def test(file, max_n_components, n_classes):
print('GaussianMixture for set: ' + file)
dataset = utils.dataset_reader(file)
X, y = utils.data_process(dataset)
list_sse = []
list_nmi = []
for n_components in range(1, max_n_components + 1):
gmm = GaussianMixture(n_components=n_components)
gmm.fit(X)
y_hat = gmm.predict(X)
sse = utils.sum_of_squared_errors(X, y_hat, gmm.means_)
nmi = utils.normalized_mutual_information(y, n_classes, y_hat,
n_components)
print('{0:2d} components, SSE: {1:.2f}, NMI: {2:.4f}'.format(
n_components, sse, nmi))
# print('iterations: ', gmm.n_iter_)
# print(gmm.means_, gmm.covariances_, gmm.weights_)
# print(gmm.lower_bound_)
list_sse.append(sse)
list_nmi.append(nmi)
utils.plot_measure_vs_k('SSE', list_sse, range(1, max_n_components + 1))
utils.plot_measure_vs_k('NMI', list_nmi, range(1, max_n_components + 1))
def testPredictClasses(self):
"""
Assert that torch.FloatTensor is handled correctly.
"""
x = torch.randn(4, 2)
n_components = np.random.randint(1, 100)
model = GaussianMixture(n_components, x.size(1))
model.fit(x)
y = model.predict(x)
# check that dimensionality of class memberships is (n)
self.assertEqual(torch.Tensor(x.size(0)).size(), y.size())
def testPredictProbabilities(self):
"""
Assert that torch.FloatTensor is handled correctly when returning class probabilities.
"""
x = torch.randn(4, 2)
n_components = np.random.randint(1, 100)
model = GaussianMixture(n_components, x.size(1))
model.fit(x)
# check that y_p has dimensions (n, k)
y_p = model.predict(x, probs=True)
self.assertEqual(
torch.Tensor(x.size(0), n_components).size(), y_p.size())
def main():
n, d = 300, 2
# generate some data points ..
data = torch.Tensor(n, d).normal_()
# .. and shift them around to non-standard Gaussians
data[:n//2] -= 1
data[:n//2] *= sqrt(3)
data[n//2:] += 1
data[n//2:] *= sqrt(2)
# Next, the Gaussian mixture is instantiated and ..
n_components = 2
model = GaussianMixture(n_components, d)
model.fit(data)
# .. used to predict the data points as they where shifted
y = model.predict(data)
plot(data, y)
# init_dataset_size = int(train_dataset.shape[0] * 0.005)
# init_dataset = train_dataset[np.random.choice(train_dataset.shape[0], init_dataset_size, replace=False)]
init_dataset = train_dataset
model = GaussianMixture(X=init_dataset,
n_components=args.components,
random_state=seed,
init_params=args.init)
init_metrics = {
'aic': model.aic(train_dataset),
'bic': model.bic(train_dataset),
'll': model.score(train_dataset)
}
model.fit(train_dataset, args.epochs, train_dataset_labels, args,
output_dir)
predicted_labels = model.predict_proba(train_dataset).tolist()
predicted_labels = np.array(predicted_labels)
print('\nSaving images...')
metrics = model.history_['metrics']
for key in metrics:
metrics[key].insert(0, init_metrics[key])
plot_metric(metrics['ll'], args.epochs, output_dir, 'Epochs',
'Log-Likelihood')
plot_metric(metrics['aic'], args.epochs, output_dir, 'Epochs', 'AIC')
plot_metric(metrics['bic'], args.epochs, output_dir, 'Epochs', 'BIC')
