TP4 Parties 2-4 : pipeline.py (split -> train --register -> promote) + workflow Forgejo Actions (PR -> main) + requirements

.forgejo/workflows/pipeline.yml

@@ -0,0 +1,50 @@
+name: pipeline
+
+# Partie 4 : le pipeline ML est rejoue automatiquement a chaque Pull Request
+# vers la branche principale (Q4.1). Autres declencheurs possibles (Q4.4) :
+# push sur main, tag de release, planification (schedule/cron), declenchement
+# manuel (workflow_dispatch).
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  train-and-register:
+    runs-on: docker
+    # Le runner (mode docker, reseau mlops-net) lance le job dans ce conteneur.
+    # On y monte en lecture seule les donnees source du fil rouge et le magasin
+    # de certificats du host (pour faire confiance a la CA interne ENI MLOps).
+    container:
+      image: node:20-bookworm
+      volumes:
+        - /data/modelling:/data/modelling:ro
+        - /etc/ssl/certs/ca-certificates.crt:/etc/ssl/certs/ca-certificates.crt:ro
+    steps:
+      - name: Recuperation du code
+        uses: actions/checkout@v4
+
+      - name: Installation de Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.14"
+
+      - name: Installation des dependances
+        run: pip install -r requirements.txt
+
+      - name: Execution du pipeline (split -> train --register -> promote)
+        run: python pipeline.py
+        env:
+          # Serveur MLflow (basic auth) : URLs HTTPS via Caddy, resolues sur mlops-net.
+          MLFLOW_TRACKING_URI: ${{ secrets.MLFLOW_TRACKING_URI }}
+          MLFLOW_TRACKING_USERNAME: ${{ secrets.MLFLOW_TRACKING_USERNAME }}
+          MLFLOW_TRACKING_PASSWORD: ${{ secrets.MLFLOW_TRACKING_PASSWORD }}
+          MLFLOW_EXPERIMENT_NAME: ${{ secrets.MLFLOW_EXPERIMENT_NAME }}
+          # Artefacts sur S3 Garage (log_model).
+          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          MLFLOW_S3_ENDPOINT_URL: ${{ secrets.MLFLOW_S3_ENDPOINT_URL }}
+          # CA interne ENI MLOps (requests/boto3 n'utilisent pas le store systeme par defaut).
+          REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
+          AWS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
+          # Import du package lab depuis la racine du depot.
+          PYTHONPATH: ${{ github.workspace }}