def loadDetails(catalog, moviesDetailsFile):
"""
Carga cada una de las lineas del archivo de películas.
- Se agrega cada película al catalogo de películas.
- Por cada película se encuentra su productora y por cada
productora, se crea una lista con sus películas
"""
t1_start = process_time() #tiempo inicial
moviesDetailsFile = cf.data_dir + moviesDetailsFile
input_file = csv.DictReader(open(moviesDetailsFile, encoding="utf-8-sig"),
delimiter=";")
for movie in input_file:
model.addMovie(catalog, movie)
producers = movie['production_companies'].split(",")
# countries = movie['production_countries'].split(",")
for producer in producers:
model.addMovietoMovieFilmProducer(catalog, producer.strip(), movie)
# for country in countries:
# model.addMovietoCountry(catalog, country.strip(), movie)
for gender in genres:
model.addMovietoGender(catalog, gender.strip(), movie)
t1_stop = process_time() #tiempo final
print("Tiempo de ejecución ", t1_stop - t1_start, " segundos")
def loadData(catalog, movies_file1, movies_file2, n: int = "ALL"):
"""
Carga cada una de las lineas del archivo de libros.
- Se agrega cada libro al catalogo de libros
- Por cada libro se encuentran sus autores y por cada
autor, se crea una lista con sus libros>
"""
dialect = csv.excel()
dialect.delimiter = ";"
movies_file1 = cf.data_dir + movies_file1
movies_file2 = cf.data_dir + movies_file2
input_file1 = csv.DictReader(open(movies_file1, encoding="utf-8-sig"),
dialect=dialect)
input_file2 = csv.DictReader(open(movies_file2, encoding="utf-8-sig"),
dialect=dialect)
count = 0
for movie1, movie2 in zip(input_file1, input_file2):
if (n != "ALL") and (count > n):
break
movie1.update(
movie2) # se que es severo machetazo :V, lo sugirio erich
model.addMovie(catalog, movie1)
count += 1
def loadDetails(catalog, fileD, sep=';'):
t1_start = process_time() # tiempo inicial
dialect = csv.excel()
dialect.delimiter = sep
with open(fileD, encoding="utf-8-sig") as csvfile:
input_file = csv.DictReader(csvfile, dialect=dialect)
for movie in input_file:
model.addMovie(catalog, movie)
productora = movie['production_companies']
if productora == 'none':
pass
else:
model.addProductora(catalog, movie)
pais = movie['production_countries']
if pais == 'none':
pass
else:
model.addPais(catalog, movie)
generos = movie['genres'].split('|')
if len(generos) == 0:
pass
for genre in generos:
genre = genre.lower()
model.addGenero(catalog, movie, genre)
t1_stop = process_time() # tiempo final
print("Tiempo de ejecución ", t1_stop - t1_start, " segundos")
def loadData(catalog, detailsfile, castingfile):
"""
Carga cada una de las lineas del archivo de libros.
- Se agrega cada libro al catalogo de libros
- Por cada libro se encuentran sus autores y por cada
autor, se crea una lista con sus libros
"""
t1_start = process_time() #tiempo inicial
dialect = csv.excel()
dialect.delimiter = ";"
detailsfile = cf.data_dir + detailsfile
#input_file = #csv.DictReader(open(detailsfile,encoding="utf-8"), dialect=dialect)
input_file = csv.DictReader(open(detailsfile, encoding="utf-8-sig"),
dialect=dialect)
castingfile = cf.data_dir + castingfile
input_file2 = csv.DictReader(open(castingfile, encoding="utf-8"),
dialect=dialect)
#i = 0
#j = 0
for movie, casting in zip(input_file, input_file2):
#i += 1
model.addMovie(catalog, movie)
model.addCasting(catalog, casting, movie)
#print(i)
t1_stop = process_time()
#print(t1_stop)
"""for casting in input_file2:
j += 1
model.addCasting(catalog,casting)
print(j)
t1_stop = process_time() #tiempo final"""
print("Tiempo de ejecución ", t1_stop - t1_start, " segundos")
def loadMovies(catalog, moviesfile):
"""
Carga cada una de las lineas del archivo de películas.
- Se agrega cada película al catalogo de películas
"""
moviesfile = cf.data_dir + moviesfile
dialect = csv.excel()
dialect.delimiter = ';'
try:
with open(moviesfile, encoding="utf-8-sig") as csvfile:
row = csv.DictReader(csvfile, dialect=dialect)
for movie in row:
lst = model.nueva_lista("ARRAY_LIST")
model.addMovie(catalog, movie)
producers = movie[
'production_companies'] # Se obtienen las productoras
countries = movie[
'production_countries'] # Se obtienen los países
release_date = movie['release_date']
year = release_date.split("/")
model.addMovieProducer(catalog, producers, movie)
model.añanir_pelicula(lst, movie['title'])
model.añanir_pelicula(lst, year[-1])
model.añanir_pelicula(lst, movie['id'])
model.addCountry(catalog, countries, lst)
genre = movie['genres']
genre_sep = genre.split('|')
for genero in genre_sep:
model.addMovieGenre(catalog, genero, movie)
except:
print("Hubo un error en la carga de archivos")
def loadPeliculas(lst, file):
dialect = csv.excel()
dialect.delimiter = ";"
try:
with open(cf.data_dir + file, encoding="utf-8") as csvfile:
row = csv.DictReader(csvfile, dialect=dialect)
for elemento in row:
## Eliminar la información que no fue solicitada para el laboratorio
elemento.pop("id")
elemento.pop("budget")
elemento.pop("genres")
elemento.pop("imdb_id")
elemento.pop("original_language")
elemento.pop("overview")
elemento.pop("popularity")
elemento.pop("production_companies")
elemento.pop("production_countries")
elemento.pop("revenue")
elemento.pop("runtime")
elemento.pop("status")
elemento.pop("tagline")
elemento.pop("original_title")
elemento.pop("production_companies_number")
elemento.pop("spoken_languages_number")
elemento.pop("production_countries_number")
model.addMovie(lst, elemento)
except:
print("Hubo un error con la carga del archivo")
return lst
def loadMovies(catalog, moviesfile):
moviesfile= cf.data_dir + moviesfile
input_file= cvs.DictReader(open(moviesfile))
for movies in input_file:
model.addMovie(catalog, movie)
directors= movie["director"].split(",")
for director in directors:
model.addMovieDirector(catalog, director.strip(), movie)
def loadPeliculas(lst, fileC):
fileC = cf.data_dir + fileC
input_file = csv.DictReader(open(fileC, encoding="utf-8"))
for Movie in input_file:
model.addMovie(lst, Movie)
Companys = Movie['production_companies'].split(";")
for company in Companys:
model.addMoviesCompany(lst, company.strip(), Movie)
def loadMovie(catalog, moviesfile):
moviesfile = cf.data_dir + moviesfile
dialect = csv.excel()
dialect.delimiter = ";"
input_file = csv.DictReader(open(moviesfile, encoding="utf-8"),
dialect=dialect)
for movie in input_file:
model.addMovie(catalog, movie)
def loadcasting(lst, fileC):
fileC = cf.data_dir + fileC
input_file = csv.DictReader(open(fileC, encoding="utf-8"), delimiter=";")
for Movie in input_file:
model.addMovie(lst, Movie)
directores = Movie['director_name'].split(";")
for director in directores:
model.addMoviesDirector(lst, director.strip(), Movie)
def loadData(catalogo, detailsfile, castingfile):
detailsfile = cf.data_dir + detailsfile
input_file = csv.DictReader(open(detailsfile))
for movie in input_file:
model.addMovie(catalogo, movie)
companies = movie['production_companies'].split(
",") # Se obtienen las compañias productoras
for company in companies:
model.addCompany(catalogo, company.strip(), movie)
def loadmoviesdetails(catalog, moviesdetails):
"""
Carga en el catalogo los tags a partir de la informacion
del archivo de etiquetas
"""
moviesdetails = cf.data_dir + moviesdetails
input_file = csv.DictReader(open(moviesdetails, encoding='utf-8-sig'), delimiter=";")
for movie in input_file:
model.addMovie(catalog, movie)
model.addProductionCompanie(catalog, movie["production_companies"], movie)
model.add_genre(catalog,movie["genres"],movie)
model.addCountrie(catalog,movie["production_countries"],movie)
def loadDetails (catalogo,movies_details,sep=";"):
dialect= csv.excel()
dialect.delimiter=sep
with open(movies_details, encoding="utf-8-sig") as csvfile:
spamreader = csv.DictReader(csvfile,dialect=dialect)
for row in spamreader:
model.addMovie(catalogo,row)
model.addCompanyMovie(catalogo,row["production_companies"].lower(),row)
generos = row["genres"].split('|')
for i in generos:
model.addGenreMovie(catalogo, i.lower(), row)
return catalogo
def loadCSVFile(linkC, linkD, data, sep=";"):
dialect = csv.excel()
dialect.delimiter = sep
with open(linkC, encoding="utf-8-sig") as csvfileC, open(
linkD, encoding="utf-8-sig") as csvfileD:
bufferC = csv.DictReader(csvfileC, dialect=dialect)
bufferD = csv.DictReader(csvfileD, dialect=dialect)
cont = 0
for movieC, movieD in zip(bufferC, bufferD):
cont += 1
if cont == elements:
break
model.addMovie(data, movieD, movieC)
def loadData(catalog, detailsfile, castingfile):
"""
Carga los datos de los archivos en el modelo
"""
dialect = csv.excel()
dialect.delimiter = ";"
detailsfile = cf.data_dir + detailsfile
input_file = csv.DictReader(open(detailsfile, encoding='utf-8'),
dialect=dialect)
#open(config.data_dir + archivo, encoding="utf-8") as csvfile:
for details in input_file:
model.addMovie(catalog, details)
producers = details['production_companies'].split(
",") # Se obtienen las productoras
for producer in producers:
model.addMovieProducer(catalog, producer.strip(), details)
genres_peli = details["genres"].split(",")
for genre in genres_peli:
model.AddMovieByGenre(catalog, genre.strip(), details)
countries = details["production_countries"].split(",")
castingfile = cf.data_dir + castingfile
input_c_file = csv.DictReader(open(castingfile, encoding='utf-8'),
dialect=dialect)
#open(config.data_dir + archivo, encoding="utf-8") as csvfile:
for casting in input_c_file:
directors = casting['director_name'].split(
",") # Se obtienen los directores
for director in directors:
model.addMovieDirector(catalog, director.strip(), details, casting)
actor1 = casting["actor1_name"].split(",")
actor2 = casting["actor2_name"].split(",")
actor3 = casting["actor3_name"].split(",")
actor4 = casting["actor4_name"].split(",")
actor5 = casting["actor5_name"].split(",")
for actoruno in actor1:
model.AddMovieByActor(catalog, actoruno.strip(), input_file,
casting)
for actordos in actor2:
model.AddMovieByActor(catalog, actordos.strip(), input_file,
casting)
for actortres in actor3:
model.AddMovieByActor(catalog, actortres.strip(), input_file,
casting)
for actorcuatro in actor4:
model.AddMovieByActor(catalog, actorcuatro.strip(), input_file,
casting)
for actorcinco in actor5:
model.AddMovieByActor(catalog, actorcinco.strip(), input_file,
casting)
def funciones(catalog, lista_unida):
it1 = it.newIterator(lista_unida)
while it.hasNext(it1):
movie = it.next(it1)
model.addMovie(catalog, movie)
companies = movie["production_companies"].split(",")
for company in companies:
model.addMovieCompany(catalog, company, movie)
model.addMovieDirector(catalog, movie["director_name"], movie)
model.addMovieActor(catalog, movie["actor1_name"], movie)
model.addMovieActor(catalog, movie["actor2_name"], movie)
model.addMovieActor(catalog, movie["actor3_name"], movie)
model.addMovieActor(catalog, movie["actor4_name"], movie)
model.addMovieActor(catalog, movie["actor5_name"], movie)
#model.directoresDEactores(catalog)
model.addMovieGenres(catalog, movie["genres"], movie)
model.addMovieCountry(catalog, movie["production_countries"], movie)
def loadData(catalog, Detailsfile, Castingfile):
"""
Carga los datos de los archivos en el modelo
"""
list_unida = lt.newList("ARRAY_LIST", None)
list_details = loadDetails(catalog, Detailsfile)
list_casting = loadCasting(catalog, Castingfile)
it1 = it.newIterator(list_details)
while it.hasNext(it1):
movie = it.next(it1)
model.addMovie(catalog, movie)
it2 = it.newIterator(list_casting)
while it.hasNext(it2):
peli = it.next(it2)
if movie["id"] == peli["id"]:
union = {**movie, **peli}
lt.addLast(list_unida, union)
break
return list_unida
def loadMoviesCasting(catalog, moviesCasting):
moviesCasting = cf.data_dir + moviesCasting
input_file = csv.DictReader(open(moviesCasting))
for director in input_file:
model.addMovie(catalog, director)
def loadMovieDetails(catalog, moviesDetails):
moviesDetails = cf.data_dir + moviesDetails
input_file = csv.DictReader(open(moviesDetails))
for movie in input_file:
model.addMovie(catalog, movie)
