def _create_default_config(dataset: Union[str, dd.core.DataFrame, pd.DataFrame,
DatasetInfo],
target_name: str = None,
time_limit_s: Union[int, float] = None) -> dict:
"""
Returns auto_train configs for three available combiner models.
Coordinates the following tasks:
- extracts fields and generates list of FieldInfo objects
- gets field metadata (i.e avg. words, total non-null entries)
- builds input_features and output_feautures section of config
- for each combiner, adds default training, hyperopt
- infers resource constraints and adds gpu and cpu resource allocation per
trial
# Inputs
:param dataset: (str) filepath to dataset.
:param target_name: (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) dictionaries contain auto train config files for all available
combiner types
"""
_ray_init()
resources = get_available_resources()
experiment_resources = allocate_experiment_resources(resources)
dataset_info = dataset
if not isinstance(dataset, DatasetInfo):
dataset_info = get_dataset_info(dataset)
input_and_output_feature_config = get_features_config(
dataset_info.fields, dataset_info.row_count, resources, target_name)
model_configs = {}
for model_name, path_to_defaults in model_defaults.items():
default_model_config = load_yaml(path_to_defaults)
default_model_config.update(input_and_output_feature_config)
default_model_config['hyperopt']['executor'].update(
experiment_resources)
default_model_config['hyperopt']['executor'][
'time_budget_s'] = time_limit_s
model_configs[model_name] = default_model_config
return model_configs
def train_with_config(
dataset: Union[str, pd.DataFrame, dd.core.DataFrame],
config: dict,
output_directory: str = OUTPUT_DIR,
random_seed: int = default_random_seed,
**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.
: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
# Returns
:return: (AutoTrainResults) results containing hyperopt experiments and best model
"""
_ray_init()
model_type = get_model_type(config)
hyperopt_results = _train(config,
dataset,
output_directory=output_directory,
model_name=model_type,
random_seed=random_seed,
**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)
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 = config[COMBINER][TYPE]
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)
def _create_default_config(
dataset: Union[str, dd.core.DataFrame, pd.DataFrame, DatasetInfo],
target_name: Union[str, List[str]] = None,
time_limit_s: Union[int, float] = None,
) -> dict:
"""Returns auto_train configs for three available combiner models. Coordinates the following tasks:
- extracts fields and generates list of FieldInfo objects
- gets field metadata (i.e avg. words, total non-null entries)
- builds input_features and output_features section of config
- for each combiner, adds default training, hyperopt
- infers resource constraints and adds gpu and cpu resource allocation per
trial
# Inputs
:param dataset: (str) filepath to dataset.
:param target_name: (str, List[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) dictionaries contain auto train config files for all available
combiner types
"""
_ray_init()
resources = get_available_resources()
experiment_resources = allocate_experiment_resources(resources)
dataset_info = dataset
if not isinstance(dataset, DatasetInfo):
dataset_info = get_dataset_info(dataset)
input_and_output_feature_config = get_features_config(
dataset_info.fields, dataset_info.row_count, resources, target_name)
model_configs = {}
# read in base config and update with experiment resources
base_automl_config = load_yaml(BASE_AUTOML_CONFIG)
base_automl_config["hyperopt"]["executor"].update(experiment_resources)
base_automl_config["hyperopt"]["executor"]["time_budget_s"] = time_limit_s
if time_limit_s is not None:
base_automl_config["hyperopt"]["sampler"]["scheduler"][
"max_t"] = time_limit_s
base_automl_config.update(input_and_output_feature_config)
model_configs["base_config"] = base_automl_config
# read in all encoder configs
for feat_type, default_configs in encoder_defaults.items():
if feat_type not in model_configs.keys():
model_configs[feat_type] = {}
else:
for encoder_name, encoder_config_path in default_configs.items():
model_configs[feat_type][encoder_name] = load_yaml(
encoder_config_path)
# read in all combiner configs
model_configs["combiner"] = {}
for combiner_type, default_config in combiner_defaults.items():
combiner_config = load_yaml(default_config)
model_configs["combiner"][combiner_type] = combiner_config
return model_configs