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

[CI] Use latest RAPIDS; Pandas 2.0 compatibility fix (#10175)

Browse Source 
* [CI] Update RAPIDS to latest stable

* [CI] Use rapidsai stable channel; fix syntax errors in Dockerfile.gpu

* Don't combine astype() with loc()

* Work around https://github.com/dmlc/xgboost/issues/10181

* Fix formatting

* Fix test

---------

Co-authored-by: hcho3 <hcho3@users.noreply.github.com>
Co-authored-by: Hyunsu Cho <chohyu01@cs.washington.edu>
This commit is contained in:
github-actions[bot] 2024-04-15 13:38:53 -07:00 committed by GitHub
parent 6e5c335cea
commit 2925cebdca
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 18 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
python-package/xgboost/data.py
View File

@ -909,9 +909,19 @@ def _transform_cudf_df(
enable_categorical: bool, enable_categorical: bool,
) -> Tuple[ctypes.c_void_p, list, Optional[FeatureNames], Optional[FeatureTypes]]: ) -> Tuple[ctypes.c_void_p, list, Optional[FeatureNames], Optional[FeatureTypes]]:
try: try:
from cudf.api.types import is_categorical_dtype from cudf.api.types import is_bool_dtype, is_categorical_dtype
except ImportError: except ImportError:
from cudf.utils.dtypes import is_categorical_dtype from cudf.utils.dtypes import is_categorical_dtype
from pandas.api.types import is_bool_dtype
# Work around https://github.com/dmlc/xgboost/issues/10181
if _is_cudf_ser(data):
if is_bool_dtype(data.dtype):
data = data.astype(np.uint8)
else:
data = data.astype(
{col: np.uint8 for col in data.select_dtypes(include="bool")}
)
if _is_cudf_ser(data): if _is_cudf_ser(data):
dtypes = [data.dtype] dtypes = [data.dtype]

4
python-package/xgboost/testing/__init__.py
View File

@ -429,8 +429,8 @@ def make_categorical(
categories = np.arange(0, n_categories) categories = np.arange(0, n_categories)
for col in df.columns: for col in df.columns:
if rng.binomial(1, cat_ratio, size=1)[0] == 1: if rng.binomial(1, cat_ratio, size=1)[0] == 1:
df.loc[:, col] = df[col].astype("category") df[col] = df[col].astype("category")
df.loc[:, col] = df[col].cat.set_categories(categories) df[col] = df[col].cat.set_categories(categories)
if sparsity > 0.0: if sparsity > 0.0:
for i in range(n_features): for i in range(n_features):

2
tests/buildkite/conftest.sh
View File

@ -24,7 +24,7 @@ set -x
CUDA_VERSION=11.8.0 CUDA_VERSION=11.8.0
NCCL_VERSION=2.16.5-1 NCCL_VERSION=2.16.5-1
RAPIDS_VERSION=24.02 RAPIDS_VERSION=24.04
SPARK_VERSION=3.4.0 SPARK_VERSION=3.4.0
JDK_VERSION=8 JDK_VERSION=8
R_VERSION=4.3.2 R_VERSION=4.3.2

8
tests/ci_build/Dockerfile.gpu
View File

@ -21,14 +21,14 @@ ENV PATH=/opt/mambaforge/bin:$PATH
# Create new Conda environment with cuDF, Dask, and cuPy # Create new Conda environment with cuDF, Dask, and cuPy
RUN \ RUN \
conda install -c conda-forge mamba && \ export NCCL_SHORT_VER=$(echo "$NCCL_VERSION_ARG" | cut -d "-" -f 1) && \
mamba create -n gpu_test -c rapidsai-nightly -c rapidsai -c nvidia -c conda-forge -c defaults \ mamba create -y -n gpu_test -c rapidsai -c nvidia -c conda-forge \
python=3.10 cudf=$RAPIDS_VERSION_ARG* rmm=$RAPIDS_VERSION_ARG* cudatoolkit=$CUDA_VERSION_ARG \ python=3.10 cudf=$RAPIDS_VERSION_ARG* rmm=$RAPIDS_VERSION_ARG* cudatoolkit=$CUDA_VERSION_ARG \
nccl>=$(cut -d "-" -f 1 << $NCCL_VERSION_ARG) \ "nccl>=${NCCL_SHORT_VER}" \
dask=2024.1.1 \ dask=2024.1.1 \
dask-cuda=$RAPIDS_VERSION_ARG* dask-cudf=$RAPIDS_VERSION_ARG* cupy \ dask-cuda=$RAPIDS_VERSION_ARG* dask-cudf=$RAPIDS_VERSION_ARG* cupy \
numpy pytest pytest-timeout scipy scikit-learn pandas matplotlib wheel python-kubernetes urllib3 graphviz hypothesis \ numpy pytest pytest-timeout scipy scikit-learn pandas matplotlib wheel python-kubernetes urllib3 graphviz hypothesis \
pyspark>=3.4.0 cloudpickle cuda-python && \ "pyspark>=3.4.0" cloudpickle cuda-python && \
mamba clean --all && \ mamba clean --all && \
conda run --no-capture-output -n gpu_test pip install buildkite-test-collector conda run --no-capture-output -n gpu_test pip install buildkite-test-collector

9
tests/python-gpu/test_from_cudf.py
View File

@ -71,15 +71,6 @@ def _test_from_cudf(DMatrixT):
assert dtrain.num_col() == 1 assert dtrain.num_col() == 1
assert dtrain.num_row() == 5 assert dtrain.num_row() == 5
# Boolean is not supported.
X_boolean = cudf.DataFrame({"x": cudf.Series([True, False])})
with pytest.raises(Exception):
dtrain = DMatrixT(X_boolean)
y_boolean = cudf.DataFrame({"x": cudf.Series([True, False, True, True, True])})
with pytest.raises(Exception):
dtrain = DMatrixT(X_boolean, label=y_boolean)
def _test_cudf_training(DMatrixT): def _test_cudf_training(DMatrixT):
import pandas as pd import pandas as pd