parity-violation
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.6%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: sh2099
- Language: Python
- Default Branch: main
- Size: 160 KB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
This repository contains the foundations of the code used for our paper: An Unsupervised search for parity violation in the Large Scale Structure.
Installation
Clone
```bash
clone project
git clone git@github.com:sh2099/parity-violation.git cd parity-violation ```
Install using Micromamba (/Conda/Mamba)
For conda or mamba replace micromamba with conda or mamba below.
bash
micromamba env create -f environment.yaml # create mamba environment
micromamba activate parity_env # activate environment
pip install -e . # install as an editable package
Install using Pip
Not sorted yet
Accessing BOSS data
The LSS data from the 12th BOSS data release can be found at https://data.sdss.org/sas/dr12/boss/lss/
For now, I recommend saving any fits files into the data folder.
Environment variables may be introduced later in construction.
Jupyter Notebook Demonstration
The Notebook ml_pv/demo.ipynb has been created to walk through the process step by step, so is a good place to start.\ The hydra setup can then be used for more efficient modular handling.
Generating Images
bash
python -m datagen.image_gen.run_img_gen
To change the number of images, I recommend first trying with the hydra call
bash
python -m datagen.image_gen.run_img_gen images.num_test_samples=24 images.num_train_samples=96
Once initial testing is done, the default values can be changed in the configs.datagen.image_gen.yaml.
Training the model
bash
python -m ml.train_nn