Merge pull request #1 from allenai/opensource

initial commit

.dockerignore

@@ -0,0 +1,16 @@
+.git
+.gitlab-ci.yml
+.dockerignore
+dist
+Dockerfile
+docker-compose.yml
+**/.ipynb_checkpoints
+**/.pytest_cache
+**/__pycache__
+**/*.ipynb
+**/__pycache__
+tests/test_outputs/
+tests/test_files/dev
+tests/test_files/full_moon
+tests/test_files/new_moon
+src/feedback_model/vvd_annotations/**

.gitattributes

@@ -0,0 +1,2 @@
+docs/**
+example/sample_response.json

.github/workflows/lint.yml

@@ -0,0 +1,28 @@
+name: Lint (type checking, security, code quality, ruff)
+
+on:
+ push:
+ branches:
+ - "main"
+ pull_request:
+ branches:
+ - "main"
+
+jobs:
+ linting:
+ runs-on: ubuntu-latest
+
+ steps:
+ - uses: actions/checkout@v3
+ with:
+ lfs: false
+
+ - name: Set up Python 3.10
+ uses: actions/setup-python@v4
+ with:
+ python-version: 3.10.10
+
+ - name: Linting
+ run: |
+ pip install pre-commit interrogate
+ pre-commit run --all-files

.github/workflows/push_image.yml

@@ -0,0 +1,46 @@
+name: Create and publish a Docker image
+
+on:
+ push:
+ branches:
+
+env:
+ REGISTRY: ghcr.io
+ IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+ build-and-push-image:
+ runs-on: ubuntu-latest
+ permissions:
+ contents: read
+ packages: write
+
+ steps:
+ - name: Checkout repository
+ uses: actions/checkout@v3
+ with:
+ lfs: false
+
+ - name: Log in to the Container registry
+ uses: docker/login-action@v2
+ with:
+ registry: ghcr.io
+ username: ${{ github.actor }}
+ password: ${{ secrets.GITHUB_TOKEN }}
+
+ - name: Extract metadata (tags, labels) for Docker
+ id: meta
+ uses: docker/metadata-action@v4
+ with:
+ images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+ tags: |
+ type=sha,format=short
+ type=raw,value=latest,enable={{is_default_branch}}
+
+ - name: Build and push Docker image
+ uses: docker/build-push-action@v3
+ with:
+ context: .
+ push: true
+ tags: ${{ steps.meta.outputs.tags }}
+ labels: ${{ steps.meta.outputs.labels }}

.github/workflows/tests.yml

@@ -0,0 +1,53 @@
+name: Run tests
+
+on:
+ push:
+ branches:
+ - "main"
+ pull_request:
+ branches:
+ - "main"
+
+jobs:
+ unit-tests:
+ runs-on: ubuntu-latest
+ env:
+ COMPOSE_FILE: docker-compose.yml
+
+ steps:
+ - name: Checkout repository
+ uses: actions/checkout@v3
+ with:
+ lfs: true
+
+ - name: Checkout LFS objects for test cases
+ run: git lfs checkout
+
+ - name: Log in to the Container registry
+ uses: docker/login-action@v2
+ with:
+ registry: ghcr.io
+ username: ${{ github.actor }}
+ password: ${{ secrets.GITHUB_TOKEN }}
+
+ - name: Build docker images
+ env:
+ EARTHDATA_TOKEN: "${{ secrets.EARTHDATA_TOKEN }}"
+ run: |
+
+ COMPOSE_DOCKER_CLI_BUILD=1 DOCKER_BUILDKIT=1 docker compose build
+
+ - name: Run unit and integration tests
+ env:
+ EARTHDATA_TOKEN: "${{ secrets.EARTHDATA_TOKEN }}"
+ run: |
+ docker compose run test pytest --ignore=/src/tests/test_main.py -vv
+
+ - name: Start server and test sample request
+ env:
+ EARTHDATA_TOKEN: "${{ secrets.EARTHDATA_TOKEN }}"
+ run: |
+ COMPOSE_DOCKER_CLI_BUILD=1 DOCKER_BUILDKIT=1 docker compose -f docker-compose.yml up -d
+ sleep 5
+ docker ps -a
+ docker compose -f docker-compose.yml exec -T test pytest tests/test_main.py -vv

.gitignore

@@ -0,0 +1,22 @@
+.DS_Store
+*.ipynb
+.ipynb_checkpoints/
+__pycache__/
+debug/
+.venv/
+.vscode/
+tests/test_outputs
+*nc.aux.xml
+dataset/
+**/wandb
+src/feedback_model/viirs_classifier/**/*.jpeg
+single_file_inference.py
+creds.json
+tests/test_files/dev/
+.coverage
+docs/data_card.md
+tests/.coverage
+tests/test_files/chips/
+tests/test_files/full_moon/
+tests/test_files/new_moon/
+src/feedback_images/

.pre-commit-config.yaml

@@ -0,0 +1,77 @@
+repos:
+ - repo: https://github.com/pre-commit/pre-commit-hooks
+ rev: v4.4.0
+ hooks:
+ - id: check-yaml
+ - id: end-of-file-fixer
+ - id: trailing-whitespace
+ - id: check-json
+ - id: mixed-line-ending
+ - id: requirements-txt-fixer
+ - id: pretty-format-json
+ args: ["--autofix"]
+ - id: check-case-conflict
+ - id: check-docstring-first
+ - id: check-added-large-files
+ - id: check-ast
+ - id: check-byte-order-marker
+ - id: check-executables-have-shebangs
+ - id: check-merge-conflict
+ - id: check-toml
+ - id: debug-statements
+ - id: detect-aws-credentials
+ args: [--allow-missing-credentials]
+ - id: detect-private-key
+ - repo: https://github.com/pre-commit/mirrors-mypy
+ rev: v1.1.1
+ hooks:
+ - id: mypy
+ args:
+ [
+ --install-types,
+ --ignore-missing-imports,
+ --disallow-untyped-defs,
+ --ignore-missing-imports,
+ --non-interactive,
+ ]
+ - repo: https://github.com/pre-commit/pre-commit-hooks
+ rev: v4.4.0
+ hooks:
+ - id: detect-private-key
+ - repo: https://github.com/pre-commit/pre-commit-hooks
+ rev: v4.4.0
+ hooks:
+ - id: check-added-large-files
+ - repo: https://github.com/PyCQA/bandit
+ rev: "1.7.5"
+ hooks:
+ - id: bandit
+ exclude: ^tests/
+ args:
+ - -s
+ - B101
+ - repo: local
+ hooks:
+ - id: interrogate
+ name: interrogate
+ language: system
+ entry: interrogate
+ types: [python]
+ args:
+ [
+ --ignore-init-method,
+ --ignore-init-module,
+ -p,
+ -vv,
+ src,
+ --exclude,
+ src/feedback_model/wandb/,
+ --exclude,
+ .ipynb_checkpoints/,
+ --fail-under=90,
+ ]
+ - repo: https://github.com/charliermarsh/ruff-pre-commit
+ rev: "v0.0.257"
+ hooks:
+ - id: ruff
+ exclude: docs/openapi.json

CONTRIBUTING.md

@@ -0,0 +1,55 @@
+# Contributing
+
+We want to make contributing to this project as easy and transparent as possible. If you identify a bug or have a feature request please open an issue. If you discover a new method or an improvement on the models, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement" if you discover an issue but don't have a solution.
+
+## Issues
+
+Please ensure your description is clear and has sufficient instructions to be able to reproduce the issue. The recommended issue format is:
+
+---
+
+#### To Reproduce
+
+`How to reproduce the issue.`
+
+#### Expected behavior
+
+`Expected output.`
+
+#### Environment
+
+`Your environment.`
+
+---
+
+## Developer environment
+
+Test project:
+
+```bash
+pytest .
+```
+
+Lint project:
+Linting is required for PRs. Lint via ruff or use the provided pre commit hooks.
+
+### Precommit hooks
+
+Hooks can be installed from .pre-commit-config.yaml. For example:
+
+1. `$ pip install pre-commit`
+2. `$ pre-commit install`
+
+## Pull Requests
+
+We actively welcome your pull requests.
+
+1. Fork the repo and create your branch from `main`.
+2. If you've changed APIs, update the documentation.
+3. Ensure the test suite passes (`pytest`). These are also required for PRs.
+4. Make sure your code lints (`ruff`). This is also required for PRs.
+
+## Coding Style
+
+We use
+[![Code style: ruff](https://github.com/astral-sh/ruff)](https://github.com/astral-sh/ruff)

Dockerfile

@@ -0,0 +1,20 @@
+FROM ubuntu:22.04@sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21
+
+RUN apt-get update -y
+RUN apt-get install ffmpeg libsm6 libxext6 -y
+
+RUN apt-get install libhdf5-serial-dev netcdf-bin libnetcdf-dev -y
+
+RUN apt-get update && apt-get install -y \
+ python3-pip
+
+COPY requirements/requirements.txt requirements.txt
+
+RUN pip3 install --no-cache-dir --upgrade -r requirements.txt
+
+WORKDIR /src
+
+COPY ./src /src
+COPY ./tests /src/tests
+
+CMD ["python3", "main.py"]

data.md

@@ -0,0 +1,54 @@
+
+## Data for inference
+There are two required datasets for inference, the light intensity data (*DNB_NRT) and supporting data including geolocation, moonlight illumination, and other files used during inference. In addition to these two data sources, there are several optional datasets that are used to improve the quality of the detections. The optional datasets are cloud masks (CLDMSK_NRT) and additional bands (MOD_NRT) used for gas flare identification and removal. The DNB and MOD datasets are provided in near real time through [earthdata](https://www.earthdata.nasa.gov/learn/find-data/near-real-time/viirs) and the cloud masks are provided in near real time through [sips-data](https://sips-data.ssec.wisc.edu/nrt/). The urls for each dataset and satellite is below. Note that downloads require a token, if using the API. Register for the API and create a token at [earthdata](https://urs.earthdata.nasa.gov/).
+Suomi NPP (NOAA/NASA Suomi National Polar-orbiting Partnership)
+| File | SUOMI-NPP | NOAA-20 |
+|-------------------------------|-----------------------------------------------------------------------|----------|
+| Day/Night Band (DNB) | [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VNP02DNB_NRT) | [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VJ102DNB_NRT) |
+| Terrain Corrected Geolocation (DNB) | [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VNP03DNB_NRT)| [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VJ103DNB_NRT)|
+| Clear sky confidence | [url](https://sips-data.ssec.wisc.edu/nrt/CLDMSK_L2_VIIRS_SNPP_NRT) | [url](https://sips-data.ssec.wisc.edu/nrt/CLDMSK_L2_VIIRS_NOAA20_NRT)|
+| Gas Flares Band | [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VNP02MOD_NRT/) | [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VJ102MOD_NRT/)|
+| Terrain Corrected Geolocation (MOD) | [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VNP03MOD_NRT/)| [url](https://nrt3.modaps.eosdis.nasa.gov/archive/allData/5200/VJ103DNB_NRT/)|
+
+## Downloading data
+1. Register an account on earthdata and download a token: https://www.earthdata.nasa.gov/learn/find-data
+2. Set this token in your environment e.g. (export EARTHDATA_TOKEN=$DOWNLOADED_TOKEN)
+3. Download data for each img_path (DNB, GEO data, and cloud masks are required with the default configuration on and around full moons)
+```python
+TOKEN = f"{os.environ.get('EARTHDATA_TOKEN')}"
+with open(dnb_path, "w+b") as fh:
+ utils.download_url(img_path, TOKEN, fh)
+```
+Sample data can be found in the test_files directory. The example requests reference data within test_files.
+## API documentation
+The API schema is automatically generated from src.utils.autogen_api_schema. The schema is written to docs/openapi.json (open in openapi editor such as swagger: https://editor.swagger.io/). Documentation and additional examples are available at http://0.0.0.0:5555/redoc after starting server. Example data is located in test_files.
+
+To regenerate the schema:
+```bash
+python -c 'from src import utils; utils.autogen_api_schema()'
+```
+
+## Tuning the model
+Parameters are defined in src/config/config.yml. Within that config, there are in line comments for the most important parameters, along with recommendations on appropriate ranges to tune those values in order to achieve higher precision or higher recall.
+
+By default, the model filters out a variety of light sources and image artifacts that cause false positive detections. These filters are defined in pipeline section, and can be turned off or on within the config. By default, there are filters for auroral lit clouds, moonlit clouds, image artifacts (bowtie/noise smiles, edge noise), near shore detections, non-max suppression, lightning, and gas flares.
+
+## Generate a labeled dataset
+There are two types of training datasets. The first contains bounding box annotations for each detection in a frame. The second contains image level labels (crops of detected vessels) for training the supervised CNN referenced in src/postprocessor.
+
+To generate a new object detection dataset:
+
+1. Create account at https://nrt3.modaps.eosdis.nasa.gov/
+2. Download earthdata token by clicking on profile icon and "Download token"
+3. Build and run docker container with an an optional mounted volume:
+```bash
+docker run -d -m="50g" --cpus=120 --mount type=bind,source="$(pwd)"/target,target=/src/raw_data skylight-vvd-service:latest
+```
+4. Set this token in your environment: e.g. ```export EARTHDATA_TOKEN=YOUR_DOWNLOADED_TOKEN_FROM_STEP_2```
+5. Annotate the data from within the docker container using ```python src/gen_object_detection_dataset.py```
+
+
+To generate a new image label dataset:
+1. Use src/gen_image_labeled_dataset.py. Sample imagery to train the feedback model is contained within the feedback_model/viirs_classifier folder
+
+Note that a sample dataset of ~1000 detections (<1 GB) has been provided within this repository.

docker-compose.yml

@@ -0,0 +1,14 @@
+version: "3.9"
+services:
+ test:
+ hostname: vvd-test
+ environment:
+ - EARTHDATA_TOKEN=${EARTHDATA_TOKEN}
+ build:
+ context: .
+ dockerfile: Dockerfile
+ extra_hosts:
+ - "host.docker.internal:host-gateway"
+ stdin_open: true
+ ports:
+ - 5555:5555