def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
index = 0
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
movie = Movie(title, release_year)
for actor in row['Actors'].split(","):
actor = Actor(actor.strip())
if actor not in self.__actors:
self.__actors.add(actor)
movie.add_actor(actor)
director = Director(row['Director'].strip())
if director not in self.__directors:
self.__directors.add(director)
movie.director = director
for genre in row['Genre'].split(','):
genre = Genre(genre.strip())
if genre not in self.__genres:
self.__genres.add(genre)
movie.add_genre(genre)
movie.runtime_minutes = row["Runtime (Minutes)"]
movie.description = row["Description"]
self.__movies.append(movie)
index += 1
def test_completed_attributes():
filename = 'datafiles/Data1000Movies.csv'
movie_file_reader = MovieFileCSVReader(filename)
movie_file_reader.read_csv_file()
movie_name = "Guardians of the Galaxy"
movie = movie_file_reader.movie_object(movie_name)
# normal attributes
assert movie.title == "Guardians of the Galaxy"
assert movie.release_year == 2014
assert movie.description == "A group of intergalactic criminals are forced to work together " \
"to stop a fanatical warrior from taking control of the universe."
assert movie.director == Director("James Gunn")
assert movie.actors == [
Actor("Chris Pratt"),
Actor("Vin Diesel"),
Actor("Bradley Cooper"),
Actor("Zoe Saldana")
]
assert movie.genres == [
Genre("Action"), Genre("Adventure"),
Genre("Sci-Fi")
]
assert movie.runtime_minutes == 121
# extra attributes
assert movie.rank == 1
assert movie.rating == 8.1
assert movie.revenue == 333.13
assert movie.votes == 757074
assert movie.metascore == 76
def test_remove_genre(self, movie):
genre1 = Genre("Horror")
genre2 = Genre("Anthology")
movie.add_genre(genre1)
movie.add_genre(genre2)
movie.remove_genre(genre1)
assert movie.genres == [genre2]
def test_setters(self): # inherently tests getters too
a_movie = Movie("Back To The Future", 1965)
director1 = Director("Brad Bird")
a_movie.title = " Mission Impossible: Ghost Protocol "
assert a_movie.title == "Mission Impossible: Ghost Protocol"
a_movie.title = 15
#assert a_movie.title == "Mission Impossible: Ghost Protocol"
a_movie.description = " An action movie "
assert a_movie.description == "An action movie"
a_movie.director = director1
assert a_movie.director == director1
actor1 = Actor("Tom Cruise")
actor2 = Actor("Simon Pegg")
a_movie.actors = [actor1, actor2]
assert a_movie.actors == [actor1, actor2]
genre1 = Genre("Action")
genre2 = Genre("Comedy")
a_movie.genres = [genre1, genre2]
assert a_movie.genres == [genre1, genre2]
a_movie.runtime_minutes = 100
assert a_movie.runtime_minutes == 100
assert type(a_movie.runtime_minutes) == int
with pytest.raises(ValueError):
a_movie.runtime_minutes = 0
a_movie.runtime_minutes = -10
def test_incomplete_attributes():
filename = 'datafiles/Data1000Movies.csv'
movie_file_reader = MovieFileCSVReader(filename)
movie_file_reader.read_csv_file()
movie_name = "Hounds of Love"
movie = movie_file_reader.movie_object(movie_name)
# normal attributes
assert movie.title == "Hounds of Love"
assert movie.release_year == 2016
assert movie.description == "A cold-blooded predatory couple while cruising the streets in search of their " \
"next victim, will stumble upon a 17-year-old high school girl, who will be sedated, " \
"abducted and chained in the strangers' guest room."
assert movie.director == Director("Ben Young")
assert movie.actors == [
Actor("Emma Booth"),
Actor("Ashleigh Cummings"),
Actor("Stephen Curry"),
Actor("Susie Porter")
]
assert movie.genres == [Genre("Crime"), Genre("Drama"), Genre("Horror")]
assert movie.runtime_minutes == 108
# extra attributes
assert movie.rank == 23
assert movie.rating == 6.7
assert movie.revenue is None
assert movie.votes == 1115
assert movie.metascore == 72
def test_more_methods(self):
a_movie = Movie("Back To The Future", 1965)
actor1 = Actor("Michael J. Fox")
actor2 = Actor("Christopher Lloyd")
genre1 = Genre("Horror")
genre2 = Genre("Comedy")
a_movie.add_actor(actor1)
assert a_movie.actors == [actor1]
a_movie.add_actor(actor1)
assert a_movie.actors == [actor1] # test it doesn't add duplicate actors
a_movie.add_actor(actor2)
assert a_movie.actors == [actor1, actor2] # tests actors are added (and in order, not that it matters)
a_movie.remove_actor(actor1)
assert a_movie.actors == [actor2]
a_movie.remove_actor(5) # test it doesn't throw an error if not an actor
assert a_movie.actors == [actor2] # test it doesn't randomly remove an actor (I don't see how but yeah)
a_movie.add_genre(genre1)
assert a_movie.genres == [genre1]
a_movie.add_genre(genre1)
assert a_movie.genres == [genre1] # test it doesn't add duplicate actors
a_movie.add_genre(genre2)
assert a_movie.genres == [genre1, genre2] # tests actors are added (and in order, not that it matters)
a_movie.remove_genre(genre1)
assert a_movie.genres == [genre2]
a_movie.remove_genre(5) # test it doesn't throw an error if not a genre
assert a_movie.genres == [genre2] # test it doesn't randomly remove an genre (I don't see how but yeah)
def testGenres(self):
print("Genre testing:")
movie1 = Movie("Moana", 2016)
movie1.add_genre(Genre("Cheesy"))
movie1.add_genre(Genre("Action"))
movie1.remove_genre(Genre("Cheesy"))
print(movie1.genres)
def test_movie_runtime(self):
movie = Movie("Moana", 2016)
movie.description = " This is a movie "
assert movie.description == "This is a movie"
movie.director = Director("Ron Clements")
assert movie.director.director_full_name is "Ron Clements"
assert repr(movie.director) == "<Director Ron Clements>"
actors = [
Actor("Auli'i Cravalho"),
Actor("Dwayne Johnson"),
Actor("Rachel House"),
Actor("Temuera Morrison")
]
for actor in actors:
movie.add_actor(actor)
assert repr(
movie.actors
) == "[<Actor Auli\'i Cravalho>, <Actor Dwayne Johnson>, <Actor Rachel House>, <Actor Temuera Morrison>]"
movie.remove_actor(Actor("Dwayne Johnson"))
assert repr(
movie.actors
) == "[<Actor Auli\'i Cravalho>, <Actor Rachel House>, <Actor Temuera Morrison>]"
genres = [Genre("Animated"), Genre("Comedy")]
for genre in genres:
movie.add_genre(genre)
assert repr(movie.genres) == "[<Genre Animated>, <Genre Comedy>]"
movie.remove_genre(Genre("Comedy"))
assert repr(movie.genres) == "[<Genre Animated>]"
movie.runtime_minutes = 100
assert movie.runtime_minutes is 100
def test_init_and_repr(self):
genre1 = Genre("Horror")
assert repr(genre1) == "<Genre Horror>"
genre2 = Genre("")
assert genre2.genre_name is None
genre3 = Genre(42)
assert genre3.genre_name is None
def test_read_csv_file(self):
filename = '../datafiles/Data1000Movies.csv'
movie_file_reader = MovieFileCSVReader(filename)
movie_file_reader.read_csv_file()
# check dataset sizes
assert len(movie_file_reader.dataset_of_movies) == 1000
assert len(movie_file_reader.dataset_of_actors) == 1985
assert len(movie_file_reader.dataset_of_directors) == 644
assert len(movie_file_reader.dataset_of_genres) == 20
# check assigning of all attributes from CSV to Movie obj
movie = movie_file_reader.dataset_of_movies[0]
assert movie.title == "Guardians of the Galaxy"
assert movie.genres == [
Genre("Action"),
Genre("Adventure"),
Genre("Sci-Fi")
]
assert movie.description == "A group of intergalactic criminals are forced " \
"to work together to stop a fanatical warrior " \
"from taking control of the universe."
assert movie.director == Director("James Gunn")
assert movie.actors == [
Actor("Chris Pratt"),
Actor("Vin Diesel"),
Actor("Bradley Cooper"),
Actor("Zoe Saldana")
]
assert movie.year == 2014
assert movie.runtime_minutes == 121
assert movie.rating == 8.1
assert movie.votes == 757074
assert movie.revenue == 333.13
assert movie.metascore == 76
def test_init(self):
genre1 = Genre("Action")
assert repr(genre1) == "<Genre Action>"
genre2 = Genre("")
assert genre2.genre_name is None
genre3 = Genre(42)
assert genre3.genre_name is None
def test_init(self):
genre1 = Genre("Comedy")
assert repr(genre1) == "<Genre Comedy>"
genre2 = Genre("Horror")
assert (genre1 == genre2) == False
assert (genre1 < genre2) == True
assert hash(genre1) == hash("Comedy")
def test_init():
genre1 = Genre("Comedy")
assert repr(genre1) == "<Genre Comedy>"
genre2 = Genre("")
assert genre2.genre_name is None
genre3 = Genre(42)
assert genre3.genre_name is None
def test_genres(self):
# correct input
movie1 = Movie("Moana", 2016)
movie1.genres = [Genre("Animation"), Genre("Comedy")]
assert movie1.genres == [Genre("Animation"), Genre("Comedy")]
# incorrect input
movie2 = Movie("Frozen", 2014)
def test_le():
genre1 = Genre("Comedy")
genre2 = Genre("Drama")
assert genre1 <= genre2
assert genre2 >= genre1
genre1 = Genre("Comedy")
genre2 = Genre("Comedy")
assert genre1 <= genre2
assert genre2 >= genre1
def test_genre():
genre1 = Genre("Comedy")
assert repr(genre1) == "<Genre Comedy>"
genre2 = Genre("")
assert genre2.genre_name is None
genre3 = Genre(42)
assert genre3.genre_name is None
genre4 = Genre("Horror")
assert genre1 < genre4
def test_remove_people(self, movie):
movie.remove_actor(Actor("Sam"))
assert movie.actors == [Actor("Cherry")]
movie.remove_genre(Genre("Kids"))
assert movie.genres == []
movie.remove_genre(Genre("Comedy"))
assert movie.genres == []
movie.remove_actor(Actor("Paul"))
assert movie.actors == [Actor("Cherry")]
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
index = 0
for row in movie_file_reader:
title = row["Title"]
release_year = int(row["Year"])
movie = Movie(title, release_year)
movie.description = row["Description"]
director = row["Director"]
movie.director = director
if Director(director) not in self.__dataset_of_directors:
self.__dataset_of_directors.append(Director(director))
actors = row["Actors"].split(",")
for actor in actors:
movie.add_actor(Actor(actor))
if Actor(actor) not in self.__dataset_of_actors:
self.__dataset_of_actors.append(Actor(actor))
genres = row["Genre"].split(",")
for genre in genres:
movie.add_genre(Genre(genre))
if Genre(genre) not in self.__dataset_of_genres:
self.__dataset_of_genres.append(Genre(genre))
movie.runtime_minutes = int(row["Runtime (Minutes)"])
try:
movie.external_rating = float(row["Rating"])
except ValueError:
pass
try:
movie.rating_votes = int(row["Votes"])
except ValueError:
pass
try:
movie.revenue_in_millions = float(row["Revenue (Millions)"])
except ValueError:
pass
try:
movie.metascore = int(row["Metascore"])
except ValueError:
pass
self.__dataset_of_movies.append(movie)
# title = row['Title']
# release_year = int(row['Year'])
# print(f"Movie {index} with title: {title}, release year {release_year}")
index += 1
def test_init(genre):
assert genre.genre_name == 'Drama'
genre1 = Genre("Comedy")
assert repr(genre1) == "<Genre Comedy>"
genre2 = Genre("")
assert genre2.genre_name is None
genre3 = Genre(42)
assert genre3.genre_name is None
assert repr(genre2) == "<Genre None>"
assert repr(genre3) == "<Genre None>"
def test_preference_by_preference():
user = User("Trump", "twitterking")
user.add_preference(Genre("Action"))
user.add_preference(Genre("Sci-Fi"))
assert user.preference.sort()==recommend.get_user_preference(user).sort()
indicator = 0
for movie in recommend.get_recommended_watch_list(user):
for genre in movie.genres:
if genre in recommend.get_user_preference(user):
indicator += 1
assert indicator > 0 # all movie is linked to preference
indicator = 0
def test_filter_by_list_of_genres():
filename = 'datafiles/Data1000Movies.csv'
movie_file_reader = MovieFileCSVReader(filename)
movie_file_reader.read_csv_file()
genre = [Genre("Action"), Genre("Crime"), Genre("Mystery")]
movie_file_reader.filter_by_genre(genre)
assert len(movie_file_reader.movies_filtered_by_genre) == 3
assert movie_file_reader.movies_filtered_by_genre == [
Movie("Salt", 2010),
Movie("Jack Reacher", 2012),
Movie("Escape Plan", 2013)
]
def test_hash():
genre1 = Genre("Comedy")
genre2 = Genre("Comedy")
assert hash(genre1) == hash(genre2)
genre2 = Genre("Comedz")
assert hash(genre1) != hash(genre2)
dict1 = dict()
dict1[genre1] = genre2
assert dict1[genre1] == genre2
assert repr(dict1[genre1]) == "<Genre Comedz>"
genre1 = Genre("")
genre2 = Genre(7)
dict1[genre1] = genre2
assert dict1[genre1] == genre2
assert repr(dict1[genre1]) == "<Genre None>"
def test_eq(self):
genre1 = Genre("Horror")
genre2 = Genre("")
genre3 = Genre("Horror")
genre4 = Genre(1)
assert genre1.__eq__(genre2) == False
assert genre1.__eq__(genre3) == True
assert genre2.__eq__(genre4) == False
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
index = 0
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
self.__dataset_of_movies.append(Movie(title, release_year))
print(f"Movie {index} with title: {title}, release year {release_year}")
actors = row['Actors'].split(',')
temp_director = Director(row['Director'])
genres = row['Genre'].split(',')
for a in actors:
temp_actor = Actor(a.strip())
if temp_actor not in self.__dataset_of_actors:
self.__dataset_of_actors.append(temp_actor)
if temp_director not in self.__dataset_of_directors:
self.__dataset_of_directors.append(temp_director)
for g in genres:
temp_genre = Genre(g.strip())
if temp_genre not in self.__dataset_of_genres:
self.__dataset_of_genres.append(temp_genre)
index += 1
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
index = 0
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
movie = Movie(title, release_year)
actors1 = row['Actors'].split(",")
actors2 = []
for i in actors1:
actors2.append(Actor(i))
director = Director(row['Director'])
genres1 = row['Genre'].split(",")
genres2 = []
for i in genres1:
genres2.append(Genre(i))
self.__dataset_of_movies.add(movie)
for actor in actors2:
self.__dataset_of_actors.add(actor)
self.__dataset_of_directors.add(director)
for genre in genres2:
self.__dataset_of_genres.add(genre)
index += 1
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
movie = Movie(title, release_year)
movie.votes = row['Votes']
movie.metascore = row['Metascore']
movie.rating = row['Rating']
movie.description = row['Description']
self.__movies.append(movie)
director = Director(row['Director'])
if director not in self.__directors:
self.__directors.append(director)
actors = re.split(", |,", row["Actors"])
for actor_splited in actors:
actor = Actor(actor_splited)
if actor not in self.__actors:
self.__actors.append(actor)
genres = row['Genre'].split(",")
for genre_splited in genres:
genre = Genre(genre_splited)
if genre not in self.__genres:
self.__genres.append(genre)
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
for row in movie_file_reader:
movie = Movie(row['Title'], int(row['Year']))
movie.description = row['Description']
movie.runtime_minutes = int(row['Runtime (Minutes)'])
director = Director(row['Director'])
self.__dataset_of_directors.add(director)
movie.director = director
parsed_genres = row['Genre'].split(',')
for genre_string in parsed_genres:
genre = Genre(genre_string)
self.__dataset_of_genres.add(genre)
movie.add_genre(genre)
parsed_actors = row['Actors'].split(',')
for actor_string in parsed_actors:
actor = Actor(actor_string)
self.__dataset_of_actors.add(actor)
movie.add_actor(actor)
self.__dataset_of_movies.append(movie)
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
movie = Movie(title, release_year)
self.__dataset_of_movies.append(movie)
actors = row["Actors"]
actors = actors.split(",")
for actor in actors:
actor = Actor(actor)
movie.add_actor(actor)
if actor not in self.__dataset_of_actors:
self.__dataset_of_actors.append(actor)
director = Director(row["Director"])
movie.director = director
if director not in self.__dataset_of_directors:
self.__dataset_of_directors.append(director)
genres = row["Genre"]
genres = genres.split(",")
for genre in genres:
genre = Genre(genre)
movie.add_genre(genre)
if genre not in self.__dataset_of_genres:
self.__dataset_of_genres.append(genre)
movie.description = row["Description"]
movie.runtime_minutes = row["Runtime (Minutes)"]
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
# Rank,Title,Genre,Description,Director,Actors,Year,Runtime (Minutes),Rating,Votes,Revenue (Millions),Metascore
movie_file_reader = csv.DictReader(csvfile)
index = 0
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
self.__dataset_of_movies.append(Movie(title, release_year))
actors = [
Actor(actor.strip()) for actor in row['Actors'].split(",")
]
for actor in actors:
if actor not in self.__dataset_of_actors:
self.__dataset_of_actors.append(actor)
director = Director(row['Director'])
if director not in self.__dataset_of_directors:
self.__dataset_of_directors.append(director)
genres = [
Genre(genre.strip()) for genre in row['Genre'].split(",")
]
for genre in genres:
if genre not in self.__dataset_of_genres:
self.__dataset_of_genres.append(genre)
# print(f"Movie {index} with title: {title}, release year {release_year}")
index += 1
def read_csv_file(self):
with open(self.__file_name, mode='r', encoding='utf-8-sig') as csvfile:
movie_file_reader = csv.DictReader(csvfile)
for row in movie_file_reader:
title = row['Title']
release_year = int(row['Year'])
movie = Movie(title, release_year)
self.__dataset_of_movies.append(movie)
actors = row['Actors'].split(",")
for actor_full_name in actors:
actor = Actor(actor_full_name)
if actor not in self.__dataset_of_actors:
self.__dataset_of_actors.append(actor)
director = Director(row['Director'])
if director not in self.__dataset_of_directors:
self.__dataset_of_directors.append(director)
genres = row['Genre'].split(",")
for genre in genres:
genre_type = Genre(genre)
if genre_type not in self.__dataset_of_genres:
self.__dataset_of_genres.append(genre_type)