def memory_tune_config(config, dataset):
fits_in_memory = False
raw_config = merge_with_defaults(config)
training_set_metadata = get_trainingset_metadata(raw_config, dataset)
modified_hyperparam_search_space = copy.deepcopy(
raw_config[HYPEROPT]["parameters"])
params_to_modify = RANKED_MODIFIABLE_PARAM_LIST[get_model_name(raw_config)]
param_list = list(params_to_modify.keys())
current_param_values = {}
max_memory = get_machine_memory()
while param_list is not None:
# compute memory utilization
current_param_values = get_new_params(
current_param_values, modified_hyperparam_search_space,
params_to_modify)
temp_config = sub_new_params(raw_config, current_param_values)
if compute_memory_usage(temp_config,
training_set_metadata) < max_memory:
fits_in_memory = True
break
# check if we have exhausted tuning of current param (e.g. we can no longer reduce the param value)
param, min_value = param_list[0], params_to_modify[param_list[0]]
if param in modified_hyperparam_search_space.keys():
param_space = modified_hyperparam_search_space[param]["space"]
if param_space == "choice":
if (len(modified_hyperparam_search_space[param]["categories"])
> 2 and modified_hyperparam_search_space[param]
["categories"][-2] > min_value):
modified_hyperparam_search_space[param][
"categories"] = modified_hyperparam_search_space[
param]["categories"][:-1]
else:
param_list.pop(0) # exhausted reduction of this parameter
else:
# reduce by 10%
upper_bound, lower_bound = (
modified_hyperparam_search_space[param]["upper"],
modified_hyperparam_search_space[param]["lower"],
)
reduction_val = (upper_bound - lower_bound) * 0.1
new_upper_bound = upper_bound - reduction_val
if (new_upper_bound
) > lower_bound and new_upper_bound > min_value:
modified_hyperparam_search_space[param][
"upper"] = new_upper_bound
else:
param_list.pop(0) # exhausted reduction of this parameter
else:
param_list.pop(0) # param not in hyperopt search space
modified_config = copy.deepcopy(config)
modified_config[HYPEROPT]["parameters"] = modified_hyperparam_search_space
return modified_config, fits_in_memory
def train_with_config(
dataset: Union[str, pd.DataFrame, dd.core.DataFrame],
config: dict,
output_directory: str = OUTPUT_DIR,
**kwargs,
) -> AutoTrainResults:
"""
Performs hyperparameter optimization with respect to the given config
and selects the best model.
# Inputs
:param dataset: (str) filepath to dataset.
:param config: (dict) optional Ludwig configuration to use for training, defaults
to `create_auto_config`.
:param output_directory: (str) directory into which to write results, defaults to
current working directory.
# Returns
:return: (AutoTrainResults) results containing hyperopt experiments and best model
"""
_ray_init()
model_name = get_model_name(config)
hyperopt_results = _train(config,
dataset,
output_directory=output_directory,
model_name=model_name,
**kwargs)
# catch edge case where metric_score is nan
# TODO (ASN): Decide how we want to proceed if at least one trial has
# completed
for trial in hyperopt_results.ordered_trials:
if np.isnan(trial.metric_score):
warnings.warn(
"There was an error running the experiment. "
"A trial failed to start. "
"Consider increasing the time budget for experiment. ")
experiment_analysis = hyperopt_results.experiment_analysis
return AutoTrainResults(experiment_analysis)