Initialization
- automl.interface. init ( engine = 'dask' , engine_opts = {'dask_scheduler': None} , logger = None , loglevel = None , check_deprecation_warnings = True )
-
Initializes the AutoMLx framework’s execution engine. AutoMLx can work with a variety of parallelization platforms.
Warning
Dask and Spark parallelization frameworks and their options are deprecated and will be removed in version 23.3.0.
- Parameters
-
-
engine ( str ) –
Name of the parallelization framework. Can be one of:
-
'local'
: Use Python’s inbuilt multiprocessing framework. -
'threading'
: Use Python’s inbuilt multithreading framework. -
'dask'
: Use Dask as the distributed compute engine.
Defaults to
'dask'
. -
-
engine_opts ( dict ) –
Options for the parallelization framework. When engine is:
-
'local'
:engine_opts
is of the form{'n_jobs' : val1, 'model_n_jobs' : val2}
, whereval1
is the degree of inter-model parallelism andval2
is the degree of intra-model parallelism. -
'threading'
:engine_opts
is of the form{'n_jobs' : val}
, whereval
is the degree of parallelism. -
'dask'
:engine_opts
is of the form{'dask_scheduler' : val}
, whereval
can be one of-
URI of the dask scheduler (e.g. 127.0.0.1:8786)
-
an already initialized
dask.Client
instance -
None
-
Defaults to
{'dask_scheduler' : None}
. -
-
logger (logging.Logger, str, optional ) –
Logging mode. One of
-
None
: Log to console with specified loglevel (by defaultlogging.WARNING
). -
str : Log to the provided file path and console.
-
logging.Logger
: Use existingLogger
object.
Defaults to
None
. -
-
loglevel (int, optional ) – Log level is derived from the python logging module, and adjusts the logging verbosity in the following increasing order:
logging.CRITICAL < logging.WARNING < logging.INFO < logging.DEBUG
. Defaults toNone
(use logging module’s configuration). Setting the loglevel here does nothing if the root logger already has handlers configured. -
check_deprecation_warnings (bool, optional ) – If true, the deprecation warnings for the package will be checked and displayed; however, it affects the running time of the AutoML pipeline.
-