Lazy import cuDF and Dask (#6522)

* 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>

python-package/xgboost/compat.py

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

python-package/xgboost/dask.py

@@ -27,7 +27,6 @@
 from .compat import LazyLoader
 from .compat import sparse, scipy_sparse
 from .compat import PANDAS_INSTALLED, DataFrame, Series, pandas_concat
-from .compat import CUDF_concat
 from .compat import lazy_isinstance
 
 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)
     if lazy_isinstance(value[0], 'cudf.core.dataframe', 'DataFrame') or \
        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)
     if lazy_isinstance(value[0], 'cupy.core.core', 'ndarray'):
         import cupy             # pylint: disable=import-error