Machine learning for streamflow prediction
Project description
mlstream
Machine learning for streamflow prediction.
Oxford English Dictionary:
maelstrom, n. /ˈmeɪlˌstrɑm/
- A powerful whirlpool, originally (usually Maelstrom) one in the Arctic Ocean off the west coast of Norway, which was formerly supposed to suck in and destroy all vessels within a wide radius.
- Any state of turbulence or confusion; a swirling mass of small objects.
Usage
This project is still work in progress. The idea is to create an easy way of training machine learning streamflow models: Just provide your data, select a model (or provide your own), and get the predictions.
Training
exp = Experiment(data_path, is_train=True, run_dir=run_dir,
start_date='01012000', end_date='31122015',
basins=train_basin_ids,
forcing_attributes=['precip', 'tmax', 'tmin'],
static_attributes=['area', 'regulation'])
exp.set_model(model)
exp.train()
Inference
run_dir = Path('./experiments')
exp = Experiment(data_path, is_train=False,
run_dir=run_dir,
basins=test_basin_ids,
start_date='01012016', end_date='31122018')
model.load(run_dir / 'model.pkl')
exp.set_model(model)
results = exp.predict()
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
mlstream-0.1.tar.gz
(19.8 kB
view hashes)
Built Distribution
mlstream-0.1-py3-none-any.whl
(27.9 kB
view hashes)