Adapt MAIS to 3W Dataset 2.0

[castrokelly]

This pull request adapts the MAIS (Modular Artificial Intelligence System) to be compatible with the 3W Dataset 2.0.

Key changes:

• Updated the MAEDataset class to use the load_3w_dataset() function for loading data.
• Adjusted the feature extraction and label mapping strategies to work with the new dataset structure.
• Adapted the example experiments to use the 3W Dataset 2.0.
• Updated the documentation to reflect the changes.
• Updated the train_lgbm.py and tune_lgbm.py scripts to use the new MAEDataset class and the 3W Dataset 2.0.

Benefits:

• Enables the use of the MAIS with the latest version of the 3W Dataset.
• Provides a more efficient and streamlined workflow for loading and analyzing the data.
• Allows users to take advantage of the new features and data in the 3W Dataset 2.0.

This contribution enhances the 3W Toolkit by providing a modular and adaptable system for developing and testing Machine Learning models with the 3W Dataset 2.0.

---

By creating this pull request, I confirm that I have read and fully accept and agree with one of the Petrobras' Contributor License Agreements (CLAs):

• ICLA: Individual Contributor License Agreement;
• CCLA: Corporate Contributor License Agreement.

Our CLAs are based on the Apache Software Foundation's CLAs:

• ICLA: Individual Contributor License Agreement;
• CCLA: Corporate Contributor License Agreement.