hookeai.miscellaneous.pruning.pruning_dataset.plot_pruning_iterative_data

plot_pruning_iterative_data(pruning_dir, pruning_params, testing_types, pruning_iterative_data, performance_threshold_ratio=0.1, is_plot_performance_threshold=False, save_dir=None, is_save_fig=False, is_stdout_display=False, is_latex=True)

Plot pruning iterative data.

Parameters:

• pruning_dir (str) – Pruning main directory.

• pruning_params (dict) – Pruning parameters.

• testing_types (tuple[str]) – Types of testing data sets used to assess the performance of the model trained on the pruned training data sets.

• pruning_iterative_data (dict) – Pruning iterative data (item, dict) for each pruning iteration (key, str).

• performance_threshold_ratio (float, default=0.1) – Performance degradation threshold ratio. Defines a relative increase with the respect to the testing loss obtained with the largest training data set size. Data that can be pruned without exceeding the performance degradation threshold is considered redundant.

• is_plot_performance_threshold (bool, default=False) – If True, then plot performance degradation threshold.

• save_dir (str, default=None) – Directory where data set plots are saved. If None, then plots are saved in current working directory.

• is_save_fig (bool, default=False) – Save figure.

• is_stdout_display (bool, default=False) – True if displaying figure to standard output device, False otherwise.

• is_latex (bool, default=False) – If True, then render all strings in LaTeX. If LaTex is not available, then this option is silently set to False and all input strings are processed to remove $(…)$ enclosure.