No project description provided
Project description
NDVI TRENDS
A module for studying NDVI Trends (from S2/LSAT) with a particular emphasis on determining or deriving relvant features for cover-cropping.
- Generate and Save NDVI Series for small Regions a. grab NDVI Series on the fly for any geom b. for a large set of geoms efficiently grab and save all
- Smooth NDVI Series a. linear interpolation b. remove drops c. sg smoothing d. window smoothing e. 1 at a time or save a stack
- Days over (normalized) NDVI Threshold
- Cover Crop Detection
- green-up dates
- features (AUC, mean/median differences for set time periods, other metrics)
PROPOSED MODULES
smoothing: handles smoothing data
data: get/save data (in real time, 1 at a time, map over a bunch)
gee: helpers for google earth engine
nb: helpers for visual outputs for notebooks
calc: smooths data, extracts features of interest, computes GREEN-DAYS
cli: automates batch jobs
REQUIREMENTS
Packages are managed through a conda yaml file. To create/update the ndvi_trends
environment:
# create
conda env create -f conda-env.yaml
# update
### NOTE: prune not working https://github.com/conda/conda/issues/7279
conda env update -f conda-env.yaml --prune
### use mamba as workaround:
mamba env update -f conda-env.yaml --prune
Additionally this repo is using config_args and mproc still in developmemt. Clone the repos and then (with ndvi_trends conda env activated) run pip install --e .
Note: the minimal conda-env does not specify the required package versions. requirements.txt can be used to recreate the exact env.
QUICK START
Usage example
DOCUMENTATION
DEPLOY TO PYPI:
# (optional) need to first remove old distributions or be more selective with * on twine-upload
rm -rf dist
# https://packaging.python.org/en/latest/tutorials/packaging-projects/
python -m build
python -m twine upload dist/*
NOTE: When testing locally the editable environment (pip install -e .
) might behave differently than the pacakage. For example, the pyproject.toml should explicitly include submodules. In this case:
[tool.setuptools]
packages = [
"ndvi_trends",
"ndvi_trends.utils"
]
My original file did not include ndvi_trends.utils
but behaved correctly locally. However when deployed this lead to problems. Before deploying drop the -e
!
MODULES:
├── ndvi_trends │ ├── calc: extracts features and statistics from NDVI Series │ ├── data: methods for fetching NDVI data from Harmonized S2-Landsat using GEE │ ├── smoothing: gap filling and smoothing utilities │ └── utils │ └── ee: helper methods for GEE
See doc-strings for documentation of python modules.
STYLE-GUIDE
Following PEP8. See setup.cfg for exceptions. Keeping honest with pycodestyle .
Project details
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
File details
Details for the file ndvi_trends-0.0.8.tar.gz
.
File metadata
- Download URL: ndvi_trends-0.0.8.tar.gz
- Upload date:
- Size: 17.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.10.14
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 22a3b171f69589a7e13b6bf4fce65b88b007f079a12671c480bbbf1073ac57f0 |
|
MD5 | a2b7eb5bfe26c49ad86b8a31904d57db |
|
BLAKE2b-256 | 7fe487988044f067094d510f0072f4ff2abaa1db6f903c07bf876aab2925f3d5 |
File details
Details for the file ndvi_trends-0.0.8-py3-none-any.whl
.
File metadata
- Download URL: ndvi_trends-0.0.8-py3-none-any.whl
- Upload date:
- Size: 18.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.10.14
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3b6d108eda6186bfe0cc605d8f65cc26a81f56efa335d6395f452183589aa472 |
|
MD5 | 97ebd8c4032577ea8a56383a6031d2c8 |
|
BLAKE2b-256 | c7d3954e0f04867da5980b26cb9867915d97cb1a9c21dd9c727514f48e7d098e |