PCA visualizer is not rendering 3D plot

[Kautumn06]

The PCADecomposition visualizer should generate a 3D plot when passed proj_dim=3; however, it currently needs to be explicitly passed a matplotlib 3D axis in order to render correctly. For instance, the following code will return a 2D plot despite the proj_dim parameter being set to 3.

from yellowbrick.datasets import load_credit
from yellowbrick.features import PCADecomposition

X, y = load_credit()

visualizer = PCADecomposition(scale=True, proj_dim=3)
visualizer.fit_transform(X, y)
visualizer.show()

However, a 3D plot will be returned when explicitly passed a 3D axis, as in this example:

import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

from yellowbrick.datasets import load_credit
from yellowbrick.features import PCADecomposition

X, y = load_credit()

# Create a figure and add a 3D axis
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')

visualizer = PCADecomposition(scale=True, proj_dim=3, ax=ax)
visualizer.fit_transform(X, y)
visualizer.show()

[naresh-bachwani]

Hey there @Kautumn06,
We changed the proj_dim parameter to projection in #908. Try using projection! :)

[pdamodaran]

Thanks @naresh-bachwani for pointing this out! I tested this out using the new parameter and I can now see a 3d plot.

from yellowbrick.datasets import load_credit
from yellowbrick.features import PCADecomposition

X, y = load_credit()

visualizer = PCADecomposition(scale=True, projection=3)
visualizer.fit_transform(X, y)
visualizer.show()