def __init__(self,
session=None,
master="local[*]",
app_name="optimus",
checkpoint=False,
path=None,
file_system="local",
verbose=False,
dl=False,
server=False,
repositories=None,
packages=None,
jars=None,
options=None,
additional_options=None,
enricher_host="localhost",
enricher_port=27017,
queue_url=None,
queue_exchange=None,
queue_routing_key="optimus"):
"""
Transform and roll out
:param master: 'Master', 'local' or ip address to a cluster
:param app_name: Spark app name
:param path: path to the checkpoint folder
:param checkpoint: If True create a checkpoint folder
:param file_system: 'local' or 'hadoop'
:param additional_options:
:param options: Configuration options that are passed to spark-submit.
See `the list of possible options
<https://spark.apache.org/docs/2.1.0/configuration.html#available-properties>`_.
Note that any options set already through PYSPARK_SUBMIT_ARGS will override
these.
:type options: (dict[str,str])
:param repositories: List of additional maven repositories for package lookup.
:type repositories: (list[str])
:param packages: Spark packages that should be installed.
:type packages: (list[str])
:param jars: Full paths to jar files that we want to include to the session.
:type jars: (list[str])
"""
if session is None:
# print("Creating Spark Session...")
# If a Spark session in not passed by argument create it
self.master = master
self.app_name = app_name
if options is None:
options = {}
self.options = options
if packages is None:
packages = []
else:
packages = val_to_list(packages)
self.packages = packages
self.repositories = repositories
if jars is None:
jars = {}
self.jars = jars
self.additional_options = additional_options
self.verbose(verbose)
# Load Avro.
# TODO: if the Spark 2.4 version is going to be used this is not neccesesary.
# Maybe we can check a priori which version fo Spark is going to be used
# self._add_spark_packages(["com.databricks:spark-avro_2.11:4.0.0"])
if dl is True:
self._add_spark_packages(
["databricks:spark-deep-learning:1.5.0-spark2.4-s_2.11"])
self._start_session()
from optimus.dl.models import DL
self.dl = DL()
else:
self._start_session()
if path is None:
path = os.getcwd()
if checkpoint is True:
self._set_check_point_folder(path, file_system)
else:
# If a session is passed by arguments just save the reference
Spark.instance = session
# Initialize Spark
logger.print("""
____ __ _
/ __ \____ / /_(_)___ ___ __ _______
/ / / / __ \/ __/ / __ `__ \/ / / / ___/
/ /_/ / /_/ / /_/ / / / / / / /_/ (__ )
\____/ .___/\__/_/_/ /_/ /_/\__,_/____/
/_/
""")
logger.print(STARTING_OPTIMUS)
if server:
logger.print("Starting Optimus Server...")
s = Server()
s.start()
self.server_instance = s
logger.print(SUCCESS)
self.create = Create()
self.load = Load()
self.read = self.spark.read
self.profiler = Profiler(queue_url=queue_url,
queue_exchange=queue_exchange,
queue_routing_key=queue_routing_key)
self.ml = ML()
self.enricher = Enricher(
op=self,
host=enricher_host,
port=enricher_port,
)
def __init__(self, session=None, master="local[*]", app_name="optimus", checkpoint=False, path=None,
file_system="local",
verbose=False,
server=False,
repositories=None,
packages=None,
jars=None,
driver_class_path=None,
options=None,
additional_options=None,
queue_url=None,
queue_exchange=None,
queue_routing_key="optimus"
):
"""
Transform and roll out
:param master: 'Master', 'local' or ip address to a cluster
:param app_name: Spark app name
:param path: path to the checkpoint folder
:param checkpoint: If True create a checkpoint folder
:param file_system: 'local' or 'hadoop'
:param additional_options:
:param options: Configuration options that are passed to spark-submit.
See `the list of possible options
<https://spark.apache.org/docs/2.4.1/configuration.html#available-properties>`_.
Note that any options set already through PYSPARK_SUBMIT_ARGS will override
these.
:type options: (dict[str,str])
:param repositories: List of additional maven repositories for package lookup.
:type repositories: (list[str])
:param packages: Spark packages that should be installed.
:type packages: (list[str])
:param jars: Full paths to jar files that we want to include to the session.
:type jars: (list[str])
"""
if session is None:
# print("Creating Spark Session...")
# If a Spark session in not passed by argument create it
self.master = master
self.app_name = app_name
if options is None:
options = {}
self.options = options
if packages is None:
packages = []
else:
packages = val_to_list(packages)
self.packages = packages
self.repositories = repositories
# Jars
self.jars = jars
self._add_jars(jars)
# Class Drive Path
self.driver_class_path = driver_class_path
self._add_driver_class_path(driver_class_path)
# Additional Options
self.additional_options = additional_options
self.verbose(verbose)
# Load Avro.
# TODO:
# if the Spark 2.4 version is going to be used this is not neccesesary.
# Maybe we can check a priori which version fo Spark is going to be used
self._add_spark_packages(["com.databricks:spark-avro_2.11:4.0.0"])
def c(files):
return [Path(path + file).as_posix() for file in files]
path = os.path.dirname(os.path.abspath(__file__))
# Add databases jars
self._add_jars(["../jars/RedshiftJDBC42-1.2.16.1027.jar", "../jars/mysql-connector-java-8.0.16.jar",
"../jars/ojdbc7.jar", "../jars/postgresql-42.2.5.jar"])
self._add_driver_class_path(
c(["//jars//RedshiftJDBC42-1.2.16.1027.jar", "//jars//mysql-connector-java-8.0.16.jar",
"//jars//ojdbc7.jar", "//jars//postgresql-42.2.5.jar"]))
self._start_session()
if path is None:
path = os.getcwd()
if checkpoint is True:
self._set_check_point_folder(path, file_system)
else:
# If a session is passed by arguments just save the reference
Spark.instance = Spark().load(session)
# Initialize Spark
logger.print("""
____ __ _
/ __ \____ / /_(_)___ ___ __ _______
/ / / / __ \/ __/ / __ `__ \/ / / / ___/
/ /_/ / /_/ / /_/ / / / / / / /_/ (__ )
\____/ .___/\__/_/_/ /_/ /_/\__,_/____/
/_/
""")
logger.print(STARTING_OPTIMUS)
if server:
logger.print("Starting Optimus Server...")
s = Server()
s.start()
self.server_instance = s
logger.print(SUCCESS)
self.create = Create()
self.load = Load()
self.read = self.spark.read
self.profiler = Profiler(
queue_url=queue_url,
queue_exchange=queue_exchange,
queue_routing_key=queue_routing_key
)
self.ml = ML()
#
self._load_css()
# Set global output as html
self.output("html")