Merge remote-tracking branch 'origin/branch-24.10' into HEAD

res-life · Sep 4, 2024 · 069ea47 · 069ea47
2 parents a9d83d6 + fa1486e
commit 069ea47
Show file tree

Hide file tree

Showing 12 changed files with 79 additions and 213 deletions.
diff --git a/cpp/include/cudf/column/column_factories.hpp b/cpp/include/cudf/column/column_factories.hpp
@@ -469,7 +469,7 @@ std::unique_ptr<column> make_strings_column(size_type num_strings,
  * offsets (depth 1)   {0, 2, 5, 7}
  * data    (depth 1)
  * offsets (depth 2)
- * data    (depth 1)   {1, 2, 3, 4, 5, 6, 7}
+ * data    (depth 2)   {1, 2, 3, 4, 5, 6, 7}
  * @endcode
  *
  * @param[in] num_rows The number of lists the column represents.

diff --git a/cpp/src/join/mixed_join_kernel.cuh b/cpp/src/join/mixed_join_kernel.cuh
@@ -130,7 +130,7 @@ void launch_mixed_join(table_device_view left_table,
                        int64_t shmem_size_per_block,
                        rmm::cuda_stream_view stream)
 {
-  mixed_join<DEFAULT_JOIN_BLOCK_SIZE, true>
+  mixed_join<DEFAULT_JOIN_BLOCK_SIZE, has_nulls>
     <<<config.num_blocks, config.num_threads_per_block, shmem_size_per_block, stream.value()>>>(
       left_table,
       right_table,

diff --git a/cpp/src/join/mixed_join_size_kernel.cuh b/cpp/src/join/mixed_join_size_kernel.cuh
@@ -124,7 +124,7 @@ std::size_t launch_compute_mixed_join_output_size(
   // Allocate storage for the counter used to get the size of the join output
   rmm::device_scalar<std::size_t> size(0, stream, mr);
 
-  compute_mixed_join_output_size<DEFAULT_JOIN_BLOCK_SIZE, true>
+  compute_mixed_join_output_size<DEFAULT_JOIN_BLOCK_SIZE, has_nulls>
     <<<config.num_blocks, config.num_threads_per_block, shmem_size_per_block, stream.value()>>>(
       left_table,
       right_table,

diff --git a/cpp/tests/CMakeLists.txt b/cpp/tests/CMakeLists.txt
@@ -110,10 +110,6 @@ ConfigureTest(SCALAR_TEST scalar/scalar_test.cpp scalar/scalar_device_view_test.
 # * timestamps tests ------------------------------------------------------------------------------
 ConfigureTest(TIMESTAMPS_TEST wrappers/timestamps_test.cu)
 
-# ##################################################################################################
-# * cudf tests ------------------------------------------------------------------------------------
-ConfigureTest(ERROR_TEST error/error_handling_test.cu)
-
 # ##################################################################################################
 # * groupby tests ---------------------------------------------------------------------------------
 ConfigureTest(

diff --git a/cpp/tests/error/error_handling_test.cu b/cpp/tests/error/error_handling_test.cu
diff --git a/docs/cudf/source/conf.py b/docs/cudf/source/conf.py
@@ -566,6 +566,8 @@ def on_missing_reference(app, env, node, contnode):
     ("py:obj", "cudf.Index.to_flat_index"),
     ("py:obj", "cudf.MultiIndex.to_flat_index"),
     ("py:meth", "pyarrow.Table.to_pandas"),
+    ("py:class", "pd.DataFrame"),
+    ("py:class", "pandas.core.indexes.frozen.FrozenList"),
     ("py:class", "pa.Array"),
     ("py:class", "ScalarLike"),
     ("py:class", "ParentType"),

diff --git a/java/ci/Dockerfile.rocky b/java/ci/Dockerfile.rocky
@@ -28,7 +28,7 @@ ARG TARGETPLATFORM=linux/amd64
 FROM --platform=$TARGETPLATFORM nvidia/cuda:$CUDA_VERSION-devel-rockylinux$OS_RELEASE
 ARG TOOLSET_VERSION=11
 ### Install basic requirements
-RUN dnf --enablerepo=powertools install -y  scl-utils gcc-toolset-${TOOLSET_VERSION} git zlib-devel maven tar wget patch ninja-build
+RUN dnf --enablerepo=powertools install -y  scl-utils gcc-toolset-${TOOLSET_VERSION} git zlib-devel maven tar wget patch ninja-build boost-devel
 ## pre-create the CMAKE_INSTALL_PREFIX folder, set writable by any user for Jenkins
 RUN mkdir /usr/local/rapids /rapids && chmod 777 /usr/local/rapids /rapids
 

diff --git a/python/cudf/cudf/_lib/text.pyx b/python/cudf/cudf/_lib/text.pyx
@@ -86,4 +86,4 @@ def read_text(object filepaths_or_buffers,
             delim,
             c_options))
 
-    return {None: Column.from_unique_ptr(move(c_col))}
+    return Column.from_unique_ptr(move(c_col))
diff --git a/python/cudf/cudf/core/dataframe.py b/python/cudf/cudf/core/dataframe.py
@@ -473,15 +473,8 @@ def __getitem__(self, arg):
         ca = self._frame._data
         index = self._frame.index
         if col_is_scalar:
-            s = Series._from_data(
-                data=ColumnAccessor(
-                    {key: ca._data[key] for key in column_names},
-                    multiindex=ca.multiindex,
-                    level_names=ca.level_names,
-                    verify=False,
-                ),
-                index=index,
-            )
+            name = column_names[0]
+            s = Series._from_column(ca._data[name], name=name, index=index)
             return s._getitem_preprocessed(row_spec)
         if column_names != list(self._frame._column_names):
             frame = self._frame._from_data(
@@ -7770,8 +7763,8 @@ def interleave_columns(self):
                 "interleave_columns does not support 'category' dtype."
             )
 
-        return self._constructor_sliced._from_data(
-            {None: libcudf.reshape.interleave_columns([*self._columns])}
+        return self._constructor_sliced._from_column(
+            libcudf.reshape.interleave_columns([*self._columns])
         )
 
     @_performance_tracking