Add format and linter (#62)

format, linter and associated workflow
---------

Co-authored-by: Amogh Joshi <[email protected]>

.github/workflows/ci.yml

@@ -0,0 +1,40 @@
+name: ci
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    name: Test - ${{ matrix.python-version }} - ${{matrix.os}}
+    runs-on: ${{matrix.os}}
+
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12"]
+        os: [ubuntu-latest, macOs-latest]
+      fail-fast: false
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install the latest version of uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "latest"
+          enable-cache: true
+          cache-dependency-glob: "**/pyproject.toml"
+
+      - name: Check if cache used
+        if: steps.setup-uv.outputs.cache-hit == 'true'
+        run: echo "Cache was restored"
+
+      - name: Set up python env
+        run: |
+          uv venv --python  ${{ matrix.python-version }}
+          uv sync --dev
+
+      - name: Run pre-commit
+        continue-on-error: true
+        run: make pre-commit
+
+      - name: Run tests
+        # For example, using `pytest`
+        run: make test

.gitignore

@@ -141,7 +141,6 @@ __MACOSX
 # Extra directories/files
 /**data*/
 
-**/**test*.*
 !tests/*/*
 agml/_helios
 agml/helios_config.sh
@@ -161,6 +160,7 @@ agml/models/training/*.log
 agml/models/training/*.err
 agml/models/training/*.out
 agml/models/training/*.csv
-.*/
+# .*/
 /
 *.pptx
+.ruff_cache

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Contributing Guidelines
 
-Thank you for choosing to contribute to AgML! 
+Thank you for choosing to contribute to AgML!
 
 ## Contributing Data
 
@@ -29,15 +29,15 @@ Image classification datasets are organized in the following directory tree:
     └── <label 2>
         ├── image1.png
         ├── image2.png
-        └── image3.png               
+        └── image3.png
 ```
 
 The `AgMLDataLoader` generates a mapping between each of the label names "label 1", "label 2", etc.,
-and a numerical value. 
+and a numerical value.
 
 #### Object Detection
 
-Object detection datasets are constructed using COCO JSON formatting. For a general overview, see 
+Object detection datasets are constructed using COCO JSON formatting. For a general overview, see
 [https://cocodataset.org/#format-data](https://cocodataset.org/#format-data).
 Another good resource is [https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/cd-transform-coco.html](https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/cd-transform-coco.html).
 Once you have the images and the bounding box annotations, this involves generating a dictionary with four keys:
@@ -75,7 +75,7 @@ The dictionary containing this information should be written to a file called `a
     └── images
         ├── image1.png
         ├── image2.png
-        └── image3.png              
+        └── image3.png
 ```
 
 #### Semantic Segmentation
@@ -104,7 +104,7 @@ The directory tree should look like follows:
 ## Contributing a Dataset
 
 If you've found a new dataset that *isn't already being used* in AgML and you want to add it, there's a few things you
-need to do. 
+need to do.
 
 Any preprocessing code being used for the dataset can be kept in `agml/_internal/preprocess.py`, by adding an `elif` statement
 to the `preprocess()` method with the dataset name. If there is no preprocessing code, then just put a `pass` statement in the block.
@@ -164,7 +164,7 @@ then put "worldwide" for both "continent" and "country".
 | Dataset Format | `ml_task` | `annotation_format` |
 | :------------: | :-------: | :-----------------: |
 | Image Classification | `image_classification` | `directory_names` |
-| Object Detection | `object_detection` | `coco_json` | 
+| Object Detection | `object_detection` | `coco_json` |
 | Semantic Segmentation | `semantic_segmentation` | `image` |
 
 
@@ -184,3 +184,38 @@ If the dataset has no license or has no citation, leave the corresponding lines
 Once you've readied the dataset, create a new pull request on the AgML repository.
 We will then review the changes and review next steps for adding the dataset into AgML's public data storage.
 
+
+## Developement Guidelines
+
+
+### Installing uv
+Dependencies and admin actions are done using `uv`. To Install uv follow the guidelines in  https://docs.astral.sh/uv/getting-started/installation/, it is recommended to use the standalone installation.
+
+
+### Building Project
+
+The build the associated wheels simply run:
+
+```
+make build
+```
+
+To sync the dependencies simply run:
+
+```
+uv sync
+```
+
+### Running tests
+
+```
+make test
+```
+
+### Running scripts
+
+For running scripts or one-offs using the project's installed enviroment
+
+```
+uv run python <script>
+```

Makefile

@@ -0,0 +1,74 @@
+
+SHELL := bash
+
+version := 0.7.0
+
+src.python := $(shell find ./agml -type f -name "*.py" || :)
+test.python := $(shell find ./tests -type f -name "*.py" || :)
+
+uv.project.enviroment := .venv
+dist.dir := dist
+build.wheel := $(dist.dir)/agml-$(version).tar.gz
+
+
+
+
+
+.PHONY: help
+help: ## Print the help screen.
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":|:[[:space:]].*?##"}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+
+# Setup and Build
+
+
+install: setup ## Installing dependencies
+	uv sync
+
+setup: ## Setup the project.
+	uv venv $(uv.project.enviroment)
+
+
+$(build.wheel): $(src.python) ## Build wheels
+	uv build -o $(dist.dir)
+
+build: $(build.wheel) ## Build the distribution wheel.
+
+test: $(test.python) $(src.python) ## Run tests
+	uv run pytest -c=config/pytest.ini $(test.python)
+
+
+# Quality Checks
+
+.PHONY: pre-commit
+pre-commit: check-format lint check-types docstring-coverage
+
+
+.PHONY: check-types
+check-types: ## Run mypy to check type definitions.
+	uv run mypy --config=config/mypy.ini $(src.python) $(test.python)
+
+
+.PHONY: check-format
+check-format: ## Check ruff format
+	uv run ruff format --check --config=config/ruff.toml $(src.python) $(test.python)
+
+
+.PHONY: lint
+lint: ## Run ruff Code Linter
+	uv run ruff check --config=config/ruff.toml $(src.python) $(test.python)
+
+.PHONY:docstring-coverage
+docstring-coverage: ## Compute docstring coverage
+	uv run interrogate -c config/interrogate.toml .
+
+# Automated Quality fixes
+
+.PHONY: lint-fix
+lint-fix: ## Fix ruff Lint issues
+	uv run ruff check --fix --config=config/ruff.toml $(src.python) $(test.python)
+
+
+.PHONY: format
+format: ## Run ruff format (Includes sorting of imports)
+	uv run ruff check --select I --config=config/ruff.toml --fix
+	uv run ruff format --config=config/ruff.toml $(src.python) $(test.python)

agml/__init__.py

@@ -12,27 +12,31 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = '0.7.0'
-__all__ = ['data', 'synthetic', 'backend', 'viz', 'io']
+__version__ = "0.7.0"
+__all__ = ["data", "synthetic", "backend", "viz", "io"]
 
 
 # If AgML is being imported for the first time, then we need to setup
 # the module, namely prepping the config file.
 def _setup():
-    import os as _os
     import json as _json
-    if not _os.path.exists(_os.path.expanduser('~/.agml')):
-        _os.makedirs(_os.path.expanduser('~/.agml'))
-        with open(_os.path.join(
-                _os.path.expanduser('~/.agml/config.json')), 'w') as f:
-            _json.dump({'data_path': _os.path.expanduser('~/.agml/datasets'),
-                        'viz_backend': 'matplotlib'}, f)
-_setup(); del _setup # noqa
+    import os as _os
 
-
-# There are no top-level imported functions or classes, only the modules.
-from . import data, backend, synthetic, viz, io
+    if not _os.path.exists(_os.path.expanduser("~/.agml")):
+        _os.makedirs(_os.path.expanduser("~/.agml"))
+        with open(_os.path.join(_os.path.expanduser("~/.agml/config.json")), "w") as f:
+            _json.dump(
+                {
+                    "data_path": _os.path.expanduser("~/.agml/datasets"),
+                    "viz_backend": "matplotlib",
+                },
+                f,
+            )
 
 
+_setup()
+del _setup  # noqa
 
 
+# There are no top-level imported functions or classes, only the modules.
+from . import backend, data, io, synthetic, viz