def _prepare_data(self, X, y=None, **kwargs):
logger.info(
"Preparing data for outer fold "
+ str(self.cross_validaton_info.outer_folds[self.outer_fold_id].fold_nr)
+ "..."
)
# Prepare Train and validation set data
train_indices = self.cross_validaton_info.outer_folds[
self.outer_fold_id
].train_indices
test_indices = self.cross_validaton_info.outer_folds[
self.outer_fold_id
].test_indices
self._validation_X, self._validation_y, self._validation_kwargs = PhotonDataHelper.split_data(
X, y, kwargs, indices=train_indices
)
self._test_X, self._test_y, self._test_kwargs = PhotonDataHelper.split_data(
X, y, kwargs, indices=test_indices
)
# write numbers to database info object
self.result_object.number_samples_validation = self._validation_y.shape[0]
self.result_object.number_samples_test = self._test_y.shape[0]
if self._pipe._estimator_type == "classifier":
self.result_object.class_distribution_validation = FoldInfo.data_overview(
self._validation_y
)
self.result_object.class_distribution_test = FoldInfo.data_overview(
self._test_y
)
def test_data_overview(self):
expected_outcome = {str(i): 10 for i in range(10)}
data_count = FoldInfo.data_overview(self.kwargs['groups'].astype(int))
self.assertDictEqual(expected_outcome, data_count)
def test_class_distribution_info(self):
unique, counts = np.unique(self.__y, return_counts=True)
nr_dict = FoldInfo.data_overview(self.__y)
self.assertEqual(counts[1], nr_dict["1"])