Lab Solutions: Difference between revisions

From info216
No edit summary
m (Added lab1 solutions)
Tags: Replaced Visual edit
 
(156 intermediate revisions by 7 users not shown)
Line 1: Line 1:
This page will be updated with Python examples related to the lectures and labs. We will add more examples after each lab has ended. The first examples will use Python's RDFlib. We will introduce other relevant libraries later.
Here we will present suggested solutions after each lab. ''The page will be updated as the course progresses''
 
=Getting started (Lab 1)=
 
==Lecture 1: Python, RDFlib, and PyCharm==
 
 
===Printing the triples of the Graph in a readable way===
<syntaxhighlight>
<syntaxhighlight>
# The turtle format has the purpose of being more readable for humans.
print(g.serialize(format="turtle").decode())
</syntaxhighlight>


===Coding Tasks Lab 1===
from rdflib import Graph, Namespace
<syntaxhighlight>
from rdflib import Graph, Namespace, URIRef, BNode, Literal
from rdflib.namespace import RDF, FOAF, XSD
 
g = Graph()
ex = Namespace("http://example.org/")
 
g.add((ex.Cade, ex.married, ex.Mary))
g.add((ex.France, ex.capital, ex.Paris))
g.add((ex.Cade, ex.age, Literal("27", datatype=XSD.integer)))
g.add((ex.Mary, ex.age, Literal("26", datatype=XSD.integer)))
g.add((ex.Mary, ex.interest, ex.Hiking))
g.add((ex.Mary, ex.interest, ex.Chocolate))
g.add((ex.Mary, ex.interest, ex.Biology))
g.add((ex.Mary, RDF.type, ex.Student))
g.add((ex.Paris, RDF.type, ex.City))
g.add((ex.Paris, ex.locatedIn, ex.France))
g.add((ex.Cade, ex.characteristic, ex.Kind))
g.add((ex.Mary, ex.characteristic, ex.Kind))
g.add((ex.Mary, RDF.type, FOAF.Person))
g.add((ex.Cade, RDF.type, FOAF.Person))
 
</syntaxhighlight>
 
===Lab 1/2 - Different ways of Making an Address ===
 
<syntaxhighlight>


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


g = Graph()
g = Graph()
ex = Namespace("http://example.org/")
# How to represent the address of Cade Tracey. From probably the worst solution to the best.
# Solution 1 -
# Make the entire address into one Literal. However, Generally we want to seperate each part of an address into their own triples. This is useful for instance if we want to find only the streets where people live.
g.add((ex.Cade_Tracey, ex.livesIn, Literal("1516_Henry_Street, Berkeley, California 94709, USA")))
# Solution 2 -
# Seperate the different pieces information into their own triples
g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
g.add((ex.Cade_tracey, ex.city, Literal("Berkeley")))
g.add((ex.Cade_tracey, ex.state, Literal("California")))
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
g.add((ex.Cade_tracey, ex.country, Literal("USA")))
# Solution 3 - Some parts of the addresses can make more sense to be resources than Literals.
# Larger concepts like a city or state are typically represented as resources rather than Literals, but this is not necesarilly a requirement in the case that you don't intend to say more about them.
g.add((ex.Cade_tracey, ex.street, Literal("1516_Henry_Street")))
g.add((ex.Cade_tracey, ex.city, ex.Berkeley))
g.add((ex.Cade_tracey, ex.state, ex.California))
g.add((ex.Cade_tracey, ex.zipcode, Literal("94709")))
g.add((ex.Cade_tracey, ex.country, ex.USA))
# Solution 4
# Grouping of the information into an Address. We can Represent the address concept with its own URI OR with a Blank Node.
# One advantage of this is that we can easily remove the entire address, instead of removing each individual part of the address.
# Solution 4 or 5 is how I would recommend to make addresses. Here, ex.CadeAddress could also be called something like ex.address1 or so on, if you want to give each address a unique ID.
# Address URI - CadeAdress
g.add((ex.Cade_Tracey, ex.address, ex.CadeAddress))
g.add((ex.CadeAddress, RDF.type, ex.Address))
g.add((ex.CadeAddress, ex.street, Literal("1516 Henry Street")))
g.add((ex.CadeAddress, ex.city, ex.Berkeley))
g.add((ex.CadeAddress, ex.state, ex.California))
g.add((ex.CadeAddress, ex.postalCode, Literal("94709")))
g.add((ex.CadeAddress, ex.country, ex.USA))
# OR
# Blank node for Address. 
address = BNode()
g.add((ex.Cade_Tracey, ex.address, address))
g.add((address, RDF.type, ex.Address))
g.add((address, ex.street, Literal("1516 Henry Street", datatype=XSD.string)))
g.add((address, ex.city, ex.Berkeley))
g.add((address, ex.state, ex.California))
g.add((address, ex.postalCode, Literal("94709", datatype=XSD.string)))
g.add((address, ex.country, ex.USA))
# Solution 5 using existing vocabularies for address
# (in this case https://schema.org/PostalAddress from schema.org).
# Also using existing ontology for places like California. (like http://dbpedia.org/resource/California from dbpedia.org)
schema = "https://schema.org/"
dbp = "https://dpbedia.org/resource/"
g.add((ex.Cade_Tracey, schema.address, ex.CadeAddress))
g.add((ex.CadeAddress, RDF.type, schema.PostalAddress))
g.add((ex.CadeAddress, schema.streetAddress, Literal("1516 Henry Street")))
g.add((ex.CadeAddress, schema.addresCity, dbp.Berkeley))
g.add((ex.CadeAddress, schema.addressRegion, dbp.California))
g.add((ex.CadeAddress, schema.postalCode, Literal("94709")))
g.add((ex.CadeAddress, schema.addressCountry, dbp.United_States))
</syntaxhighlight>
===Lab 2 - Collection Example ===
<syntaxhighlight>
from rdflib import Graph, Namespace
from rdflib.collection import Collection
# Sometimes we want to add many objects or subjects for the same predicate at once.
# In these cases we can use Collection() to save some time.
# In this case I want to add all countries that Emma has visited at once.
b = BNode()
g.add((ex.Emma, ex.visit, b))
Collection(g, b,
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])


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


g.add((ex.Emma, ex.visit, ex.EmmaVisits))
# The Mueller Investigation was lead by Robert Mueller
Collection(g, ex.EmmaVisits,
g.add((ex.MuellerInvestigation, ex.leadBy, ex.RobertMueller))
    [ex.Portugal, ex.Italy, ex.France, ex.Germany, ex.Denmark, ex.Sweden])


</syntaxhighlight>
# 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))


===Lab 3/4 - SPARQL queries from the lecture ===
# Paul Manafort was business partner of Rick Gates
<syntaxhighlight>
g.add((ex.PaulManafort, ex.businessPartner, ex.RickGates))
SELECT DISTINCT ?p WHERE {
    ?s ?p ?o .
}
</syntaxhighlight>


<syntaxhighlight>
# He was campaign chairman for Donald Trump
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
g.add((ex.PaulManafort, ex.campaignChairman, ex.DonaldTrump))


SELECT DISTINCT ?t WHERE {
# He was charged with money laundering, tax evasion, and foreign lobbying.
    ?s rdf:type ?t .
g.add((ex.PaulManafort, ex.chargedWith, ex.MoneyLaundering))
}
g.add((ex.PaulManafort, ex.chargedWith, ex.TaxEvasion))
</syntaxhighlight>
g.add((ex.PaulManafort, ex.chargedWith, ex.ForeignLobbying))


<syntaxhighlight>
# He was convicted for bank and tax fraud.
PREFIX owl: <http://www.w3.org/2002/07/owl#>
g.add((ex.PaulManafort, ex.convictedOf, ex.BankFraud))
CONSTRUCT {
g.add((ex.PaulManafort, ex.convictedOf, ex.TaxFraud))
    ?s owl:sameAs ?o2 .  
} WHERE {
    ?s owl:sameAs ?o .
    FILTER(REGEX(STR(?o), "^http://www\\.", "s"))
    BIND(URI(REPLACE(STR(?o), "^http://www\\.", "http://", "s")) AS ?o2)
}
</syntaxhighlight>


===Lab 3/4 - SPARQL - Select all contents of lists (rdfllib.Collection)===
# He pleaded guilty to conspiracy.
<syntaxhighlight>
g.add((ex.PaulManafort, ex.pleadGuiltyTo, ex.Conspiracy))


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


PREFIX ex:  <http://example.org/>
# He negotiated a plea agreement.
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
g.add((ex.PaulManafort, ex.negotiated, ex.PleaAgreement))


SELECT ?visit
# Rick Gates was charged with money laundering, tax evasion and foreign lobbying.
WHERE {
g.add((ex.RickGates, ex.chargedWith, ex.MoneyLaundering))
  ex:Emma ex:visit/rdf:rest*/rdf:first ?visit
g.add((ex.RickGates, ex.chargedWith, ex.TaxEvasion))
}
g.add((ex.RickGates, ex.chargedWith, ex.ForeignLobbying))
</syntaxhighlight>
 
 
===Lab 3/4/6 - SELECTING data from Blazegraph via Python ===
<syntaxhighlight>


from SPARQLWrapper import SPARQLWrapper, JSON
# 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))


# This creates a server connection to the same URL that contains the graphic interface for Blazegraph.  
# Use the serialize method of rdflib.Graph to write out the model in different formats (on screen or to file)
# You also need to add "sparql" to end of the URL like below.
print(g.serialize(format="ttl")) # To screen
#g.serialize("lab1.ttl", format="ttl") # To file


sparql = SPARQLWrapper("http://84.211.55.37:9999/blazegraph/sparql")
# 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)


# SELECT all triples in the database.
# --- IF you have more time tasks ---


sparql.setQuery("""
# Michael Cohen, Michael Flynn and the lying is part of lab 2 and therefore the answer is not provided this week
    SELECT DISTINCT ?p WHERE {
    ?s ?p ?o.
    }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


for result in results["results"]["bindings"]:
#Write a method (function) that submits your model for rendering and saves the returned image to file.
    print(result["p"]["value"])
import requests
import shutil


# SELECT all interests of Cade
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)


sparql.setQuery("""
graph = g.serialize(format="ttl")
    PREFIX ex: <http://example.org/>
graphToImage(graph)
    SELECT DISTINCT ?interest WHERE {
    ex:Cade ex:interest ?interest.
    }
""")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()


for result in results["results"]["bindings"]:
    print(result["interest"]["value"])
</syntaxhighlight>
</syntaxhighlight>
<div class="credits" style="text-align: right; direction: ltr; margin-left: 1em;">''INFO216, UiB, 2017-2020. All code examples are [https://creativecommons.org/choose/zero/ CC0].'' </div>

Latest revision as of 09:10, 3 February 2025

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

Getting started (Lab 1)

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)