00 Important Notes¶
Four short notes that save you time in this course. The last video of Section 00, "Step-04: Important Notes", walks through them.
1. Code and website¶
All the code for this course is in its GitHub repository. Each section has its own folder with the scripts you need, and a README that walks you through the section step by step.
The same READMEs, laid out for easy reading, are on the course website: https://machine-learning-end-to-end.stacksimplify.com
2. Your numbers may differ from the videos¶
Most of this course was recorded on an Intel Mac, and the final runs (the numbers you see in the slides and READMEs) were done on an Apple Silicon Mac. So you will see some differences between the videos and the written numbers. For example, in Section 07 the tuned model shows $46,525 on camera and $50,550 in the README, and the winning class_weight can come out as 1:100 or 1:200. Your own results depend on your processor and its math library. The improvement story stays the same: the tuned model beats the baseline on our Net Benefit metric. Section 07 explains why this happens.
3. About MLflow, KServe and "advanced sections"¶
When a lecture mentions MLflow, KServe, DVC, Docker, Kubernetes, Knative, Prometheus, Grafana, "advanced sections" or MLOps, those are not part of this course. This course covers the machine learning side, end to end.
4. If pip is missing¶
If a new conda environment says pip is not found, activate the environment and run:
Section 02 shows the setup step by step.
Back to 00 - Introduction, or go on to 01 - Machine Learning Fundamentals.
Prefer to learn by watching?
The video course builds this whole project with you on screen, step by step.