Big bang!

.flake8

@@ -0,0 +1,6 @@
+[flake8]
+extend-ignore = E203,E266,E501,W503
+max-line-length = 88
+max-complexity = 18
+select = B,C,E,F,W,T4,B9
+mypy_config = .mypy.ini

.github/workflows/mypy-flake-test.yml

@@ -0,0 +1,48 @@
+name: Q&A and Tests
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "bico/**"
+      - "tests/**"
+      - "poetry.lock"
+  pull_request:
+    paths:
+      - "bico/**"
+      - "tests/**"
+      - "poetry.lock"
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | POETRY_VERSION=1.8.2 python3 -
+          poetry run pip install -U pip
+          poetry install --with dev
+
+      - name: Run MyPy
+        run: |
+          mkdir .mypy_cache
+          poetry run mypy --install-types --non-interactive bico
+      - name: Run Flake8
+        run: |
+          poetry run flake8 bico/
+      - name: Run Tests
+        run: |
+          poetry run python -m unittest discover tests -v

.github/workflows/publish.yml

@@ -0,0 +1,30 @@
+name: Upload to PyPi
+
+on:
+  release:
+    types: [published]
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.10"
+    - name: Install poetry
+      run: |
+        curl -sSL https://install.python-poetry.org | POETRY_VERSION=1.8.2 python3 -
+        export PATH="/root/.local/bin:$PATH"
+        poetry run pip install -U pip
+        poetry install
+    - name: Publish package
+      run: poetry publish --build --username __token__ --password ${{ secrets.PYPI_TOKEN }}

.gitignore

@@ -0,0 +1,166 @@
+# Prerequisites
+*.d
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+.vscode/
+.idea/
+.DS_Store

.mypy.ini

@@ -0,0 +1,9 @@
+[mypy]
+disallow_untyped_defs = True
+disallow_untyped_calls = True
+ignore_missing_imports = True
+warn_no_return = True
+warn_return_any = True
+warn_unreachable = True
+warn_unused_configs = True
+exclude = _external

.pre-commit-config.yaml

@@ -0,0 +1,26 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.0.1
+  hooks:
+  - id: end-of-file-fixer
+    exclude: \\w+.pdf
+  - id: trailing-whitespace
+    exclude: \\w+.pdf
+- repo: https://github.com/psf/black
+  rev: 22.3.0
+  hooks:
+  - id: black
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+  - id: isort
+- repo: https://github.com/PyCQA/flake8
+  rev: 7.0.0
+  hooks:
+  - id: flake8
+    additional_dependencies: ["flake8-bugbear==21.4.3"]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.10.0
+  hooks:
+  - id: mypy
+    args: ["--install-types", "--non-interactive"]

README.md

@@ -0,0 +1,104 @@
+[![Build Status](https://github.com/algo-hhu//actions/workflows/mypy-flake-test.yml/badge.svg)](https://github.com/algo-hhu/bico/actions)
+[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
+[![Supported Python version](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/release/python-390/)
+[![Stable Version](https://img.shields.io/pypi/v/bico?label=stable)](https://pypi.org/project/bico/)
+
+# BICO
+
+BICO is a fast streaming algorithm to compute high quality solutions for the k-means problem on very large sets of points. It combines the tree data structure of SIGMOND Test of Time Award winning algorithm BIRCH with insights from clustering theory to obtain solutions fast while keeping the error regarding the k-means cost function low.
+
+<!---
+TODO: Add logo
+<p align="center">
+  <img src="https://github.com/algo-hhu/bico/blob/main/images/logo.png" alt="BICO Logo"/>
+</p>
+-->
+
+## Installation
+
+```bash
+pip install bico
+```
+
+## Example
+
+```python
+from bico import BICO
+import numpy as np
+import time
+
+np.random.seed(42)
+
+data = np.random.rand(10000, 10)
+
+start = time.time()
+bico = BICO(n_clusters=3, random_state=0, fit_coreset=True)
+bico.fit(data)
+
+print("Time:", time.time() - start)
+# Time: 0.08275651931762695
+
+print(bico.coreset_points_)
+# BICO returns a set of points that act as a summary of the entire dataset.
+# By default, at most 200 * n_clusters points are returned.
+# This behaviour can be changed by setting the `summary_size` parameter.
+
+# [[0.45224018 0.70183673 0.55506671 ... 0.70132665 0.57244196 0.66789088]
+#  [0.73712952 0.5250208  0.43809322 ... 0.61427161 0.67910981 0.56207661]
+#  [0.89905336 0.46942062 0.20677639 ... 0.74210482 0.75714522 0.49651055]
+#  ...
+#  [0.68744494 0.41508081 0.39197623 ... 0.44093386 0.21983902 0.37237243]
+#  [0.60820965 0.29406341 0.67067782 ... 0.66435474 0.2390822  0.20070476]
+#  [0.67385626 0.33474823 0.68238779 ... 0.3581703  0.65646253 0.41386131]]
+
+print(bico.cluster_centers_)
+# If the `fit_coreset` parameter is set to True, the cluster centers are computed using KMeans from sklearn based on the coreset.
+
+# [[0.46892639 0.41968333 0.47302945 0.51782955 0.39390839 0.56209413
+#   0.4481691  0.49521457 0.31394509 0.5104331 ]
+#  [0.54384638 0.518978   0.49456809 0.56677848 0.63881783 0.33627504
+#   0.49873782 0.5541338  0.52913562 0.56017203]
+#  [0.48639347 0.55542596 0.54350474 0.41931257 0.48117255 0.60089563
+#   0.55457724 0.44833238 0.67583389 0.43069267]]
+```
+
+## Development
+
+Install [poetry](https://python-poetry.org/docs/#installation)
+```bash
+curl -sSL https://install.python-poetry.org | python3 -
+```
+
+Install clang
+```bash
+sudo apt-get install clang
+```
+
+Set clang variables
+```bash
+export CXX=/usr/bin/clang++
+export CC=/usr/bin/clang
+```
+
+Install the package
+```bash
+poetry install
+```
+
+If the installation does not work and you do not see the C++ output, you can build the package to see the stack trace
+```bash
+poetry build
+```
+
+Run the tests
+```bash
+poetry run python -m unittest discover tests -v
+```
+
+## Citation
+
+If you use this code, please cite [the following paper](https://link.springer.com/chapter/10.1007/978-3-642-40450-4_41):
+
+```
+Hendrik Fichtenberger, Marc Gillé, Melanie Schmidt, Chris Schwiegelshohn and Christian Sohler. "BICO: BIRCH Meets Coresets for k-Means Clustering" (2013). ESA 2013.
+```

bico/__init__.py

@@ -0,0 +1,3 @@
+from bico.core import BICO
+
+__all__ = ["BICO"]