How macster9/galaxyclassifier works
Project type and purpose
• From the file tree and minimal README (“GalaxyClassifier”), this is a Python-based machine-learning pipeline/tool designed to train, evaluate, and run a classifier on galaxy data. It combines data ingestion, preprocessing, model training/evaluation, and interactive analysis in notebooks.
File structure
• Top-level files:
• main.py / run.bat / __install__.bat / __update__.bat – entrypoints and automation scripts
• config.yml – central configuration for paths, parameters, hyperparameters
• requirements.txt – Python dependencies
• data/ – raw and intermediary CSV/GZ data artifacts (train, test, validation, error logs, reference tables)
• scripts/:
• data_pipeline.py – orchestrates ingestion + preprocessing
• training.py – model training and checkpointing
• tools/: reusable modules:
• read.py – data I/O utilities
• utils.py – preprocessing helpers
• network.py – model architecture definitions
• plot.py – visualization routines
• setup.py – environment or dependency setup logic
• notebooks/: Execute.ipynb for exploratory analysis and interactive runs.
README for additional insights
• There is no further architectural description beyond the title. We’ll infer typical ML pipeline stages and automation intent from batch scripts.