PyPVRoof: a Python package for the modular extraction of minimal metadata of rooftop PV installations

Yann Trémenbert, Gabriel Kasmi, Laurent Dubus, Yves‐Marie Saint‐Drenan, Philippe BlancZenodo 2023 · DOI

Abstract

This repository contains the necessary data and notebooks to replicate the results and analyses carried out in the paper "PyPVRoof: a Python package for the modular extraction of minimal metadata of rooftop PV installations". This repository is self-sufficient to replicate the models and results. The dataset is organized as follows: <strong>characteristics/</strong> root folder for the replication of the results <strong>/CSV</strong>: contains the `.csv` files necessary to train and evaluate the methods <strong>/Data</strong>: main folder for the data <strong>/BDAPPV</strong>: folder containing the BDAPPV dataset <strong>/DSFrance</strong>: folder containing auxiliary data to run the methods on the outputs of DeepPVMapper <strong>/LiDAR</strong>: folder containing a sample of LiDAR images for evaluation <strong>/Yann</strong>: folder containing auxiliary data and annotations. <strong>/models</strong>: folder containing the weights of the models <strong>/notebooks</strong>: folder containing the Jupyter notebooks in which the models are defined and evaluated. <strong>Methods_Static_Analysis.ipynb</strong> is the main notebook from which the results can be replicated <strong>Characteristics_Extraction_Methods.ipynb</strong> is the notebook in which the methods are gathered and defined. The other notebooks can be used to generate the models using the data located in the <strong>/Data</strong> folder. <strong>/scalers</strong>: folder containing the scaler for the random forest defined for tilt and azimuth estimation <strong>env.yml</strong>: use this file to defined a virtual environment from which the notebooks can be launched. hands-on/ Root folder to run the hands-on notebook from the repository, accessible here : https://github.com/gabrielkasmi/characteristics/blob/main/hands-on.ipynb metadata.csv: a file containing ground truth information for installations located in France. This dataset is filtered from the BDAPPV dataset. Localizations were added based on the information on the departement. arrays_69.geojson. A raw file coming from DeepPVMapper' first step (detection and segmentation). This file is the output of the hands-on notebook of DeepPVMapper. You can access the repository here: https://github.com/gabrielkasmi/deeppvmapper README.md : the Readme file.
BibTeX
@inproceedings{tremenbert2023pypvroof,
  author = {Yann Trémenbert and Gabriel Kasmi and Laurent Dubus and Yves‐Marie Saint‐Drenan and Philippe Blanc},
  title = {{PyPVRoof: a Python package for the modular extraction of minimal metadata of rooftop PV installations}},
  booktitle = {Zenodo},
  year = {2023},
  doi = {10.5281/zenodo.7544394},
}
Figure