def get_text_lines(
file,
return_lines=None,
rstrip=True,
sort=False,
remove_empty_lines=True,
encoding=None,
):
"""
Return only the nth line of a text file
:param file: Any text file
:param return_lines: Which specific line/lines to read
:param rstrip: Remove trailing characters
:param sort: If true, naturally sort the data
:param remove_empty_lines: If True, ignore empty lines
:param encoding: What encoding the text file has.
Default: None (platform dependent)
:return: The nth line
"""
with open(file, encoding=encoding) as f:
lines = f.readlines()
if rstrip:
lines = [line.strip() for line in lines]
if remove_empty_lines:
lines = list.remove_empty_string(lines)
if sort:
lines = natsorted(lines)
if return_lines is not None:
lines = lines[return_lines]
return lines
def summary_run(args):
# if args.structures_file_path is None:
# args.structures_file_path = get_structures_path()
# reference_structures_table = pd.read_csv(args.structures_file_path)
# else:
# raise NotImplementedError(
# "Only the Allen adult mouse atlas is " "currently supported."
# )
reference_structures_table = pd.read_csv(get_structures_path())
if not args.regions and not args.regions_list:
# regions = list(pd.read_csv(args.structures_file_path)["name"])
regions = list(pd.read_csv(get_structures_path())["name"])
else:
regions = []
if args.regions:
regions = regions + args.regions
if args.regions_list:
regions = regions + list(pd.read_csv(args.regions_list)["name"])
regions = remove_empty_string(regions)
regions = unique_elements_lists(regions)
csvs_folder = args.csv_dir
destination_folder = os.path.join(args.csv_dir, "summary")
csvs_names = [f for f in os.listdir(csvs_folder) if f.endswith(".csv")]
if len(csvs_names) == 0:
raise FileNotFoundError(
"No CSV files were found in the directory: "
"{}. Please check the arguments".format(csvs_folder))
csvs_paths = [os.path.join(csvs_folder, f) for f in csvs_names]
if not os.path.exists(destination_folder):
os.makedirs(destination_folder)
for csv_file_path in csvs_paths:
print("CSV file: {}".format(os.path.basename(csv_file_path)))
summary = make_summary_df_for_brain(
csv_file_path,
regions,
reference_structures_table,
sum_regions=args.sum_regions,
)
filename = os.path.basename(csv_file_path)
dest_path = os.path.join(destination_folder, filename)
summary.to_csv(dest_path, index=False)
print("Done!")
def test_remove_empty_string():
assert (
list_tools.remove_empty_string(list_with_empty) == list_without_empty)