syndi.task.Task

class syndi.task.Task(task_id=None, train_dataset=None, test_dataset=None, target=None, path_to_generator=None, sampling_method_id=None, pycaret_model=None, run_num=None, output_dir=None, is_regression=False, regression_bins=5)

A class that stores the configurations to a prediction task.

__init__(task_id=None, train_dataset=None, test_dataset=None, target=None, path_to_generator=None, sampling_method_id=None, pycaret_model=None, run_num=None, output_dir=None, is_regression=False, regression_bins=5)

Create a task configuration object from a list of settings. :param task_id: an identifier for the task. :type task_id: str :param train_dataset: the path where train dataset csv is stored :type train_dataset: str :param test_dataset: the path where test dataset csv is stored :type test_dataset: str :param target: the name of the target column in train_dataset and test_dataset :type target: str :param path_to_generator: the path where the generator is stored :type path_to_generator: str :param sampling_method_id: unique sampling method id: “uniform” , “original”, or “baseline” :type sampling_method_id: str :param pycaret_model: the pycaret classifier ID, this classifier will be trained and tested :type pycaret_model: str :param run_num: the number of runs for the classifier and synthetic data generator. :type run_num: int :param is_regression: perform regression to predict target (default is classification) :type is_regression: bool

Methods

__init__([task_id, train_dataset, …])	Create a task configuration object from a list of settings.
load(file_path)
save_as(file_path)	Save the task configurations to the given address.

Attributes

is_regression
output_dir
path_to_generator
pycaret_model
regression_bins
run_num
sampling_method_id
target
task_id
test_dataset
train_dataset

previous

syndi.task.get_sample_method_ids

next

syndi.task.Task.save_as