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 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:
rank = row['Rank']
# make movie from data
movie = Movie(row['Title'], int(row['Year']))
movie.description = row['Description']
movie.runtime_minutes = int(row['Runtime (Minutes)'])
movie.external_rating = float(
row['Rating']) if row['Rating'] != "N/A" else None
movie.rating_votes = int(
row['Votes']) if row['Votes'] != "N/A" else None
movie.revenue = float(
row['Revenue (Millions)']
) if row['Revenue (Millions)'] != "N/A" else None
movie.metascore = int(
row['Metascore']) if row['Metascore'] != "N/A" else None
director = Director(row['Director'])
actors = row['Actors'].split(",")
genres = row['Genre'].split(",")
movie.director = director
self._directors.add(director)
for actor in actors:
actor = Actor(actor)
movie.add_actor(actor)
self._actors.add(actor)
for genre in genres:
genre = Genre(genre)
movie.add_genre(genre)
self._genres.add(genre)
self.dataset_of_movies.add(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)
self.__dataset_of_movies = list()
self.__dataset_of_actors = list()
self.__dataset_of_directors = list()
self.__dataset_of_genres = list()
index = 0
for row in movie_file_reader:
title = row['Title'].strip() # stripping to safe
release_year = int(row['Year'])
actor_full_name_list = get_list_from_comma_string(
row['Actors'])
director_full_name = row['Director'].strip(
) # stripping to safe
genre_name_list = get_list_from_comma_string(row['Genre'])
#- other things
rank = int(row['Rank'])
description = row['Description']
runtime_minutes = int(row['Runtime (Minutes)'])
external_rating = float(row['Rating'])
external_rating_votes = int(row['Votes'])
# These require try/except because some values are N/A's (preferably all would but it's SUPER ugly code)
try:
revenue = float(row['Revenue(Millions)'])
except:
revenue = None
try:
metascore = int(row['Metascore'])
except:
metascore = None
#-------- Make Actor, Director and Genre Objects
actor_object_list = [
Actor(actor_full_name)
for actor_full_name in actor_full_name_list
]
director_object = Director(director_full_name)
genre_object_list = [
Genre(genre_name) for genre_name in genre_name_list
]
#-------- Create and set up Movie Object
movie_object = Movie(title, release_year)
movie_object.actors = actor_object_list # thanks to my setter implementation
movie_object.director = director_full_name
movie_object.genres = genre_object_list # ^ ditto
movie_object.release_year = release_year
#- other things
movie_object.description = description
movie_object.runtime_minutes = runtime_minutes
movie_object.external_rating = external_rating
movie_object.external_rating_votes = external_rating_votes
if revenue != None:
movie_object.revenue = revenue
if metascore != None:
movie_object.metascore = metascore
#-------- Take all the above information, and add to datasets
self.__dataset_of_movies.append(
movie_object
) # the assumption is that each row in the csv is a unique movie
# I could create a function that adds unique things to lists only, nvm
for actor_object in actor_object_list:
if actor_object not in self.__dataset_of_actors:
self.__dataset_of_actors.append(actor_object)
if director_object not in self.__dataset_of_directors:
self.__dataset_of_directors.append(director_object)
for genre_object in genre_object_list:
if genre_object not in self.__dataset_of_genres:
self.__dataset_of_genres.append(genre_object)
index += 1
# To test my assigmnent, run the following lines of code (I have copy and pasted these in my test_all.py file too)
#movie_file_csv_reader_object = MovieFileCSVReader(r"C:\Users\Nathan Longhurst\OneDrive - The University of Auckland\b Comp235\Assignment\GitHub Clone (Current)\CS235FlixSkeleton\datafiles\Data1000Movies.csv")
#unclean_dict = movie_file_csv_reader_object.check_csv_file()
#movie_file_csv_reader_object.clean_csv_file(unclean_dict)
