Merge branch 'main' into patch-1

Author: benfred

.github/workflows/build.yml

@@ -16,70 +16,27 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
-
-    - name: Set up Python
-      uses: actions/setup-python@v4
+    - uses: actions/checkout@v6
+    - uses: actions/setup-python@v6
       with:
-        python-version: 3.9
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements-dev.txt
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=11 --max-line-length=127 --statistics
-        flake8 --filename='*.pyx,*.px*' --ignore E901,E225,E226,E227,E402,E999
-    - name: Lint with black
-      run: |
-        black --check .
-    - name: Lint with clang-format
-      run: |
-        sudo apt install clang-format
-        find implicit | grep -E '\.(cu|cuh|h|cpp)$' | xargs clang-format --dry-run --Werror
-      if: runner.os == 'Linux'
-    - name: Lint with isort
-      run: |
-        isort -c .
-    - name: Lint with codespell
-      run: |
-        codespell
-    - name: Lint with pylint
-      run: |
-        pylint implicit tests benchmarks examples
+        python-version: 3.12
+    - uses: pre-commit/action@v3.0.1
 
   build-wheels:
     needs: [lint]
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest, ubuntu-latest, windows-latest]
-        python-version: [36, 37, 38, 39, 310, 311, 312]
-        cibw-arch: [auto, aarch64]
-        exclude:
-          - os: macos-latest
-            cibw-arch: aarch64
-          - os: windows-latest
-            cibw-arch: aarch64
+        os: [macos-latest, ubuntu-latest, windows-latest, ubuntu-24.04-arm]
+        python-version: [39, 310, 311, 312, 313, 314]
 
     steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up QEMU
-        if: runner.os == 'Linux'
-        uses: docker/setup-qemu-action@v3
-        with:
-          platforms: all
+      - uses: actions/checkout@v6
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.16.2
         env:
           CIBW_BUILD: cp${{matrix.python-version}}-*
-          CIBW_ARCHS_LINUX: ${{ matrix.cibw-arch }}
+        uses: pypa/cibuildwheel@v3.4.1
 
       - name: Build sdist
         run: |
@@ -93,42 +50,39 @@ jobs:
         if: runner.os == 'Linux'
 
       - name: Upload Binaries
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v7
         with:
-          name: wheels
-          path: wheelhouse
+          name: wheels-${{ matrix.os }}-${{ matrix.python-version }}
+          path: ./wheelhouse/*.whl
 
   test-wheels:
     needs: [build-wheels]
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9, '3.10', '3.11', '3.12']
-        os: [macos-latest, ubuntu-latest, windows-latest]
+        python-version: [3.9, '3.10', '3.11', '3.12', '3.13', '3.14']
+        os: [macos-latest, ubuntu-latest, windows-latest, ubuntu-24.04-arm]
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v6
       with:
         path: implicit_source
-    - uses: actions/download-artifact@v3
+    - uses: actions/download-artifact@v8
       with:
-        name: wheels
+        pattern: wheels-${{ matrix.os }}-*
+        merge-multiple: true
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v6
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         pip install pytest
         pip install -r implicit_source/requirements.txt
-    - name: Install h5py
-      run: pip install h5py
-
     - name: Install ANN Libraries
       run: pip install annoy nmslib
-      if: ${{ matrix.python-version != '3.12' &&  matrix.python-version != '3.11' && runner.os == 'Linux' }}
-
+      if: ${{ matrix.python-version != '3.14' && runner.os == 'Linux' }}
     - name: Install wheel
       run: |
         pip install --force-reinstall --no-deps --no-index --find-links . implicit
@@ -142,15 +96,16 @@ jobs:
     if: "startsWith(github.ref, 'refs/tags/')"
     needs: [test-wheels]
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v8
         with:
-          name: wheels
+          pattern: wheels-*
+          merge-multiple: true
       - name: Create GitHub Release
         uses: fnkr/github-action-ghr@v1.3
         env:
           GHR_PATH: .
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v6
         with:
           python-version: 3.9
       - name: Push to PyPi

.pre-commit-config.yaml

@@ -1,31 +1,18 @@
 repos:
-      - repo: https://github.com/timothycrosley/isort
-        rev: 5.12.0
+      - repo: https://github.com/astral-sh/ruff-pre-commit
+        rev: v0.15.12
         hooks:
-        - id: isort
-          additional_dependencies: [toml]
-      - repo: https://github.com/python/black
-        rev: 23.3.0
-        hooks:
-        - id: black
-      - repo: https://github.com/pycqa/flake8
-        rev: 6.0.0
-        hooks:
-        - id: flake8
-      - repo: https://github.com/pycqa/pylint
-        rev: v2.17.4
-        hooks:
-        - id: pylint
+        - id: ruff-check
+          types_or: [ python, pyi, jupyter, pyproject ]
+          args: [ --fix ]
+        - id: ruff-format
       - repo: https://github.com/codespell-project/codespell
         rev: v2.2.4
         hooks:
         - id: codespell
-      - repo: local
+      - repo: https://github.com/pre-commit/mirrors-clang-format
+        rev: v22.1.4
         hooks:
         - id: clang-format
-          name: clang-format
-          description: Format files with ClangFormat.
-          entry: clang-format --dry-run --Werror
-          language: system 
           files: \.(cu|cuh|h|cpp)$
 

.pylintrc

@@ -45,3 +45,6 @@ disable=fixme,
 min-similarity-lines=64
 ignore-docstrings=yes
 ignore-imports=yes
+
+[DESIGN]
+max-positional-arguments=12

CMakeLists.txt

@@ -1,13 +1,17 @@
-cmake_minimum_required(VERSION 3.17.0)
+cmake_minimum_required(VERSION 3.21...4.0)
 
 project(implicit)
 
+find_package(
+  Python
+  COMPONENTS Interpreter Development.Module
+  REQUIRED)
+include(UseCython)
+
 enable_testing()
 
-find_package(PythonExtensions REQUIRED)
-find_package(Cython REQUIRED)
 find_package(OpenMP)
 
 include_directories(.)
-set (CMAKE_CXX_STANDARD 11)
+set (CMAKE_CXX_STANDARD 17)
 add_subdirectory(implicit)

benchmarks/benchmark_als.py

@@ -1,4 +1,5 @@
-""" test script to verify the CG method works, and time it versus cholesky """
+"""test script to verify the CG method works, and time it versus cholesky"""
+
 import argparse
 import json
 import logging

ci/install_cuda.sh

@@ -0,0 +1,9 @@
+dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo
+
+dnf install -y \
+    cuda-nvcc-13-0 \
+    cuda-cudart-devel-13-0 \
+    libcurand-devel-13-0 \
+    libcublas-devel-13-0 
+
+ln -s cuda-13.0 /usr/local/cuda

ci/install_cuda_13.sh

@@ -1,13 +1,13 @@
-""" An example of using this library to calculate related artists
+"""An example of using this library to calculate related artists
 from the last.fm dataset. More details can be found
 at http://www.benfrederickson.com/matrix-factorization/
 
 This code will automatically download a HDF5 version of the dataset from
 GitHub when it is first run. The original dataset can also be found at
 http://ocelma.net/MusicRecommendationDataset/lastfm-360K.html
 """
+
 import argparse
-import codecs
 import logging
 import time
 
@@ -102,7 +102,7 @@ def calculate_similar_artists(output_filename, model_name="als"):
     # write out as a TSV of artistid, otherartistid, score
     logging.debug("writing similar items")
     with tqdm.tqdm(total=len(to_generate)) as progress:
-        with codecs.open(output_filename, "w", "utf8") as o:
+        with open(output_filename, "w", encoding="utf8") as o:
             batch_size = 1000
             for startidx in range(0, len(to_generate), batch_size):
                 batch = to_generate[startidx : startidx + batch_size]
@@ -146,7 +146,7 @@ def calculate_recommendations(output_filename, model_name="als"):
     # generate recommendations for each user and write out to a file
     start = time.time()
     with tqdm.tqdm(total=len(users)) as progress:
-        with codecs.open(output_filename, "w", "utf8") as o:
+        with open(output_filename, "w", encoding="utf8") as o:
             batch_size = 1000
             to_generate = np.arange(len(users))
             for startidx in range(0, len(to_generate), batch_size):

examples/lastfm.py

@@ -13,7 +13,6 @@
 from __future__ import print_function
 
 import argparse
-import codecs
 import logging
 import time
 
@@ -87,7 +86,7 @@ def calculate_similar_movies(output_filename, model_name="als", min_rating=4.0,
 
     log.debug("calculating similar movies")
     with tqdm.tqdm(total=len(to_generate)) as progress:
-        with codecs.open(output_filename, "w", "utf8") as o:
+        with open(output_filename, "w", encoding="utf8") as o:
             batch_size = 1000
             for startidx in range(0, len(to_generate), batch_size):
                 batch = to_generate[startidx : startidx + batch_size]

examples/movielens.py

@@ -85,11 +85,12 @@
    "source": [
     "from implicit.nearest_neighbours import bm25_weight\n",
     "\n",
-    "# weight the matrix, both to reduce impact of users that have played the same artist thousands of times\n",
-    "# and to reduce the weight given to popular items\n",
+    "# weight the matrix, both to reduce impact of users that have played the same artist thousands\n",
+    "# of times and to reduce the weight given to popular items\n",
     "artist_user_plays = bm25_weight(artist_user_plays, K1=100, B=0.8)\n",
     "\n",
-    "# get the transpose since the most of the functions in implicit expect (user, item) sparse matrices instead of (item, user)\n",
+    "# get the transpose since the most of the functions in implicit expect (user, item) sparse\n",
+    "# matrices instead of (item, user)\n",
     "user_plays = artist_user_plays.T.tocsr()"
    ]
   },
@@ -293,7 +294,14 @@
     "# Use pandas to display the output in a table, pandas isn't a dependency of implicit otherwise\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "pd.DataFrame({\"artist\": artists[ids], \"score\": scores, \"already_liked\": np.in1d(ids, user_plays[userid].indices)})"
+    "\n",
+    "pd.DataFrame(\n",
+    "    {\n",
+    "        \"artist\": artists[ids],\n",
+    "        \"score\": scores,\n",
+    "        \"already_liked\": np.isin(ids, user_plays[userid].indices),\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -423,7 +431,7 @@
    ],
    "source": [
     "# get related items for the beatles (itemid = 25512)\n",
-    "ids, scores= model.similar_items(252512)\n",
+    "ids, scores = model.similar_items(252512)\n",
     "\n",
     "# display the results using pandas for nicer formatting\n",
     "pd.DataFrame({\"artist\": artists[ids], \"score\": scores})"