Benchmark

class pymultifracs.Benchmark(signal_gen_grid, signal_param_grid, estimation_grid, estimation_param_grid, folder='.')

Compute and plot benchmarks, varying the models and analysis parameters.

Attributes:

signal_gen_griddict[str, Callable]

Dictionary associating a name to a function that samples time series.

signal_param_griddict[str, ndarray of Any] | dict[str, dict[str, ndarray of Any]]

Dictionary associating to each signal generating function the dictionary associating to each signal parameter the array of the values that the parameter will take. May be empty.

estimation_griddict[str, Callable]

Dictionary associating to an estimation method’s name its callable function.

estimation_param_griddict[str, dict[str, ndarray of Any]]

Dictionary associating to each estimation method the dictionary of estimation parameters. May be empty.

folderstr | Path

Path to the folder which will contain the output files.

resultsDataFrame

Dataframe collecting the outcomes of the estimation on the generated signals.

compute_benchmark(n_jobs=1, save_load_signals=False, save=False)

Compute the benchmark.

Parameters:

n_jobsint

Number of jobs that joblib will start in parallel. Each job handles a different signal configuration.

save_load_signalsbool

Whether to save the signals, and load them if found, to speed up computation. Currently not implemented yet.

savebool

Whether the save the final results dataframe to a pickled file.

get_df_fnames()

Get results filename.

Returns:

Path

Path to the results filename (if saved)