haipipe-data-4-aidata

What problem does it solve?

This Skill transforms raw case data into machine-learning-ready datasets, handling complex splitting and feature transformations required for model training.

Core Features & Use Cases

• Data Splitting: Divides datasets into training, validation, and testing sets using various strategies (time-based, random, stratified).
• Feature Transformation: Converts raw case features into formats suitable for ML models (e.g., token embeddings, numerical sequences).
• Use Case: Prepare a large patient dataset for a diabetes prediction model by splitting it into train/validation/test sets and transforming time-series CGM data into token sequences.

Quick Start

Use the haipipe-data-4-aidata skill to cook a new AIDataSet using the provided configuration file.