diff --git a/nannyml/chunk.py b/nannyml/chunk.py index f986448f..4fe6ced0 100644 --- a/nannyml/chunk.py +++ b/nannyml/chunk.py @@ -331,14 +331,14 @@ class SizeBasedChunker(Chunker): """ - def __init__(self, chunk_size: int, incomplete: str = 'append', timestamp_column_name: Optional[str] = None): + def __init__(self, chunk_size: int, incomplete: str = 'keep', timestamp_column_name: Optional[str] = None): """Create a new SizeBasedChunker. Parameters ---------- chunk_size: int The preferred size of the resulting Chunks, i.e. the number of observations in each Chunk. - incomplete: str, default='append' + incomplete: str, default='keep' Choose how to handle any leftover observations that don't make up a full Chunk. The following options are available: @@ -429,7 +429,7 @@ class CountBasedChunker(Chunker): """ - def __init__(self, chunk_number: int, incomplete: str = 'append', timestamp_column_name: Optional[str] = None): + def __init__(self, chunk_number: int, incomplete: str = 'keep', timestamp_column_name: Optional[str] = None): """Creates a new CountBasedChunker. It will calculate the amount of observations per chunk based on the given chunk count. @@ -450,7 +450,7 @@ def __init__(self, chunk_number: int, incomplete: str = 'append', timestamp_colu - ``'append'``: append leftover observations to the last complete Chunk (overfilling it) - Defaults to ``'append'``. + Defaults to ``'keep'``. Returns ------- diff --git a/nannyml/config.py b/nannyml/config.py index adc43b45..2e8e4743 100644 --- a/nannyml/config.py +++ b/nannyml/config.py @@ -40,12 +40,6 @@ class WriterConfig(BaseModel): write_args: Optional[Dict[str, Any]] -class ChunkerConfig(BaseModel): - chunk_size: Optional[int] - chunk_period: Optional[str] - chunk_count: Optional[int] - - class IntervalSchedulingConfig(BaseModel): weeks: Optional[int] days: Optional[int]