def create_auto_config(
dataset: Union[str, pd.DataFrame, dd.core.DataFrame, DatasetInfo],
target: Union[str, List[str]],
time_limit_s: Union[int, float],
tune_for_memory: bool,
user_config: Dict = None,
) -> dict:
"""Returns an auto-generated Ludwig config with the intent of training the best model on given given dataset /
target in the given time limit.
# Inputs
:param dataset: (str, pd.DataFrame, dd.core.DataFrame, DatasetInfo) data source to train over.
:param target: (str, List[str]) name of target feature
:param time_limit_s: (int, float) total time allocated to auto_train. acts
as the stopping parameter
:param tune_for_memroy: (bool) refine hyperopt search space for available
host / GPU memory
# Return
:return: (dict) selected model configuration
"""
default_configs = _create_default_config(dataset, target, time_limit_s)
model_config = _model_select(dataset, default_configs, user_config)
if tune_for_memory:
if ray.is_initialized():
model_config, _ = ray.get(
ray.remote(num_cpus=1)(memory_tune_config).remote(
model_config, dataset))
else:
model_config, _ = memory_tune_config(model_config, dataset)
return model_config
def create_auto_config(
dataset: Union[str, pd.DataFrame, dd.core.DataFrame, DatasetInfo],
target: str,
time_limit_s: Union[int, float],
tune_for_memory: bool,
) -> dict:
"""
Returns an auto-generated Ludwig config with the intent of training
the best model on given given dataset / target in the given time
limit.
# Inputs
:param dataset: (str) filepath to dataset.
:param target: (str) name of target feature
:param time_limit_s: (int, float) total time allocated to auto_train. acts
as the stopping parameter
# Return
:return: (dict) selected model configuration
"""
default_configs = _create_default_config(dataset, target, time_limit_s)
model_config = _model_select(default_configs)
if tune_for_memory:
if ray.is_initialized():
model_config, _ = ray.get(
ray.remote(num_cpus=1)(memory_tune_config).remote(
model_config, dataset))
else:
model_config, _ = memory_tune_config(model_config, dataset)
return model_config
def create_auto_config(
dataset: Union[str, pd.DataFrame, dd.core.DataFrame, DatasetInfo],
target: Union[str, List[str]],
time_limit_s: Union[int, float],
tune_for_memory: bool,
user_config: Dict = None,
random_seed: int = default_random_seed,
use_reference_config: bool = False,
) -> dict:
"""Returns an auto-generated Ludwig config with the intent of training the best model on given given dataset /
target in the given time limit.
# Inputs
:param dataset: (str, pd.DataFrame, dd.core.DataFrame, DatasetInfo) data source to train over.
:param target: (str, List[str]) name of target feature
:param time_limit_s: (int, float) total time allocated to auto_train. acts
as the stopping parameter
:param tune_for_memory: (bool) refine hyperopt search space for available
host / GPU memory
:param user_config: (dict) override automatic selection of specified config items
:param random_seed: (int, default: `42`) a random seed that will be used anywhere
there is a call to a random number generator, including
hyperparameter search sampling, as well as data splitting,
parameter initialization and training set shuffling
:param use_reference_config: (bool) refine hyperopt search space by setting first
search point from reference model config, if any
# Return
:return: (dict) selected model configuration
"""
default_configs = _create_default_config(dataset, target, time_limit_s,
random_seed)
model_config, model_category, row_count = _model_select(
dataset, default_configs, user_config, use_reference_config)
if tune_for_memory:
if ray.is_initialized():
resources = get_available_resources() # check if cluster has GPUS
if resources["gpu"] > 0:
model_config, fits_in_memory = ray.get(
ray.remote(num_gpus=1, num_cpus=1,
max_calls=1)(memory_tune_config).remote(
model_config, dataset, model_category,
row_count))
else:
model_config, fits_in_memory = ray.get(
ray.remote(num_cpus=1)(memory_tune_config).remote(
model_config, dataset, model_category, row_count))
else:
model_config, fits_in_memory = memory_tune_config(
model_config, dataset, model_category, row_count)
if not fits_in_memory:
warnings.warn(
"AutoML with tune_for_memory enabled did not return estimation that model will fit in memory. "
"If out-of-memory occurs, consider setting AutoML user_config to reduce model memory footprint. "
)
return model_config