Pipeline di riaddestramento automatico con GitHub Actions

# .github/workflows/retrain.yml (YAML structure shown)
# name: Model Retraining Pipeline
#
# on:
#   schedule:
#     - cron: '0 2 * * 1'  # every Monday at 2 AM UTC
#   workflow_dispatch:       # also allow manual trigger
#
# jobs:
#   retrain:
#     runs-on: ubuntu-latest
#     steps:
#       - uses: actions/checkout@v4
#       - name: Set up Python
#         uses: actions/setup-python@v5
#         with:
#           python-version: '3.11'
print('Workflow YAML structure shown above.')

# Common cron schedule examples for ML pipelines
# '0 2 * * 1'      -- Every Monday at 02:00 UTC (weekly)
# '0 3 * * *'      -- Every day at 03:00 UTC (nightly)
# '0 */6 * * *'    -- Every 6 hours
# '0 2 1 * *'      -- First day of every month at 02:00

# All times are UTC in GitHub Actions
# Use https://crontab.guru to verify cron expressions

# Example in YAML:
# on:
#   schedule:
#     - cron: '0 3 * * *'   # nightly at 3 AM UTC
#   workflow_dispatch:

print('Cron schedule examples shown above.')

# .github/workflows/retrain.yml -- steps section
# steps:
#   - uses: actions/checkout@v4
#
#   - name: Set up Python 3.11
#     uses: actions/setup-python@v5
#     with:
#       python-version: '3.11'
#
#   - name: Cache pip packages
#     uses: actions/cache@v4
#     with:
#       path: ~/.cache/pip
#       key: pip-${{ hashFiles('requirements.txt') }}
#
#   - name: Install dependencies
#     run: pip install -r requirements.txt

print('Workflow steps shown above.')

# .github/workflows/retrain.yml -- env section with secrets
# jobs:
#   retrain:
#     runs-on: ubuntu-latest
#     env:
#       MLFLOW_TRACKING_URI: ${{ secrets.MLFLOW_TRACKING_URI }}
#       AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
#       AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
#       DATABASE_URL: ${{ secrets.PROD_DATABASE_URL }}
#
# In train.py, read normally:
import os
DB_URL = os.getenv('DATABASE_URL')
MLFLOW_URI = os.getenv('MLFLOW_TRACKING_URI')
print('Config loaded from environment.')

# train.py -- called by GitHub Actions
import os
import mlflow
import mlflow.sklearn
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import f1_score

mlflow.set_tracking_uri(os.getenv('MLFLOW_TRACKING_URI', 'http://localhost:5000'))
mlflow.set_experiment('automated_retraining')

with mlflow.start_run(run_name='scheduled_retrain'):
    n_est = int(os.getenv('N_ESTIMATORS', '200'))
    lr = float(os.getenv('LEARNING_RATE', '0.05'))
    mlflow.log_param('n_estimators', n_est)
    mlflow.log_param('learning_rate', lr)

    clf = GradientBoostingClassifier(n_estimators=n_est, learning_rate=lr, random_state=42)
    # clf.fit(X_train, y_train)
    # f1 = f1_score(y_test, clf.predict(X_test))
    # mlflow.log_metric('test_f1', f1)
    # mlflow.sklearn.log_model(clf, 'model', registered_model_name='SentimentClassifier')
    print('Training step complete.')

# evaluate.py -- compare new version against production
from mlflow.tracking import MlflowClient
import sys

client = MlflowClient()
MODEL_NAME = 'SentimentClassifier'

def get_f1(run_id):
    return client.get_run(run_id).data.metrics.get('test_f1', 0)

# Get latest registered version (just added by train.py)
new_versions = client.get_latest_versions(MODEL_NAME, stages=['None'])
new_v = sorted(new_versions, key=lambda v: int(v.version))[-1]
new_f1 = get_f1(new_v.run_id)

prod_versions = client.get_latest_versions(MODEL_NAME, stages=['Production'])
if prod_versions:
    prod_f1 = get_f1(prod_versions[0].run_id)
    print(f'Champion F1: {prod_f1:.4f}  Challenger F1: {new_f1:.4f}')
    should_promote = new_f1 > prod_f1
else:
    print('No champion found.')
    should_promote = True

print('should_promote=' + str(should_promote).lower())
sys.exit(0 if should_promote else 1)  # exit code drives next step

# promote.py -- transition new version to Production
from mlflow.tracking import MlflowClient

client = MlflowClient()
MODEL_NAME = 'SentimentClassifier'

new_versions = client.get_latest_versions(MODEL_NAME, stages=['None'])
new_v = sorted(new_versions, key=lambda v: int(v.version))[-1]

client.transition_model_version_stage(
    name=MODEL_NAME,
    version=new_v.version,
    stage='Production',
    archive_existing_versions=True
)
print(f'Version {new_v.version} promoted to Production.')

# In the workflow YAML:
# - name: Promote model
#   if: success()  # only runs if evaluate.py exits with 0
#   run: python promote.py

# download_data.py -- fetch latest training data from S3
import boto3
import os
from datetime import date

DATA_DATE = os.getenv('DATA_DATE', str(date.today()))  # e.g., 2024-06-15
BUCKET = os.getenv('S3_BUCKET', 'my-ml-data')
KEY = f'datasets/sentiment/{DATA_DATE}/train.parquet'

s3 = boto3.client('s3')
os.makedirs('/tmp/data', exist_ok=True)
s3.download_file(BUCKET, KEY, '/tmp/data/train.parquet')
print(f'Downloaded data for {DATA_DATE}')

# In train.py, log data_date as a parameter:
# mlflow.log_param('data_date', DATA_DATE)

import os
import requests
import json

SLACK_WEBHOOK = os.getenv('SLACK_WEBHOOK_URL')
PROMOTED = os.getenv('PROMOTED', 'false') == 'true'
NEW_VERSION = os.getenv('NEW_VERSION', 'N/A')
NEW_F1 = os.getenv('NEW_F1', 'N/A')

status_icon = ':white_check_mark:' if PROMOTED else ':x:'
status_text = 'Promoted to Production' if PROMOTED else 'Champion retained'

message = {
    'text': (f'{status_icon} *ML Retraining Pipeline*\n'
             f'Model: SentimentClassifier v{NEW_VERSION}\n'
             f'Status: {status_text}\n'
             f'New F1: {NEW_F1}')
}
if SLACK_WEBHOOK:
    requests.post(SLACK_WEBHOOK, data=json.dumps(message))
    print('Slack notification sent.')

# Full workflow summary (pseudo-YAML)
# name: Weekly Model Retraining
# on:
#   schedule: [{cron: '0 3 * * 1'}]
#   workflow_dispatch: {}
# jobs:
#   download_data:
#     runs-on: ubuntu-latest
#     steps: [checkout, setup-python, install, run download_data.py]
#   train:
#     needs: download_data
#     steps: [checkout, setup-python, install, run train.py]
#   evaluate:
#     needs: train
#     steps: [checkout, setup-python, install, run evaluate.py]
#   promote:
#     needs: evaluate
#     if: success()
#     steps: [checkout, setup-python, install, run promote.py]
#   notify:
#     needs: [evaluate, promote]
#     if: always()
#     steps: [run notify.py]
print('Full workflow YAML structure shown above.')