Create Plots
Now, we will create plots for each of the six distributions, showing the original distribution and the transformed distribution using Box-Cox, Yeo-Johnson, and Quantile Transformer.
distributions = [
("Lognormal", X_lognormal),
("Chi-squared", X_chisq),
("Weibull", X_weibull),
("Gaussian", X_gaussian),
("Uniform", X_uniform),
("Bimodal", X_bimodal),
]
colors = ["#D81B60", "#0188FF", "#FFC107", "#B7A2FF", "#000000", "#2EC5AC"]
fig, axes = plt.subplots(nrows=8, ncols=3, figsize=plt.figaspect(2))
axes = axes.flatten()
axes_idxs = [
(0, 3, 6, 9),
(1, 4, 7, 10),
(2, 5, 8, 11),
(12, 15, 18, 21),
(13, 16, 19, 22),
(14, 17, 20, 23),
]
axes_list = [(axes[i], axes[j], axes[k], axes[l]) for (i, j, k, l) in axes_idxs]
for distribution, color, axes in zip(distributions, colors, axes_list):
name, X = distribution
X_train, X_test = train_test_split(X, test_size=0.5)
## perform power transforms and quantile transform
X_trans_bc = bc.fit(X_train).transform(X_test)
lmbda_bc = round(bc.lambdas_[0], 2)
X_trans_yj = yj.fit(X_train).transform(X_test)
lmbda_yj = round(yj.lambdas_[0], 2)
X_trans_qt = qt.fit(X_train).transform(X_test)
ax_original, ax_bc, ax_yj, ax_qt = axes
ax_original.hist(X_train, color=color, bins=BINS)
ax_original.set_title(name, fontsize=FONT_SIZE)
ax_original.tick_params(axis="both", which="major", labelsize=FONT_SIZE)
for ax, X_trans, meth_name, lmbda in zip(
(ax_bc, ax_yj, ax_qt),
(X_trans_bc, X_trans_yj, X_trans_qt),
("Box-Cox", "Yeo-Johnson", "Quantile transform"),
(lmbda_bc, lmbda_yj, None),
):
ax.hist(X_trans, color=color, bins=BINS)
title = "After {}".format(meth_name)
if lmbda is not None:
title += "\n$\\lambda$ = {}".format(lmbda)
ax.set_title(title, fontsize=FONT_SIZE)
ax.tick_params(axis="both", which="major", labelsize=FONT_SIZE)
ax.set_xlim([-3.5, 3.5])
plt.tight_layout()
plt.show()