Merge branch 'catboost-integration-tests' of github.com:Matt711/cudf …

…into catboost-integration-tests
rapidsai · Nov 13, 2024 · dbcfb25 · dbcfb25
2 parents 614e406 + b173250
commit dbcfb25
Show file tree

Hide file tree

Showing 370 changed files with 8,534 additions and 2,694 deletions.
diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml
@@ -63,7 +63,8 @@ jobs:
       branch: ${{ inputs.branch }}
       date: ${{ inputs.date }}
       sha: ${{ inputs.sha }}
-      run_script: "ci/clang_tidy.sh"
+      run_script: "ci/cpp_linters.sh"
+      file_to_upload: iwyu_results.txt
   conda-python-cudf-tests:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -90,8 +90,8 @@ repos:
         entry: |
           # Check for usage of default_rng without seeding
           default_rng\(\)|
-          # Check for usage of np.random.seed
-          np.random.seed\(
+          # Check for usage of np.random.seed (NPY002 only disallows this being called)
+          np.random.seed
         language: pygrep
         types: [python]
       - id: cmake-format

diff --git a/ci/build_wheel_cudf.sh b/ci/build_wheel_cudf.sh
@@ -27,4 +27,6 @@ python -m auditwheel repair \
     -w ${package_dir}/final_dist \
     ${package_dir}/dist/*
 
+./ci/validate_wheel.sh ${package_dir} final_dist
+
 RAPIDS_PY_WHEEL_NAME="cudf_${RAPIDS_PY_CUDA_SUFFIX}" rapids-upload-wheels-to-s3 python ${package_dir}/final_dist
diff --git a/ci/build_wheel_cudf_polars.sh b/ci/build_wheel_cudf_polars.sh
@@ -6,6 +6,7 @@ set -euo pipefail
 package_dir="python/cudf_polars"
 
 ./ci/build_wheel.sh cudf-polars ${package_dir}
+./ci/validate_wheel.sh ${package_dir} dist
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen ${RAPIDS_CUDA_VERSION})"
 RAPIDS_PY_WHEEL_NAME="cudf_polars_${RAPIDS_PY_CUDA_SUFFIX}" RAPIDS_PY_WHEEL_PURE="1" rapids-upload-wheels-to-s3 python ${package_dir}/dist
diff --git a/ci/build_wheel_dask_cudf.sh b/ci/build_wheel_dask_cudf.sh
@@ -6,6 +6,7 @@ set -euo pipefail
 package_dir="python/dask_cudf"
 
 ./ci/build_wheel.sh dask-cudf ${package_dir}
+./ci/validate_wheel.sh ${package_dir} dist
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen ${RAPIDS_CUDA_VERSION})"
 RAPIDS_PY_WHEEL_NAME="dask_cudf_${RAPIDS_PY_CUDA_SUFFIX}" RAPIDS_PY_WHEEL_PURE="1" rapids-upload-wheels-to-s3 python ${package_dir}/dist
diff --git a/ci/build_wheel_libcudf.sh b/ci/build_wheel_libcudf.sh
@@ -37,4 +37,6 @@ python -m auditwheel repair \
     -w ${package_dir}/final_dist \
     ${package_dir}/dist/*
 
+./ci/validate_wheel.sh ${package_dir} final_dist
+
 RAPIDS_PY_WHEEL_NAME="${package_name}_${RAPIDS_PY_CUDA_SUFFIX}" rapids-upload-wheels-to-s3 cpp "${package_dir}/final_dist"
diff --git a/ci/build_wheel_pylibcudf.sh b/ci/build_wheel_pylibcudf.sh
@@ -25,4 +25,6 @@ python -m auditwheel repair \
     -w ${package_dir}/final_dist \
     ${package_dir}/dist/*
 
+./ci/validate_wheel.sh ${package_dir} final_dist
+
 RAPIDS_PY_WHEEL_NAME="pylibcudf_${RAPIDS_PY_CUDA_SUFFIX}" rapids-upload-wheels-to-s3 python ${package_dir}/final_dist
diff --git a/ci/clang_tidy.sh b/ci/clang_tidy.sh
diff --git a/ci/cpp_linters.sh b/ci/cpp_linters.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+set -euo pipefail
+
+rapids-logger "Create checks conda environment"
+. /opt/conda/etc/profile.d/conda.sh
+
+ENV_YAML_DIR="$(mktemp -d)"
+
+rapids-dependency-file-generator \
+  --output conda \
+  --file-key clang_tidy \
+  --matrix "cuda=${RAPIDS_CUDA_VERSION%.*};arch=$(arch);py=${RAPIDS_PY_VERSION}" | tee "${ENV_YAML_DIR}/env.yaml"
+
+rapids-mamba-retry env create --yes -f "${ENV_YAML_DIR}/env.yaml" -n clang_tidy
+
+# Temporarily allow unbound variables for conda activation.
+set +u
+conda activate clang_tidy
+set -u
+
+RAPIDS_VERSION_MAJOR_MINOR="$(rapids-version-major-minor)"
+
+source rapids-configure-sccache
+
+# TODO: For testing purposes, clone and build IWYU. We can switch to a release
+# once a clang 19-compatible version is available, which should be soon
+# (https://github.com/include-what-you-use/include-what-you-use/issues/1641).
+git clone --depth 1 https://github.com/include-what-you-use/include-what-you-use.git
+pushd include-what-you-use
+# IWYU's CMake build uses some Python scripts that assume that the cwd is
+# importable, so support that legacy behavior.
+export PYTHONPATH=${PWD}:${PYTHONPATH:-}
+cmake -S . -B build -GNinja --install-prefix=${CONDA_PREFIX}
+cmake --build build
+cmake --install build
+popd
+
+# Run the build via CMake, which will run clang-tidy when CUDF_STATIC_LINTERS is enabled.
+cmake -S cpp -B cpp/build -DCMAKE_BUILD_TYPE=Release -DCUDF_STATIC_LINTERS=ON -GNinja
+cmake --build cpp/build 2>&1 | python cpp/scripts/parse_iwyu_output.py
+
+# Remove invalid components of the path for local usage. The path below is
+# valid in the CI due to where the project is cloned, but presumably the fixes
+# will be applied locally from inside a clone of cudf.
+sed -i 's/\/__w\/cudf\/cudf\///' iwyu_results.txt
diff --git a/ci/test_cudf_polars_polars_tests.sh b/ci/test_cudf_polars_polars_tests.sh
@@ -3,22 +3,6 @@
 
 set -eou pipefail
 
-# We will only fail these tests if the PR touches code in pylibcudf
-# or cudf_polars itself.
-# Note, the three dots mean we are doing diff between the merge-base
-# of upstream and HEAD. So this is asking, "does _this branch_ touch
-# files in cudf_polars/pylibcudf", rather than "are there changes
-# between upstream and this branch which touch cudf_polars/pylibcudf"
-# TODO: is the target branch exposed anywhere in an environment variable?
-if [ -n "$(git diff --name-only origin/branch-24.12...HEAD -- python/cudf_polars/ python/cudf/cudf/_lib/pylibcudf/)" ];
-then
-    HAS_CHANGES=1
-    rapids-logger "PR has changes in cudf-polars/pylibcudf, test fails treated as failure"
-else
-    HAS_CHANGES=0
-    rapids-logger "PR does not have changes in cudf-polars/pylibcudf, test fails NOT treated as failure"
-fi
-
 rapids-logger "Download wheels"
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen ${RAPIDS_CUDA_VERSION})"
@@ -63,9 +47,4 @@ if [ ${EXITCODE} != 0 ]; then
 else
     rapids-logger "Running polars test suite PASSED"
 fi
-
-if [ ${HAS_CHANGES} == 1 ]; then
-    exit ${EXITCODE}
-else
-    exit 0
-fi
+exit ${EXITCODE}
diff --git a/ci/test_wheel_cudf_polars.sh b/ci/test_wheel_cudf_polars.sh
@@ -3,22 +3,6 @@
 
 set -eou pipefail
 
-# We will only fail these tests if the PR touches code in pylibcudf
-# or cudf_polars itself.
-# Note, the three dots mean we are doing diff between the merge-base
-# of upstream and HEAD. So this is asking, "does _this branch_ touch
-# files in cudf_polars/pylibcudf", rather than "are there changes
-# between upstream and this branch which touch cudf_polars/pylibcudf"
-# TODO: is the target branch exposed anywhere in an environment variable?
-if [ -n "$(git diff --name-only origin/branch-24.12...HEAD -- python/cudf_polars/ python/pylibcudf/)" ];
-then
-    HAS_CHANGES=1
-    rapids-logger "PR has changes in cudf-polars/pylibcudf, test fails treated as failure"
-else
-    HAS_CHANGES=0
-    rapids-logger "PR does not have changes in cudf-polars/pylibcudf, test fails NOT treated as failure"
-fi
-
 rapids-logger "Download wheels"
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen ${RAPIDS_CUDA_VERSION})"
@@ -65,9 +49,4 @@ if [ ${EXITCODE} != 0 ]; then
 else
     rapids-logger "Testing PASSED"
 fi
-
-if [ ${HAS_CHANGES} == 1 ]; then
-    exit ${EXITCODE}
-else
-    exit 0
-fi
+exit ${EXITCODE}
diff --git a/ci/validate_wheel.sh b/ci/validate_wheel.sh
@@ -0,0 +1,21 @@
+#!/bin/bash
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+set -euo pipefail
+
+package_dir=$1
+wheel_dir_relative_path=$2
+
+cd "${package_dir}"
+
+rapids-logger "validate packages with 'pydistcheck'"
+
+pydistcheck \
+    --inspect \
+    "$(echo ${wheel_dir_relative_path}/*.whl)"
+
+rapids-logger "validate packages with 'twine'"
+
+twine check \
+    --strict \
+    "$(echo ${wheel_dir_relative_path}/*.whl)"
diff --git a/conda/environments/all_cuda-118_arch-x86_64.yaml b/conda/environments/all_cuda-118_arch-x86_64.yaml
@@ -55,7 +55,7 @@ dependencies:
 - nbsphinx
 - ninja
 - notebook
-- numba-cuda>=0.0.13
+- numba-cuda>=0.0.13,<0.0.18
 - numpy>=1.23,<3.0a0
 - numpydoc
 - nvcc_linux-64=11.8
@@ -66,10 +66,10 @@ dependencies:
 - pandas
 - pandas>=2.0,<2.2.4dev0
 - pandoc
-- polars>=1.11,<1.13
+- polars>=1.11,<1.14
 - pre-commit
 - ptxcompiler
-- pyarrow>=14.0.0,<18.0.0a0
+- pyarrow>=14.0.0,<19.0.0a0
 - pydata-sphinx-theme!=0.14.2
 - pytest-benchmark
 - pytest-cases>=3.8.2

diff --git a/conda/environments/all_cuda-125_arch-x86_64.yaml b/conda/environments/all_cuda-125_arch-x86_64.yaml
@@ -54,7 +54,7 @@ dependencies:
 - nbsphinx
 - ninja
 - notebook
-- numba-cuda>=0.0.13
+- numba-cuda>=0.0.13,<0.0.18
 - numpy>=1.23,<3.0a0
 - numpydoc
 - nvcomp==4.1.0.6
@@ -64,9 +64,9 @@ dependencies:
 - pandas
 - pandas>=2.0,<2.2.4dev0
 - pandoc
-- polars>=1.11,<1.13
+- polars>=1.11,<1.14
 - pre-commit
-- pyarrow>=14.0.0,<18.0.0a0
+- pyarrow>=14.0.0,<19.0.0a0
 - pydata-sphinx-theme!=0.14.2
 - pynvjitlink>=0.0.0a0
 - pytest-benchmark

diff --git a/conda/recipes/cudf-polars/meta.yaml b/conda/recipes/cudf-polars/meta.yaml
@@ -43,7 +43,7 @@ requirements:
   run:
     - python
     - pylibcudf ={{ version }}
-    - polars >=1.11,<1.12
+    - polars >=1.11,<1.14
     - {{ pin_compatible('cuda-version', max_pin='x', min_pin='x') }}
 
 test:

diff --git a/conda/recipes/cudf/meta.yaml b/conda/recipes/cudf/meta.yaml
@@ -80,7 +80,7 @@ requirements:
     - typing_extensions >=4.0.0
     - pandas >=2.0,<2.2.4dev0
     - cupy >=12.0.0
-    - numba-cuda >=0.0.13
+    - numba-cuda >=0.0.13,<0.0.18
     - numpy >=1.23,<3.0a0
     - pyarrow>=14.0.0,<18.0.0a0
     - libcudf ={{ version }}

diff --git a/cpp/.clang-tidy b/cpp/.clang-tidy
@@ -39,8 +39,8 @@ Checks:
        -clang-analyzer-optin.core.EnumCastOutOfRange,
        -clang-analyzer-optin.cplusplus.UninitializedObject'
 
-WarningsAsErrors: '*'
-HeaderFilterRegex: '.*cudf/cpp/(src|include|tests).*'
+WarningsAsErrors: ''
+HeaderFilterRegex: '.*cudf/cpp/(src|include).*'
 ExcludeHeaderFilterRegex: '.*(Message_generated.h|Schema_generated.h|brotli_dict.hpp|unbz2.hpp|cxxopts.hpp).*'
 FormatStyle:     none
 CheckOptions: