def setUp(self):
self.strings_to_sort = ['name1', 'name11', 'name10', 'name2', 'name21']
self.correct_order_of_strings = ['name1', 'name2', 'name10', 'name11', 'name21']
self.filenames_to_sort = ['20190718_beans_01_s1.nt' + str(i) + '.mda' for i in range(1, 64)]
self.file_sorter = FileSorter()
self.sorted_strings = self.file_sorter.sort_filenames(self.strings_to_sort)
self.sorted_filenames = self.file_sorter.sort_filenames(self.filenames_to_sort)
def get_all_epochs(self, date: str) -> list:
all_datasets = []
directories = os.listdir(self.data_path + '/' + self.animal_name +
'/preprocessing/' + date)
FileSorter.sort_filenames(directories)
for directory in directories:
if directory.startswith(date):
dataset_name = (directory.split('_')[2] + '_' +
directory.split('_')[3]).split('.')[0]
if not dataset_name in all_datasets:
all_datasets.append(dataset_name)
return all_datasets
def get_probes_from_directory(path: str):
probes = []
files = FileSorter.sort_filenames(os.listdir(path))
for probe_file in files:
if fnmatch.fnmatch(probe_file, "probe*.yml"):
probes.append(path + '/' + probe_file)
return probes
def __extract_experiments(self, data_path, animal_name, dates):
preprocessing_path = data_path + animal_name + '/preprocessing'
if not dates:
dates = FileSorter.sort_filenames(os.listdir(preprocessing_path))
return {
date: self.__extract_datasets(preprocessing_path + '/' + date)
for date in dates
}
class TestFilenameSorter(TestCase):
def setUp(self):
self.strings_to_sort = ['name1', 'name11', 'name10', 'name2', 'name21']
self.correct_order_of_strings = ['name1', 'name2', 'name10', 'name11', 'name21']
self.filenames_to_sort = ['20190718_beans_01_s1.nt' + str(i) + '.mda' for i in range(1, 64)]
self.file_sorter = FileSorter()
self.sorted_strings = self.file_sorter.sort_filenames(self.strings_to_sort)
self.sorted_filenames = self.file_sorter.sort_filenames(self.filenames_to_sort)
def test_string_sorting(self):
self.assertEqual(self.sorted_strings, self.correct_order_of_strings)
def test_filename_sorting(self):
self.assertEqual(self.sorted_filenames[1], '20190718_beans_01_s1.nt2.mda')
self.assertEqual(self.sorted_filenames[9], '20190718_beans_01_s1.nt10.mda')
self.assertEqual(self.sorted_filenames[18], '20190718_beans_01_s1.nt19.mda')
self.assertEqual(self.sorted_filenames[19], '20190718_beans_01_s1.nt20.mda')
def __extract_experiments(self, data_path, animal_name, dates):
preprocessing_path = os.path.join(data_path, animal_name,
'preprocessing')
if not dates:
dates = FileSorter.sort_filenames(os.listdir(preprocessing_path))
return {
date:
self.__extract_datasets(os.path.join(preprocessing_path, date))
for date in dates
}
def __extract_datasets(date_path):
existing_datasets = set()
datasets = {}
directories = FileSorter.sort_filenames(os.listdir(date_path))
for directory in directories:
dir_split = directory.split('_')
if dir_split[0].isdigit():
dir_last_part = dir_split.pop().split('.')
dataset_name = dir_split.pop() + '_' + dir_last_part[0]
if not (dataset_name in existing_datasets):
datasets[dataset_name] = Dataset(dataset_name)
existing_datasets.add(dataset_name)
for dataset in datasets.values():
if dataset_name == dataset.name:
dataset.add_data_to_dataset(
date_path + '/' + directory + '/',
dir_last_part.pop())
return datasets
def get_all_data_from_dataset(self, data_type):
directories = os.listdir(self.data[data_type])
FileSorter.sort_filenames(directories)
return directories