Lab Solutions

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'))