These are my study notes and solutions to the exercises proposed in the book Hands-On ML with Scikit-Learn, Keras, and TensorFlow 2nd Edition by Aurélien Géron.
The notes (text and code) are written in the Jupyter notebooks inside this repo. Some parts of it were explicitly copied from the textbook just to keep it concise with the explanation and the code provided. However, I also wrote some paragraphs by my own hand where I think I could explain the concepts with my own point of view about the subject.
The topics and subtopics covered in my notes are:
- Chapter 02 - End to End Machine Learning Project
- California housing Pricing
- Fetch the Data
- Create a test set: Data Snooping Bias and Stratified Sampling
- Visualizing Geographical Data
- Looking for Correlations
- Experimenting with Attributes Combinations
- Prepare the data for Machine Learning
- Data Cleaning
- Handling Text and Categorial Attributes
- Custom Tranformers
- Feature Scaling and Transformation Pipelines
- Select and train a model
- Better Evaluation using Cross-Validation
- Fine-Tune your model
- Randomized Search and Ensemble Methods
- Analyze the Best Models and Their Errors
- Evaluate your system on the test set
- Exercise