def test_manifold_LLE(): train_set, valid_set, test_set = read_dataset(dataset_name='dataset_simulation_zero_iterations.csv') dataset, result = train_set dataset = get_gaussian_normalization(dataset) dataset = get_LLE(dataset, num_components=2, n_neighbors=80) assert dataset is not None
def test_dimensionality_reduction_PCA(): train_set, valid_set, test_set = read_dataset(dataset_name='dataset_simulation_zero_iterations.csv') dataset, result = train_set dataset, explained_variance_ratio_ = get_pca(dataset, num_components=2) assert dataset is not None assert explained_variance_ratio_ is not None
print' ... plotting sample {}'.format(idx) print vis_mf, chain_input lst_output = vis_mf with open(os.path.join('trained_models', name_model), 'wb') as f: cPickle.dump(model, f, protocol=cPickle.HIGHEST_PROTOCOL) return lst_output if __name__ == '__main__': # dataset = 'mnist.pkl.gz' # datasets = load_data(dataset) from datasets.DatasetManager import read_dataset datasets = read_dataset('dataset_simulation_20.csv', shared=True) train_set_x, train_set_y = datasets[0] n_in = train_set_x.get_value().shape[1] n_out = train_set_y.get_value().shape[1] x = T.matrix('x') rng = numpy.random.RandomState(123) theano_rng = RandomStreams(rng.randint(2 ** 30)) # construct the RBM class rbm = RBM( input=x, n_visible=n_in, n_hidden=1000, numpy_rng=rng,
def test_solve_missing_values(): train_set, valid_set, test_set = read_dataset(dataset_name='dataset_simulation_zero_iterations.csv') dataset, result = train_set dataset = solve_missing_values(dataset) assert dataset is not None
def test_scaling_linear(): train_set, valid_set, test_set = read_dataset(dataset_name='dataset_simulation_zero_iterations.csv') dataset, result = train_set dataset = get_linear_normalization(dataset) assert dataset is not None
def test_dataset_manager(): assert read_dataset(dataset_name="dataset_simulation_20.csv", shared=False) assert read_dataset(dataset_name="dataset_simulation_20.csv", shared=True)