Support numpy>=1.20.0 (#192)

* Support numpy>=1.20.0

* Github actions
---------

Co-authored-by: ekzhu <[email protected]>

.github/workflows/doc.yml

@@ -0,0 +1,40 @@
+name: Documentation
+
+on:
+  workflow_run:
+    workflows: ["Test", "Test Mongo", "Test Cassandra"]
+    types:
+      - completed
+    branches:
+      - master
+
+jobs:
+  build:
+    runs-on: "ubuntu-latest"
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install flake8 pytest
+      - name: Install package
+        run: |
+          # Disable Cassandra optional extensions (faster testing).
+          export CASS_DRIVER_NO_EXTENSIONS=1
+          pip install -e .
+      - name: Compile documentation
+        run: |
+          python -m pip install sphinx
+          cd docs
+          make html
+      - name: Deploy to GitHub pages
+        uses: JamesIves/github-pages-deploy-action@v4
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          BRANCH: gh-pages
+          FOLDER: docs/_build/html
+          CLEAN: true

.github/workflows/python-publish.yml → .github/workflows/pypi.yml

@@ -17,23 +17,22 @@ permissions:
 
 jobs:
   deploy:
-
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python
-      uses: actions/setup-python@v3
-      with:
-        python-version: '3.x'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install build
-    - name: Build package
-      run: python -m build
-    - name: Publish package
-      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
-      with:
-        user: __token__
-        password: ${{ secrets.PYPI_API_TOKEN }}
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build
+      - name: Build package
+        run: python -m build
+      - name: Publish package
+        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/test-cassandra.yml

@@ -0,0 +1,53 @@
+name: Test Cassandra
+
+on:
+  workflow_run:
+    workflows:
+      - Test
+    types:
+      - completed
+
+jobs:
+  build:
+    runs-on: "ubuntu-latest"
+    strategy:
+      matrix:
+        # python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.11"]
+    services:
+      cassandra:
+        image: cassandra
+        ports:
+          - 9042:9042
+        options: --health-cmd "cqlsh --debug" --health-interval 5s --health-retries 10
+    steps:
+      - uses: actions/checkout@v3
+      # - name: Setup Cassandra
+      #   uses: fabasoad/[email protected]
+      # - 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:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install flake8 pytest
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Install package
+        run: |
+          # Disable Cassandra optional extensions (faster testing).
+          export CASS_DRIVER_NO_EXTENSIONS=1
+          pip install -e .[test,experimental_aio]
+      - name: Test with pytest
+        run: |
+          export DO_TEST_CASSANDRA=true
+          pytest

.github/workflows/test-mongo.yml

@@ -0,0 +1,42 @@
+name: Test Mongo
+
+on:
+  workflow_run:
+    workflows:
+      - Test
+    types:
+      - completed
+
+jobs:
+  build:
+    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
+        uses: supercharge/[email protected]
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install flake8 pytest
+      - name: Install package
+        run: |
+          # Disable Cassandra optional extensions (faster testing).
+          export CASS_DRIVER_NO_EXTENSIONS=1
+          pip install -e .[test,experimental_aio]
+      - name: Test with pytest
+        run: |
+          export DO_TEST_MONGO=true
+          pytest

.github/workflows/test.yml

@@ -0,0 +1,30 @@
+name: Test
+
+# Triggers the workflow on push or pull request events
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: "ubuntu-latest"
+    strategy:
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install flake8 pytest
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Install package
+        run: |
+          # Disable Cassandra optional extensions (faster testing).
+          export CASS_DRIVER_NO_EXTENSIONS=1
+          pip install -e .[test,experimental_aio]
+      - name: Test with pytest
+        run: |
+          pytest

datasketch/lshensemble.py

@@ -103,7 +103,7 @@ class MinHashLSHEnsemble(object):
     .. _`the paper`: http://www.vldb.org/pvldb/vol9/p1185-zhu.pdf
     '''
 
-    def __init__(self, threshold=0.9, num_perm=128, num_part=16, m=8, 
+    def __init__(self, threshold=0.9, num_perm=128, num_part=16, m=8,
             weights=(0.5,0.5), storage_config=None, prepickle=None):
         if threshold > 1.0 or threshold < 0.0:
             raise ValueError("threshold must be in [0.0, 1.0]")
@@ -142,7 +142,7 @@ def _init_optimal_params(self, weights):
                                                xq,
                                                false_positive_weight,
                                                false_negative_weight)
-                                for xq in self.xqs], dtype=np.int)
+                                for xq in self.xqs], dtype=int)
         # Find all unique r
         rs = set()
         for _, r in self.params:
@@ -154,7 +154,7 @@ def _get_optimal_param(self, x, q):
         if i == len(self.params):
             i = i - 1
         return self.params[i]
-    
+
     def _get_storage_config(self, basename, base_config, partition, r):
         config = dict(base_config)
         config["basename"] = b"-".join(
@@ -200,7 +200,7 @@ def index(self, entries):
                 curr_part += 1
             for r in self.indexes[curr_part]:
                 self.indexes[curr_part][r].insert(key, minhash)
-    
+
     def query(self, minhash, size):
         '''
         Giving the MinHash and size of the query set, retrieve

setup.py

@@ -81,6 +81,7 @@
             'pymongo>=3.9.0',
             'nose>=1.3.7',
             'nose-exclude>=0.5.0',
+            'pytest',
         ],
         'experimental_aio': [
             "aiounittest ; python_version>='3.6'",