BUG: Fix no build_categorical_column error of GPU read_parquet (#832)

xorbitsai · Dec 5, 2024 · dfcbf96 · dfcbf96
1 parent 183734a
commit dfcbf96
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 6 deletions.
diff --git a/.github/workflows/python.yaml b/.github/workflows/python.yaml
@@ -155,7 +155,7 @@ jobs:
           pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
           pip install --upgrade --upgrade-strategy only-if-needed --no-cache-dir ".[doc]"
         else
-          pip install -e "git+https://github.com/xorbitsai/xoscar.git@main#subdirectory=python&egg=xoscar"
+          pip install "xoscar<=0.4.1"
           pip install -U numpy scipy cython pyftpdlib coverage flaky numexpr
 
           if [[ "$MODULE" == "xorbits/pandas" ]]; then
@@ -283,7 +283,7 @@ jobs:
       if: ${{ matrix.module == 'gpu' }}
       run: |
         source activate ${{ env.CONDA_ENV }}
-        pip install --extra-index-url=https://pypi.nvidia.com cudf-cu12==24.8.*
+        pip install --extra-index-url=https://pypi.nvidia.com cudf-cu12==24.10.*
         pip install ucxx-cu12 cython "numpy>=1.14.0,<2.0.0" cloudpickle scikit-learn \
           pyyaml psutil tornado sqlalchemy defusedxml tqdm uvloop coverage \
           pytest pytest-cov pytest-timeout pytest-forked pytest-asyncio pytest-mock

diff --git a/doc/source/getting_started/installation.rst b/doc/source/getting_started/installation.rst
@@ -34,6 +34,7 @@ an older version of pandas, you should either upgrade your pandas or downgrade X
 ======= =================== ======== ========= ========== =========== ===========
 Xorbits Python              `NumPy`_ `pandas`_ `xgboost`_ `lightgbm`_ `datasets`_
 ======= =================== ======== ========= ========== =========== ===========
+0.8.1   3.9,3.10,3.11,3.12  2.1.3    2.2.3     2.1.3      4.5.0       3.1.0
 0.8.0   3.9,3.10,3.11,3.12  2.1.3    2.2.3     2.1.2      4.5.0       3.1.0
 0.7.4   3.9,3.10,3.11       1.26.4   2.2.3     2.1.1      4.5.0       3.0.1
 ======= =================== ======== ========= ========== =========== ===========

diff --git a/python/xorbits/_mars/dataframe/datasource/read_parquet.py b/python/xorbits/_mars/dataframe/datasource/read_parquet.py
@@ -272,12 +272,12 @@ def read_partitioned_to_cudf(
             codes = cudf.core.column.as_column(
                 dictionary.index(value), length=len(raw_df)
             )
-            raw_df[col] = cudf.core.column.build_categorical_column(
-                categories=dictionary,
-                codes=codes,
+            raw_df[col] = cudf.core.column.CategoricalColumn(
+                data=None,
+                dtype=cudf.CategoricalDtype(categories=dictionary, ordered=False),
                 size=codes.size,
                 offset=codes.offset,
-                ordered=False,
+                children=(codes,),
             )
         return raw_df