def test_KMeansMachine():
# Test a KMeansMachine
means = np.array([[3, 70, 0], [4, 72, 0]], "float64")
test_val = np.array([3, 70, 1], "float64")
test_arr = np.array([[3, 70, 1], [5, 72, 0]], "float64")
for transform in (to_numpy, to_dask_array):
means, test_val, test_arr = transform(means, test_val, test_arr)
# Initializes a KMeansMachine
km = KMeansMachine(2)
km.centroids_ = means
# Distance and closest mean
np.testing.assert_equal(km.transform(test_val)[0], np.array([1]))
np.testing.assert_equal(km.transform(test_val)[1], np.array([6]))
index = km.predict(test_val)
assert index == 0
indices = km.predict(test_arr)
np.testing.assert_equal(indices, np.array([0, 1]))
# Check __eq__ and is_similar_to
km2 = KMeansMachine(2)
assert km != km2
assert not km.is_similar_to(km2)
km2 = copy.deepcopy(km)
assert km == km2
assert km.is_similar_to(km2)
km2.centroids_[0, 0] += 1
assert km != km2
assert not km.is_similar_to(km2)
def test_KMeansMachine_var_and_weight():
for transform in (to_numpy, to_dask_array):
kmeans = KMeansMachine(2)
kmeans.centroids_ = transform(np.array([[1.2, 1.3], [0.2, -0.3]]))
data = np.array([[1.0, 1], [1.2, 3], [0, 0], [0.3, 0.2], [0.2, 0]])
data = transform(data)
variances, weights = kmeans.get_variances_and_weights_for_each_cluster(
data)
variances_result = np.array([[0.01, 1.0], [0.01555556, 0.00888889]])
weights_result = np.array([0.4, 0.6])
np.testing.assert_almost_equal(variances, variances_result, decimal=7)
np.testing.assert_equal(weights, weights_result)