Function table_to_dataframe

python/pyarrow/pandas_compat.py:794–853

(
    options, table, categories=None, ignore_metadata=False, types_mapper=None
)

def table_to_dataframe(
    options, table, categories=None, ignore_metadata=False, types_mapper=None
):
    all_columns = []
    column_indexes = []
    attributes = {}
    pandas_metadata = table.schema.pandas_metadata

    if not ignore_metadata and pandas_metadata is not None:
        all_columns = pandas_metadata['columns']
        column_indexes = pandas_metadata.get('column_indexes', [])
        attributes = pandas_metadata.get('attributes', {})
        index_descriptors = pandas_metadata['index_columns']
        table = _add_any_metadata(table, pandas_metadata)
        table, index = _reconstruct_index(table, index_descriptors,
                                          all_columns, types_mapper)
        ext_columns_dtypes = _get_extension_dtypes(
            table, all_columns, types_mapper, options, categories)
    else:
        index = _pandas_api.pd.RangeIndex(table.num_rows)
        ext_columns_dtypes = _get_extension_dtypes(
            table, [], types_mapper, options, categories
        )

    _check_data_column_metadata_consistency(all_columns)
    columns = _deserialize_column_index(table, all_columns, column_indexes)

    column_names = table.column_names
    result = pa.lib.table_to_blocks(options, table, categories,
                                    list(ext_columns_dtypes.keys()))
    if _pandas_api.is_ge_v3():
        from pandas.api.internals import create_dataframe_from_blocks

        blocks = [
            _reconstruct_block(
                item, column_names, ext_columns_dtypes, return_block=False)
            for item in result
        ]
        df = create_dataframe_from_blocks(blocks, index=index, columns=columns)
        df.attrs = attributes

        return df
    else:
        from pandas.core.internals import BlockManager
        from pandas import DataFrame

        blocks = [
            _reconstruct_block(item, column_names, ext_columns_dtypes)
            for item in result
        ]
        axes = [columns, index]
        mgr = BlockManager(blocks, axes)
        if _pandas_api.is_ge_v21():
            df = DataFrame._from_mgr(mgr, mgr.axes)
        else:
            df = DataFrame(mgr)

        df.attrs = attributes