openml.evaluations.list_evaluations_setups

openml.evaluations.list_evaluations_setups(function: str, offset: Union[int, NoneType] = None, size: Union[int, NoneType] = None, task: Union[List, NoneType] = None, setup: Union[List, NoneType] = None, flow: Union[List, NoneType] = None, run: Union[List, NoneType] = None, uploader: Union[List, NoneType] = None, tag: Union[str, NoneType] = None, per_fold: Union[bool, NoneType] = None, sort_order: Union[str, NoneType] = None, output_format: str = 'dataframe', parameters_in_separate_columns: bool = False) → Union[Dict, pandas.core.frame.DataFrame]

List all run-evaluation pairs matching all of the given filters and their hyperparameter settings.

Parameters
functionstr

the evaluation function. e.g., predictive_accuracy

offsetint, optional

the number of runs to skip, starting from the first

sizeint, optional

the maximum number of runs to show

tasklist[int], optional

the list of task IDs

setup: list[int], optional

the list of setup IDs

flowlist[int], optional

the list of flow IDs

runlist[int], optional

the list of run IDs

uploaderlist[int], optional

the list of uploader IDs

tagstr, optional

filter evaluation based on given tag

per_foldbool, optional
sort_orderstr, optional

order of sorting evaluations, ascending (“asc”) or descending (“desc”)

output_format: str, optional (default=’dataframe’)

The parameter decides the format of the output. - If ‘dict’ the output is a dict of dict - If ‘dataframe’ the output is a pandas DataFrame

parameters_in_separate_columns: bool, optional (default= False)

Returns hyperparameters in separate columns if set to True. Valid only for a single flow

Returns
dict or dataframe with hyperparameter settings as a list of tuples.