plot_predicted_vs_true_bars¶
-
mastml.plot_helper.
plot_predicted_vs_true_bars
(y_true, y_pred_list, avg_stats, savepath, title='best worst with bars', label='target_value', groups=None)[source]¶ Method to calculate parity plot (predicted vs. true) of average predictions, averaged over all CV splits, with error
bars on each point corresponding to the standard deviation of the predicted values over all CV splits.
Args:
y_true: (numpy array), array of true y data
y_pred_list: (list), list of numpy arrays containing predicted y data for each CV split
avg_stats: (dict), dict of calculated average metrics over all CV splits
savepath: (str), path to save plots to
title: (str), title of the best_worst_per_point plot
label: (str), label used for axis labeling
Returns:
None