How har2yqn78/epl-ml works
Project type and purpose
• From the file tree and README (“EPL-ML”), this is a data-science / machine-learning project built in Python.
File structure
• Top-level directories:
• app/ → Python modules for reusable logic (main.py orchestration, utils.py helper functions)
• dataset/ → Raw CSV data (EPL-2015-2025.csv)
• notebook/ → Jupyter notebooks for EDA, visualization, modeling experiments
• pypyr/ → YAML config (train_model.yaml) for pipeline orchestration
• requirements.txt → Python dependencies
• Key patterns:
• A clear separation of raw data, exploratory analysis (notebooks), and production pipeline (app + pypyr).
• Use of pypyr for “pipeline as code” to glue data-loading, preprocessing, model training steps.
• No web service or database components—this is a batch/ETL + training pipeline.
README for additional insights
• README only names the project (“EPL-ML”) but does not define architecture.
Detail
• Every major .py module and its role
• That main.py orchestrates the pipeline when invoked by pypyr
• A note about requirements.txt feeding into environment setup