.github/workflows/pipeline.yml

name: Predictive Maintenance ML Pipeline

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
  workflow_dispatch:

env:
  PYTHON_VERSION: '3.11'
  HF_USERNAME: 'SharleyK'
  DATASET_NAME: 'PredictiveMaintenance'
  MODEL_NAME: 'engine-predictive-maintenance'
  MLFLOW_TRACKING_URI: 'file:./mlruns'

jobs:
  data-registration:
    name: Data Registration
    runs-on: ubuntu-latest

    steps:
      - name: Checkout repository
        uses: actions/checkout@v3

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: 3.11

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Create project folders
        run: |
          python scripts/01_create_folders.py

      - name: Register data to Hugging Face
        env:
          HF_TOKEN: ${ secrets.HF_TOKEN }
        run: |
          python scripts/02_register_data.py

      - name: Verify data registration
        env:
          HF_TOKEN: ${ secrets.HF_TOKEN }
        run: |
          python scripts/03_verify_data.py

  exploratory-analysis:
    name: Exploratory Data Analysis
    runs-on: ubuntu-latest
    needs: data-registration

    steps:
      - name: Checkout repository
        uses: actions/checkout@v3

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: 3.11

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Run EDA analysis
        env:
          HF_TOKEN: ${ secrets.HF_TOKEN }
        run: |
          python scripts/05_run_eda.py

  data-preparation:
    name: Data Preparation
    runs-on: ubuntu-latest
    needs: exploratory-analysis

    steps:
      - name: Checkout repository
        uses: actions/checkout@v3

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: 3.11

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Clean and prepare data
        env:
          HF_TOKEN: ${ secrets.HF_TOKEN }
        run: |
          python scripts/07_clean_data.py
          python scripts/09_train_test_split.py
          python scripts/10_upload_processed_data.py

  model-training:
    name: Model Training & Experimentation
    runs-on: ubuntu-latest
    needs: data-preparation

    steps:
      - name: Checkout repository
        uses: actions/checkout@v3

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: 3.11

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Train all models
        env:
          HF_TOKEN: ${ secrets.HF_TOKEN }
        run: |
          python scripts/13_train_decision_tree.py
          python scripts/14_train_bagging.py
          python scripts/15_train_random_forest.py
          python scripts/16_train_adaboost.py
          python scripts/17_train_gradient_boosting.py
          python scripts/18_train_xgboost.py

      - name: Compare and register best model
        env:
          HF_TOKEN: ${ secrets.HF_TOKEN }
        run: |
          python scripts/19_compare_models.py
          python scripts/20_register_best_model.py