From bc1b76217690b7f2a65f7ad14f0991b13c8cfe75 Mon Sep 17 00:00:00 2001 From: Eric Zhu Date: Sun, 19 Feb 2023 07:23:54 -0800 Subject: [PATCH] Add note to documentation to address #195 (#197) * #195 add doc note * edit actions --- .github/workflows/doc.yml | 12 ++++-------- .github/workflows/test-cassandra.yml | 12 ------------ .github/workflows/test-mongo.yml | 6 ------ datasketch/version.py | 2 +- datasketch/weighted_minhash.py | 3 +++ setup.py | 10 +++------- 6 files changed, 11 insertions(+), 34 deletions(-) diff --git a/.github/workflows/doc.yml b/.github/workflows/doc.yml index 9b2e3734..38840b25 100644 --- a/.github/workflows/doc.yml +++ b/.github/workflows/doc.yml @@ -1,12 +1,7 @@ -name: Documentation +name: Build Documentation -on: - workflow_run: - workflows: ["Test", "Test Mongo", "Test Cassandra"] - types: - - completed - branches: - - master +# Triggers the workflow on push or pull request events +on: [push, pull_request] jobs: build: @@ -32,6 +27,7 @@ jobs: cd docs make html - name: Deploy to GitHub pages + if: ${{ github.ref == 'refs/heads/master' }} uses: JamesIves/github-pages-deploy-action@v4 with: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} diff --git a/.github/workflows/test-cassandra.yml b/.github/workflows/test-cassandra.yml index 58046e17..7dcf3688 100644 --- a/.github/workflows/test-cassandra.yml +++ b/.github/workflows/test-cassandra.yml @@ -12,7 +12,6 @@ jobs: runs-on: "ubuntu-latest" strategy: matrix: - # python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"] python-version: ["3.11"] services: cassandra: @@ -22,17 +21,6 @@ jobs: options: --health-cmd "cqlsh --debug" --health-interval 5s --health-retries 10 steps: - uses: actions/checkout@v3 - # - name: Setup Cassandra - # uses: fabasoad/setup-cassandra-action@v1.0.2 - # - name: Install and Start Cassandra - # run: | - # echo "deb http://debian.datastax.com/community stable main" | sudo tee -a /etc/apt/sources.list.d/cassandra.sources.list - # curl -L http://debian.datastax.com/debian/repo_key | sudo apt-key add - - # sudo apt-get update - # sudo apt-get install openjdk-8-jdk - # java -version - # sudo apt-get install cassandra cython3 - # bash travis/wait_for_cassandra.sh - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v4 with: diff --git a/.github/workflows/test-mongo.yml b/.github/workflows/test-mongo.yml index 892c9fc4..a0e0ce72 100644 --- a/.github/workflows/test-mongo.yml +++ b/.github/workflows/test-mongo.yml @@ -12,13 +12,7 @@ jobs: runs-on: "ubuntu-latest" strategy: matrix: - # python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"] python-version: ["3.11"] - # services: - # mongo: - # image: mongo - # ports: - # - 27017:27017 steps: - uses: actions/checkout@v3 - name: Setup MongoDB diff --git a/datasketch/version.py b/datasketch/version.py index ea64649c..f1fb20fd 100644 --- a/datasketch/version.py +++ b/datasketch/version.py @@ -1 +1 @@ -__version__="1.5.8" +__version__="1.5.9" diff --git a/datasketch/weighted_minhash.py b/datasketch/weighted_minhash.py index fcf6179a..fdd2a11f 100644 --- a/datasketch/weighted_minhash.py +++ b/datasketch/weighted_minhash.py @@ -147,6 +147,9 @@ def minhash_many(self, X : Union[sp.sparse.spmatrix, np.ndarray]) \ multi-set, and each column stores the integer frequency of the element of a dimension. + Note: this method is experimental and does not yield the same MinHash + hash values as `minhash`. + Args: X (Union[sp.sparse.spmatrix, np.ndarray]): A matrix of Jaccard vectors (rows). diff --git a/setup.py b/setup.py index 6ee7b537..d32415f4 100644 --- a/setup.py +++ b/setup.py @@ -39,15 +39,11 @@ 'Topic :: Database', 'Topic :: Scientific/Engineering :: Information Analysis', 'License :: OSI Approved :: MIT License', - 'Programming Language :: Python :: 2.7', - 'Programming Language :: Python :: 3', - 'Programming Language :: Python :: 3.2', - 'Programming Language :: Python :: 3.3', - 'Programming Language :: Python :: 3.4', - 'Programming Language :: Python :: 3.5', - 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: 3.7', 'Programming Language :: Python :: 3.8', + 'Programming Language :: Python :: 3.9', + 'Programming Language :: Python :: 3.10', + 'Programming Language :: Python :: 3.11', ], keywords='database datamining', packages=find_packages(include=['datasketch*']),