def test_pass_if_consistent_on_similar_random_data(self):
test_cases = [
(5, [0, 1, 0], 5),
(5, [0, 1, 2, 1, 0], 5),
]
for n, labels, repeats in test_cases:
rdata = RandomData(seed=0, n_features=n, window_size=5)
k = len(set(labels))
t = 200 * k * len(labels)
breaks = [(i) * t // len(labels) for i, _ in enumerate(labels, 1)]
rdata.generate_cluster_params(k)
# Reuse same cluster parameters for each dataset
data = [
rdata.generate_points(labels, breaks, True)[0]
for i in range(repeats)
]
ticc = TICC(n_clusters=k,
window_size=5,
beta=300,
n_jobs=4,
random_state=0,
cluster_reassignment=0.3,
verbose=True)
y_preds = [ticc.fit_predict(X) for X in data]
for y1, y2 in combinations(y_preds, 2):
result = np.sum(np.not_equal(y1, y2)) / t
assert result < 0.02
def test_recycling_clusters_between_calls(self):
test_cases = [
([0, 1, 0], [20, 40, 60], 0),
([0, 1, 0], [20, 40, 60], 10),
([0, 1, 0], [20, 40, 60], 100),
]
for seg, b, seed in test_cases:
rdata = RandomData(seed)
rdata.generate_cluster_params(len(set(seg)))
X1, y1 = rdata.generate_points(seg, b, True)
C1 = rdata.clusters
X2, y2 = rdata.generate_points(seg, b, True)
C2 = rdata.clusters
assert C1 == C2
