def test_find_point_furthest_away():
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K)
# Equal distance for point 0
centroids = [[1.0,3.0,1.0],[2.0,1.0,3.0]]
mask_centroids = [[0,1,1],[1,1,0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.closest_cluster(X[0],0,M[0]) # MSE = 1.0 vs 1.0
kmeans.closest_cluster(X[1],1,M[1]) # MSE = 4.0 vs 16.0
kmeans.closest_cluster(X[2],2,M[2]) # MSE = 44.5 vs 37.0
expected_furthest_away = 2
furthest_away = kmeans.find_point_furthest_away()
assert expected_furthest_away == furthest_away
def test_find_point_furthest_away():
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K)
# Equal distance for point 0
centroids = [[1.0, 3.0, 1.0], [2.0, 1.0, 3.0]]
mask_centroids = [[0, 1, 1], [1, 1, 0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.closest_cluster(X[0], 0, M[0]) # MSE = 1.0 vs 1.0
kmeans.closest_cluster(X[1], 1, M[1]) # MSE = 4.0 vs 16.0
kmeans.closest_cluster(X[2], 2, M[2]) # MSE = 44.5 vs 37.0
expected_furthest_away = 2
furthest_away = kmeans.find_point_furthest_away()
assert expected_furthest_away == furthest_away
def test_closest_cluster():
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K)
# Equal distance for point 0
centroids = [[1.0,3.0,1.0],[2.0,1.0,3.0]]
mask_centroids = [[0,1,1],[1,1,0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster_0 = 0 # MSE = 1.0 vs 1.0
expected_closest_cluster_1 = 0 # MSE = 4.0 vs 16.0
expected_closest_cluster_2 = 1 # MSE = 44.5 vs 37.0
closest_cluster_0 = kmeans.closest_cluster(X[0],0,M[0])
closest_cluster_1 = kmeans.closest_cluster(X[1],1,M[1])
closest_cluster_2 = kmeans.closest_cluster(X[2],2,M[2])
assert expected_closest_cluster_0 == closest_cluster_0
assert expected_closest_cluster_1 == closest_cluster_1
assert expected_closest_cluster_2 == closest_cluster_2
# Also test whether the distances are set correctly
expected_distances = [1.0,4.0,37.0]
distances = kmeans.distances
assert numpy.array_equal(expected_distances,distances)
# Test when all MSEs return None (impossible but still testing behaviour)
centroids = numpy.ones((2,3))
mask_centroids = [[0,0,1],[0,0,0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster = 1
closest_cluster = kmeans.closest_cluster(X[0],0,M[0])
assert expected_closest_cluster == closest_cluster
def test_closest_cluster():
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K)
# Equal distance for point 0
centroids = [[1.0, 3.0, 1.0], [2.0, 1.0, 3.0]]
mask_centroids = [[0, 1, 1], [1, 1, 0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster_0 = 0 # MSE = 1.0 vs 1.0
expected_closest_cluster_1 = 0 # MSE = 4.0 vs 16.0
expected_closest_cluster_2 = 1 # MSE = 44.5 vs 37.0
closest_cluster_0 = kmeans.closest_cluster(X[0], 0, M[0])
closest_cluster_1 = kmeans.closest_cluster(X[1], 1, M[1])
closest_cluster_2 = kmeans.closest_cluster(X[2], 2, M[2])
assert expected_closest_cluster_0 == closest_cluster_0
assert expected_closest_cluster_1 == closest_cluster_1
assert expected_closest_cluster_2 == closest_cluster_2
# Also test whether the distances are set correctly
expected_distances = [1.0, 4.0, 37.0]
distances = kmeans.distances
assert numpy.array_equal(expected_distances, distances)
# Test when all MSEs return None (impossible but still testing behaviour)
centroids = numpy.ones((2, 3))
mask_centroids = [[0, 0, 1], [0, 0, 0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster = 1
closest_cluster = kmeans.closest_cluster(X[0], 0, M[0])
assert expected_closest_cluster == closest_cluster
