https://hub.imt-atlantique.fr/datascience-toolkit/session2/index.html Presentation & objectives This session focuses on implementing complete data science workflows, from exploratory analysis in notebooks to production-ready machine learning systems. Students will learn to handle real-world data challenges including time-series analysis, geographic data processing, and the critical transition from experimental code to structured, maintainable ML pipelines. Assessment Information This session contributes to your final assessment through two complementary mini-projects. For detailed evaluation criteria and requirements, please refer to the Assessment Guidelines section. Hugo en-us https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_1/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_1/index.html Duration2h30 x 2 AI Banned Introduction This practical session introduces advanced concepts of time series data analysis and predictive modeling using Python through a real-world air quality monitoring case study. You’ll work with authentic PM2.5 measurement data from African cities to develop essential data science skills for temporal and geospatial datasets using Pandas, NumPy, Matplotlib, and Scikit-learn. Through hands-on exercises, you will learn to: https://hub.imt-atlantique.fr/datascience-toolkit/session2/lesson_1/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://hub.imt-atlantique.fr/datascience-toolkit/session2/lesson_1/index.html Duration30 min AI Allowed Introduction This foundational lesson explores the critical transition from exploratory data science to production-ready machine learning systems. As data scientists, we often begin our work in Jupyter notebooks, which excel at rapid experimentation and iterative analysis. However, the journey from prototype to production requires a fundamental shift in how we structure and organize our code. Through this theoretical foundation, you will understand essential concepts for professional ML development: https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_2/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_2/index.html Duration2h30 x 2 AI Banned Introduction This practical session focuses on transforming exploratory notebook code into structured, production-ready machine learning pipelines. You’ll learn to convert the air quality analysis notebook you previously developed into a modular, testable, and maintainable Python package that follows software engineering best practices. Through this hands-on workshop, you will master essential skills for transitioning from data science experimentation to production deployment: https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_3/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_3/index.html Duration2h30 AI Banned Introduction This practical session extends your structured ML pipeline by introducing advanced algorithms and systematic hyperparameter optimization. You’ll transform your linear regression baseline into a comprehensive comparison framework supporting gradient boosting models with automated parameter tuning. Through this hands-on workshop, you will master advanced machine learning engineering skills: Advanced Algorithms: Implement XGBoost and LightGBM for improved predictive performance Hyperparameter Optimization: Apply GridSearchCV with geographic cross-validation to prevent data leakage Model Comparison: Systematically evaluate multiple algorithms with statistical rigor Production Optimization: Learn when and how to apply optimization in real-world scenarios Performance Analysis: Understand the trade-offs between model complexity, training time, and predictive accuracy The challenge is to extend your existing pipeline architecture while maintaining geographic cross-validation integrity and implementing robust optimization strategies. This represents the natural evolution from proof-of-concept to production-ready ML systems. https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_4/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_4/index.html Duration2h30 AI Banned Introduction This practical session introduces MLflow for systematic experiment tracking and model management in machine learning pipelines. You’ll learn to transform your structured air quality pipeline into a fully tracked and reproducible ML workflow that follows industry best practices for experiment management. Through this hands-on workshop, you will master essential MLOps skills: Experiment Tracking: Systematically log parameters, metrics, and artifacts for all ML experiments Model Management: Version and organize trained models with metadata and lineage tracking Reproducibility: Ensure experiments can be reproduced and compared reliably Collaboration: Share experiment results and models across team members Production Readiness: Prepare models for deployment with proper versioning and metadata MLflow is the industry standard for ML experiment tracking, used by companies like Databricks, Netflix, and many organizations to manage their ML lifecycles. Learning MLflow prepares you for real-world ML engineering roles where experiment tracking and model management are critical. https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_5/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://hub.imt-atlantique.fr/datascience-toolkit/session2/practical_5/index.html Duration2h30 AI Allowed Introduction This final practical session focuses on the Evaluation phase of CRISP-DM, where you synthesize your technical achievements into meaningful business insights. You’ll leverage all the tools developed in previous sessions to conduct a comprehensive analysis and complete your professional README for the final assessment. Source: IBM CRISP-DM Help Overview