def test_timings(self):
"""
Test the twinx double axes with k-elbow timings
"""
visualizer = KElbowVisualizer(
KMeans(random_state=0), k=5, timings=True
)
visualizer.fit(X)
# Check that we kept track of time
assert len(visualizer.k_timers_) == 4
assert all([t > 0 for t in visualizer.k_timers_])
# Check that we plotted time on a twinx
assert hasattr(visualizer, "axes")
assert len(visualizer.axes) == 2
# delete the timings axes and
# overwrite k_timers_, k_values_ for image similarity Tests
visualizer.axes[1].remove()
visualizer.k_timers_ = [
0.01084589958190918, 0.011144161224365234,
0.017028093338012695, 0.010634183883666992
]
visualizer.k_values_ = [2, 3, 4, 5]
# call draw again which is normally called in fit
visualizer.draw()
visualizer.poof()
self.assert_images_similar(visualizer)
def test_timings(self):
"""
Test the twinx double axes with k-elbow timings
"""
visualizer = KElbowVisualizer(KMeans(random_state=0),
k=5,
timings=True)
visualizer.fit(X)
# Check that we kept track of time
self.assertEqual(len(visualizer.k_timers_), 4)
self.assertTrue(all([t > 0 for t in visualizer.k_timers_]))
# Check that we plotted time on a twinx
self.assertTrue(hasattr(visualizer, "axes"))
self.assertEqual(len(visualizer.axes), 2)
# delete the timings axes and
# overwrite k_timers_, k_values_ for image similarity Tests
visualizer.axes[1].remove()
visualizer.k_timers_ = [
0.01084589958190918, 0.011144161224365234, 0.017028093338012695,
0.010634183883666992
]
visualizer.k_values_ = [2, 3, 4, 5]
# call draw again which is normally called in fit
visualizer.draw()
visualizer.poof()
self.assert_images_similar(visualizer)
def test_integrated_mini_batch_kmeans_elbow(self):
"""
Test no exceptions for mini-batch kmeans k-elbow visualizer
"""
# NOTE #182: cannot use occupancy dataset because of memory usage
# Generate a blobs data set
X, y = make_blobs(n_samples=1000,
n_features=12,
centers=6,
shuffle=True,
random_state=42)
try:
fig = plt.figure()
ax = fig.add_subplot()
visualizer = KElbowVisualizer(MiniBatchKMeans(random_state=42),
k=4,
ax=ax)
visualizer.fit(X)
visualizer.poof()
self.assert_images_similar(visualizer)
except Exception as e:
self.fail("error during k-elbow: {}".format(e))
def test_topic_modeling_k_means(self):
"""
Test topic modeling k-means on the hobbies corpus
"""
corpus = self.load_corpus("hobbies")
tfidf = TfidfVectorizer()
docs = tfidf.fit_transform(corpus.data)
visualizer = KElbowVisualizer(KMeans(), k=(4, 8))
visualizer.fit(docs)
visualizer.poof()
self.assert_images_similar(visualizer)
def test_silhouette_metric(self):
"""
Test the silhouette metric of the k-elbow visualizer
"""
visualizer = KElbowVisualizer(KMeans(random_state=0),
k=5,
metric="silhouette",
timings=False)
visualizer.fit(X)
expected = np.array([0.691636, 0.456646, 0.255174, 0.239842])
self.assertEqual(len(visualizer.k_scores_), 4)
visualizer.poof()
self.assert_images_similar(visualizer)
assert_array_almost_equal(visualizer.k_scores_, expected)
def test_distortion_metric(self):
"""
Test the distortion metric of the k-elbow visualizer
"""
visualizer = KElbowVisualizer(KMeans(random_state=0),
k=5,
metric="distortion",
timings=False)
visualizer.fit(X)
expected = np.array([7.677785, 8.364319, 8.893634, 8.013021])
self.assertEqual(len(visualizer.k_scores_), 4)
visualizer.poof()
self.assert_images_similar(visualizer)
assert_array_almost_equal(visualizer.k_scores_, expected)
def test_silhouette_metric(self):
"""
Test the silhouette metric of the k-elbow visualizer
"""
visualizer = KElbowVisualizer(
KMeans(random_state=0), k=5, metric="silhouette", timings=False
)
visualizer.fit(X)
expected = np.array([ 0.691636, 0.456646, 0.255174, 0.239842])
assert len(visualizer.k_scores_) == 4
visualizer.poof()
self.assert_images_similar(visualizer)
assert_array_almost_equal(visualizer.k_scores_, expected)
def test_distortion_metric(self):
"""
Test the distortion metric of the k-elbow visualizer
"""
visualizer = KElbowVisualizer(
KMeans(random_state=0), k=5, metric="distortion", timings=False
)
visualizer.fit(X)
expected = np.array([ 7.677785, 8.364319, 8.893634, 8.013021])
assert len(visualizer.k_scores_) == 4
visualizer.poof()
self.assert_images_similar(visualizer)
assert_array_almost_equal(visualizer.k_scores_, expected)
def test_integrated_mini_batch_kmeans_elbow(self):
"""
Test no exceptions for mini-batch kmeans k-elbow visualizer
See #182: cannot use occupancy dataset because of memory usage
"""
# Generate a blobs data set
X, y = make_blobs(n_samples=1000,
n_features=12,
centers=6,
shuffle=True)
try:
visualizer = KElbowVisualizer(MiniBatchKMeans(), k=4)
visualizer.fit(X)
visualizer.poof()
except Exception as e:
self.fail("error during k-elbow: {}".format(e))
def test_calinski_harabaz_metric(self):
"""
Test the calinski-harabaz metric of the k-elbow visualizer
"""
visualizer = KElbowVisualizer(KMeans(random_state=0),
k=5,
metric="calinski_harabaz",
timings=False)
visualizer.fit(X)
expected = np.array([
81.662726256035683, 50.992378259195554, 40.952179227847012,
35.939494
])
self.assertEqual(len(visualizer.k_scores_), 4)
visualizer.poof()
self.assert_images_similar(visualizer)
assert_array_almost_equal(visualizer.k_scores_, expected)
def test_calinski_harabaz_metric(self):
"""
Test the calinski-harabaz metric of the k-elbow visualizer
"""
visualizer = KElbowVisualizer(
KMeans(random_state=0), k=5,
metric="calinski_harabaz", timings=False
)
visualizer.fit(X)
assert len(visualizer.k_scores_) == 4
expected = np.array([
81.662726256035683, 50.992378259195554,
40.952179227847012, 35.939494
])
visualizer.poof()
self.assert_images_similar(visualizer)
assert_array_almost_equal(visualizer.k_scores_, expected)
def test_integrated_kmeans_elbow(self):
"""
Test no exceptions for kmeans k-elbow visualizer on blobs dataset
"""
# NOTE #182: cannot use occupancy dataset because of memory usage
# Generate a blobs data set
X,y = make_blobs(
n_samples=1000, n_features=12, centers=6,
shuffle=True, random_state=42
)
try:
_, ax = plt.subplots()
visualizer = KElbowVisualizer(KMeans(random_state=42), k=4, ax=ax)
visualizer.fit(X)
visualizer.poof()
self.assert_images_similar(visualizer)
except Exception as e:
pytest.fail("error during k-elbow: {}".format(e))
