Clusternets: A deep learning approach to probe clustering dark energy

This directory contains all the necessary data, codes, and notebooks to reproduce the results of the paper titled "Clusternets: A deep learning approach to probe clustering dark energy" Directories Codes: This directory contains different codes used to generate and post-process the simulation data, including k-evolution, gevolution, Pylians, CLASS, and LATfield2. Final figures and data: This directory includes the data for the power spectra, simulation settings and Jupyter notebooks to produce the figures. How to Use Download the files to your local machine. Navigate to the directory where the files are saved. Install the necessary packages Navigate to the "Final figures and data" directory and open the Jupyter notebooks in your preferred environment. Run the cells in the notebooks to reproduce the figures. Navigate to the "Codes" directory and use the appropriate code to generate and post-process the simulation data. Use the simulation setting files in the "Final figures and data" directory to replicate the simulations. Note: Some of the simulations may require high computational resources and may take a significant amount of time to run. If you have any feedback or request feel free to email chgeniamirsbu@gmail.com and farbod.hassani@gmail.com