Allena un modello di classificazione

In questo esercizio continuerai a lavorare con l'insieme di dati meteo e allenerai un Random Forest Classifier per prevedere la pioggia. Il file preprocess_dataset.py contiene funzioni di supporto per il pre-processing dell'insieme di dati, mentre train.py contiene il codice di training.

Il tuo compito è eseguire in sequenza il codice di pre-processing e quello di training per generare metriche e grafici in output. Al termine dell'esecuzione, il contenuto di metrics.json verrà aggiornato automaticamente con i valori corretti.

NOTA: usa python3 invece di python per eseguire gli script Python.

Questo esercizio fa parte del corso

CI/CD per Machine Learning

Visualizza il corso

Esercizio pratico interattivo

Passa dalla teoria alla pratica con uno dei nostri esercizi interattivi

Inizia esercizio

Questo esercizio fa parte del corso

CI/CD per Machine Learning

AvançadoNível de habilidade

4.8+

306 reviews

Inizia il corso gratis

In this chapter, you will explore the essential principles of Continuous Integration/Continuous Delivery (CI/CD) and YAML. You'll grasp the software development life cycle and key terms like build, test, and deploy. Discover the differences between Continuous Integration, Continuous Delivery, and Continuous Deployment. Moreover, you'll investigate the significance of CI/CD in machine learning and experimentation.

Exercise 1: Introduction to Continuous Integration/Continuous Delivery for Machine Learning Exercise 2: Continuous deployment and delivery Exercise 3: Machine learning workflow Exercise 4: Introduction to YAML Exercise 5: YAML syntax Exercise 6: YAML mappings and sequences Exercise 7: Introduction to GitHub Actions Exercise 8: Utility of GitHub Actions Exercise 9: Anatomy of GitHub Actions

Get ready to explore GitHub Actions (GHA), an influential platform for executing CI/CD workflows. Uncover the diverse components of GHA, encompassing events, actions, jobs, steps, runners, and context. Gain insights into crafting workflows that activate upon events like push and pull requests, and tailor runner machines. Dive into hands-on learning as you establish fundamental CI pipelines and grasp the intricacies of the GHA log.

Exercise 1: Intermediate YAML Exercise 2: Find the correct combination Exercise 3: Design a Continuous Integration workflow Exercise 4: Setting a basic CI pipeline Exercise 5: Interpret GitHub Actions Workflow Exercise 6: Write a GitHub Actions Workflow Exercise 7: Running repository code Exercise 8: Feature branches in shared repository model Exercise 9: Running Python code in GitHub Actions Exercise 10: Environment Variables and Secrets Exercise 11: What is GITHUB_TOKEN?Exercise 12: Working with environment variables Exercise 13: Working with secrets

In this chapter, you'll explore the integration of machine learning model training into a GitHub Action pipeline using Continuous Machine Learning GitHub Action. You'll generate a comprehensive markdown report including model metrics and plots. You will also delve into data versioning in Machine Learning by adopting Data Version Control (DVC) to track data changes. The chapter also covers setting DVC remotes and dataset transfers. Finally, you'll explore DVC pipelines, configuring a DVC YAML file to orchestrate reproducible model training.

Exercise 1: Addestramento del modello con GitHub Actions Exercise 2: Sviluppa un modello di classificazione Exercise 3: Allena un modello di classificazione

Esercizio in corso

Exercise 4: Configura l’addestramento del modello con CML Exercise 5: Versionare gli insiemi di dati con Data Version Control Exercise 6: Perché servono i file .dvc?Exercise 7: Versionamento dei dati in pratica Exercise 8: Interagire con i remote di DVC Exercise 9: Esplorare i vantaggi dei remote DVC Exercise 10: DVC remotes in azione Exercise 11: Pipeline DVC Exercise 12: Creare una pipeline DVC Exercise 13: Allena modelli di ML con DVC

In this chapter, you will direct your attention towards the analysis of model performance and the fine-tuning of hyperparameters. You will acquire practical expertise in comparing metrics and visualizations across different branches to assess changes in model performance. You will conduct hyperparameter tuning using scikit-learn's GridSearchCV. Furthermore, you will delve into the automation of pull requests using the optimal model configuration.

Exercise 1: Comparing metrics and plots in DVC Exercise 2: Adding metrics and plots to dvc.yaml Exercise 3: Comparing metrics across Git branches Exercise 4: Run DVC pipeline in GitHub Actions Exercise 5: Hyperparameter Tuning with DVC Exercise 6: Adding Hyperparameter tuning to dvc.yaml Exercise 7: Running Hyperparameter tuning DVC pipelines Exercise 8: GitHub Actions workflow for Hyperparameter Tuning Exercise 9: Loose Coupling Exercise 10: Setup Hyperparameter Tuning in GitHub Actions Exercise 11: Congratulations!