gluonts.dataset.arrow.file module#

class gluonts.dataset.arrow.file.ArrowFile(path: pathlib.Path, _start: int = 0, _take: Optional[int] = None)[source]#

Bases: File

property batch_offsets#
decoder: ArrowDecoder#
iter_batches()[source]#
location_for(idx)[source]#
metadata() Dict[str, str][source]#
path: Path#
reader: RecordBatchFileReader#
property schema#
class gluonts.dataset.arrow.file.ArrowStreamFile(path: pathlib.Path, _start: int = 0, _take: Optional[int] = None)[source]#

Bases: File

metadata() Dict[str, str][source]#
path: Path#
class gluonts.dataset.arrow.file.File[source]#

Bases: object

SUFFIXES = {'.arrow', '.feather', '.parquet'}#
static infer(path: Path) Union[ArrowFile, ArrowStreamFile, ParquetFile][source]#

Return ArrowFile, ArrowStreamFile or ParquetFile by inspecting provided path.

Arrow’s random-access format starts with ARROW1, so we peek the provided file for it.

abstract metadata() Dict[str, str][source]#
class gluonts.dataset.arrow.file.ParquetFile(path: pathlib.Path, _start: int = 0, _take: Optional[int] = None, _row_group_sizes: List[int] = <factory>)[source]#

Bases: File

location_for(idx)[source]#
metadata() Dict[str, str][source]#
path: Path#
reader: ParquetFile#