def test_matches_original_paper_macro_F1(self):
test_cases = [
# n_features, label order, macro f1 to-beat
(5, [0, 1, 0], 0.9),
(5, [0, 1, 2, 1, 0], 0.9),
(5, [0, 1, 2, 3, 0, 1, 2, 3], 0.9),
(5, [0, 1, 1, 0, 2, 2, 2, 0], 0.9),
]
for n, labels, expected in test_cases:
rdata = RandomData(0, n, window_size=5)
# Original paper code performs at 100p/cluster!
samples_per_segment = 120
k = len(set(labels)) # Num clusters
t = samples_per_segment * k * len(labels) # total ts length
breaks = [(i) * t // len(labels) for i, _ in enumerate(labels, 1)]
X, y_tru = rdata.generate_points(labels, breaks)
ticc = TICC(n_clusters=k, window_size=5, n_jobs=4, random_state=0)
y = ticc.fit_predict(X)
# We use best_f1 because label:segment assignments are arbitrary
result = best_f1(y_tru, y, average='macro')
assert result > expected
# %% Generate data
n_features = 5
label_seq = [0, 1, 2, 0, 2, 1]
samples_per_segment = 250
window_size = 8
# Derived from above params
k = len(set(label_seq)) # Num clusters
t = samples_per_segment * len(label_seq) # total ts length
breaks = [i * t // len(label_seq) for i in range(1, len(label_seq) + 1)]
palette = {n: c['color'] for n, c in zip(range(n_features), colors)}
randomdata = RandomData(seed=1234,
n_features=n_features,
window_size=window_size)
X, y_true = randomdata.generate_points(label_seq, breaks)
# Plot Synthetic Data
plot_synthetic_data(X, breaks)
# %% Fit TICC and GMM to data
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
ticc = TICC(n_clusters=k, window_size=window_size, random_state=1234, beta=200)
gmm = GaussianMixture(n_components=k, random_state=1234)
X_stacked = ticc.stack_data(X_scaled)
y_ticc = ticc.fit_predict(X)
y_gmm = gmm.fit_predict(X_stacked)
# Macro F1 Scores