odps/mars_extension/legacy/dataframe/datasource.py [726:752]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @classmethod
    def estimate_size(cls, ctx, op):
        import numpy as np

        def is_object_dtype(dtype):
            try:
                return (
                    np.issubdtype(dtype, np.object_)
                    or np.issubdtype(dtype, np.unicode_)
                    or np.issubdtype(dtype, np.bytes_)
                )
            except TypeError:  # pragma: no cover
                return False

        if op.split_size is None:
            ctx[op.outputs[0].key] = (0, 0)
            return

        arrow_size = (op.memory_scale or ORC_COMPRESSION_RATIO) * op.split_size
        if op.meta_raw_size is not None:
            raw_arrow_size = (op.memory_scale or 1) * op.meta_raw_size
            arrow_size = max(arrow_size, raw_arrow_size)

        n_strings = len([dt for dt in op.dtypes if is_object_dtype(dt)])
        if op.estimate_rows or op.nrows:
            rows = op.nrows if op.nrows is not None else op.estimate_rows
            pd_size = arrow_size + n_strings * rows * STRING_FIELD_OVERHEAD
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



odps/mars_extension/oscar/dataframe/datasource.py [525:551]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @classmethod
    def estimate_size(cls, ctx, op):
        import numpy as np

        def is_object_dtype(dtype):
            try:
                return (
                    np.issubdtype(dtype, np.object_)
                    or np.issubdtype(dtype, np.unicode_)
                    or np.issubdtype(dtype, np.bytes_)
                )
            except TypeError:  # pragma: no cover
                return False

        if op.split_size is None:
            ctx[op.outputs[0].key] = (0, 0)
            return

        arrow_size = (op.memory_scale or ORC_COMPRESSION_RATIO) * op.split_size
        if op.meta_raw_size is not None:
            raw_arrow_size = (op.memory_scale or 1) * op.meta_raw_size
            arrow_size = max(arrow_size, raw_arrow_size)

        n_strings = len([dt for dt in op.dtypes if is_object_dtype(dt)])
        if op.estimate_rows or op.nrows:
            rows = op.nrows if op.nrows is not None else op.estimate_rows
            pd_size = arrow_size + n_strings * rows * STRING_FIELD_OVERHEAD
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -