Function read_table

python/pyarrow/feather.py:230–279

Read a pyarrow.Table from Feather format Parameters ---------- source : str file path, or file-like object You can use MemoryMappedFile as source, for explicitly use memory map. columns : sequence, optional Only read a specific set of columns. If not provided, a

(source, columns=None, memory_map=False, use_threads=True)

def read_table(source, columns=None, memory_map=False, use_threads=True):
    """
    Read a pyarrow.Table from Feather format

    Parameters
    ----------
    source : str file path, or file-like object
        You can use MemoryMappedFile as source, for explicitly use memory map.
    columns : sequence, optional
        Only read a specific set of columns. If not provided, all columns are
        read.
    memory_map : boolean, default False
        Use memory mapping when opening file on disk, when source is a str
    use_threads : bool, default True
        Whether to parallelize reading using multiple threads.

    Returns
    -------
    table : pyarrow.Table
        The contents of the Feather file as a pyarrow.Table
    """
    reader = _feather.FeatherReader(
        source, use_memory_map=memory_map, use_threads=use_threads)

    if columns is None:
        return reader.read()

    if not isinstance(columns, Sequence):
        raise TypeError("Columns must be a sequence but, got {}"
                        .format(type(columns).__name__))

    column_types = [type(column) for column in columns]
    if all(map(lambda t: t == int, column_types)):
        table = reader.read_indices(columns)
    elif all(map(lambda t: t == str, column_types)):
        table = reader.read_names(columns)
    else:
        column_type_names = [t.__name__ for t in column_types]
        raise TypeError("Columns must be indices or names. "
                        f"Got columns {columns} of types {column_type_names}")

    # Feather v1 already respects the column selection
    if reader.version < 3:
        return table
    # Feather v2 reads with sorted / deduplicated selection
    elif sorted(set(columns)) == columns:
        return table
    else:
        # follow exact order / selection of names
        return table.select(columns)