モデルの拡張性を描画する
fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(16, 12), sharex=True)
for ax_idx, (fit_times, score_times, estimator) in enumerate(
zip(
[fit_times_nb, fit_times_svm],
[score_times_nb, score_times_svm],
[naive_bayes, svc],
)
):
## scalability regarding the fit time
ax[0, ax_idx].plot(train_sizes, fit_times.mean(axis=1), "o-")
ax[0, ax_idx].fill_between(
train_sizes,
fit_times.mean(axis=1) - fit_times.std(axis=1),
fit_times.mean(axis=1) + fit_times.std(axis=1),
alpha=0.3,
)
ax[0, ax_idx].set_ylabel("Fit time (s)")
ax[0, ax_idx].set_title(
f"Scalability of the {estimator.__class__.__name__} classifier"
)
## scalability regarding the score time
ax[1, ax_idx].plot(train_sizes, score_times.mean(axis=1), "o-")
ax[1, ax_idx].fill_between(
train_sizes,
score_times.mean(axis=1) - score_times.std(axis=1),
score_times.mean(axis=1) + score_times.std(axis=1),
alpha=0.3,
)
ax[1, ax_idx].set_ylabel("Score time (s)")
ax[1, ax_idx].set_xlabel("Number of training samples")