probixi 0.1.0__tar.gz

probixi-0.1.0/.github/workflows/cov.yml

@@ -0,0 +1,44 @@
+name: Test+Upload probixi
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-26]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
+
+    steps:
+    - uses: actions/checkout@v6
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v8.2.0
+
+    - name: Set up Python ${{ matrix.python-version }}
+      run: uv python install ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: |
+        uv venv --python ${{ matrix.python-version }}
+        uv pip install pytest pytest-cov
+        uv pip install -e ".[dev]"
+
+    - name: Test with pytest
+      run: |
+        uv run pytest tests/ -v --cov=probixi --cov-report=xml
+
+    - name: Upload coverage reports to Codecov
+      uses: codecov/codecov-action@v7
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}

probixi-0.1.0/.github/workflows/format.yml

@@ -0,0 +1,45 @@
+name: Auto-format Code
+
+on:
+  pull_request:
+    branches: [main, devel*]
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  format:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          ref: ${{ github.head_ref || github.ref_name }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.11'
+
+      - name: Install formatters
+        run: pip install black isort ruff
+
+      - name: Auto-fix lint issues with Ruff
+        run: ruff check --fix --exit-zero .
+
+      - name: Sort imports with isort
+        run: isort .
+
+      - name: Format with Black
+        run: black .
+
+      - name: Commit changes
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git diff --quiet || (git add -A && git commit -m "Auto-format code (black, isort, ruff)")
+          git push
+
+      - name: Flag remaining lint issues with Ruff
+        run: ruff check --output-format=github .

probixi-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,71 @@
+# This workflow will upload a Python Package to PyPI when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  release-build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.x"
+
+      - name: Build release distributions
+        run: |
+          # NOTE: put your own distribution build steps here.
+          python -m pip install build
+          python -m build
+
+      - name: Upload distributions
+        uses: actions/upload-artifact@v7
+        with:
+          name: release-dists
+          path: dist/
+
+  pypi-publish:
+    runs-on: ubuntu-latest
+    needs:
+      - release-build
+    permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write
+
+    # Dedicated environments with protections for publishing are strongly recommended.
+    # For more information, see: https://docs.github.com/en/actions/deployment/targeting-different-environments/using-environments-for-deployment#deployment-protection-rules
+    environment:
+      name: pypi
+      # OPTIONAL: uncomment and update to include your PyPI project URL in the deployment status:
+      # url: https://pypi.org/p/YOURPROJECT
+      #
+      # ALTERNATIVE: if your GitHub Release name is the PyPI project version string
+      # ALTERNATIVE: exactly, uncomment the following line instead:
+      # url: https://pypi.org/project/YOURPROJECT/${{ github.event.release.name }}
+
+    steps:
+      - name: Retrieve release distributions
+        uses: actions/download-artifact@v8
+        with:
+          name: release-dists
+          path: dist/
+
+      - name: Publish release distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/

probixi-0.1.0/.gitignore

@@ -0,0 +1,227 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# Other
+uv.lock
+.DS_Store
+test_data/
+testing.py
+
+tests/test_data/
+tests/*.h5

probixi-0.1.0/.readthedocs.yml

@@ -0,0 +1,24 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.13"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+   configuration: docs/conf.py
+
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+  - requirements: docs/requirements.txt
+  - method: pip
+    path: .

probixi-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Ryan O'Dea
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

probixi-0.1.0/PKG-INFO

@@ -0,0 +1,231 @@
+Metadata-Version: 2.4
+Name: probixi
+Version: 0.1.0
+Summary: Self-Calibrating Probabilistic Peak Finding for Serial X-Ray Crystallography
+Project-URL: Homepage, https://github.com/ryan-odea/probixi
+Project-URL: Repository, https://github.com/ryan-odea/probixi
+Project-URL: Bug Tracker, https://github.com/ryan-odea/probixi/issues
+Project-URL: Ryan O'Dea (ORCID), https://orcid.org/0009-0000-0103-9546
+Author-email: Ryan O'Dea <ryan.odea@psi.ch>
+Maintainer-email: Ryan O'Dea <ryan.odea@psi.ch>
+License: MIT
+License-File: LICENSE
+Keywords: peak finding,probabilistic,x-ray crystallography
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.9
+Requires-Dist: click
+Requires-Dist: h5py
+Requires-Dist: hdf5plugin
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: pillow
+Requires-Dist: torch
+Provides-Extra: dev
+Requires-Dist: black; extra == 'dev'
+Requires-Dist: isort; extra == 'dev'
+Requires-Dist: myst-parser; extra == 'dev'
+Requires-Dist: piccolo-theme; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Requires-Dist: sphinx; extra == 'dev'
+Requires-Dist: sphinx-autodoc-typehints; extra == 'dev'
+Requires-Dist: sphinx-copybutton; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: myst-parser; extra == 'docs'
+Requires-Dist: piccolo-theme; extra == 'docs'
+Requires-Dist: sphinx; extra == 'docs'
+Requires-Dist: sphinx-autodoc-typehints; extra == 'docs'
+Requires-Dist: sphinx-copybutton; extra == 'docs'
+Description-Content-Type: text/markdown
+
+# probixi - Self-Calibrating (PROB)ab(I)listic Peak Detection for Serial (X)-Ray Crystallograph(I)c Data
+
+[![Lifecycle:
+experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
+[![PyPI version](https://badge.fury.io/py/probixi.svg)](https://pypi.org/project/probixi) 
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/probixi)
+[![PyTorch](https://img.shields.io/badge/PyTorch-2.4+-ee4c2c.svg)](https://pytorch.org/)
+[![codecov](https://codecov.io/gh/ryan-odea/Probixi/graph/badge.svg?token=DMOVJJUWXP)](https://codecov.io/gh/ryan-odea/Probixi)
+[![CUDA](https://img.shields.io/badge/CUDA-supported-76b900.svg)](https://developer.nvidia.com/cuda-zone)
+[![Apple Silicon MPS](https://img.shields.io/badge/Apple%20Silicon-MPS-000000.svg?logo=apple)](https://developer.apple.com/metal/pytorch/)
+[![Downloads](https://static.pepy.tech/badge/probixi)](https://pepy.tech/project/probixi)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+[![Documentation Status](https://readthedocs.org/projects/probixi/badge/?version=latest)](https://probixi.readthedocs.io)
+[![Code Style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
+
+`probixi` proposes that bragg peaks can be found/recovered from a detector image by observing the background noise distributional shape over time, per pixel, and collecting peak candidates from an outlier set. Since this noise model is determined in an unsupervised fashion, the user does not need to tune hyperparameters for finding peaks. We are still testing robustness to different types of data collection (synchrotron, FEL) and random fluence changes, results will be included in this README as they arrive.
+
+## Installing the Package
+
+You can install via Pypi with pip:
+
+```bash
+pip install probixi
+```
+
+Or the latest development version with
+
+```bash
+pip install git+https://github.com/ryan-odea/probixi.git
+```
+
+## Using `probixi`
+
+`probixi` can be interacted with either via the command line interface, or through the python API. In it's current implementation, via python, the `Probixi` API returns iterables, which remain on a GPU tensor via pytorch up until collection - meaning that you can further pass information for any downstream processing. Through the CLI, this is currently a one-stop-shop for peakfinding and indexing. **This may change in the future**
+
+`probixi` also has a 'burn-in' phase, where the noise model reaches some stable point, this can be further interrogated with a handy gif.
+
+Via the CLI:
+
+```bash
+probixi -i files.lst -g myGeometry.geom -p myCell.cell -o stream.stream --device cuda --gif myNoiseModel.gif
+```
+
+Or with python:
+
+```python
+import torch
+
+from probixi import Probixi
+from probixi.io import DataOffloader
+
+pipeline = Probixi(
+    list_file="files.lst",
+    geometry_file="myGeometry.geom",
+    cell_file="myCell.cell",
+    device=torch.device("cuda"),
+)
+
+pipeline.noise_diagnostics("myNoiseModel.gif", stop=32)
+cal = pipeline.calibrate(n_seed=1636)
+print(f"kappa={cal.kappa:.2f}  prior_peak={cal.prior_peak:.4f}  "
+      f"threshold={pipeline.threshold_calibration.threshold:.2f}")
+
+# Stream every frame through detect -> index -> predict + integrate. The stream
+# is lazy and each result stays on the GPU until you touch it, so you can branch
+# off any downstream processing with torch
+with DataOffloader(
+    "stream.stream",
+    geometry=pipeline.geometry,
+    cell=pipeline.target_cell,
+    geometry_file="myGeometry.geom",
+    files=pipeline.metadata.files,
+) as off:
+    for result in pipeline.index_stream(pipeline.frames(), batch_size=8):
+        off.write(result)  # or: pipeline.index_stream(...).to_stream(off)
+        print(f"frame {result.frame_index}: "
+              f"{result.n_indexed}/{result.n_peaks} indexed (rmsd {result.rmsd:.4f})")
+```
+
+## Comparison with other works
+
+Here, we provide a comparison with other peakfinding algorithms with real data. Using a randomly sampled 10,000 frames from experimentally collected data. 
+
+Notes:
+
+1. For wall time, because `probixi` handles optimizing internal hyperparameters automatically, I have included time used for loose manual hyperparameter tuning on 10% subsamples to find optimal SNR, threshold, and minimum pixels. CPU time for only peakfinding and indexing is bracketed.
+2. Percent agreement is calculated as the (set of crystals indexed by probixi) / (set of crystals indexed by the reference) * 100. Greater than 100 indicates that `probixi` was able to index more crystals.
+
+Benchmarks were run on:
+
+- GPU: A100
+- CPU: TODO which CPU do Ra nodes use?
+
+### `peakfinder8 + indexamajig`
+
+| Dataset                               | Percent Indexed (`probixi`) | GPU time (`probixi`) | Percent Indexed (`peakfinder8+indexamajig`) | CPU Time (`peakfinder8+indexamajig`) [No-Tuning] | Percent Agreement |
+|---------------------------------------|---------------------------|---------------------|-------------------------------------|-------------------------------|-------------------|
+| Lysozyme-Synchrotron                  |                           |                     |                                     |                               |                   |
+| Lysozyme-FEL                          |                           |                     |                                     |                               |                   |
+| BacterioRhodopsin-Synchrotron         |                           |                     |                                     |                               |                   |
+| BacterioRhodopsin-FEL                 |                           |                     |                                     |                               |                   |
+| Randomly Dimmed Lysozyme-FEL          |                           |                     |                                     |                               |                   |
+| Randomly Dimmed BacterioRhodopsin-FEL |                           |                     |                                     |                               |                   |
+
+### pyFAI + TORO
+
+Perhaps a more fair comparison, especially with respect to speed, is [pyFAI][pyfai] (azimuthal
+integration and peak picking) paired with the [TORO][toro] indexer, which both run on the GPU.
+
+[pyfai]: https://doi.org/10.1107/S1600576715004306
+[toro]: https://doi.org/10.1107/S1600576724003182
+
+
+| Dataset                               | Percent Indexed (`probixi`) | GPU time (`probixi`) | Percent Indexed (`pyFAI+TORO`) | GPU Time (`pyFAI+TORO`) [No-Tuning] | Percent Agreement |
+|---------------------------------------|---------------------------|---------------------|-------------------------------------|-------------------------------|-------------------|
+| Lysozyme-Synchrotron                  |                           |                     |                                     |                               |                   |
+| Lysozyme-FEL                          |                           |                     |                                     |                               |                   |
+| BacterioRhodopsin-Synchrotron         |                           |                     |                                     |                               |                   |
+| BacterioRhodopsin-FEL                 |                           |                     |                                     |                               |                   |
+| Randomly Dimmed Lysozyme-FEL          |                           |                     |                                     |                               |                   |
+| Randomly Dimmed BacterioRhodopsin-FEL |                           |                     |                                     |                               |                   |
+
+
+### Using `probixi` as only a peakfinder
+
+Of course, if you only want to use probixi as a peakfinder and prefer to use your own indexing regime, this is possible -- through the CLI's `--peaks-only` flag or the Python API's `peak_stream`.
+
+Via the CLI:
+
+```bash
+probixi -i files.lst -g myGeometry.geom -o peaks.stream --peaks-only --device cuda
+```
+
+Or with python:
+
+```python
+import torch
+
+from probixi import Probixi
+from probixi.io import PeakOffloader
+
+pipeline = Probixi(
+    list_file="files.lst",
+    geometry_file="myGeometry.geom",
+    device=torch.device("cuda"),
+)
+
+# Calibrate the noise model + detection threshold on the seed frames, as usual.
+pipeline.calibrate(n_seed=1636)
+
+peaks = pipeline.peak_stream(pipeline.frames(), estimate_scale=False)
+with PeakOffloader(
+    "peaks.stream",
+    geometry=pipeline.geometry,
+    geometry_file="myGeometry.geom",
+    files=pipeline.metadata.files,
+) as off:
+    for result in peaks:
+        if len(result):       # skip blanks; export only frames with peaks
+            off.write(result)
+```
+
+## Dependencies
+
+- python >= 3.9
+  - click
+  - h5py
+  - hdf5plugin
+  - numpy
+  - torch
+  - matplotlib
+  - pillow
+
+## Contributing
+
+There are many different ways to contribute to further development of this tool. If you experience a bug or would like an additional feature, please open up a [ticket](https://github.com/ryan-odea/probixi/issues). 
+
+If you would like to contribute actively by merging code, please open a PR with the following:
+
+1. Code is formatted with `isort`, then `black`, followed by a `ruff --check`. This will initiate on PR, so it might be best to check beforehand.
+2. Docstrings are minimally on user-facing functions in [`numpy` style](https://numpydoc.readthedocs.io/en/latest/format.html). 
+3. Comments, or some explanation (in PR) for the additions, limited to the scope of the project. If fixing a bug, comments should be included in the PR rather than the code itself.