def test_copies_labels_if_present(self):
dataset = data_utils.as_normalized(SPECTRA, COORDINATES,
labels=DATASET.labels)
npt.assert_equal(dataset.labels, [8])
unlabeled = data_utils.as_normalized(SPECTRA, COORDINATES,
labels=None)
self.assertIsNone(unlabeled.labels)
def regenerate_dataset(dataset_path: str, analysis_root: str):
"""Regenerate file with transformed dataset"""
transformed_path = os.path.join(analysis_root, 'result.pkl')
result = joblib.load(transformed_path)
metadata = get_metadata(analysis_root)
dataset = data_utils.as_normalized(result, metadata.coordinates,
metadata.labels)
data_utils.dumps_txt(dataset_path, dataset)
def tSNE(self, analysis_name: str, dataset_name: str, **kwargs):
# preprocessing of our current strange format
analysis_details = dataset_name, tSNE.__name__, analysis_name
manifold = TSNE(**kwargs, verbose=True)
with status_notifier(self) as notify, \
open_analysis(*analysis_details) as tmp_path:
notify('PRESERVING CONFIGURATION')
config_path = os.path.join(tmp_path, 'options')
dump_configuration(config_path, kwargs)
notify('LOADING DATA')
data = load_dataset(dataset_name)
notify('RUNNING T-SNE')
result = manifold.fit_transform(data.spectra)
notify('PRESERVING RESULTS')
model_path = os.path.join(tmp_path, 'model')
joblib.dump(manifold, model_path + '.pkl')
result_path = os.path.join(tmp_path, 'result')
joblib.dump(result, result_path + '.pkl')
np.savetxt(result_path + '.csv', result)
normalized = data_utils.as_normalized(result, data.coordinates,
data.labels)
dataset_path = os.path.join(tmp_path, 'data.txt')
data_utils.dumps_txt(dataset_path, normalized)
def test_creates_artificial_mzs(self):
dataset = data_utils.as_normalized(SPECTRA, COORDINATES)
npt.assert_equal(dataset.mz, [0, 1])
def test_throws_on_sizes_mismatch(self):
with self.assertRaises(ValueError):
data_utils.as_normalized(np.array([[1], [2]]), COORDINATES)
with self.assertRaises(ValueError):
data_utils.as_normalized(np.array([]), COORDINATES)