def execute(download=True):
res = reset_database(download)
# Conexiones a todas las bases de datos, para ver que incluye el resultado descomentar la siguiente lInea
# pprint(res)
autorizados = connect(res[0][0], res[0][1])
flota = connect(res[1][0], res[1][1])
# 1. CORRECCION DE ELEMENTOS ERRoNEOS
coches_no(flota)
suprimir_no(flota)
coches_no(flota)
# 2. OPERACIONES flota
documentos_disponibles(flota)
tiempo_licencias(flota)
mostrar_10_documentos(flota)
media_obtencion_licencias(flota)
# 3. OPERACIONES autorizados
autorizados_combustible(autorizados)
creacion_vehiculos(autorizados)
# 4. OPERACIONES vehiculos
vehiculos = connect(res[0][0], 'vehiculos')
vehiculos_por_marca(vehiculos)
aplanado_modelos(vehiculos)
vehiculos_aplanado = connect(res[0][0], 'vehiculos_aplanado')
actualizacion_vehiculos(vehiculos)
mostrar_1_documento(vehiculos)
limpieza_modelos_vehiculos(vehiculos)
mostrar_10_documentos(vehiculos)
documentos_disponibles(autorizados)
vehiculo_mas_comprado(vehiculos_aplanado)
def execute():
res = reset_dataset()
coll = connect(res[0], res[1])
ej1(coll)
ej2(coll)
ej3(coll)
coll2 = connect('clase', 'datasetaplanado')
ej4(coll2)
ej5(coll2)
ej6(coll2)
ej7(coll2)
def ej3(collection):
collection.aggregate([
{
'$unwind': '$grades'
},
{
'$project': {
'_id': 0,
'building': "$address.building",
'street': "$address.street",
'zipcode': '$address.zipcode',
'borough': 1,
'cuisine': 1,
'date': '$address.date',
'grade': '$grades.grade',
'score': '$grades.score',
'name': 1,
'restaurant_id': 1,
},
},
{
'$out': 'datasetaplanado'
},
])
print(
str(connect('clase', 'datasetaplanado').count({})) + " documento/s\n")
def taxi_download(download=True):
"""
Donwload taxi files
:param download: True to download data, False to use downloaded datasets
:return: list of tuples ('database', 'collection') imported
"""
csv_paths = dict()
json_paths = dict()
csv_links = dict({
'autorizados':
'https://datos.madrid.es/egob/catalogo/207347-1-taxi-modelo-vehiculos.csv',
'flota':
'https://datos.madrid.es/egob/catalogo/300226-0-taxi-flota-diaria.csv',
})
# Download and parse csv to json files
for key, csv_link in csv_links.items():
if download:
json_path = csv_to_json(download_csv(csv_link))
else:
json_path = get_json_path(
os.path.basename(csv_link).replace('csv', 'json'))
json_paths[key] = json_path
# Bulk Import of json files
for key, json_path in json_paths.items():
c = connect('practica', key)
c.drop()
bulk_file_import(c, json_path)
return [('practica', key) for key in json_paths.keys()]
def execute():
coll = connect('clase', 'arts')
reset_arts(coll)
ej1(coll)
ej2(coll)
ej3(coll)
ej2(coll)
ej4(coll)
ej5(coll)
def incidences_download():
"""
Dataset of incidences downloader
:return: list of tuples ('database', 'collection') imported
"""
link_json = 'https://datosabiertos.jcyl.es/web/jcyl/risp/es/transporte/incidencias_carreteras/1284212099243.json'
json_path = download_json(link_json)
c = connect('datos_abiertos', 'incidencias')
c.drop()
bulk_file_import(c, json_path)
return [('datos_abiertos', 'incidencias')]
def twitter_download():
"""
Dataset of twitter downloader
:return: list of tuples ('database', 'collection') imported
"""
link_zip = 'https://drive.google.com/uc?export=download&id=1aqZUFkAm1EW9H8skKnhfAeAhIO28TZjl'
json_path = get_json_path('twitter.json')
zip_path = download_zip(link_zip)
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
zip_ref.extractall(get_json_path())
c = connect('clase', 'twitter')
c.drop()
bulk_file_mongoimport(c, json_path)
return [('clase', 'twitter')]
def full_primer_dataset_download():
"""
Dataset of full_primer-dataset downloader
:return: list of tuples ('database', 'collection') imported
"""
link_zip = 'https://drive.google.com/uc?export=download&id=1WswYNzSv-R7ultIs7CB-xsO9WepT-YQT'
json_path = get_json_path('full_primer-dataset.json')
zip_path = download_zip(link_zip)
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
zip_ref.extractall(get_json_path())
c = connect('clase', 'primer')
c.drop()
bulk_file_mongoimport(c, json_path)
return [('clase', 'primer')]
def restaurants_download():
"""
Dataset of restaurants downloader
:return: list of tuples ('database', 'collection') imported
"""
link_zip = 'https://drive.google.com/uc?export=download&id=1qUgzM5JHvnH2d1Ayh8oES9BIZPj03Nol'
json_path = get_json_path('restaurants.json')
zip_path = download_zip(link_zip)
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
zip_ref.extractall(get_json_path())
c = connect('clase', 'restaurant')
c.drop()
bulk_file_mongoimport(c, json_path)
return [('clase', 'restaurant')]
def execute():
res = reset_dataset()
coll = connect(res[0], res[1])
ej1(coll)
ej2(coll)
def reset_dataset():
connect('clase', 'datasetaplanado').drop()
return full_primer_dataset_download()[0]
def reset_database(download=True):
mas_info = 'https://datos.gob.es/en/catalogo/l01280796-taxi-tarifas-suplementos-municipios-paradas-eventuales-regimen-de-descanso-y-duracion-del-servicio'
connect('practica', 'vehiculos').drop()
connect('practica', 'vehiculos_aplanado').drop()
return taxi_download(download)
def execute():
coll = connect('clase', 'inventory')
reset_dataset(coll)
ej1(coll)
ej2_1(coll)
ej2_2(coll)
