference between revisions

From info216
No edit summary
No edit summary
 
(116 intermediate revisions by 8 users not shown)
Line 1: Line 1:
This page will be updated with Python examples related to the lectures and labs. We will add more examples after each lab has ended. The first examples will use Python's RDFlib. We will introduce other relevant libraries later.
Here we will present suggested solutions after each lab. ''The page will be updated as the course progresses''
=[[/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


==Lecture 1: Python, RDFlib, and PyCharm==
ex = Namespace('http://example.org/')


g = Graph()


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


===Coding Tasks Lab 1===
# The Mueller Investigation was lead by Robert Mueller
<syntaxhighlight>
g.add((ex.MuellerInvestigation, ex.leadBy, ex.RobertMueller))
from rdflib import Graph, Namespace, URIRef, BNode, Literal
from rdflib.namespace import RDF, FOAF, XSD


g = Graph()
# It involved Paul Manafort, Rick Gates, George Papadopoulos, Michael Flynn, Michael Cohen, and Roger Stone.
ex = Namespace("http://example.org/")
g.add((ex.MuellerInvestigation, ex.involved, ex.PaulManafort))
g.add((ex.MuellerInvestigation, ex.involved, ex.RickGates))
g.add((ex.MuellerInvestigation, ex.involved, ex.GeorgePapadopoulos))
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelFlynn))
g.add((ex.MuellerInvestigation, ex.involved, ex.MichaelCohen))
g.add((ex.MuellerInvestigation, ex.involved, ex.RogerStone))


g.add((ex.Cade, ex.married, ex.Mary))
# Paul Manafort was business partner of Rick Gates
g.add((ex.France, ex.capital, ex.Paris))
g.add((ex.PaulManafort, ex.businessPartner, ex.RickGates))
g.add((ex.Cade, ex.age, Literal("27", datatype=XSD.integer)))
g.add((ex.Mary, ex.age, Literal("26", datatype=XSD.integer)))
g.add((ex.Mary, ex.interest, ex.Hiking))
g.add((ex.Mary, ex.interest, ex.Chocolate))
g.add((ex.Mary, ex.interest, ex.Biology))
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Paris, RDF.type, ex.City))
g.add((ex.Paris, ex.locatedIn, ex.France))
g.add((ex.Cade, ex.characteristic, ex.Kind))
g.add((ex.Mary, ex.characteristic, ex.Kind))
g.add((ex.Mary, RDF.type, FOAF.Person))
g.add((ex.Cade, RDF.type, FOAF.Person))


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


==Lecture 2: RDF programming==
# 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))


===Different ways to create an address===
# He was convicted for bank and tax fraud.
g.add((ex.PaulManafort, ex.convictedOf, ex.BankFraud))
g.add((ex.PaulManafort, ex.convictedOf, ex.TaxFraud))


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


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


g = Graph()
# He negotiated a plea agreement.
ex = Namespace("http://example.org/")
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))


# How to represent the address of Cade Tracey. From probably the worst solution to the best.
# 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))


# Solution 1 -
# Use the serialize method of rdflib.Graph to write out the model in different formats (on screen or to 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.  
print(g.serialize(format="ttl")) # To screen
#g.serialize("lab1.ttl", format="ttl") # To file


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


# Solution 2 -
# Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week
# Seperate the different pieces information into their own triples


g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
#Write a method (function) that submits your model for rendering and saves the returned image to file.
g.add((ex.Cade_tracey, ex.city, Literal("Berkeley")))
import requests
g.add((ex.Cade_tracey, ex.state, Literal("California")))
import shutil
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
g.add((ex.Cade_tracey, ex.country, Literal("USA")))


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)


# Solution 3 - Some parts of the addresses can make more sense to be resources than Literals.
graph = g.serialize(format="ttl")
# 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.
graphToImage(graph)


g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
</syntaxhighlight>
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))


=2 [[/info216.wiki.uib.no/Lab: SPARQL|Lab: SPARQL queries]] =
<syntaxhighlight>
List all triples in your graph.


# Solution 4
select * where {
# Grouping of the information into an Address. We can Represent the address concept with its own URI OR with a Blank Node.  
?s ?p ?o .
# 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.  
 
List the first 100 triples in your graph.


# Address URI - CadeAdress
select * where {
?s ?p ?o .
} limit 100


g.add((ex.Cade_Tracey, ex.address, ex.CadeAddress))
Count the number of triples in your graph.
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
select (count(?s)as ?tripleCount) where {
?s ?p ?o .
}


# Blank node for Address.
Count the number of indictments in your graph.
address = BNode()
g.add((ex.Cade_Tracey, ex.address, address))
g.add((address, RDF.type, ex.Address))
g.add((address, ex.street, Literal("1516 Henry Street", datatype=XSD.string)))
g.add((address, ex.city, ex.Berkeley))
g.add((address, ex.state, ex.California))
g.add((address, ex.postalCode, Literal("94709", datatype=XSD.string)))
g.add((address, ex.country, ex.USA))


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


# Solution 5 using existing vocabularies for address
List everyone who pleaded guilty, along with the name of the investigation.


# (in this case https://schema.org/PostalAddress from schema.org).
PREFIX m: <http://example.org#>
# Also using existing ontology for places like California. (like http://dbpedia.org/resource/California from dbpedia.org)
select ?name ?s where {
?s ?p m:guilty-plea;
    m:name ?name.
} 


schema = "https://schema.org/"
List everyone who were convicted, but who had their conviction overturned by which president.
dbp = "https://dpbedia.org/resource/"


g.add((ex.Cade_Tracey, schema.address, ex.CadeAddress))
PREFIX muellerkg: <http://example.org#>
g.add((ex.CadeAddress, RDF.type, schema.PostalAddress))
#List everyone who were convicted, but who had their conviction overturned by which president.
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>
select ?name ?president  where {
?s ?p muellerkg:conviction;
muellerkg:name ?name;
    muellerkg:overturned true;
    muellerkg:president ?president. 
} limit 100


===Typed Literals===
For each investigation, list the number of indictments made.
<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)))
PREFIX muellerkg: <http://example.org#>
g.add((ex.Cade, ex.gpa, Literal(3.3, datatype=XSD.float)))
select ?investigation (count(?investigation) as ?numIndictments) where {
g.add((ex.Cade, FOAF.name, Literal("Cade Tracey", datatype=XSD.string)))
?s muellerkg:investigation ?investigation .
g.add((ex.Cade, ex.birthday, Literal("2006-01-01", datatype=XSD.date)))
} group by (?investigation)
</syntaxhighlight>


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


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


<syntaxhighlight>
For each investigation with multiple indictments, list the number of indictments made, sorted with the most indictments first.
  # 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
PREFIX muellerkg: <http://example.org#>
parsed_graph = g.parse(location="triples.txt", format="turtle")
select ?investigation (count(?investigation) as ?numIndictments) where {
?s muellerkg:investigation ?investigation.
} group by (?investigation)
having (?numIndictments > 1)
order by desc(?numIndictments)


  # Parsing a remote endpoint like Dbpedia
For each president, list the numbers of convictions and of pardons made after conviction.
dbpedia_graph = g.parse("http://dbpedia.org/resource/Pluto")
</syntaxhighlight>


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


===Collection Example===
</syntaxhighlight>


== 3 [[/info216.wiki.uib.no/Lab: SPARQL Programming|Lab: SPARQL programming]] ==
<syntaxhighlight>
<syntaxhighlight>
from rdflib import Graph, Namespace
from rdflib.collection import Collection


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


# Sometimes we want to add many objects or subjects for the same predicate at once.
g = Graph()
# In these cases we can use Collection() to save some time.
g.parse("Russia_investigation_kg.ttl")
# In this case I want to add all countries that Emma has visited at once.


b = BNode()
# ----- RDFLIB -----
g.add((ex.Emma, ex.visit, b))
ex = Namespace('http://example.org#')
Collection(g, b,
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])


# OR
NS = {
 
    '': ex,
g.add((ex.Emma, ex.visit, ex.EmmaVisits))
    'rdf': RDF,
Collection(g, ex.EmmaVisits,
     'foaf': FOAF,
     [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])
}
 
</syntaxhighlight>
 
==Lecture 3: SPARQL==


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


<syntaxhighlight>
print(list(task1))
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


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


<syntaxhighlight>
print(list(task2))
PREFIX owl: <http://www.w3.org/2002/07/owl#>
CONSTRUCT {
    ?s owl:sameAs ?o2 .
} WHERE {
    ?s owl:sameAs ?o .
    FILTER(REGEX(STR(?o), "^http://www\\.", "s"))
    BIND(URI(REPLACE(STR(?o), "^http://www\\.", "http://", "s")) AS ?o2)
}
</syntaxhighlight>


===Select all contents of lists (rdfllib.Collection)===
# 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 = {}
 
# 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
task3 = g.query("""
WHERE {
SELECT ?president ?person WHERE{
  ex:Emma ex:visit/rdf:rest*/rdf:first ?visit
    ?s :president ?president;
      :name ?person;
      :outcome :indictment.
}
}
</syntaxhighlight>
""", initNs=NS)


==Lecture 4- SPARQL PROGRAMMING==
for president, person in task3:
    if president not in task3_dic:
        task3_dic[president] = [person]
    else:
        task3_dic[president].append(person)


===Using paramters/variables in rdflib queries===
print(task3_dic)


<syntaxhighlight>
# Use an ASK query to investigate whether Donald Trump has pardoned more than 5 people.
from rdflib import Graph, Namespace, URIRef
from rdflib.plugins.sparql import prepareQuery


g = Graph()
task4 = g.query("""
ex = Namespace("http://example.org/")
    ASK{
g.bind("ex", ex)
        SELECT ?count WHERE{{
 
          SELECT (COUNT(?s) as ?count) WHERE{
g.add((ex.Cade, ex.livesIn, ex.France))
            ?s :pardoned :true;
g.add((ex.Anne, ex.livesIn, ex.Norway))
                  :president :Bill_Clinton  .
g.add((ex.Sofie, ex.livesIn, ex.Sweden))
                }}
g.add((ex.Per, ex.livesIn, ex.Norway))
         FILTER (?count > 5)  
g.add((ex.John, ex.livesIn, ex.USA))
         }
 
    }
 
""", initNs=NS)
def find_people_from_country(country):
         country = URIRef(ex + country)
         q = prepareQuery(
        """
        PREFIX ex: <http://example.org/>
        SELECT ?person WHERE {
        ?person ex:livesIn ?country.
        }
        """)


        capital_result = g.query(q, initBindings={'country': country})
print(task4.askAnswer)


        for row in capital_result:
            print(row)
find_people_from_country("Norway")
</syntaxhighlight>


===SELECTING data from Blazegraph via Python===
# task5 = g.query("""
<syntaxhighlight>
# DESCRIBE :Donald_Trump
# """, initNs=NS)


from SPARQLWrapper import SPARQLWrapper, JSON
# print(task5.serialize())


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


sparql = SPARQLWrapper("http://localhost:9999/blazegraph/sparql")
SERVER = 'http://localhost:7200' #Might need to replace this
REPOSITORY = 'Labs' #Replace with your repository name


# SELECT all triples in the database.
# 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("""
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===
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, POST, DIGEST
 
namespace = "kb"
sparql = SPARQLWrapper("http://localhost:9999/blazegraph/namespace/"+ namespace + "/sparql")


sparql.setMethod(POST)
# Describe investigation number 100 (muellerkg:investigation_100).
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)


</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>


More examples can be found in the example section on the official query service here: https://query.wikidata.org/.
print(rdf_Types)


===Download from BlazeGraph===
# 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#>


<syntaxhighlight>
    INSERT{
"""
        ?invest rdf:type ns1:Investigation .
Dumps a database to a local RDF file.
    }
You need to install the SPARQLWrapper package first...
    WHERE{
"""
        ?s ns1:investigation ?invest .
}"""


import datetime
sparqlUpdate.setQuery(update_str)
from SPARQLWrapper import SPARQLWrapper, RDFXML
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


# your namespace, the default is 'kb'
#To Test
ns = 'kb'
sparql.setQuery("""
 
    prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
# the SPARQL endpoint
    PREFIX ns1: <http://example.org#>
endpoint = 'http://info216.i2s.uib.no/bigdata/namespace/' + ns + '/sparql'
 
# - the endpoint just moved, the old one was:
# endpoint = 'http://i2s.uib.no:8888/bigdata/namespace/' + ns + '/sparql'
 
# create wrapper
wrapper = SPARQLWrapper(endpoint)
 
# prepare the SPARQL update
wrapper.setQuery('CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }')
wrapper.setReturnFormat(RDFXML)
 
# execute the SPARQL update and convert the result to an rdflib.Graph
graph = wrapper.query().convert()
 
# the destination file, with code to make it timestamped
destfile = 'rdf_dumps/slr-kg4news-' + datetime.datetime.now().strftime('%Y%m%d-%H%M') + '.rdf'
 
# serialize the result to file
graph.serialize(destination=destfile, format='ttl')
 
# report and quit
print('Wrote %u triples to file %s .' %
      (len(res), destfile))
</syntaxhighlight>
 
===Query Dbpedia with SparqlWrapper===
 
<syntaxhighlight>
from SPARQLWrapper import SPARQLWrapper, JSON
 
sparql = SPARQLWrapper("http://dbpedia.org/sparql")


sparql.setQuery("""
     ASK{
     PREFIX dbr: <http://dbpedia.org/resource/>
        ns1:watergate rdf:type ns1:Investigation.
    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"))
     }
     }
""")
""")
Line 397: Line 358:
sparql.setReturnFormat(JSON)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
results = sparql.query().convert()
print(results['boolean'])


for result in results["results"]["bindings"]:
# Update the graph to that every resource that is an object in a muellerkg:person triple has the rdf:type muellerkg:IndictedPerson.
     print(result["comment"]["value"])
update_str = """
</syntaxhighlight>
    PREFIX ns1: <http://example.org#>
     PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>


== Lecture 5: RDFS==
    INSERT{
        ?person rdf:type ns1:IndictedPerson .
    }
    WHERE{
        ?s ns1:name ?person .
}"""


===RDFS inference with RDFLib===
sparqlUpdate.setQuery(update_str)
You can use the OWL-RL package to add inference capabilities to RDFLib. Download it [https://github.com/RDFLib/OWL-RL GitHub] and copy the ''owlrl'' subfolder into your project folder next to your Python files.
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


[https://owl-rl.readthedocs.io/en/latest/owlrl.html OWL-RL documentation.]
#To test, run the query in the above task, replacing the ask query with e.g. ns1:Deborah_Gore_Dean rdf:type ns1:IndictedPerson


Example program to get started:
# 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.
<syntaxhighlight>
update_str = """
import rdflib.plugins.sparql.update
    PREFIX ns1: <http://example.org#>
import owlrl.RDFSClosure
    PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
    PREFIX dc: <http://purl.org/dc/elements/1.1/>


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


ex = rdflib.Namespace('http://example.org#')
sparqlUpdate.setQuery(update_str)
g.bind('', ex)
sparqlUpdate.setMethod(POST)
sparqlUpdate.query()


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


# The next three lines add inferred triples to g.
# Print out a sorted list of all the indicted persons represented in your graph.
rdfs = owlrl.RDFSClosure.RDFS_Semantics(g, False, False, False)
sparql.setQuery("""
rdfs.closure()
    PREFIX ns1: <http://example.org#>
rdfs.flush_stored_triples()
    PREFIX foaf: <http://xmlns.com/foaf/0.1/>


b = g.query("""
    SELECT ?name
PREFIX ex: <http://example.org#>
    WHERE{
ASK {
     ?s  ns1:name ?name;
     ex:Socrates rdf:type ex:Mortal .
            ns1:outcome ns1:indictment.
}  
    }
    ORDER BY ?name
""")
""")
print('Result: ' + bool(b))
</syntaxhighlight>


===Languaged tagged RDFS labels===
sparql.setReturnFormat(JSON)
<syntaxhighlight>
results = sparql.query().convert()
from rdflib import Graph, Namespace, Literal
from rdflib.namespace import RDFS


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


g.add((ex.France, RDFS.label, Literal("Frankrike", lang="no")))
for result in results["results"]["bindings"]:
g.add((ex.France, RDFS.label, Literal("France", lang="en")))
    names.append(result["name"]["value"])
g.add((ex.France, RDFS.label, Literal("Francia", lang="es")))


print(names)


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


== Lecture 6: RDFS Plus / OWL ==
sparql.setQuery("""
===RDFS Plus / OWL inference with RDFLib===
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
 
    PREFIX ns1: <http://example.org#>
You can use the OWL-RL package again as for Lecture 5.
 
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 {
    SELECT (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
    ex:Socrates ex:hasWife ex:Xanthippe .
        ?s  ns1:indictment_days ?days;
     ex:hasHusband owl:inverseOf ex:hasWife .
            ns1:outcome ns1:indictment.
      
    BIND (replace(str(?days), str(ns1:), "")  AS ?daysR)
    BIND (STRDT(STR(?daysR), xsd:float) AS ?daysRemoved)
}
}
</syntaxhighlight>
""")


<syntaxhighlight>
sparql.setReturnFormat(JSON)
ASK {
results = sparql.query().convert()
  ex:Xanthippe ex:hasHusband ex:Socrates .
}
</syntaxhighlight>


<syntaxhighlight>
for result in results["results"]["bindings"]:
ASK {
    print(f'The longest an investigation lasted was: {result["max"]["value"]}')
  ex:Socrates ^ex:hasHusband ex:Xanthippe .
    print(f'The shortest an investigation lasted was: {result["min"]["value"]}')
}
    print(f'The average investigation lasted: {result["avg"]["value"]}')
</syntaxhighlight>


<syntaxhighlight>
# Print out the minimum, average and maximum indictment days for all the indictments in the graph per investigation.
INSERT DATA {
    ex:hasWife rdfs:subPropertyOf ex:hasSpouse .
    ex:hasSpouse rdf:type owl:SymmetricProperty .
}
</syntaxhighlight>


<syntaxhighlight>
sparql.setQuery("""
ASK {
    prefix xsd: <http://www.w3.org/2001/XMLSchema#>
  ex:Socrates ex:hasSpouse ex:Xanthippe .
    PREFIX ns1: <http://example.org#>
}
</syntaxhighlight>


<syntaxhighlight>
    SELECT ?investigation (AVG(?daysRemoved) as ?avg) (MAX(?daysRemoved) as ?max) (MIN(?daysRemoved) as ?min)  WHERE{
ASK {
    ?s  ns1:indictment_days ?days;
  ex:Socrates ^ex:hasSpouse ex:Xanthippe .
        ns1:outcome ns1:indictment;
  }
        ns1:investigation ?investigation.
</syntaxhighlight>
   
    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"]}')


==Semantic Lifting - CSV==
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF, FOAF, RDFS, OWL
import pandas as pd
g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)
# Load the CSV data as a pandas Dataframe.
csv_data = pd.read_csv("task1.csv")
# Here I deal with spaces (" ") in the data. I replace them with "_" so that URI's become valid.
csv_data = csv_data.replace(to_replace=" ", value="_", regex=True)
# Here I mark all missing/empty data as "unknown". This makes it easy to delete triples containing this later.
csv_data = csv_data.fillna("unknown")
# Loop through the CSV data, and then make RDF triples.
for index, row in csv_data.iterrows():
    # The names of the people act as subjects.
    subject = row['Name']
    # Create triples: e.g. "Cade_Tracey - age - 27"
    g.add((URIRef(ex + subject), URIRef(ex + "age"), Literal(row["Age"])))
    g.add((URIRef(ex + subject), URIRef(ex + "married"), URIRef(ex + row["Spouse"])))
    g.add((URIRef(ex + subject), URIRef(ex + "country"), URIRef(ex + row["Country"])))
    # If We want can add additional RDF/RDFS/OWL information e.g
    g.add((URIRef(ex + subject), RDF.type, FOAF.Person))
# I remove triples that I marked as unknown earlier.
g.remove((None, None, URIRef("http://example.org/unknown")))
# Clean printing of the graph.
print(g.serialize(format="turtle").decode())
</syntaxhighlight>
</syntaxhighlight>


===CSV file for above example===
== Lab 4 JSON-LD==
 
Part 1<syntaxhighlight lang="json-ld">
<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>
 
==Semantic Lifting - XML==
<syntaxhighlight>
from rdflib import Graph, Literal, Namespace, URIRef
from rdflib.namespace import RDF, XSD, RDFS
import xml.etree.ElementTree as ET
 
g = Graph()
ex = Namespace("http://example.org/TV/")
prov = Namespace("http://www.w3.org/ns/prov#")
g.bind("ex", ex)
g.bind("prov", prov)
 
tree = ET.parse("tv_shows.xml")
root = tree.getroot()
 
for tv_show in root.findall('tv_show'):
    show_id = tv_show.attrib["id"]
    title = tv_show.find("title").text
 
    g.add((URIRef(ex + show_id), ex.title, Literal(title, datatype=XSD.string)))
    g.add((URIRef(ex + show_id), RDF.type, ex.TV_Show))
 
    for actor in tv_show.findall("actor"):
        first_name = actor.find("firstname").text
        last_name = actor.find("lastname").text
        full_name = first_name + "_" + last_name
       
        g.add((URIRef(ex + show_id), ex.stars, URIRef(ex + full_name)))
        g.add((URIRef(ex + full_name), ex.starsIn, URIRef(title)))
        g.add((URIRef(ex + full_name), RDF.type, ex.Actor))
 
print(g.serialize(format="turtle").decode())
</syntaxhighlight>
 
 
 
===XML Data for above example===
<syntaxhighlight>
<data>
    <tv_show id="1050">
        <title>The_Sopranos</title>
        <actor>
            <firstname>James</firstname>
            <lastname>Gandolfini</lastname>
        </actor>
    </tv_show>
    <tv_show id="1066">
        <title>Seinfeld</title>
        <actor>
            <firstname>Jerry</firstname>
            <lastname>Seinfeld</lastname>
        </actor>
        <actor>
            <firstname>Julia</firstname>
            <lastname>Louis-dreyfus</lastname>
        </actor>
        <actor>
            <firstname>Jason</firstname>
            <lastname>Alexander</lastname>
        </actor>
    </tv_show>
</data>
</syntaxhighlight>
 
==Semantic Lifting - HTML==
<syntaxhighlight>
from bs4 import BeautifulSoup as bs, NavigableString
from rdflib import Graph, URIRef, Namespace
from rdflib.namespace import RDF
 
g = Graph()
ex = Namespace("http://example.org/")
g.bind("ex", ex)
 
html = open("tv_shows.html").read()
html = bs(html, features="html.parser")
 
shows = html.find_all('li', attrs={'class': 'show'})
for show in shows:
    title = show.find("h3").text
    actors = show.find('ul', attrs={'class': 'actor_list'})
    for actor in actors:
        if isinstance(actor, NavigableString):
            continue
        else:
            actor = actor.text.replace(" ", "_")
            g.add((URIRef(ex + title), ex.stars, URIRef(ex + actor)))
            g.add((URIRef(ex + actor), RDF.type, ex.Actor))
 
    g.add((URIRef(ex + title), RDF.type, ex.TV_Show))
 
 
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 API Calls (In this case 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": {
   "@context": {
    "name": "http://xmlns.com/foaf/0.1/name",
      "@base": "http://example.org/",
    "homepage": {
      "edges": "http://example.org/triple",
       "@id": "http://xmlns.com/foaf/0.1/homepage",
      "start": "http://example.org/source",
       "@type": "@id"
      "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"
   },
   },
   "@id": "http://me.markus-lanthaler.com/",
   "@graph": [
  "name": "Markus Lanthaler",
      {
  "homepage": "http://www.markus-lanthaler.com/"
          "@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


# json-ld parsing automatically deals with @contexts
CN_BASE = 'http://api.conceptnet.io/c/en/'
g.parse(data=example, format='json-ld')


# serialisation does expansion by default
g = rdflib.Graph()
for line in g.serialize(format='json-ld').decode().splitlines():
g.parse(CN_BASE+'indictment', format='json-ld')
    print(line)


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


import json
import requests


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


==OWL - Complex Classes and Restrictions==
# To change the @context:
<syntaxhighlight>
import owlrl
from rdflib import Graph, Literal, Namespace, BNode
from rdflib.namespace import RDF, OWL, RDFS
from rdflib.collection import Collection


g = Graph()
context = {
ex = Namespace("http://example.org/")
    "@base": "http://ex.org/",
g.bind("ex", ex)
    "edges": "http://ex.org/triple/",
g.bind("owl", OWL)
    "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)


# a Season is either Autumn, Winter, Spring, Summer
g = rdflib.Graph()
seasons = BNode()
g.parse(data=json_str, format='json-ld')
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
# To extract triples (here with labels):
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
r = g.query("""
br = BNode()
        SELECT ?s ?sLabel ?p ?o ?oLabel WHERE {
g.add((br, RDF.type, OWL.Restriction))
            ?edge
g.add((br, OWL.onProperty, ex.gender))
                <http://ex.org/s/> ?s ;
g.add((br, OWL.hasValue, ex.Female))
                <http://ex.org/p/> ?p ;
bi = BNode()
                <http://ex.org/o/> ?o .
Collection(g, bi, [ex.Person, br])
            ?s <http://ex.org/label> ?sLabel .
g.add((ex.Woman, OWL.intersectionOf, bi))
            ?o <http://ex.org/label> ?oLabel .
}
        """, initNs={'cn': CN_BASE})
print(r.serialize(format='txt').decode())


# A vegetarian is a Person who only eats vegetarian food
# Construct a new graph:
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.
r = g.query("""
br = BNode()
        CONSTRUCT {
g.add((br, RDF.type, OWL.Restriction))
            ?s ?p ?o .
g.add((br, OWL.onProperty, ex.eats))
            ?s <http://ex.org/label> ?sLabel .
g.add((br, OWL.QualifiedCardinality, Literal(0)))
            ?o <http://ex.org/label> ?oLabel .
g.add((br, OWL.onClass, ex.Meat))
        } WHERE {
bi = BNode()
            ?edge <http://ex.org/s/> ?s ;
Collection(g, bi, [ex.Person, br])
                  <http://ex.org/p/> ?p ;
g.add((ex.Vegetarian, OWL.intersectionOf, bi))
                  <http://ex.org/o/> ?o .
            ?s <http://ex.org/label> ?sLabel .
            ?o <http://ex.org/label> ?oLabel .
}
        """, initNs={'cn': CN_BASE})


# A Worried Parent is a parent who has at least one sick child
print(r.graph.serialize(format='ttl'))
br = BNode()
</syntaxhighlight>
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...:  
== Lab 6 SHACL ==
g.add((ex.Bob, RDF.type, ex.Parent))
<syntaxhighlight lang="turtle">
g.add((ex.Bob, ex.hasChild, ex.John))
Every person under investigation has exactly one name.
g.add((ex.John, RDF.type, ex.Sick))
ex:PersonShape
# ...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.
  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"