libcity.pipeline.pipeline¶
-
libcity.pipeline.pipeline.hyper_parameter(task=None, model_name=None, dataset_name=None, config_file=None, space_file=None, scheduler=None, search_alg=None, other_args=None, num_samples=5, max_concurrent=1, cpu_per_trial=1, gpu_per_trial=1)[source]¶ Use Ray tune to hyper parameter tune
- Parameters
task (str) – task name
model_name (str) – model name
dataset_name (str) – dataset name
config_file (str) – config filename used to modify the pipeline’s settings. the config file should be json.
space_file (str) – the file which specifies the parameter search space
scheduler (str) – the trial sheduler which will be used in ray.tune.run
search_alg (str) – the search algorithm
other_args (dict) – the rest parameter args, which will be pass to the Config
-
libcity.pipeline.pipeline.objective_function(task=None, model_name=None, dataset_name=None, config_file=None, saved_model=True, train=True, other_args=None, hyper_config_dict=None)[source]¶
-
libcity.pipeline.pipeline.run_model(task=None, model_name=None, dataset_name=None, config_file=None, saved_model=True, train=True, other_args=None)[source]¶ - Parameters
task (str) – task name
model_name (str) – model name
dataset_name (str) – dataset name
config_file (str) – config filename used to modify the pipeline’s settings. the config file should be json.
saved_model (bool) – whether to save the model
train (bool) – whether to train the model
other_args (dict) – the rest parameter args, which will be pass to the Config