# har2yqn78/epl-ml architecture

> Architecture diagram of the GitHub repository har2yqn78/epl-ml, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/har2yqn78/epl-ml
- Repository: https://github.com/har2yqn78/epl-ml

## Overview

##### 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

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph "Prototyping Lane"
        direction TB
        DS["dataset/EPL-2015-2025.csv"]:::data
        Process["app/utils.py (Preprocessing Logic)"]:::code
        NB1["1 - Explore data.ipynb"]:::notebook
        NB2["2 - visualization.ipynb"]:::notebook
        NB3["3 - Modeling(Random Forest).ipynb"]:::notebook
        NB4["4 - Modeling(XGBoost).ipynb"]:::notebook
        NB5["5 - modeling random forest(weight class)).ipynb"]:::notebook

        DS --> NB1
        DS --> NB2
        DS --> NB3
        DS --> NB4
        DS --> NB5
        Process --> NB1
        Process --> NB2
    end

    subgraph "Production Lane"
        direction TB
        DS2["dataset/EPL-2015-2025.csv"]:::data
        Env["requirements.txt"]:::env
        Orch["pypyr/train_model.yaml"]:::orchestration
        Process2["app/utils.py"]:::code
        Main["app/main.py (Entry Point)"]:::code
        Model["Model Training"]:::code
        Output["Trained Model & Metrics"]:::output

        Env --> Orch
        DS2 --> Process2
        Process2 --> Orch
        Orch --> Main
        Main --> Model
        Model --> Output
    end

    click DS "https://github.com/har2yqn78/epl-ml/blob/main/dataset/EPL-2015-2025.csv"
    click DS2 "https://github.com/har2yqn78/epl-ml/blob/main/dataset/EPL-2015-2025.csv"
    click Process "https://github.com/har2yqn78/epl-ml/blob/main/app/utils.py"
    click Process2 "https://github.com/har2yqn78/epl-ml/blob/main/app/utils.py"
    click Orch "https://github.com/har2yqn78/epl-ml/blob/main/pypyr/train_model.yaml"
    click Main "https://github.com/har2yqn78/epl-ml/blob/main/app/main.py"
    click NB1 "https://github.com/har2yqn78/epl-ml/blob/main/notebook/1 - Explore data.ipynb"
    click NB2 "https://github.com/har2yqn78/epl-ml/blob/main/notebook/2 - visualization.ipynb"
    click NB3 "https://github.com/har2yqn78/epl-ml/blob/main/notebook/3 - Modeling(Random Forest).ipynb"
    click NB4 "https://github.com/har2yqn78/epl-ml/blob/main/notebook/4 - Modeling(XGBoost).ipynb"
    click NB5 "https://github.com/har2yqn78/epl-ml/blob/main/notebook/5 - modeling random forest(weight class)).ipynb"
    click Env "https://github.com/har2yqn78/epl-ml/blob/main/requirements.txt"

    class DS,DS2 data
    class Process,Process2,Main,Model code
    class Orch orchestration
    class NB1,NB2,NB3,NB4,NB5 notebook
    class Output output
    class Env env

    classDef data fill:#ADD8E6,stroke:#333,stroke-width:1px
    classDef code fill:#90EE90,stroke:#333,stroke-width:1px
    classDef orchestration fill:#FFA500,stroke:#333,stroke-width:1px
    classDef notebook fill:#FFD700,stroke:#333,stroke-width:1px
    classDef output fill:#D3D3D3,stroke:#333,stroke-width:1px
    classDef env fill:#E6E6FA,stroke:#333,stroke-width:1px
```
