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

Lazy import cuDF and Dask (#6522)

Browse Source 
* Lazy import cuDF

* Lazy import Dask

Co-authored-by: PSEUDOTENSOR / Jonathan McKinney <pseudotensor@gmail.com>

* Fix lint

Co-authored-by: PSEUDOTENSOR / Jonathan McKinney <pseudotensor@gmail.com>
This commit is contained in:
Philip Hyunsu Cho 2020-12-17 01:51:35 -08:00 committed by GitHub
parent ad1a527709
commit 125b3c0f2d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
python-package/xgboost/compat.py
View File

@ -41,12 +41,6 @@ except ImportError:
pandas_concat = None pandas_concat = None
PANDAS_INSTALLED = False PANDAS_INSTALLED = False
# cudf
try:
from cudf import concat as CUDF_concat
except ImportError:
CUDF_concat = None
# sklearn # sklearn
try: try:
from sklearn.base import BaseEstimator from sklearn.base import BaseEstimator
@ -104,9 +98,10 @@ except ImportError:
# dask # dask
try: try:
import dask import pkg_resources
pkg_resources.get_distribution('dask')
DASK_INSTALLED = True DASK_INSTALLED = True
except ImportError: except pkg_resources.DistributionNotFound:
dask = None dask = None
DASK_INSTALLED = False DASK_INSTALLED = False

2
python-package/xgboost/dask.py
View File

@ -27,7 +27,6 @@ from . import rabit, config
from .compat import LazyLoader from .compat import LazyLoader
from .compat import sparse, scipy_sparse from .compat import sparse, scipy_sparse
from .compat import PANDAS_INSTALLED, DataFrame, Series, pandas_concat from .compat import PANDAS_INSTALLED, DataFrame, Series, pandas_concat
from .compat import CUDF_concat
from .compat import lazy_isinstance from .compat import lazy_isinstance
from .core import DMatrix, DeviceQuantileDMatrix, Booster, _expect, DataIter from .core import DMatrix, DeviceQuantileDMatrix, Booster, _expect, DataIter
@ -121,6 +120,7 @@ def concat(value): # pylint: disable=too-many-return-statements
return pandas_concat(value, axis=0) return pandas_concat(value, axis=0)
if lazy_isinstance(value[0], 'cudf.core.dataframe', 'DataFrame') or \ if lazy_isinstance(value[0], 'cudf.core.dataframe', 'DataFrame') or \
lazy_isinstance(value[0], 'cudf.core.series', 'Series'): lazy_isinstance(value[0], 'cudf.core.series', 'Series'):
from cudf import concat as CUDF_concat # pylint: disable=import-error
return CUDF_concat(value, axis=0) return CUDF_concat(value, axis=0)
if lazy_isinstance(value[0], 'cupy.core.core', 'ndarray'): if lazy_isinstance(value[0], 'cupy.core.core', 'ndarray'):
import cupy # pylint: disable=import-error import cupy # pylint: disable=import-error