Create CD pipeline

.github/workflows/cd.yml

@@ -0,0 +1,52 @@
+name: 'Continuous Deployment'
+
+#on:
+#  push:
+#    branches:
+#      - main
+#      - develop
+#      - release/*
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Get the branch name
+        run: |
+          run: echo "branch=${GITHUB_HEAD_REF:-${GITHUB_REF#refs/heads/}}" >> $GITHUB_OUTPUT
+        id: get_branch_name
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.9'
+
+      - name: Authenticate to GCP
+        uses: 'google-github-actions/auth@v2'
+        with:
+          credentials_json: '${{ secrets.CD_SA_KEYS }}'
+
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt -r requirements-dev.txt -r requirements-test.txt
+
+      - name: Run training script
+        run: |
+          python train.py
+
+      - name: Authenticate Docker to GAR
+        uses: docker/login-action@v3
+        with:
+          registry: '${{ vars.GCP_REGION }}-docker.pkg.dev'
+          username: _json_key
+          password: ${{ secrets.CD_SA_KEYS }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          push: true
+          tags: '${{ vars.GAR_REPOSITORY }}/${{ vars.GAR_IMAGE_NAME }}'

docs/challenge.md

@@ -133,3 +133,5 @@ The CI workflows focus on running the tests and assesing the quality of the code
 The CD workflows focus on training the model, deploying the API and running the stress testing against it. These workflows only run when there's a push to the `main`, `develop` or `release` branches on the repository.
 
 * Undesirable model tracking
+* env variables ci/cd
+* makefile argument

train.py

@@ -0,0 +1,26 @@
+from challenge.model import DelayModel
+import pandas as pd
+
+print("Loading data...")
+# Read the data
+df = pd.read_csv("data/data.csv")
+print("-> Data loaded")
+
+# Create the model
+model = DelayModel()
+
+print("Preprocessing data...")
+# Preprocess the data
+X_train, y_train = model.preprocess(df, "delay")
+print("-> Preprocessed data")
+
+
+print("Training model...")
+# Train the model
+model.fit(X_train, y_train)
+print("-> Model trained")
+
+print("Saving model...")
+# Store the model
+model.save("challenge/tmp/model_checkpoint.pkl")
+print("-> Model saved")