def intercluster_distance(ax=None):
X, y = make_blobs(centers=12, n_samples=1000, n_features=16, shuffle=True)
viz = InterclusterDistance(KMeans(9), ax=ax)
viz.fit(X)
viz.finalize()
return viz
def distance_yellowbrick(
X,
y,
features,
):
plt.switch_backend('agg')
plt.clf()
X_train, X_test, y_train, y_test = train_test_split(X[features],
y,
stratify=y,
test_size=0.01)
X = pd.DataFrame(X_test, columns=features)
y = pd.Series(y_test)
n_clusters = y.nunique()
model = MiniBatchKMeans(n_clusters)
visualizer_dist = InterclusterDistance(model)
visualizer_dist.fit(X)
visualizer_dist.finalize()
return plt
