def get_monthyeardate_to_paths_map(file_prefix="pm", start_year=-np.Inf, end_year=np.Inf, samples_dir_path=None):
if isinstance(samples_dir_path, str):
samples_dir_path = Path(samples_dir_path)
monthyear_to_pathlist = {}
for monthdir in samples_dir_path.iterdir():
y, m = commons.get_year_and_month(monthdir.name)
if not (start_year <= y <= end_year):
continue
current_list = [str(p) for p in monthdir.iterdir() if p.name.startswith(file_prefix) and not p.name[-9:-1] == 8 * "0"]
monthyear_to_pathlist[datetime(y, m, 1)] = current_list
return monthyear_to_pathlist
def get_monthyeardate_to_paths_map(file_prefix="pm", start_year=-np.Inf, end_year=np.Inf, samples_dir_path=None):
if isinstance(samples_dir_path, str):
samples_dir_path = Path(samples_dir_path)
monthyear_to_pathlist = {}
for monthdir in samples_dir_path.iterdir():
y, m = commons.get_year_and_month(monthdir.name)
if not (start_year <= y <= end_year):
continue
current_list = [
str(p) for p in monthdir.iterdir() if p.name.startswith(file_prefix) and not p.name[-9:-1] == 8 * "0"
]
monthyear_to_pathlist[datetime(y, m, 1)] = current_list
return monthyear_to_pathlist
def get_seasonal_means_from_rpn_monthly_folders(samples_dir="", season_to_months=None, start_year=-np.Inf, end_year=np.Inf,
filename_prefix="pm", varname="", level=-1, level_kind=-1):
result = OrderedDict()
season_to_files = {s: [] for s in season_to_months}
smpls_dir = Path(samples_dir)
for month_folder in smpls_dir.iterdir():
y, m = get_year_and_month(month_folder.name)
# skip if the year is not in the selected range
if not start_year <= y <= end_year:
continue
for season, months in season_to_months.items():
if m in months:
for data_file in month_folder.iterdir():
if data_file.name[-9:-1] == 8 * "0":
continue
if data_file.name.startswith(filename_prefix):
season_to_files[season].append(str(data_file))
for season, months in season_to_months.items():
print("{} => {}".format(season, months))
mrpn = MultiRPN(season_to_files[season])
date_to_field = mrpn.get_all_time_records_for_name_and_level(varname=varname, level=level, level_kind=level_kind)
result[season] = np.mean([field for field in date_to_field.values()], axis=0)
return result
