Notebook improvements: 02_ml_pipeline.ipynb

1. More spacing in text
2. Avoid italics
3. More comments in code to explain code
4. `list(falklands_df.columns)` is the line necessary - as the output is very long
5. train/test split - could be clearer - test/train split 20% and 25% is confusing
6. Explain features even if they are small e.g. `%%time`
7. Consider if using [`sklearn.metrics.confusion_matrix()`](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html) and [`sklearn.metrics.ConfusionMatrixDisplay()`](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.ConfusionMatrixDisplay.html) could make code simplier?

Open 02_ml_pipeline.ipynb and review its markdown and code cells in order; first run the notebook to understand the current outputs and train/test split. Address the requested presentation, explanations, output handling, and confusion-matrix considerations, then rerun it to confirm the tutorial remains coherent.

Written by the indexing model from the issue text.