137 lines
3.4 KiB
Python
137 lines
3.4 KiB
Python
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from typing import (
|
||
|
|
TYPE_CHECKING,
|
||
|
|
Any,
|
||
|
|
)
|
||
|
|
|
||
|
|
from pandas.core.interchange.dataframe_protocol import (
|
||
|
|
Buffer,
|
||
|
|
DlpackDeviceType,
|
||
|
|
)
|
||
|
|
|
||
|
|
if TYPE_CHECKING:
|
||
|
|
import numpy as np
|
||
|
|
import pyarrow as pa
|
||
|
|
|
||
|
|
|
||
|
|
class PandasBuffer(Buffer):
|
||
|
|
"""
|
||
|
|
Data in the buffer is guaranteed to be contiguous in memory.
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(self, x: np.ndarray, allow_copy: bool = True) -> None:
|
||
|
|
"""
|
||
|
|
Handle only regular columns (= numpy arrays) for now.
|
||
|
|
"""
|
||
|
|
if x.strides[0] and not x.strides == (x.dtype.itemsize,):
|
||
|
|
# The protocol does not support strided buffers, so a copy is
|
||
|
|
# necessary. If that's not allowed, we need to raise an exception.
|
||
|
|
if allow_copy:
|
||
|
|
x = x.copy()
|
||
|
|
else:
|
||
|
|
raise RuntimeError(
|
||
|
|
"Exports cannot be zero-copy in the case "
|
||
|
|
"of a non-contiguous buffer"
|
||
|
|
)
|
||
|
|
|
||
|
|
# Store the numpy array in which the data resides as a private
|
||
|
|
# attribute, so we can use it to retrieve the public attributes
|
||
|
|
self._x = x
|
||
|
|
|
||
|
|
@property
|
||
|
|
def bufsize(self) -> int:
|
||
|
|
"""
|
||
|
|
Buffer size in bytes.
|
||
|
|
"""
|
||
|
|
return self._x.size * self._x.dtype.itemsize
|
||
|
|
|
||
|
|
@property
|
||
|
|
def ptr(self) -> int:
|
||
|
|
"""
|
||
|
|
Pointer to start of the buffer as an integer.
|
||
|
|
"""
|
||
|
|
return self._x.__array_interface__["data"][0]
|
||
|
|
|
||
|
|
def __dlpack__(self) -> Any:
|
||
|
|
"""
|
||
|
|
Represent this structure as DLPack interface.
|
||
|
|
"""
|
||
|
|
return self._x.__dlpack__()
|
||
|
|
|
||
|
|
def __dlpack_device__(self) -> tuple[DlpackDeviceType, int | None]:
|
||
|
|
"""
|
||
|
|
Device type and device ID for where the data in the buffer resides.
|
||
|
|
"""
|
||
|
|
return (DlpackDeviceType.CPU, None)
|
||
|
|
|
||
|
|
def __repr__(self) -> str:
|
||
|
|
return (
|
||
|
|
"PandasBuffer("
|
||
|
|
+ str(
|
||
|
|
{
|
||
|
|
"bufsize": self.bufsize,
|
||
|
|
"ptr": self.ptr,
|
||
|
|
"device": self.__dlpack_device__()[0].name,
|
||
|
|
}
|
||
|
|
)
|
||
|
|
+ ")"
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
class PandasBufferPyarrow(Buffer):
|
||
|
|
"""
|
||
|
|
Data in the buffer is guaranteed to be contiguous in memory.
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(
|
||
|
|
self,
|
||
|
|
buffer: pa.Buffer,
|
||
|
|
*,
|
||
|
|
length: int,
|
||
|
|
) -> None:
|
||
|
|
"""
|
||
|
|
Handle pyarrow chunked arrays.
|
||
|
|
"""
|
||
|
|
self._buffer = buffer
|
||
|
|
self._length = length
|
||
|
|
|
||
|
|
@property
|
||
|
|
def bufsize(self) -> int:
|
||
|
|
"""
|
||
|
|
Buffer size in bytes.
|
||
|
|
"""
|
||
|
|
return self._buffer.size
|
||
|
|
|
||
|
|
@property
|
||
|
|
def ptr(self) -> int:
|
||
|
|
"""
|
||
|
|
Pointer to start of the buffer as an integer.
|
||
|
|
"""
|
||
|
|
return self._buffer.address
|
||
|
|
|
||
|
|
def __dlpack__(self) -> Any:
|
||
|
|
"""
|
||
|
|
Represent this structure as DLPack interface.
|
||
|
|
"""
|
||
|
|
raise NotImplementedError()
|
||
|
|
|
||
|
|
def __dlpack_device__(self) -> tuple[DlpackDeviceType, int | None]:
|
||
|
|
"""
|
||
|
|
Device type and device ID for where the data in the buffer resides.
|
||
|
|
"""
|
||
|
|
return (DlpackDeviceType.CPU, None)
|
||
|
|
|
||
|
|
def __repr__(self) -> str:
|
||
|
|
return (
|
||
|
|
"PandasBuffer[pyarrow]("
|
||
|
|
+ str(
|
||
|
|
{
|
||
|
|
"bufsize": self.bufsize,
|
||
|
|
"ptr": self.ptr,
|
||
|
|
"device": "CPU",
|
||
|
|
}
|
||
|
|
)
|
||
|
|
+ ")"
|
||
|
|
)
|