Restructure as package of tools (with pyproject) (#31)

* Add standard python ignore and Mac system files

* Update description and instructions in README for package formulation

* Restructure as package of tools with pyproject

Co-authored-by: Alison Zhong <[email protected]>

---------

Co-authored-by: Alison Zhong <[email protected]>

.gitignore

@@ -1,5 +1,4 @@
 .idea/*
-__pycache__/*
 mini-scenes/*
 leaderboard.png
 statistics_giraffes.png
@@ -8,4 +7,169 @@ statistics_all.png
 statistics_g.png
 statistics_zg.png
 statistics_zp.png
-yolov8x.pt
+yolov8x.pt
+
+# Standard python ignore files
+# 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/
+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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# 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/
+
+# Mac System
+.DS_Store

README.md

@@ -4,38 +4,46 @@ This repository contains tools for the KABR dataset preparation.
 
 ![](https://user-images.githubusercontent.com/11778655/236357196-c09547fc-0e6b-4b2e-a7a5-18683dc944e5.png)
 
-detector2cvat.py:\
+
+These tools can be installed with:
+```
+pip install git+https://github.com/Imageomics/kabr-tools
+```
+
+Each KABR tool can be run through the command line (as described below) or imported as a python module. They each have help information which can be accessed on the command line through `<tool-name> -h`.
+
+**detector2cvat:**\
 Detect objects with Ultralytics YOLO detections, apply SORT tracking and convert tracks to CVAT format.
 
 ```
-python detector2cvat.py --video path_to_videos --save path_to_save
+detector2cvat --video path_to_videos --save path_to_save
 ```
 
-cvat2ultralytics.py:\
+**cvat2ultralytics:**\
 Convert CVAT annotations to Ultralytics YOLO dataset.
 
 ```
-python cvat2ultralytics.py --video path_to_videos --annotation path_to_annotations --dataset dataset_name [--skip skip_frames]
+cvat2ultralytics --video path_to_videos --annotation path_to_annotations --dataset dataset_name [--skip skip_frames]
 ```
 
-tracks_extractor.py:\
+**tracks_extractor:**\
 Extract mini-scenes from CVAT tracks.
 
 ```
-python tracks_extractor.py --video path_to_videos --annotation path_to_annotations [--tracking]
+tracks_extractor --video path_to_videos --annotation path_to_annotations [--tracking]
 ```
 
-player.py:\
+**player:**\
 Player for track and behavior observation.
 
 ```
-python player.py --folder path_to_folder [--save]
+player --folder path_to_folder [--save]
 ```
 
 
-cvat2slowfast.py:\
+**cvat2slowfast:**\
 Convert CVAT annotations to the dataset in Charades format.
 
 ```
-python cvat2slowfast.py --miniscene path_to_mini_scenes --dataset dataset_name --classes path_to_classes_json --old2new path_to_old2new_json
+cvat2slowfast --miniscene path_to_mini_scenes --dataset dataset_name --classes path_to_classes_json --old2new path_to_old2new_json
 ```

pyproject.toml

@@ -0,0 +1,66 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/kabr_tools"]
+
+[tool.hatch.metadata]
+allow-direct-references = true
+
+[project]
+name = "kabr_tools"
+dynamic = ["version"]
+authors = [
+  { name="Maksim Kholiavchenko", email="[email protected]" },
+  { name="Alison Zhong", email="[email protected]" },
+  { name="Elizabeth Campolongo", email="[email protected]" },
+  { name="Jenna Kline", email="[email protected]" },
+]
+description = "Tools for working with data for annotating animal behavior. These were specifically designed during construction of the KABR dataset."
+readme = "README.md"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+]
+dependencies = [
+    "numpy",
+    "opencv-python",
+    "scipy",
+    "lxml",
+    "tqdm",
+    "torch",
+    "natsort",
+    "ruamel.yaml",
+    "ultralytics",
+    "pandas",
+]
+keywords = [
+    "annotation",
+    "cv",
+    "cvat",
+    "videos",
+    "drone videos",
+    "video classification",
+    "behavior recognition",
+    "animal behavior recognition",
+    "animal behavior",
+    "mini-scenes",
+]
+
+[project.urls]
+Documentation = "https://github.com/Imageomics/kabr-tools/blob/master/README.md"
+Issues = "https://github.com/Imageomics/kabr-tools/issues"
+Source = "https://github.com/Imageomics/kabr-tools"
+
+[project.scripts]
+cvat2slowfast = "kabr_tools.cvat2slowfast:main"
+cvat2ultralytics = "kabr_tools.cvat2ultralytics:main"
+detector2cvat = "kabr_tools.detector2cvat:main"
+player = "kabr_tools.player:main"
+tracks_extractor = "kabr_tools.tracks_extractor:main"
+
+
+[tool.hatch.version]
+path = "src/kabr_tools/__about__.py"

src/kabr_tools/__about__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

src/kabr_tools/__init__.py

@@ -0,0 +1,3 @@
+from kabr_tools import cvat2slowfast, cvat2ultralytics, detector2cvat, player, tracks_extractor
+
+__all__ = ["cvat2slowfast", "cvat2ultralytics", "detector2cvat", "player", "tracks_extractor"]

cvat2slowfast.py → src/kabr_tools/cvat2slowfast.py

@@ -174,6 +174,10 @@ def parse_args():
     return local_parser.parse_args()
 
 
-if __name__ == "__main__":
+def main():
     args = parse_args()
     cvat2slowfast(args.miniscene, args.dataset, args.classes, args.old2new)
+
+
+if __name__ == "__main__":
+    main()

cvat2ultralytics.py → src/kabr_tools/cvat2ultralytics.py

@@ -196,6 +196,10 @@ def parse_args():
     return local_parser.parse_args()
 
 
-if __name__ == "__main__":
+def main():
     args = parse_args()
     cvat2ultralytics(args.video, args.annotation, args.dataset, args.skip)
+
+
+if __name__ == "__main__":
+    main()

detector2cvat.py → src/kabr_tools/detector2cvat.py

@@ -2,10 +2,11 @@
 import argparse
 import cv2
 from tqdm import tqdm
-from src.yolo import YOLOv8
-from src.tracker import Tracker, Tracks
-from src.object import Object
-from src.draw import Draw
+from kabr_tools.utils.yolo import YOLOv8
+from kabr_tools.utils.tracker import Tracker, Tracks
+from kabr_tools.utils.object import Object
+from kabr_tools.utils.draw import Draw
+
 
 
 def detector2cvat(path_to_videos, path_to_save):
@@ -113,6 +114,10 @@ def parse_args():
     return local_parser.parse_args()
 
 
-if __name__ == "__main__":
+def main():
     args = parse_args()
     detector2cvat(args.video, args.save)
+
+
+if __name__ == "__main__":
+    main()

player.py → src/kabr_tools/player.py

@@ -285,6 +285,10 @@ def parse_args():
     return local_parser.parse_args()
 
 
-if __name__ == "__main__":
+def main():
     args = parse_args()
     player(args.folder, args.save)
+
+
+if __name__ == "__main__":
+    main()