Created
April 17, 2020 09:45
-
-
Save pavlin-policar/d9857f0dd1673e0035f2a43bea5d2fe2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def confidence_histogram(y_true, y_probs, n_bins=10, ax=None): | |
if ax is None: | |
fig, ax = plt.subplots(figsize=(4, 4)) | |
confidences = np.max(y_probs, axis=1) | |
predictions = np.argmax(y_probs, axis=1) | |
accuracies = predictions == y_true | |
bins = np.linspace(0, 1 - 1 / n_bins, n_bins) | |
bin_indices = np.digitize(confidences, bins=bins[1:]) | |
bin_accuracy = np.zeros(n_bins, dtype=np.float64) | |
bin_confidence = np.zeros(n_bins, dtype=np.float64) | |
for idx in np.unique(bin_indices): | |
mask = bin_indices == idx | |
bin_accuracy[idx] = np.mean(accuracies[mask]) | |
bin_confidence[idx] = np.mean(np.max(y_probs[mask], axis=1)) | |
ax.grid(zorder=1, linestyle="dotted") | |
width = bins[1] - bins[0] | |
confs = ax.bar(bins, bin_accuracy, width=width, edgecolor="k", align="edge", zorder=2) | |
gaps = ax.bar( | |
bins, bin_confidence - bin_accuracy, bottom=bin_accuracy, color=[1, 0.7, 0.7], | |
alpha=0.5, width=width, hatch="//", edgecolor="r", align="edge", zorder=2, | |
) | |
ax.plot([0, 1], [0, 1], c="gray", linestyle="dashed") | |
ax.legend([confs, gaps], ["Outputs", "Gap"], loc="best", fontsize="small") | |
# Clean up | |
ax.set_ylabel("Accuracy") | |
ax.set_xlabel("Confidence") | |
ax.set_xlim(0, 1) | |
ax.set_ylim(0, 1) | |
return ax |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment