def test_minibatch_nmf_transform():
# Test that fit_transform is equivalent to fit.transform for MiniBatchNMF
# Only guaranteed with fresh restarts
rng = np.random.mtrand.RandomState(42)
A = np.abs(rng.randn(6, 5))
m = MiniBatchNMF(
n_components=3,
random_state=0,
tol=1e-3,
fresh_restarts=True,
)
ft = m.fit_transform(A)
t = m.transform(A)
assert_allclose(ft, t)
# data does not fit into memory.
import numpy as np
from sklearn.decomposition import MiniBatchNMF
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 10, 10, 5
true_W = rng.uniform(size=(n_samples, n_components))
true_H = rng.uniform(size=(n_components, n_features))
X = true_W @ true_H
nmf = MiniBatchNMF(n_components=n_components, random_state=0)
for _ in range(10):
nmf.partial_fit(X)
W = nmf.transform(X)
H = nmf.components_
X_reconstructed = W @ H
print(
f"relative reconstruction error: ",
f"{np.sum((X - X_reconstructed) ** 2) / np.sum(X**2):.5f}",
)
# %%
# BisectingKMeans: divide and cluster
# -----------------------------------
# The new class :class:`cluster.BisectingKMeans` is a variant of :class:`KMeans`, using
# divisive hierarchical clustering. Instead of creating all centroids at once, centroids
# are picked progressively based on a previous clustering: a cluster is split into two
# new clusters repeatedly until the target number of clusters is reached, giving a