def test_keywords_params_combine(self):
matcher = KeywordsMatching.from_dict({
'path_to_search': 'testing_data/images2d',
'filename_contains': '_g',
'filename_removefromid': 'img|_g'
})
f_list, s_list = matcher.matching_subjects_and_filenames()
self.assertEqual(len(f_list), 10)
self.assertEqual(len(s_list), 10)
matcher_comp = KeywordsMatching.from_dict({
'path_to_search':
'testing_data/images2d',
'filename_not_contains': ('_m', '_u'),
'filename_removefromid':
"img|_g"
})
f_comp, s_comp = matcher_comp.matching_subjects_and_filenames()
self.assertEqual(f_comp, f_list)
self.assertEqual(s_comp, s_list)
matcher = KeywordsMatching.from_dict({
'path_to_search':
'testing_data/images2d',
'filename_removefromid':
'img|_g|_m|_u'
})
with self.assertRaisesRegexp(ValueError, ""):
matcher.matching_subjects_and_filenames()
def test_keywords_not_contain(self):
matcher = KeywordsMatching.from_dict({
'path_to_search': 'testing_data/images2d',
'filename_not_contains': 'img'
})
with self.assertRaisesRegexp(ValueError, ""):
# not filename (not containing 'img') matched
matcher.matching_subjects_and_filenames()
matcher = KeywordsMatching.from_dict({
'path_to_search':
'testing_data/images2d',
'filename_not_contains': ('_m', '_u')
})
f_list, s_list = matcher.matching_subjects_and_filenames()
self.assertEqual(len(f_list), 10)
self.assertEqual(len(s_list), 10)
matcher_comp = KeywordsMatching.from_dict({
'path_to_search': 'testing_data/images2d',
'filename_contains': '_g'
})
f_comp, s_comp = matcher_comp.matching_subjects_and_filenames()
self.assertEqual(len(f_comp), 10)
self.assertEqual(len(f_comp), 10)
self.assertEqual(f_comp, f_list)
def test_from_dict(self):
with self.assertRaisesRegexp(ValueError, ""):
KeywordsMatching.from_dict({'path_to_search': 'wrong_folder'})
matcher = KeywordsMatching.from_dict(
{'path_to_search': 'testing_data/images2d'})
f_list, s_list = matcher.matching_subjects_and_filenames()
self.assertEqual(len(f_list), 30)
self.assertEqual(len(s_list), 30)
self.assertEqual(s_list[0][0], 'img0_g')
def match_and_write_filenames_to_csv(list_constraints, csv_file):
"""
Combine all elements of file searching until finally writing the names
:param list_constraints: list of constraints (defined by list of paths to
search, list of elements the filename should contain and of those that
are forbidden
:param csv_file: file on which to write the final list of files.
:return:
"""
name_tot = []
list_tot = []
if list_constraints is None or len(list_constraints) == 0:
return
for c in list_constraints:
list_files, name_list = \
KeywordsMatching.matching_subjects_and_filenames(c)
name_list = remove_duplicated_names(name_list)
name_tot.append(name_list)
list_tot.append(list_files)
list_combined = join_subject_id_and_filename_list(name_tot, list_tot)
touch_folder(os.path.dirname(csv_file))
# csv writer has different behaviour in python 2/3
if sys.version_info[0] >= 3:
with open(csv_file, 'w', newline='', encoding='utf8') as csvfile:
file_writer = csv.writer(csvfile)
for list_temp in list_combined:
file_writer.writerow(list_temp)
else:
with open(csv_file, 'wb') as csvfile:
file_writer = csv.writer(csvfile, delimiter=',')
for list_temp in list_combined:
file_writer.writerow(list_temp)
return
def match_and_write_filenames_to_csv(list_constraints, csv_file):
"""
Combine all elements of file searching until finally writing the names
:param list_constraints: list of constraints (defined by list of paths to
search, list of elements the filename should contain and of those that
are forbidden
:param csv_file: file on which to write the final list of files.
:return:
"""
name_tot = []
list_tot = []
if list_constraints is None or len(list_constraints) == 0:
return
for c in list_constraints:
list_files, name_list = \
KeywordsMatching.matching_subjects_and_filenames(c)
name_list = remove_duplicated_names(name_list)
name_tot.append(name_list)
list_tot.append(list_files)
list_combined = join_subject_id_and_filename_list(name_tot, list_tot)
list_combined = filter(lambda names: '' not in names, list_combined)
list_combined = list(list_combined)
touch_folder(os.path.dirname(csv_file))
write_csv(csv_file, list_combined)
return list_combined
def match_and_write_filenames_to_csv(list_constraints, csv_file):
"""
Combine all elements of file searching until finally writing the names
:param list_constraints: list of constraints (defined by list of paths to
search, list of elements the filename should contain and of those that
are forbidden
:param csv_file: file on which to write the final list of files.
:return:
"""
name_tot = []
list_tot = []
if list_constraints is None or len(list_constraints) == 0:
return
for c in list_constraints:
list_files, name_list = \
KeywordsMatching.matching_subjects_and_filenames(c)
name_list = remove_duplicated_names(name_list)
name_tot.append(name_list)
list_tot.append(list_files)
list_combined = join_subject_id_and_filename_list(name_tot, list_tot)
list_combined = filter(lambda names: '' not in names, list_combined)
list_combined = list(list_combined)
if not list_combined:
raise IOError('Nothing to write to {}'.format(csv_file))
touch_folder(os.path.dirname(csv_file))
write_csv(csv_file, list_combined)
return list_combined
def load_and_merge_csv_files(data_param, default_folder=None):
"""
Converts a list of csv_files in data_param
in to a joint list of file names (by matching the first column)
This function returns a <pandas.core.frame.DataFrame> of the
joint list
"""
if not data_param:
tf.logging.fatal('nothing to load, please check reader.names')
raise ValueError
_file_list = None
for modality_name in data_param:
try:
csv_file = data_param[modality_name].csv_file
except AttributeError:
tf.logging.fatal('unrecognised parameter format')
raise
if hasattr(data_param[modality_name], 'path_to_search') and \
len(data_param[modality_name].path_to_search):
tf.logging.info('[%s] search file folders, writing csv file %s',
modality_name, csv_file)
section_tuple = data_param[modality_name].__dict__.items()
matcher = KeywordsMatching.from_tuple(section_tuple,
default_folder)
match_and_write_filenames_to_csv([matcher], csv_file)
else:
tf.logging.info(
'[%s] using existing csv file %s, skipped folder search',
modality_name, csv_file)
if not os.path.isfile(csv_file):
tf.logging.fatal("[%s] csv file %s not found.", modality_name,
csv_file)
raise IOError
csv_list = pandas.read_csv(csv_file,
header=None,
names=['subject_id', modality_name])
if _file_list is None:
_file_list = csv_list
continue
# merge _file_list based on subject_ids (first column of each csv)
n_rows = _file_list.shape[0]
_file_list = pandas.merge(_file_list, csv_list, on='subject_id')
if _file_list.shape[0] != n_rows:
tf.logging.warning("rows not matched in %s", csv_file)
if _file_list is None or _file_list.size == 0:
tf.logging.fatal(
"empty filename lists, please check the csv "
"files. (remove csv_file keyword if it is in the config file "
"to automatically search folders and generate new csv "
"files again)\n\n"
"Please note in the matched file names, each subject name are "
"matched by removing any keywords listed `filename_contains` "
"in the config.\n\n")
raise IOError
return _file_list
def test_keywords_grep(self):
matcher = KeywordsMatching.from_dict(
{'path_to_search': 'testing_data/images2d',
'filename_contains': 'img'})
f_list, s_list = matcher.matching_subjects_and_filenames()
self.assertEqual(len(f_list), 30)
self.assertEqual(len(s_list), 30)
# filename matched 'img' will return and
# the matched string is removed from subject_id
self.assertEqual(s_list[0][0], '0_g')
def grep_files_by_data_section(self, modality_name):
"""
list all files by a given input data section::
if the ``csv_file`` property of the section corresponds to a file,
read the list from the file;
otherwise
write the list to ``csv_file``.
:return: a table with two columns,
the column names are ``(COLUMN_UNIQ_ID, modality_name)``.
"""
if modality_name not in self.data_param:
tf.logging.fatal('unknown section name [%s], '
'current input section names: %s.',
modality_name, list(self.data_param))
raise ValueError
# input data section must have a ``csv_file`` section for loading
# or writing filename lists
try:
csv_file = self.data_param[modality_name].csv_file
if not os.path.isfile(csv_file):
# writing to the same folder as data_split_file
csv_file = os.path.join(os.path.dirname(self.data_split_file),
'{}.csv'.format(modality_name))
except (AttributeError, TypeError):
tf.logging.fatal('Missing `csv_file` field in the config file, '
'unknown configuration format.')
raise
if hasattr(self.data_param[modality_name], 'path_to_search') and \
self.data_param[modality_name].path_to_search:
tf.logging.info('[%s] search file folders, writing csv file %s',
modality_name, csv_file)
section_properties = self.data_param[modality_name].__dict__.items()
# grep files by section properties and write csv
try:
matcher = KeywordsMatching.from_tuple(
section_properties,
self.default_image_file_location)
match_and_write_filenames_to_csv([matcher], csv_file)
except (IOError, ValueError) as reading_error:
tf.logging.warning('Ignoring input section: [%s], '
'due to the following error:',
modality_name)
tf.logging.warning(repr(reading_error))
return pandas.DataFrame(
columns=[COLUMN_UNIQ_ID, modality_name])
else:
tf.logging.info(
'[%s] using existing csv file %s, skipped filenames search',
modality_name, csv_file)
if not os.path.isfile(csv_file):
tf.logging.fatal(
'[%s] csv file %s not found.', modality_name, csv_file)
raise IOError
try:
csv_list = pandas.read_csv(
csv_file,
header=None,
dtype=(str, str),
names=[COLUMN_UNIQ_ID, modality_name],
skipinitialspace=True)
except Exception as csv_error:
tf.logging.fatal(repr(csv_error))
raise
return csv_list
def grep_files_by_data_section(self, modality_name):
"""
list all files by a given input data section::
if the ``csv_file`` property of ``data_param[modality_name]``
corresponds to a file, read the list from the file;
otherwise
write the list to ``csv_file``.
:return: a table with two columns,
the column names are ``(COLUMN_UNIQ_ID, modality_name)``.
"""
if modality_name not in self.data_param:
tf.logging.fatal(
'unknown section name [%s], '
'current input section names: %s.', modality_name,
list(self.data_param))
raise ValueError
# input data section must have a ``csv_file`` section for loading
# or writing filename lists
if isinstance(self.data_param[modality_name], dict):
mod_spec = self.data_param[modality_name]
else:
mod_spec = vars(self.data_param[modality_name])
#########################
# guess the csv_file path
#########################
temp_csv_file = None
try:
csv_file = os.path.expanduser(mod_spec.get('csv_file', None))
if not os.path.isfile(csv_file):
# writing to the same folder as data_split_file
default_csv_file = os.path.join(
os.path.dirname(self.data_split_file),
'{}.csv'.format(modality_name))
tf.logging.info(
'`csv_file = %s` not found, '
'writing to "%s" instead.', csv_file, default_csv_file)
csv_file = default_csv_file
if os.path.isfile(csv_file):
tf.logging.info('Overwriting existing: "%s".', csv_file)
csv_file = os.path.abspath(csv_file)
except (AttributeError, KeyError, TypeError):
tf.logging.debug('`csv_file` not specified, writing the list of '
'filenames to a temporary file.')
import tempfile
temp_csv_file = os.path.join(tempfile.mkdtemp(),
'{}.csv'.format(modality_name))
csv_file = temp_csv_file
#############################################
# writing csv file if path_to_search specified
##############################################
if mod_spec.get('path_to_search', None):
if not temp_csv_file:
tf.logging.info(
'[%s] search file folders, writing csv file %s',
modality_name, csv_file)
# grep files by section properties and write csv
try:
matcher = KeywordsMatching.from_dict(
input_dict=mod_spec,
default_folder=self.default_image_file_location)
match_and_write_filenames_to_csv([matcher], csv_file)
except (IOError, ValueError) as reading_error:
tf.logging.warning(
'Ignoring input section: [%s], '
'due to the following error:', modality_name)
tf.logging.warning(repr(reading_error))
return pandas.DataFrame(
columns=[COLUMN_UNIQ_ID, modality_name])
else:
tf.logging.info(
'[%s] using existing csv file %s, skipped filenames search',
modality_name, csv_file)
if not os.path.isfile(csv_file):
tf.logging.fatal('[%s] csv file %s not found.', modality_name,
csv_file)
raise IOError
###############################
# loading the file as dataframe
###############################
try:
csv_list = pandas.read_csv(csv_file,
header=None,
dtype=(str, str),
names=[COLUMN_UNIQ_ID, modality_name],
skipinitialspace=True)
except Exception as csv_error:
tf.logging.fatal(repr(csv_error))
raise
if temp_csv_file:
shutil.rmtree(os.path.dirname(temp_csv_file), ignore_errors=True)
return csv_list
def test_default(self):
matcher = KeywordsMatching()
with self.assertRaisesRegexp(ValueError, ""):
matcher.matching_subjects_and_filenames()
with self.assertRaisesRegexp(AttributeError, ""):
KeywordsMatching.from_dict('wrong_argument')
def grep_files_by_data_section(self, modality_name):
"""
list all files by a given input data section::
if the ``csv_file`` property of ``data_param[modality_name]``
corresponds to a file, read the list from the file;
otherwise
write the list to ``csv_file``.
:return: a table with two columns,
the column names are ``(COLUMN_UNIQ_ID, modality_name)``.
"""
if modality_name not in self.data_param:
tf.logging.fatal('unknown section name [%s], '
'current input section names: %s.',
modality_name, list(self.data_param))
raise ValueError
# input data section must have a ``csv_file`` section for loading
# or writing filename lists
if isinstance(self.data_param[modality_name], dict):
mod_spec = self.data_param[modality_name]
else:
mod_spec = vars(self.data_param[modality_name])
#########################
# guess the csv_file path
#########################
temp_csv_file = None
try:
csv_file = os.path.expanduser(mod_spec.get('csv_file', None))
if not os.path.isfile(csv_file):
# writing to the same folder as data_split_file
default_csv_file = os.path.join(
os.path.dirname(self.data_split_file),
'{}.csv'.format(modality_name))
tf.logging.info('`csv_file = %s` not found, '
'writing to "%s" instead.',
csv_file, default_csv_file)
csv_file = default_csv_file
if os.path.isfile(csv_file):
tf.logging.info('Overwriting existing: "%s".', csv_file)
csv_file = os.path.abspath(csv_file)
except (AttributeError, KeyError, TypeError):
tf.logging.debug('`csv_file` not specified, writing the list of '
'filenames to a temporary file.')
import tempfile
temp_csv_file = os.path.join(
tempfile.mkdtemp(), '{}.csv'.format(modality_name))
csv_file = temp_csv_file
#############################################
# writing csv file if path_to_search specified
##############################################
if mod_spec.get('path_to_search', None):
if not temp_csv_file:
tf.logging.info(
'[%s] search file folders, writing csv file %s',
modality_name, csv_file)
# grep files by section properties and write csv
try:
matcher = KeywordsMatching.from_dict(
input_dict=mod_spec,
default_folder=self.default_image_file_location)
match_and_write_filenames_to_csv([matcher], csv_file)
except (IOError, ValueError) as reading_error:
tf.logging.warning('Ignoring input section: [%s], '
'due to the following error:',
modality_name)
tf.logging.warning(repr(reading_error))
return pandas.DataFrame(
columns=[COLUMN_UNIQ_ID, modality_name])
else:
tf.logging.info(
'[%s] using existing csv file %s, skipped filenames search',
modality_name, csv_file)
if not os.path.isfile(csv_file):
tf.logging.fatal(
'[%s] csv file %s not found.', modality_name, csv_file)
raise IOError
###############################
# loading the file as dataframe
###############################
try:
csv_list = pandas.read_csv(
csv_file,
header=None,
dtype=(str, str),
names=[COLUMN_UNIQ_ID, modality_name],
skipinitialspace=True)
except Exception as csv_error:
tf.logging.fatal(repr(csv_error))
raise
finally:
if temp_csv_file:
os.remove(temp_csv_file)
os.rmdir(os.path.dirname(temp_csv_file))
return csv_list
def grep_files_by_data_section(self, modality_name):
"""
list all files by a given input data section::
if the ``csv_file`` property of the section corresponds to a file,
read the list from the file;
otherwise
write the list to ``csv_file``.
:return: a table with two columns,
the column names are ``(COLUMN_UNIQ_ID, modality_name)``.
"""
if modality_name not in self.data_param:
tf.logging.fatal(
'unknown section name [%s], '
'current input section names: %s.', modality_name,
list(self.data_param))
raise ValueError
# input data section must have a ``csv_file`` section for loading
# or writing filename lists
try:
csv_file = self.data_param[modality_name].csv_file
if not os.path.isfile(csv_file):
# writing to the same folder as data_split_file
csv_file = os.path.join(os.path.dirname(self.data_split_file),
'{}.csv'.format(modality_name))
except (AttributeError, TypeError):
tf.logging.fatal('Missing `csv_file` field in the config file, '
'unknown configuration format.')
raise
if hasattr(self.data_param[modality_name], 'path_to_search') and \
self.data_param[modality_name].path_to_search:
tf.logging.info('[%s] search file folders, writing csv file %s',
modality_name, csv_file)
section_properties = self.data_param[modality_name].__dict__.items(
)
# grep files by section properties and write csv
try:
matcher = KeywordsMatching.from_tuple(
section_properties, self.default_image_file_location)
match_and_write_filenames_to_csv([matcher], csv_file)
except (IOError, ValueError) as reading_error:
tf.logging.warning(
'Ignoring input section: [%s], '
'due to the following error:', modality_name)
tf.logging.warning(repr(reading_error))
return pandas.DataFrame(
columns=[COLUMN_UNIQ_ID, modality_name])
else:
tf.logging.info(
'[%s] using existing csv file %s, skipped filenames search',
modality_name, csv_file)
if not os.path.isfile(csv_file):
tf.logging.fatal('[%s] csv file %s not found.', modality_name,
csv_file)
raise IOError
try:
csv_list = pandas.read_csv(csv_file,
header=None,
dtype=(str, str),
names=[COLUMN_UNIQ_ID, modality_name],
skipinitialspace=True)
except Exception as csv_error:
tf.logging.fatal(repr(csv_error))
raise
return csv_list
