Evaluation and Reliable Machine Learning Pipelines

Why this module belongs in the course

Evaluation estimates how a system may behave on unseen cases. It cannot rescue a leaked split, a misleading target or a metric chosen after looking at the answer.

Before you begin

The concepts and project evidence from Module 3. You should also be able to create a Python virtual environment and keep private or employer data out of the exercise.

Four lessons, one connected result

1. Lesson 1Train, Validation and Test Splits Without Data Leakage80 min · Intermediate
2. Lesson 2Choose Evaluation Metrics for Classification and Clustering85 min · Intermediate
3. Lesson 3Build a Reproducible Machine Learning Pipeline90 min · Intermediate
4. Lesson 4Project: Build and Audit a Leakage-Safe Baseline150 min · Intermediate

How to know you are ready to continue

Complete the checkpoint without copying the worked example. Keep the code, output and a short decision note. Your note should explain one choice, one failure you observed and one limitation a reviewer should know.

Primary references for this module

The lessons explain the ideas in original wording. Use these primary or official sources when a library interface, standard or research claim needs verification.

• scikit-learn cross-validation
• scikit-learn common pitfalls
• scikit-learn pipelines
• scikit-learn classification metrics
• scikit-learn clustering performance
• scikit-learn calibration
• scikit-learn ColumnTransformer
• scikit-learn model persistence