Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Support for all primitive types from array. (#7003)

Browse Source 
* Change C API name.
* Test for all primitive types from array.
* Add native support for CPU 128 float.
* Convert boolean and float16 in Python.

* Fix dask version for now.
This commit is contained in:
Jiaming Yuan
2021-06-01 08:34:48 +08:00
committed by GitHub
parent 816b789bf0
commit ee4f51a631
8 changed files with 154 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
python-package/xgboost/core.py
View File

@@ -239,7 +239,18 @@ def _array_interface(data: np.ndarray) -> bytes:
interface = data.__array_interface__
if "mask" in interface:
interface["mask"] = interface["mask"].__array_interface__
interface_str = bytes(json.dumps(interface, indent=2), "utf-8")
interface_str = bytes(json.dumps(interface), "utf-8")
return interface_str
def _cuda_array_interface(data) -> bytes:
assert (
data.dtype.hasobject is False
), "Input data contains `object` dtype. Expecting numeric data."
interface = data.__cuda_array_interface__
if "mask" in interface:
interface["mask"] = interface["mask"].__cuda_array_interface__
interface_str = bytes(json.dumps(interface), "utf-8")
return interface_str
@@ -1948,10 +1959,7 @@ class Booster(object):
from .data import _transform_cupy_array
data = _transform_cupy_array(data)
interface = data.__cuda_array_interface__
if "mask" in interface:
interface["mask"] = interface["mask"].__cuda_array_interface__
interface_str = bytes(json.dumps(interface, indent=2), "utf-8")
interface_str = _cuda_array_interface(data)
_check_call(
_LIB.XGBoosterPredictFromCudaArray(
self.handle,

17
python-package/xgboost/data.py
View File

@@ -9,7 +9,8 @@ from typing import Any
import numpy as np
from .core import c_array, _LIB, _check_call, c_str, _array_interface
from .core import c_array, _LIB, _check_call, c_str
from .core import _array_interface, _cuda_array_interface
from .core import DataIter, _ProxyDMatrix, DMatrix
from .compat import lazy_isinstance
@@ -105,7 +106,7 @@ def _is_numpy_array(data):
def _ensure_np_dtype(data, dtype):
if data.dtype.hasobject:
if data.dtype.hasobject or data.dtype in [np.float16, np.bool_]:
data = data.astype(np.float32, copy=False)
dtype = np.float32
return data, dtype
@@ -141,7 +142,7 @@ def _from_numpy_array(data, missing, nthread, feature_names, feature_types):
}
config = bytes(json.dumps(args), "utf-8")
_check_call(
_LIB.XGDMatrixCreateFromArray(
_LIB.XGDMatrixCreateFromDense(
_array_interface(data),
config,
ctypes.byref(handle),
@@ -416,21 +417,19 @@ def _is_cupy_array(data):
def _transform_cupy_array(data):
import cupy # pylint: disable=import-error
if not hasattr(data, '__cuda_array_interface__') and hasattr(
data, '__array__'):
import cupy # pylint: disable=import-error
data = cupy.array(data, copy=False)
if data.dtype.hasobject or data.dtype in [cupy.float16, cupy.bool_]:
data = data.astype(cupy.float32, copy=False)
return data
def _from_cupy_array(data, missing, nthread, feature_names, feature_types):
"""Initialize DMatrix from cupy ndarray."""
data = _transform_cupy_array(data)
interface = data.__cuda_array_interface__
if 'mask' in interface:
interface['mask'] = interface['mask'].__cuda_array_interface__
interface_str = bytes(json.dumps(interface, indent=2), 'utf-8')
interface_str = _cuda_array_interface(data)
handle = ctypes.c_void_p()
_check_call(
_LIB.XGDMatrixCreateFromArrayInterface(