Merge pull request #18 from CyrilJl/improve/professional-quality

Raise package quality and reliability standards

Author: CyrilJl

.github/workflows/publish-to-pypi.yml

@@ -3,9 +3,12 @@ name: Publish to PyPI
 on:
   push:
     tags:
-      - '*'
+      - "v*"
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     runs-on: ubuntu-latest
@@ -17,7 +20,8 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: 3.x
+          python-version: "3.14"
+          cache: pip
 
       - name: Install dependencies
         run: |
@@ -28,9 +32,12 @@ jobs:
         run: |
           python -m build
 
+      - name: Validate distribution metadata
+        run: twine check dist/*
+
       - name: Publish to PyPI
         env:
           TWINE_USERNAME: __token__
           TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
         run: |
-          twine upload dist/*
+          twine upload dist/*

.github/workflows/pytest.yml

@@ -1,33 +1,36 @@
-name: Pytest
+name: Tests
 
 on:
+  push:
+    branches: [main]
   pull_request:
-    branches: [ "main" ]
+    branches: [main]
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   test:
+    name: Python ${{ matrix.python-version }}
     runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
 
     steps:
-    - name: Checkout repository
-      uses: actions/checkout@v5
-
-    - name: Set up Python
-      uses: actions/setup-python@v6
-      with:
-        python-version: '3.12'
+      - name: Check out repository
+        uses: actions/checkout@v5
 
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install pytest numpy build
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
 
-    - name: Install batchstats
-      run: |
-        python -m build
-        pip install .
+      - name: Install package and test dependencies
+        run: python -m pip install ".[test]"
 
-    - name: Run Pytest
-      run: |
-        pytest tests
+      - name: Run tests with coverage
+        run: python -m pytest --cov=batchstats

.github/workflows/ruff-format-pr.yml

@@ -1,28 +1,72 @@
-name: Format with Ruff
+name: Quality
 
 on:
+  push:
+    branches: [main]
   pull_request:
-    branches: [ main ]
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: read
 
 jobs:
-  format:
+  lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - name: Check out repository
+        uses: actions/checkout@v5
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
         with:
-          ref: ${{ github.head_ref }}
+          python-version: "3.14"
+          cache: pip
 
       - name: Install Ruff
-        run: pip install ruff
-
-      - name: Run ruff format
-        run: ruff format .
-
-      - name: Commit changes
-        if: success()
-        run: |
-          git diff --quiet || (git add . && \
-          git -c user.name="GitHub Actions" \
-              -c user.email="actions@github.com" \
-              commit -m "Format code with Ruff" && \
-          git push)
+        run: python -m pip install "ruff>=0.11,<1"
+
+      - name: Lint
+        run: python -m ruff check .
+
+      - name: Check formatting
+        run: python -m ruff format --check .
+
+  package:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v5
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.14"
+          cache: pip
+
+      - name: Install build tools
+        run: python -m pip install "build>=1.2,<2" "twine>=6,<8"
+
+      - name: Build distributions
+        run: python -m build
+
+      - name: Validate distribution metadata
+        run: python -m twine check dist/*
+
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v5
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.14"
+          cache: pip
+
+      - name: Install package and documentation dependencies
+        run: python -m pip install ".[docs]"
+
+      - name: Build documentation
+        run: python -m sphinx -W --keep-going -b html docs/source docs/_build/html

README.md

@@ -2,6 +2,7 @@
   <img src="https://raw.githubusercontent.com/CyrilJl/BatchStats/main/docs/source/_static/logo_batchstats.svg" alt="Logo BatchStats" width="200">
 
 [![PyPI Version](https://img.shields.io/pypi/v/batchstats.svg)](https://pypi.org/project/batchstats/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/batchstats.svg)](https://pypi.org/project/batchstats/)
 [![conda Version](https://anaconda.org/conda-forge/batchstats/badges/version.svg)](https://anaconda.org/conda-forge/batchstats)
 [![Documentation Status](https://img.shields.io/readthedocs/batchstats?logo=read-the-docs)](https://batchstats.readthedocs.io/en/latest/?badge=latest)
 [![Unit tests](https://github.com/CyrilJl/BatchStats/actions/workflows/pytest.yml/badge.svg)](https://github.com/CyrilJl/BatchStats/actions/workflows/pytest.yml)
@@ -10,7 +11,9 @@
 
 # BatchStats
 
-BatchStats computes statistics on data that arrives in batches, so you can stream or process large datasets without loading everything into memory. Feed batches with `update_batch`, then call the object to get the final result.
+BatchStats computes statistics on data that arrives in batches, so you can stream or process large datasets without loading everything into memory. Its incremental algorithms expose a small NumPy-friendly API and support merging independently computed accumulators.
+
+BatchStats requires Python 3.10 or newer.
 
 ## Installation
 
@@ -30,7 +33,8 @@ conda install -c conda-forge batchstats
 import numpy as np
 from batchstats import BatchMean, BatchVar
 
-data_stream = (np.random.randn(100, 10) for _ in range(10))
+rng = np.random.default_rng(0)
+data_stream = (rng.standard_normal((100, 10)) for _ in range(10))
 
 batch_mean = BatchMean()
 batch_var = BatchVar()
@@ -61,3 +65,16 @@ print(f"Variance shape: {variance.shape}")
 * `BatchCorr`
 
 Docs: https://batchstats.readthedocs.io
+
+## Development
+
+Install the development dependencies and run the local quality gates:
+
+```console
+python -m pip install -e ".[dev]"
+python -m ruff check .
+python -m ruff format --check .
+python -m pytest --cov=batchstats
+python -m build
+python -m twine check dist/*
+```

batchstats/__init__.py

@@ -1,5 +1,12 @@
 from importlib.metadata import version
 
+from ._misc import (
+    DifferentAxisError,
+    DifferentShapesError,
+    DifferentStatsError,
+    NoValidSamplesError,
+    UnequalSamplesNumber,
+)
 from .base import BatchNanStat, BatchStat
 from .nanstats import BatchNanMax, BatchNanMean, BatchNanMin, BatchNanPeakToPeak, BatchNanSum
 from .stats import (
@@ -22,19 +29,24 @@
     "BatchMax",
     "BatchMean",
     "BatchMin",
+    "BatchNanMax",
+    "BatchNanMean",
+    "BatchNanMin",
+    "BatchNanPeakToPeak",
+    "BatchNanStat",
+    "BatchNanSum",
     "BatchPeakToPeak",
     "BatchStat",
     "BatchStd",
     "BatchSum",
     "BatchVar",
     "BatchWeightedMean",
     "BatchWeightedSum",
-    "BatchNanMax",
-    "BatchNanMean",
-    "BatchNanMin",
-    "BatchNanPeakToPeak",
-    "BatchNanStat",
-    "BatchNanSum",
+    "DifferentAxisError",
+    "DifferentShapesError",
+    "DifferentStatsError",
+    "NoValidSamplesError",
+    "UnequalSamplesNumber",
 ]
 
 __version__ = version("batchstats")

batchstats/_misc.py

@@ -1,10 +1,5 @@
-import warnings
-
 import numpy as np
 
-# Customize the warning format
-warnings.formatwarning = lambda msg, *args, **kwargs: str(msg) + "\n"
-
 
 class NoValidSamplesError(ValueError):
     """
@@ -48,7 +43,7 @@ def any_nan(x, axis=None):
         numpy.ndarray: Boolean array indicating NaN presence.
 
     """
-    return np.isnan(np.add.reduce(array=x, axis=axis))
+    return np.isnan(x).any(axis=axis)
 
 
 def check_params(param, params=None, types=None):
@@ -70,8 +65,3 @@ def check_params(param, params=None, types=None):
 
     # Return the parameter if it passes the checks
     return param
-
-
-def warning(msg):
-    # Trigger a warning with the provided message
-    return warnings.warn(msg)

batchstats/base/batch_nan_stat.py

@@ -42,7 +42,7 @@ def __init__(self, axis=0):
 
     def _process_batch(self, batch):
         """
-        Process the input batch, counting valid (finite) values.
+        Process the input batch, counting non-NaN values.
 
         Args:
             batch (numpy.ndarray): Input batch.
@@ -53,7 +53,7 @@ def _process_batch(self, batch):
 
         """
         batch = np.atleast_2d(np.asarray(batch))
-        n_valid = np.isfinite(batch).sum(axis=self.axis)
+        n_valid = np.count_nonzero(~np.isnan(batch), axis=self.axis)
         self._add_valid_count(n_valid)
         return batch, n_valid
 

batchstats/base/batch_stat.py

@@ -113,10 +113,11 @@ def __repr__(self):
         return f"{self.__class__.__name__}()"
 
     def merge_test(self, other, field: str):
-        if type(self) != type(other):
+        if type(self) is not type(other):
             raise DifferentStatsError()
         if self.axis != other.axis:
             raise DifferentAxisError()
-        if hasattr(self, field) and hasattr(other, field):
-            if getattr(self, field).shape != getattr(other, field).shape:
-                raise DifferentShapesError()
+        left = getattr(self, field, None)
+        right = getattr(other, field, None)
+        if left is not None and right is not None and left.shape != right.shape:
+            raise DifferentShapesError()

batchstats/nanstats/nan_max.py

@@ -134,7 +134,7 @@ def __add__(self, other):
         else:
             ret = BatchNanMax(axis=self.axis)
             ret.n_samples = self.n_samples + other.n_samples
-            ret.max = np.maximum(self.max, other.max)
+            ret.max = np.fmax(self.max, other.max)
             return ret
 
     def merge_test(self, other, field=None):

batchstats/nanstats/nan_mean.py

@@ -1,3 +1,5 @@
+import numpy as np
+
 from ..base import BatchNanStat
 from .nan_sum import BatchNanSum
 
@@ -93,4 +95,5 @@ def __call__(self):
             numpy.ndarray: Mean of the batches.
 
         """
-        return self.sum() / self.sum.n_samples
+        with np.errstate(divide="ignore", invalid="ignore"):
+            return self.sum() / self.sum.n_samples