def _data_target(self, s):
s = s.replace("?", '"nan"')
values = json.loads(f"[{s}]")
assert (
values
), "A given series should contains a set of comma separated numeric values. At least one numeric value should be there in a series. Missing values should be indicated with ? symbol"
return np.array(values, dtype=float)
def __iter__(self):
# Basic idea is to split the dataset into roughly equally sized segments
# with lower and upper bound, where each worker is assigned one segment
bounds = get_bounds_for_mp_data_loading(len(self))
if not self.cache or (self.cache and not self._data_cache):
with self.open(self.path) as jsonl_file:
for line_number, raw in enumerate(jsonl_file):
if not bounds.lower <= line_number < bounds.upper:
continue
span = Span(path=self.path, line=line_number)
try:
parsed_line = Line(json.loads(raw), span=span)
if self.cache:
self._data_cache.append(parsed_line)
yield parsed_line
except ValueError:
raise GluonTSDataError(
f"Could not read json line {line_number}, {raw}")
else:
yield from self._data_cache
def load(file_obj):
for line in file_obj:
yield json.loads(line)
def load_json(path: Path, freq: str) -> Iterator[Any]:
for file in find_files(path, FileDataset.is_valid):
for line in open(file):
yield json.loads(line)