Merge branch 'branch-24.12' into branch-24.12-ci-tests

rapidsai · Nov 1, 2024 · 712ca19 · 712ca19
2 parents 4919a5a + 3b062b9
commit 712ca19
Show file tree

Hide file tree

Showing 66 changed files with 196 additions and 1,936 deletions.
diff --git a/.flake8 b/.flake8
@@ -14,3 +14,5 @@ per-file-ignores =
     __init__.py:F401,F403,
     _nx_cugraph/__init__.py:E501,
     nx_cugraph/__init__.py:E402,F401,F403,
+    benchmarks/nx-cugraph/pytest-based/create_results_summary_page.py:E501,W605,
+    docs/nx-cugraph/source/conf.py:E501
diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS
@@ -21,7 +21,7 @@ python/            @rapidsai/nx-cugraph-python-codeowners
 /.pre-commit-config.yaml @rapidsai/ci-codeowners
 
 #packaging code owners
-# /.devcontainer/  @rapidsai/packaging-codeowners
+/.devcontainer/    @rapidsai/packaging-codeowners
 /conda/            @rapidsai/packaging-codeowners
 /dependencies.yaml @rapidsai/packaging-codeowners
 /build.sh          @rapidsai/packaging-codeowners

diff --git a/.github/ISSUE_TEMPLATE/bug_report.yaml b/.github/ISSUE_TEMPLATE/bug_report.yaml
@@ -29,7 +29,7 @@ body:
     attributes:
       label: Version
       description: What version of nx-cugraph are you running?
-      placeholder: "example: 22.12"
+      placeholder: "example: 24.12"
     validations:
       required: true
 

diff --git a/.github/ISSUE_TEMPLATE/feature_request.yaml b/.github/ISSUE_TEMPLATE/feature_request.yaml
@@ -75,7 +75,7 @@ body:
     attributes:
       label: Describe any alternatives you have considered
       description: List any other libraries, or approaches you have looked at or tried.
-      placeholder: I have looked at library xyz and qrs, but they do not offer GPU accleration
+      placeholder: I have looked at library xyz and qrs, but they do not offer GPU acceleration
 
   - type: textarea
     id: misc

diff --git a/.github/ops-bot.yaml b/.github/ops-bot.yaml
@@ -5,5 +5,5 @@ auto_merger: true
 branch_checker: true
 label_checker: true
 release_drafter: true
-recently_updated: false
 forward_merger: true
+recently_updated: true
diff --git a/.github/workflows/pr.yaml b/.github/workflows/pr.yaml
@@ -14,8 +14,9 @@ jobs:
     needs:
       - changed-files
       - checks
-      - conda-notebook-tests
       - conda-python-build
+      - wheel-build-nx-cugraph
+      - conda-notebook-tests
       - conda-python-tests
       - docs-build
     secrets: inherit
@@ -30,27 +31,16 @@ jobs:
       files_yaml: |
         test_notebooks:
           - '**'
-          - '!.devcontainers/**'
-          - '!CONTRIBUTING.md'
           - '!README.md'
           - '!docs/**'
-          # TODO: Remove this before merging
-          - '!.github/**'
         test_python:
           - '**'
-          - '!.devcontainers/**'
-          - '!CONTRIBUTING.md'
           - '!README.md'
           - '!docs/**'
-          - '!img/**'
           - '!notebooks/**'
-          # TODO: Remove this before merging
-          - '!.github/**'
   checks:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    with:
-      enable_check_generated_files: false
   conda-python-build:
     needs: checks
     secrets: inherit
@@ -69,19 +59,22 @@ jobs:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_notebooks
+    with:
+      enable_check_generated_files: false
+  conda-python-build:
+    needs: [checks]
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
       build_type: pull-request
-      node_type: "gpu-v100-latest-1"
-      arch: "amd64"
-      container_image: "rapidsai/ci-conda:cuda11.8.0-ubuntu22.04-py3.10"
-      run_script: "ci/test_notebooks.sh"
-  docs-build:
-    needs: conda-python-build
+      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
+      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
+  wheel-build-nx-cugraph:
+    needs: [checks]
     secrets: inherit
-    uses: rapidsai/shared-workflows/.github/workflows/custom-job[email protected]
+    uses: rapidsai/shared-workflows/.github/workflows/wheels-build[email protected]
     with:
       build_type: pull-request
-      node_type: "gpu-v100-latest-1"
-      arch: "amd64"
-      container_image: "rapidsai/ci-conda:cuda11.8.0-ubuntu22.04-py3.10"
-      run_script: "ci/build_docs.sh"
+      script: ci/build_wheel_nx-cugraph.sh
+      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
+      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,53 +1,92 @@
 ## https://pre-commit.com/
 #
 # Before first use: `pre-commit install`
-# To run: `pre-commit run --all-files`
+# To run: `make lint`
+# To update: `make lint-update`
+#  - &flake8_dependencies below needs updated manually
 exclude: '^thirdparty'
+fail_fast: false
+default_language_version:
+    python: python3
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
       - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: check-ast
+      - id: check-toml
+      - id: check-yaml
+        exclude: '^conda/recipes/.*\.yaml$'
       - id: debug-statements
       - id: end-of-file-fixer
+        exclude_types: [svg]
       - id: mixed-line-ending
+      - id: no-commit-to-branch
+        args: [-p, "^branch-2....$"]
       - id: trailing-whitespace
   - repo: https://github.com/PyCQA/flake8
     rev: 7.1.1
     hooks:
       - id: flake8
-        args: ["--config=.flake8"]
-        files: nx_cugraph.*$
-        types: [file]
-        types_or: [python] # TODO: Enable [python, cython]
-        additional_dependencies: ["flake8-force"]
+        args: ["--config=.flake8"] # uses config
+        additional_dependencies: &flake8_dependencies
+          # These versions need updated manually
+          - flake8==7.1.1
+          - flake8-bugbear==24.8.19
+          - flake8-simplify==0.21.0
   - repo: https://github.com/asottile/yesqa
     rev: v1.3.0
     hooks:
       - id: yesqa
-        additional_dependencies:
-          - flake8==7.1.1
-  - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v16.0.6
+        additional_dependencies: *flake8_dependencies
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.19
+    hooks:
+      - id: validate-pyproject
+        name: Validate pyproject.toml
+  - repo: https://github.com/PyCQA/autoflake
+    rev: v2.3.1
+    hooks:
+      - id: autoflake
+        args: [--in-place]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.17.0
+    hooks:
+      - id: pyupgrade
+        args: [--py310-plus]
+  - repo: https://github.com/psf/black
+    rev: 24.8.0
+    hooks:
+      - id: black
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
     hooks:
-      - id: clang-format
-        types_or: [c, c++, cuda]
-        args: ["-fallback-style=none", "-style=file", "-i"]
+      - id: codespell
+        types_or: [python, rst, markdown]
+        additional_dependencies: [tomli]
+        files: ^(nx_cugraph|docs)/
+        args: ["-L thirdparty,coo,COO,numer"]
   - repo: https://github.com/rapidsai/pre-commit-hooks
     rev: v0.4.0
     hooks:
       - id: verify-copyright
         files: |
           (?x)
-              [.](cmake|cpp|cu|cuh|h|hpp|sh|pxd|py|pyx)$|
-              CMakeLists[.]txt$|
-              CMakeLists_standalone[.]txt$|
+              [.](sh|py)$|
               [.]flake8[.]cython$|
               meta[.]yaml$|
               setup[.]cfg$
       - id: verify-alpha-spec
+        args: ["--fix"]
   - repo: https://github.com/rapidsai/dependency-file-generator
-    rev: v1.13.11
+    rev: v1.16.0
     hooks:
         - id: rapids-dependency-file-generator
           args: ["--clean"]

diff --git a/Makefile b/Makefile
@@ -2,15 +2,7 @@
 SHELL= /bin/bash
 
 .PHONY: all
-all: plugin-info lint readme
-
-.PHONY: lint
-lint:
-	git ls-files | xargs pre-commit run --config lint.yaml --files || true
-
-.PHONY: lint-update
-lint-update:
-	pre-commit autoupdate --config lint.yaml
+all: plugin-info readme
 
 .PHONY: plugin-info
 plugin-info:

diff --git a/README.md b/README.md
@@ -8,7 +8,7 @@ to run supported algorithms with GPU acceleration.
 
 nx-cugraph requires the following:
  * NVIDIA GPU, Volta architecture or later, with [compute capability](https://developer.nvidia.com/cuda-gpus) 7.0+
- * CUDA 11.2, 11.4, 11.5, 11.8, 12.0, 12.2, or 12.5
+ * CUDA 11.4-11.8 or 12.0-12.5
  * Python version 3.10, 3.11, or 3.12
  * NetworkX >= version 3.0 (version 3.2 or higher recommended)
 

diff --git a/benchmarks/nx-cugraph/pytest-based/bench_algos.py b/benchmarks/nx-cugraph/pytest-based/bench_algos.py
@@ -11,12 +11,11 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import random
-
 import networkx as nx
 import pandas as pd
 import pytest
 from cugraph import datasets
+
 import nx_cugraph as nxcg
 
 # Attempt to import the NetworkX dispatching module, which is only needed when

diff --git a/benchmarks/nx-cugraph/pytest-based/create_results_summary_page.py b/benchmarks/nx-cugraph/pytest-based/create_results_summary_page.py
@@ -12,17 +12,17 @@
 # limitations under the License.
 
 
-import re
-import pathlib
 import json
+import pathlib
 import platform
-import psutil
+import re
 import socket
 import subprocess
 
+import psutil
+
 
 def get_formatted_time_value(time):
-    res = ""
     if time < 1:
         if time < 0.001:
             units = "us"
@@ -40,7 +40,8 @@ def get_all_benchmark_info():
     # Populate benchmarks dir from .json files
     for json_file in logs_dir.glob("*.json"):
         try:
-            data = json.loads(open(json_file).read())
+            with open(json_file) as file:
+                data = json.loads(file.read())
         except json.decoder.JSONDecodeError:
             continue
 
@@ -155,8 +156,8 @@ def get_system_info():
 if __name__ == "__main__":
     logs_dir = pathlib.Path("logs")
 
-    dataset_patt = re.compile(".*ds=([\w-]+).*")
-    backend_patt = re.compile(".*backend=(\w+).*")
+    dataset_patt = re.compile(r".*ds=([\w-]+).*")
+    backend_patt = re.compile(r".*backend=(\w+).*")
     k_patt = re.compile(".*k=(10*).*")
 
     # Organize all benchmark runs by the following hierarchy: algo -> backend -> dataset
@@ -266,7 +267,7 @@ def get_system_info():
                         f"      <td>{nx_formatted} / {cg_formatted}<br>{speedup}<br>{runtime_delta}</td>"
                     )
                 else:
-                    print(f"      <td></td>")
+                    print("      <td></td>")
 
         # If a comparison between cugraph and NX cannot be made, output empty cells
         # for each dataset

diff --git a/benchmarks/nx-cugraph/pytest-based/get_graph_bench_dataset.py b/benchmarks/nx-cugraph/pytest-based/get_graph_bench_dataset.py
@@ -18,14 +18,14 @@
 
 Positional Arguments:
     1) dataset name (e.g. 'email_Eu_core', 'cit-patents')
-       available datasets can be found here: `python/cugraph/cugraph/datasets/__init__.py`
+       available datasets can be found here:
+        - `python/cugraph/cugraph/datasets/__init__.py`
 """
 
 import sys
 
 import cugraph.datasets as cgds
 
-
 if __name__ == "__main__":
     # download and store dataset (csv) by using the Datasets API
     dataset = sys.argv[1].replace("-", "_")

diff --git a/build.sh b/build.sh
@@ -31,7 +31,6 @@ VALIDARGS="
    -g
    -n
    --pydevelop
-   --allgpuarch
    --clean
    -h
    --help
@@ -49,7 +48,6 @@ HELP="$0 [<target> ...] [<flag> ...]
    -g                         - build for debug
    -n                         - do not install after a successful build (does not affect Python packages)
    --pydevelop                - install the Python packages in editable mode
-   --allgpuarch               - build for all supported GPU architectures
    --clean                    - clean an individual target (note: to do a complete rebuild, use the clean target described above)
    -h                         - print this text
 
@@ -107,27 +105,12 @@ fi
 if hasArg -n; then
     INSTALL_TARGET=""
 fi
-if hasArg --allgpuarch; then
-    BUILD_ALL_GPU_ARCH=1
-fi
 if hasArg --pydevelop; then
     PYTHON_ARGS_FOR_INSTALL="${PYTHON_ARGS_FOR_INSTALL} -e"
 fi
 
 # If clean or uninstall targets given, run them prior to any other steps
 if hasArg uninstall; then
-    # TODO: can lines 119-128 be removed since this is just a Python project?
-    if [[ "$INSTALL_PREFIX" != "" ]]; then
-        rm -rf ${INSTALL_PREFIX}/include/cugraph
-        rm -f ${INSTALL_PREFIX}/lib/libcugraph.so
-        rm -rf ${INSTALL_PREFIX}/include/cugraph_c
-        rm -f ${INSTALL_PREFIX}/lib/libcugraph_c.so
-        rm -rf ${INSTALL_PREFIX}/include/cugraph_etl
-        rm -f ${INSTALL_PREFIX}/lib/libcugraph_etl.so
-        rm -rf ${INSTALL_PREFIX}/lib/cmake/cugraph
-        rm -rf ${INSTALL_PREFIX}/lib/cmake/cugraph_etl
-    fi
-    # uninstall nx-cugraph
     # FIXME: if multiple versions of these packages are installed, this only
     # removes the latest one and leaves the others installed. build.sh uninstall
     # can be run multiple times to remove all of them, but that is not obvious.