def main(_):
"""High level pipeline.
This scripts performs the training and evaling and testing stages for
semi-supervised learning using kMeans algorithm.
"""
# Load dataset.
_, unlabeled_data = io_tools.read_dataset('data/simple_test.csv')
n_dims = unlabeled_data.shape[1]
# Initialize model.
model = GaussianMixtureModel(n_dims,
n_components=FLAGS.n_components,
max_iter=FLAGS.max_iter)
# Unsupervised training.
# model.fit(unlabeled_data)
# Supervised training.
train_label, train_data = io_tools.read_dataset('data/simple_test.csv')
model.supervised_fit(train_data, train_label)
# Eval model.
eval_label, eval_data = io_tools.read_dataset('data/simple_test.csv')
y_hat_eval = model.supervised_predict(eval_data)
acc = np.sum(y_hat_eval == eval_label) / (1. * eval_data.shape[0])
print("Accuracy: %s" % acc)
def setUp(self):
n_dims = 2
unlabeled_data = np.random.normal(-1, 0.1, [100, n_dims])
unlabeled_data = np.concatenate(
(unlabeled_data, np.random.normal(1, 0.1, [50, n_dims])))
self.n_dims = 2
self.n_components = 2
self.max_iter = 1
self.model = GaussianMixtureModel(self.n_dims,
n_components=self.n_components,
max_iter=self.max_iter)