Add example demonstrating StandardScaler and MinMaxScaler for data preprocessing.

Background:
Data preprocessing with feature scaling is fundamental to many ML algorithms (SVM, neural networks, distance-based methods), but we currently lack a comprehensive example showing how and when to use scalers.

Scope:
Create a comprehensive example showing:

1. StandardScaler (z-score normalization: mean=0, std=1)
2. MinMaxScaler (range normalization: [0,1] or custom range)
3. When to use each type of scaling
4. Impact of scaling on algorithm performance
5. fit() vs. fit_transform() vs. transform() workflow
6. Inverse transformation

Deliverables:

• Create examples/data_preprocessing_scalers.rs
• Add book chapter: book/src/examples/data-preprocessing-scalers.md
• Update SUMMARY.md
• Show comparison: unscaled vs. StandardScaler vs. MinMaxScaler
• Demonstrate on real use case (e.g., before training SVM or K-NN)

Labels: documentation, enhancement, preprocessing