Photovoltaic per site modeling
Project description
pv-site-prediction
This repo contains code to train and evaluate pv-site models.
Organisation of the repo
.
├── exp_reports # Experiment reports - markdown notes about experiments we have made
├── exp_results # Default output for the {train,eval}_model.py scripts
├── notebooks # Diverse notebooks
├── data # Placeholder for data files
└── psp # Main python package
├── clients # Client specific code
├── data_sources # Data sources (PV, NWP, Satellite, etc.)
├── exp_configs # Experimentation configs - a config defines the different options for
│ # training and evaluation models. This directory contains many ready
│ # configs where the paths points to the data on Leonardo.
├── models # The machine learning code
├── scripts # Scripts (entry points)
└── tests # Unit tests
Training and evaluating a model
poetry run python psp/scripts/train_model.py \
--exp-config-name test_config1 \
-n test
poetry run python psp/scripts/eval_model.py \
-n test
# This will have generated a model and test results in `exp_results/test`.
# You can then look at the results in the `expriment_analysis.ipynb` and
# `sample_analysis.ipynb` notebooks by setting EXP_NAMES=["test"] in the first cells.
# Call the scripts with `--help` to see more options, in particular to run on more than one CPU.
# The script run_exp.sh can be used to train and then evaluate a model, for example
./run_exp.sh exp_config_to_use name_for_exp
Prerequisites
Development
# Installation of the dependencies.
poetry install
# Formatting
make format
# Linting
make lint
# Running the tests.
make test
# Starting the jupyter notebooks.
make notebook
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
Close
Hashes for pv_site_prediction-0.1.12.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8ab959c2fb356b469bfcc53fe61f491d3e8f17a604f9481d85a873b76b810c6d |
|
MD5 | c5ccfee5fec5ebc2f9fc4eba93706c95 |
|
BLAKE2b-256 | 130625986956e25b907ee2c438960d01b3cb48bc2824c6d87e7e97bd0922cee3 |
Close
Hashes for pv_site_prediction-0.1.12-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c5967450b9d50e8082975babbf792b818937e8e1c4906f1152d1483572821a33 |
|
MD5 | 26cf4a5371e73fced44f35d49d0ab999 |
|
BLAKE2b-256 | 41e38d2025b600837568bb8edd8b32085af46644909627a1f912e8084f05a3de |