cave.analyzer.bohb_learning_curves module

class cave.analyzer.bohb_learning_curves.BohbLearningCurves(hp_names, result_object=None, result_path=None)[source]

Bases: cave.analyzer.base_analyzer.BaseAnalyzer

Visualize hpbandster learning curves in an interactive bokeh-plot.

Parameters:
  • hp_names (List[str]) – list with hyperparameters-names
  • result_object (Result) – hpbandster-result object. must be specified if result_path is not
  • result_path (str) – path to hpbandster result-folder. must contain configs.json and results.json. must be specified if result_object is not
get_html(d=None, tooltip=None)[source]

General reports in html-format, to be easily integrated in html-code. ALSO FOR BOKEH-OUTPUT.

Returns:script, div – header and body part of html-code
Return type:str, str
get_jupyter()[source]

Depending on analysis, this creates jupyter-notebook compatible output.

get_longest_run(c_id, result_object)[source]
get_static_plots() → List[str]

Returns plot-paths, if any are available

Returns:plot_paths – returns list of strings
Return type:List[str]
get_table()

Get table, if available

plot(reset_times=False)[source]