Python implementation of Continuous Change Detection
Project description
PyCCD - Python Continuous Change Detection
pyccd creates change segments from Landsat timeseries data
Using PyCCD
>>> import ccd
>>> results = ccd.detect(dates, blues, greens, reds, nirs, swir1s, swir2s, thermals, qas, prev_results)
>>>
>>> type(results)
<class 'dict'>
>>>
>>> results
{algorithm: 'pyccd:x.x.x',
processing_mask: [bool, bool, ...],
snow_prob: float,
water_prob: float,
cloud_prob: float,
change_models: [
{start_day: int,
end_day: int,
break_day: int,
observation_count: int,
change_probability: float,
curve_qa: int,
blue: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float},
green: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float},
red: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float},
nir: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float},
swir1: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float},
swir2: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float},
thermal: {magnitude: float,
rmse: float,
coefficients: (float, float, ...),
intercept: float}}
]
}
Default processing parameters can be overridden using a dictionary (see parameters.yaml for valid keys):
>>> import ccd
>>> params = {'QA_BITPACKED': False,
'QA_FILL': 255,
'QA_CLEAR': 0,
'QA_WATER': 1,
'QA_SHADOW': 2,
'QA_SNOW': 3,
'QA_CLOUD': 4}
>>> results = ccd.detect(dates, blues, greens, reds, nirs, swir1s, swir2s, thermals, qas, params=params)
Installing
System requirements (Ubuntu)
- python3-dev
- gfortran
- libopenblas-dev
- liblapack-dev
- graphviz
- python-virtualenv
System requirements (Centos)
- python3-devel
- gfortran
- blas-dev
- lapack-dev
- graphviz
- python-virtualenv
It's highly recommended to do all your development & testing in a virtual environment.
user@dev:/home/user/$ mkdir pyccd
user@dev:/home/user/$ cd pyccd
user@dev:/home/user/pyccd$ virtualenv -p python3 .venv
user@dev:/home/user/pyccd$ . .venv/bin/activate
(.venv) user@dev:/home/user/pyccd$
Install
$ pip install -e .[test,dev,docs,deploy,profile]
Testing
$ pytest
$ pytest --profile
$ pytest --profile-svg
# pytest-watch
$ ptw
Make targets
$ make build
$ make tests
$ make docs
$ make deploy
$ make profile
Profiling
Decorate the function to be profiled with @profile
and
run make profile
. Remove decorations before committing code.
Contributing
Before committing to this repository, run the following command.
git config --local commit.template .gitmessage
This will add the LCMAP commit template to git commit
.
jira/lcmap-xxxx: Title
Description
Contributions are most welcome.
- Open an issue and discuss the change.
- Branch from major version and name it after the issue
- jira/lcmap-xxxx
- Write automated tests for your changes and make sure all tests pass.
- Update documentation in project.
- Submit pull request to the appropriate branch (e.g. 1,x)
Versions
PyCCD previously followed MAJOR.MINOR.PATCH.LABEL semantic versioning but has changed to date based semantic versioning, thus: YYYY.MM.DD[.HH.MM.SS][-label].
PyCCD's version is defined by the ccd/version.py/__version__
attribute.
References
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for lcmap_pyccd-2021.7.19-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 605230eaaeccc6d7273dc7d0675272e309819b58e70376e7f55a83dafc1fab41 |
|
MD5 | 81da25c5c6e831d6b8a72c891555a1d5 |
|
BLAKE2b-256 | 9e932ecbadaa8713491feb48d08014e29490e475bf4896e230bc5dac1e08146b |