def test_predict_equal_labels(algo):
km = KMeans(random_state=13,
n_jobs=1,
n_init=1,
max_iter=1,
algorithm=algo)
km.fit(X)
assert_array_equal(km.predict(X), km.labels_)
def test_supervised_cluster_scorers():
# Test clustering scorers against gold standard labeling.
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
km = KMeans(n_clusters=3)
km.fit(X_train)
for name in CLUSTER_SCORERS:
score1 = get_scorer(name)(km, X_test, y_test)
score2 = getattr(cluster_module, name)(y_test, km.predict(X_test))
assert_almost_equal(score1, score2)
def test_full_vs_elkan():
km1 = KMeans(algorithm='full', random_state=13).fit(X)
km2 = KMeans(algorithm='elkan', random_state=13).fit(X)
assert homogeneity_score(km1.predict(X), km2.predict(X)) == 1.0
# Visualize the results on PCA-reduced data
reduced_data = PCA(n_components=2).fit_transform(data)
kmeans = KMeans(init='k-means++', n_clusters=n_digits, n_init=10)
kmeans.fit(reduced_data)
# Step size of the mesh. Decrease to increase the quality of the VQ.
h = .02 # point in the mesh [x_min, x_max]x[y_min, y_max].
# Plot the decision boundary. For that, we will assign a color to each
x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
# Obtain labels for each point in mesh. Use last trained model.
Z = kmeans.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure(1)
plt.clf()
plt.imshow(Z,
interpolation='nearest',
extent=(xx.min(), xx.max(), yy.min(), yy.max()),
cmap=plt.cm.Paired,
aspect='auto',
origin='lower')
plt.plot(reduced_data[:, 0], reduced_data[:, 1], 'k.', markersize=2)
# Plot the centroids as a white X
centroids = kmeans.cluster_centers_
# Load Image and transform to a 2D numpy array.
w, h, d = original_shape = tuple(china.shape)
assert d == 3
image_array = np.reshape(china, (w * h, d))
print("Fitting model on a small sub-sample of the data")
t0 = time()
image_array_sample = shuffle(image_array, random_state=0)[:1000]
kmeans = KMeans(n_clusters=n_colors, random_state=0).fit(image_array_sample)
print("done in %0.3fs." % (time() - t0))
# Get labels for all points
print("Predicting color indices on the full image (k-means)")
t0 = time()
labels = kmeans.predict(image_array)
print("done in %0.3fs." % (time() - t0))
codebook_random = shuffle(image_array, random_state=0)[:n_colors]
print("Predicting color indices on the full image (random)")
t0 = time()
labels_random = pairwise_distances_argmin(codebook_random, image_array, axis=0)
print("done in %0.3fs." % (time() - t0))
def recreate_image(codebook, labels, w, h):
"""Recreate the (compressed) image from the code book & labels"""
d = codebook.shape[1]
image = np.zeros((w, h, d))
label_idx = 0
for i in range(w):