mirror of
https://github.com/deepseek-ai/smallpond
synced 2025-06-26 18:27:45 +00:00
54 lines
1.3 KiB
ReStructuredText
54 lines
1.3 KiB
ReStructuredText
smallpond.logical.dataset.ParquetDataSet
|
|
========================================
|
|
|
|
.. currentmodule:: smallpond.logical.dataset
|
|
|
|
.. autoclass:: ParquetDataSet
|
|
|
|
|
|
.. automethod:: __init__
|
|
|
|
|
|
.. rubric:: Methods
|
|
|
|
.. autosummary::
|
|
|
|
~ParquetDataSet.__init__
|
|
~ParquetDataSet.create_from
|
|
~ParquetDataSet.load_partitioned_datasets
|
|
~ParquetDataSet.log
|
|
~ParquetDataSet.merge
|
|
~ParquetDataSet.partition_by_files
|
|
~ParquetDataSet.partition_by_rows
|
|
~ParquetDataSet.partition_by_size
|
|
~ParquetDataSet.remove_empty_files
|
|
~ParquetDataSet.reset
|
|
~ParquetDataSet.sql_query_fragment
|
|
~ParquetDataSet.to_arrow_table
|
|
~ParquetDataSet.to_batch_reader
|
|
~ParquetDataSet.to_pandas
|
|
|
|
|
|
|
|
|
|
|
|
.. rubric:: Attributes
|
|
|
|
.. autosummary::
|
|
|
|
~ParquetDataSet.generated_columns
|
|
~ParquetDataSet.absolute_paths
|
|
~ParquetDataSet.columns
|
|
~ParquetDataSet.empty
|
|
~ParquetDataSet.estimated_data_size
|
|
~ParquetDataSet.num_files
|
|
~ParquetDataSet.num_rows
|
|
~ParquetDataSet.paths
|
|
~ParquetDataSet.recursive
|
|
~ParquetDataSet.resolved_paths
|
|
~ParquetDataSet.resolved_row_ranges
|
|
~ParquetDataSet.root_dir
|
|
~ParquetDataSet.udfs
|
|
~ParquetDataSet.union_by_name
|
|
|
|
|